[Fix] (DirectGLES): lower gl_ClipDistance for Adreno's ESSL compiler - shadow the builtin in a Private array with constant-index flushes before EmitVertex/return, loop-copy gl_in clip distances through dynamic indices (whole-array reads segfault the Qualcomm compiler, constant-index element reads miscompile), strip the SPIRV-Cross redeclaration Adreno rejects, and split const struct-array LUT initializers so they stay dynamically indexable; quirk-gated to Qualcomm with MOBILEGL_QUIRK_CLIP_DISTANCE override

CMakeLists.txt

@@ -194,6 +194,9 @@ set(SOURCE_FILES
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUboMemberRelaxedPrecisionPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripNoPerspectivePass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EmulateNoPerspectivePass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FoldConstOffsetFor1DFetchPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerClipDistanceForEsslPass.cpp
+    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DefeatConstStructArrayLutPass.cpp
 
     MobileGL/MG_Util/BackendLoaders/OpenGL/Loader.cpp
     MobileGL/MG_Util/BackendLoaders/Vulkan/Loader.cpp
@@ -455,21 +458,8 @@ if (ANDROID)
 endif()
 
 if (APPLE AND NOT MOBILEGL_IOS)
-    # MobileGL statically embeds glslang, SPIRV-Tools, and SPIRV-Cross. When
-    # this dylib is injected with DYLD_INSERT_LIBRARIES, exporting those C++
-    # symbols interposes incompatible copies embedded by host libraries such
-    # as shaderc. Keep only the public GL/EGL/CGL loader surface globally
-    # visible; GetProcAddress can still return pointers to hidden internals.
-    set(MOBILEGL_MACOS_EXPORTED_SYMBOLS
-        "${CMAKE_CURRENT_SOURCE_DIR}/MobileGL/MG_Impl/DyldInterpose/ExportedSymbols.txt")
-    target_link_options(${CMAKE_PROJECT_NAME} PRIVATE
-        "LINKER:-exported_symbols_list,${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
-    set_property(TARGET ${CMAKE_PROJECT_NAME} APPEND PROPERTY
-        LINK_DEPENDS "${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
-
     target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
         "-framework Cocoa"
-        "-framework CoreVideo"
         "-framework QuartzCore"
         "-framework Foundation"
         "-framework OpenGL"
@@ -477,7 +467,6 @@ if (APPLE AND NOT MOBILEGL_IOS)
     if(TARGET ${CMAKE_PROJECT_NAME}_s)
         target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC
             "-framework Cocoa"
-            "-framework CoreVideo"
             "-framework QuartzCore"
             "-framework Foundation"
             "-framework OpenGL"

MobileGL/Config.h

@@ -80,6 +80,11 @@ namespace MobileGL::MG_Config {
         // rewrites the recognized workgroup prefix-scan template on Qualcomm devices with
         // subgroups wider than 32 lanes (see ShaderSourceProcessor's quirk registry).
         QuirkOverride SubgroupPrefixScanQuirk = QuirkOverride::Auto;
+        // MOBILEGL_QUIRK_CLIP_DISTANCE: overrides the DirectGLES quirk that lowers
+        // gl_ClipDistance for Adreno's ESSL compiler (shadow Private arrays with
+        // constant-index builtin flushes, dynamic-index gl_in copy loop, redeclaration
+        // strip, and const struct-array LUT splitting). Auto detects Qualcomm.
+        QuirkOverride ClipDistanceQuirk = QuirkOverride::Auto;
         // MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE: overrides the DirectVulkan quirk that
         // strips depth writes from accumulation-blended pipelines (MIN/MAX or additive
         // ONE+ONE - the multi-pass depth-equality signature) on drivers without

MobileGL/ConfigLoader.cpp

@@ -135,6 +135,7 @@ namespace MobileGL::MG_ConfigLoader {
         features.DisableUboRing = QueryEnvFlag("MOBILEGL_DISABLE_UBO_RING");
         features.RelaxedSemantics = QueryEnvFlag("MOBILEGL_RELAXED_SEMANTICS");
         features.SubgroupPrefixScanQuirk = QueryEnvQuirkOverride("MOBILEGL_QUIRK_SUBGROUP_PREFIX_SCAN");
+        features.ClipDistanceQuirk = QueryEnvQuirkOverride("MOBILEGL_QUIRK_CLIP_DISTANCE");
         features.MagmaDisableBlendedDepthWriteQuirk =
             QueryEnvQuirkOverride("MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE");
         features.DisableRobustBufferAccess = QueryEnvFlag("MOBILEGL_DISABLE_ROBUST_BUFFER_ACCESS");

MobileGL/Init.cpp

@@ -14,7 +14,6 @@
 #include <MG_State/EGLState/Core.h>
 #include <MG_Impl/GLImpl/Texture/ProxyTexture.h>
 #include <MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h>
-#include <MG_Impl/GLImpl/Sync/GL_Sync.h>
 
 #include <atomic>
 #include <mutex>
@@ -38,12 +37,6 @@ namespace MobileGL {
                 MGLOG_I("MobileGL closing...");
             }
             glslang::FinalizeProcess();
-            // GL syncs die with their contexts, and every context is gone by the
-            // time full teardown runs: drain the live-sync registry while the
-            // backend function table can still release the backend handles (and
-            // before a re-initialized library could pair them with the wrong
-            // backend's DeleteSync).
-            MG_Impl::GLImpl::DestroyAllSyncObjects();
             MG_Backend::pActiveBackendObject.reset();
             MG_State::pGLContext.reset();
             MG_State::pEGLContext.reset();
@@ -107,11 +100,9 @@ namespace MobileGL {
     // (EGL/WGL/CGL): initialization happens lazily on the first entry point
     // via EnsureInitialized(), and full teardown happens deterministically
     // when the last EGL display is terminated with nothing current (EGLImpl
-    // calls Destroy()). There is intentionally no backend-initializing static
-    // constructor, no static destructor, and no DllMain: the global singletons
-    // use leak-at-exit storage (see GlobalObjects.cpp), so a process that exits
+    // calls Destroy()). There is intentionally no static constructor, no
+    // static destructor, and no DllMain: the global singletons use
+    // leak-at-exit storage (see GlobalObjects.cpp), so a process that exits
     // without eglTerminate simply leaks them to the OS instead of running
-    // backend destructors during static teardown. macOS has a lightweight
-    // dyld constructor that installs NSOpenGL dispatch hooks only; full backend
-    // initialization still enters here from the first hooked CGL context.
+    // backend destructors during static teardown.
 } // namespace MobileGL

MobileGL/Init.h

@@ -13,10 +13,9 @@ namespace MobileGL {
     void Initialize();
     // Thread-safe, idempotent, and re-entrant wrapper around Initialize().
     // Host layers (EGL/WGL/CGL entry points) call this lazily on first use so
-    // full backend initialization never depends on ELF/DLL static constructors,
-    // and so a fresh init can follow a full Destroy() (e.g. after the last
-    // eglTerminate). The macOS dyld bootstrap installs only lightweight
-    // NSOpenGL method hooks.
+    // MobileGL's lifecycle never depends on ELF/DLL static constructors, and
+    // so a fresh init can follow a full Destroy() (e.g. after the last
+    // eglTerminate).
     void EnsureInitialized();
     void Destroy();
 

MobileGL/MG_Backend/DirectGLES/DirectGLES.cpp

@@ -449,6 +449,20 @@ namespace MobileGL::MG_Backend::DirectGLES {
                     }
                 }
             }
+
+            // Textures attached only to the READ framebuffer (blit / ReadPixels sources) need
+            // their content synced too, or the backend reads stale texel data.
+            const auto& readFBO =
+                MG_State::pGLContext->GetFramebufferBindingSlot(FramebufferTarget::Read).GetBoundObject();
+            if (readFBO && readFBO != currentFBO) {
+                for (const auto& attachment : readFBO->GetAllAttachmentObjects()) {
+                    if (!attachment.IsTexture()) continue;
+                    auto& textureObject = attachment.GetTexture();
+                    if (textureObject) {
+                        SyncTextureObjectToBackend(textureObject);
+                    }
+                }
+            }
         }
 
         static Bool SupportsLayeredImageBinding(TextureTarget target) {

MobileGL/MG_Backend/DirectGLES/Managers.cpp

@@ -1262,15 +1262,31 @@ namespace MobileGL::MG_Backend::DirectGLES {
             const auto& allAttributes = stateVAOObject->GetAllAttributes();
             for (Uint attribIndex = 0; attribIndex < allAttributes.size(); ++attribIndex) {
                 const auto& attrib = allAttributes[attribIndex];
+                const Uint32 attribBit = 1u << attribIndex;
+
+                // An enabled attrib with neither a buffer object nor a client pointer has no
+                // source; GL tolerates the state (only draws consuming it are undefined), but
+                // Adreno's ES driver memcpys the "client array" from address 0 at draw time
+                // (SIGSEGV). Keep such attribs disabled on the backend VAO and re-enable them
+                // the moment they gain a source - the mask-vs-current compare below triggers
+                // the enable even when only the Buffer/Format versions changed.
+                const Bool unsourceable = attrib.Enabled && !attrib.Buffer && attrib.Offset == 0;
+                const Bool wasForceDisabled = (m_forceDisabledAttribsMask & attribBit) != 0;
+
                 Bool needsSyncSwitch = allAttributeVersions[attribIndex].SwitchVersion !=
                                        m_syncedAttributeVersions[attribIndex].SwitchVersion;
-                if (needsSyncSwitch) {
-                    if (attrib.Enabled) {
+                if (needsSyncSwitch || unsourceable != wasForceDisabled) {
+                    if (attrib.Enabled && !unsourceable) {
                         g_GLESFuncs.glEnableVertexAttribArray(attribIndex);
                     } else {
                         g_GLESFuncs.glDisableVertexAttribArray(attribIndex);
                     }
                 }
+                if (unsourceable) {
+                    m_forceDisabledAttribsMask |= attribBit;
+                } else {
+                    m_forceDisabledAttribsMask &= ~attribBit;
+                }
 
                 Bool needsSyncFormat = allAttributeVersions[attribIndex].FormatVersion !=
                                        m_syncedAttributeVersions[attribIndex].FormatVersion;
@@ -1278,7 +1294,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
                                        m_syncedAttributeVersions[attribIndex].BufferVersion;
                 if (!needsSyncFormat && !needsSyncBuffer) continue;
 
+                if (unsourceable) continue;
+
+                // Client-side array with a non-null pointer: the pointer is uploaded and applied
+                // per draw by SyncClientSideAttributesForDrawArrays.
+                if (!attrib.Buffer) continue;
+
                 if (!BindAttributeBuffer(attrib)) {
+                    if (attrib.Enabled) {
+                        g_GLESFuncs.glDisableVertexAttribArray(attribIndex);
+                        m_forceDisabledAttribsMask |= attribBit;
+                    }
                     continue;
                 }
 
@@ -3265,6 +3291,19 @@ namespace MobileGL::MG_Backend::DirectGLES {
             }
             auto& shaderSpirvs = stateProgramObject->GetGeneratedSpirv();
 
+            // Adreno's ESSL compiler mishandles gl_ClipDistance (rejects redeclarations,
+            // miscompiles non-constant-index writes and constant-index gl_in element reads,
+            // crashes on whole-array gl_in reads) and cannot dynamically index the global
+            // const struct[] LUTs SPIRV-Cross likes to emit. Gate the workarounds to
+            // Qualcomm; MOBILEGL_QUIRK_CLIP_DISTANCE overrides the device detection.
+            const MG_Config::QuirkOverride clipDistanceQuirkOverride =
+                MG_Config::Features.ClipDistanceQuirk;
+            const Bool applyClipDistanceQuirk =
+                clipDistanceQuirkOverride == MG_Config::QuirkOverride::ForceOn ||
+                (clipDistanceQuirkOverride == MG_Config::QuirkOverride::Auto &&
+                 pActiveBackendObject &&
+                 pActiveBackendObject->GetDynamicParameters().GpuVendor == GpuVendorKind::Qualcomm);
+
             for (int index = 0; index < attachedShaders.size(); ++index) {
                 auto& shader = attachedShaders[index];
                 GLenum glShaderType = MG_Util::ConvertShaderStageToGLEnum(shader->GetShaderStage());
@@ -3287,6 +3326,63 @@ namespace MobileGL::MG_Backend::DirectGLES {
                     effectiveSpirv = &loweredSpirv;
                 }
 
+                // GL 3.3 only promises undefined *values* for out-of-bounds array indexing, but
+                // Adreno's ESSL compiler constant-folds a provably out-of-bounds local-array
+                // index into poison that corrupts the whole shader's output. Clamp every
+                // access-chain index to its declared bounds before transpiling.
+                Vector<unsigned int> clampedSpirv;
+                if (MG_Util::ShaderTranspiler::ShaderCompiler::ClampAccessChainIndicesForEssl(*effectiveSpirv,
+                                                                                              clampedSpirv) &&
+                    !clampedSpirv.empty()) {
+                    effectiveSpirv = &clampedSpirv;
+                } else {
+                    MGLOG_W("ClampAccessChainIndicesForEssl failed, continuing with unclamped SPIR-V.");
+                }
+
+                // SPIRV-Cross emulates 1D samplers as 2D for ES: it widens texelFetch coordinates
+                // to ivec2 but keeps the ConstOffset operand scalar, which is not a valid ESSL
+                // texelFetchOffset overload (Adreno rejects it). Fold the constant offset into the
+                // coordinate instead (texelFetchOffset(t,P,l,o) == texelFetch(t,P+o,l)).
+                Vector<unsigned int> foldedOffsetSpirv;
+                if (MG_Util::ShaderTranspiler::ShaderCompiler::FoldConstOffsetFor1DFetchForEssl(
+                        *effectiveSpirv, foldedOffsetSpirv) &&
+                    !foldedOffsetSpirv.empty()) {
+                    effectiveSpirv = &foldedOffsetSpirv;
+                } else {
+                    MGLOG_W("FoldConstOffsetFor1DFetchForEssl failed, continuing with unfolded SPIR-V.");
+                }
+
+                // Adreno quirk: shadow gl_ClipDistance in Private arrays so the transpiled
+                // ESSL only writes the builtin with literal constant indices (flushed before
+                // EmitVertex/return) and only reads gl_in clip distances through dynamic loop
+                // indices - the shapes this driver compiles correctly. Must run after the
+                // access-chain clamp above so the flush indices stay literal constants.
+                Vector<unsigned int> clipDistanceSpirv;
+                if (applyClipDistanceQuirk &&
+                    (glShaderType == GL_VERTEX_SHADER || glShaderType == GL_GEOMETRY_SHADER)) {
+                    if (MG_Util::ShaderTranspiler::ShaderCompiler::LowerClipDistanceForEssl(
+                            *effectiveSpirv, clipDistanceSpirv) &&
+                        !clipDistanceSpirv.empty()) {
+                        effectiveSpirv = &clipDistanceSpirv;
+                    } else {
+                        MGLOG_W("LowerClipDistanceForEssl failed, continuing with unlowered SPIR-V.");
+                    }
+                }
+
+                // Adreno quirk: split single constant-composite stores of struct arrays so
+                // SPIRV-Cross does not promote them to global const struct[] LUTs, which this
+                // driver cannot dynamically index ("Cannot offset into the structure").
+                Vector<unsigned int> structLutSpirv;
+                if (applyClipDistanceQuirk) {
+                    if (MG_Util::ShaderTranspiler::ShaderCompiler::DefeatConstStructArrayLutForEssl(
+                            *effectiveSpirv, structLutSpirv) &&
+                        !structLutSpirv.empty()) {
+                        effectiveSpirv = &structLutSpirv;
+                    } else {
+                        MGLOG_W("DefeatConstStructArrayLutForEssl failed, continuing with unsplit SPIR-V.");
+                    }
+                }
+
                 // ESSL stage-matches uniform blocks by member precision, but SPIRV-Cross prints
                 // a RelaxedPrecision member as explicit "mediump" in the vertex stage and as
                 // UNQUALIFIED (mediump-by-default) in the fragment stage; after
@@ -3345,6 +3441,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
 
                 source = RebindImageUniformsToFrontendUnits(std::move(source), stateProgramObject);
                 source = RemoveLayoutBinding(source);
+                if (applyClipDistanceQuirk) {
+                    // Adreno rejects the gl_ClipDistance redeclaration SPIRV-Cross still emits
+                    // ("reserved built-in name") but accepts plain usage with
+                    // GL_EXT_clip_cull_distance required; drop the line, keep the #extension.
+                    source = RemoveClipDistanceRedeclaration(source);
+                }
                 source = ProcessOutColorLocations(source);
                 source = ForceFlatIntegerVaryings(source, glShaderType);
                 source = EmulateBaseInstanceInVertexShader(std::move(source), glShaderType);

MobileGL/MG_Backend/DirectGLES/Managers.h

@@ -258,6 +258,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
         private:
             Uint m_backendVAOId = 0;
             Array<Uint, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS> m_clientAttributeBufferIds;
+            // Attribs the frontend has Enabled but that have no source at all (no buffer object
+            // and NULL client pointer). GL keeps such attribs latently enabled, but Adreno's ES
+            // driver treats them as client arrays and memcpys from address 0 at draw time
+            // (SIGSEGV), so they are kept disabled on the backend VAO until they gain a source.
+            Uint32 m_forceDisabledAttribsMask = 0;
             Bool m_isInitialized = false;
             Uint16 m_syncedIndexBufferVersion = 0;
             Array<MG_State::GLState::VertexAttributeVersion, MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS>

MobileGL/MG_Backend/DirectGLES/Utils.cpp

@@ -342,6 +342,41 @@ namespace MobileGL::MG_Backend::DirectGLES {
             }
             return result;
         }
+
+        String RemoveClipDistanceRedeclaration(const String& glslCode) {
+#ifdef TRACY_ENABLE
+            ZoneScopedC(TRACY_ZONECOLOR_BACKEND);
+#endif
+            // Adreno rejects any redeclaration of gl_ClipDistance/gl_CullDistance ("reserved
+            // built-in name") even with GL_EXT_clip_cull_distance required, but accepts plain
+            // usage of the builtin. Drop the desktop-style redeclaration line SPIRV-Cross
+            // prints; the "#extension GL_EXT_clip_cull_distance : require" line stays.
+            static const std::regex redeclarationRegex(
+                R"(^\s*(?:out|in)\s+(?:(?:high|medium|low)p\s+)?float\s+gl_(?:Clip|Cull)Distance\[[0-9]+\];\s*$)");
+
+            String result;
+            result.reserve(glslCode.size());
+            SizeT lineStart = 0;
+            Bool firstLine = true;
+            while (lineStart <= glslCode.size()) {
+                SizeT lineEnd = glslCode.find('\n', lineStart);
+                const Bool lastLine = lineEnd == String::npos;
+                String line = glslCode.substr(lineStart, lastLine ? String::npos : lineEnd - lineStart);
+
+                if (!std::regex_match(line, redeclarationRegex)) {
+                    if (!firstLine) {
+                        result += '\n';
+                    }
+                    result += line;
+                    firstLine = false;
+                }
+                if (lastLine) {
+                    break;
+                }
+                lineStart = lineEnd + 1;
+            }
+            return result;
+        }
     } // namespace PrgramImpl
 
     namespace Utils {

MobileGL/MG_Backend/DirectGLES/Utils.h

@@ -105,6 +105,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
                                         Uint32 unormOutputMask);
         String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType);
         String RemoveLayoutBinding(const String& glslCode);
+        String RemoveClipDistanceRedeclaration(const String& glslCode);
     } // namespace PrgramImpl
 
     namespace Utils {

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp

@@ -469,9 +469,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // treat them as signaled/available with zero results from here on.
         BumpRendererGeneration();
         pVulkanRenderer.reset();
-        // The reflection cache is file-scope, not renderer-owned; without this the
-        // deleted programs' reflection strings survive full context teardown.
-        ClearProgramResourceCaches();
         BackendObject::ReleaseEGLResources();
     }
 
@@ -481,9 +478,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // treat them as signaled/available with zero results from here on.
         BumpRendererGeneration();
         pVulkanRenderer.reset();
-        // The reflection cache is file-scope, not renderer-owned; without this the
-        // deleted programs' reflection strings survive full context teardown.
-        ClearProgramResourceCaches();
     }
 
     const RendererInfo& BackendObject_DirectVulkan::GetRendererInfo() const {

MobileGL/MG_Backend/DirectVulkan/DirectVulkan.cpp

@@ -61,12 +61,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         };
 
         struct ProgramResourceCache {
-            // Lifetime id of the program the cached reflection belongs to. GL names are
-            // recycled (IndexGenerator hands freed indices straight back), and a
-            // recreated program's backendStateVersion restarts at the same small values,
-            // so the version alone can collide; the never-reused lifetime id makes the
-            // slot's ownership unambiguous.
-            Uint64 programLifetimeId = 0;
             Uint32 backendStateVersion = 0;
             Vector<StorageBlockResource> storageBlocks;
             Vector<BufferVariableResource> bufferVariables;
@@ -88,11 +82,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint32 baseInstance = 0;
         };
 
-        // Keyed by GL program name so the freed-name reuse in IndexGenerator bounds the
-        // map at the peak-simultaneous-program high-water mark; each slot's ownership is
-        // checked against the program's lifetime id before it is served (see
-        // GetProgramResourceCache). Cleared wholesale at EGL teardown via
-        // ClearProgramResourceCaches.
         UnorderedMap<GLuint, ProgramResourceCache> g_programResourceCaches;
 
         void ClearReadPixelsOutput(GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels) {
@@ -153,19 +142,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         ProgramResourceCache& GetProgramResourceCache(const MG_State::GLState::ProgramObject& program) {
             auto& cache = g_programResourceCaches[program.GetExternalIndex()];
-            const Uint64 programLifetimeId = program.GetLifetimeId();
             const Uint32 backendStateVersion = program.GetBackendStateVersion();
-            // The lifetime id must match too: a new program that reuses a deleted
-            // program's name and happens to land on the same backendStateVersion (both
-            // count from zero) would otherwise be served the dead program's reflection.
-            if (cache.programLifetimeId == programLifetimeId &&
-                cache.backendStateVersion == backendStateVersion &&
+            if (cache.backendStateVersion == backendStateVersion &&
                 (!cache.storageBlocks.empty() || !cache.bufferVariables.empty())) {
                 return cache;
             }
 
             cache = {};
-            cache.programLifetimeId = programLifetimeId;
             cache.backendStateVersion = backendStateVersion;
 
             Vector<SpvReflectShaderModule> modules;
@@ -383,15 +366,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     } // namespace
 
-    void ClearProgramResourceCaches() {
-        // Called from EGL teardown while the backend's m_eglStateMutex is held; GL
-        // calls are serialized in this codebase (contexts migrate threads but never
-        // run concurrently), so no other thread can be inside the unsynchronized map.
-        // Live programs in another context self-heal: their entry rebuilds from the
-        // retained generated SPIR-V on the next resource query.
-        g_programResourceCaches.clear();
-    }
-
     GLuint GetShaderStorageBlockIndex(const MG_State::GLState::ProgramObject& program, const String& name) {
         auto& cache = GetProgramResourceCache(program);
         const auto it = std::find_if(cache.storageBlocks.begin(), cache.storageBlocks.end(),

MobileGL/MG_Backend/DirectVulkan/DirectVulkan.h

@@ -23,12 +23,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     Uint64 GetRendererGeneration();
     void BumpRendererGeneration();
 
-    // Drops every cached program-resource reflection entry (CPU-side strings/vectors
-    // only, no Vulkan handles). Called at EGL teardown next to the renderer reset;
-    // safe because GL calls are serialized in this codebase, and any still-live
-    // program rebuilds its entry from the retained generated SPIR-V on demand.
-    void ClearProgramResourceCaches();
-
     void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
     void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.cpp

@@ -150,30 +150,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     Bool FrameContext::TransitionToPresent(VkImage image, VkImageLayout oldLayout, VkImageLayout presentLayout) {
         auto& frame = GetCurrent();
-        if (oldLayout == presentLayout || oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
+        if (frame.hasCommandBufferRecorded || frame.isCommandRecording || oldLayout == presentLayout ||
+            oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
             return false;
         }
 
-        // The barrier belongs in the frame's own recording. Bailing out because
-        // something was already recorded (the previous behaviour) dropped the
-        // transition entirely for every frame that never ran a default-framebuffer
-        // render pass - the only other thing that carries the image to
-        // PRESENT_SRC_KHR, via that pass's finalLayout - so the swapchain image was
-        // handed to the WSI still in the layout it was acquired in.
-        // A closed-but-unsubmitted buffer can only come from a submit that already
-        // failed (SubmitPendingCommandBuffer leaves the flag set on error), and
-        // appending to it is illegal while reopening would reset the frame's own
-        // commands away. The device is gone on that path anyway - stay silent-safe
-        // rather than trade a lost device for a barrier into a closed buffer.
-        if (frame.hasCommandBufferRecorded) {
-            MGLOG_E("TransitionToPresent: command buffer already closed; skipping the present barrier");
-            return false;
-        }
-
-        // Reopening a recording here would vkResetCommandBuffer this frame's own
-        // commands away, so append to the open one and let the caller close it.
-        const Bool openedRecording = !frame.isCommandRecording;
-        VkCommandBuffer commandBuffer = openedRecording ? BeginCommandRecording() : frame.commandBuffer;
+        auto& commandBuffer = BeginCommandRecording();
 
         VkImageMemoryBarrier presentBarrier{};
         presentBarrier.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER;
@@ -192,9 +174,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         vkCmdPipelineBarrier(commandBuffer, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT, 0, 0,
                              nullptr, 0, nullptr, 1, &presentBarrier);
 
-        if (openedRecording) {
-            EndCommandRecording();
-        }
+        EndCommandRecording();
         return true;
     }
 
@@ -247,21 +227,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         result = vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
                                        &outImageIndex);
-        // VK_SUBOPTIMAL_KHR is a success code: an image *was* acquired and
-        // imageAvailableSemaphore *will* be signaled. Bailing out on it skipped both
-        // the consumed-flag reset (leaving a stale "already consumed", so the next
-        // submit never waited on the pending signal) and the fence reset (leaving
-        // the slot's fence signaled for the next submit to reuse). Only a genuine
-        // failure - VK_ERROR_OUT_OF_DATE_KHR and friends, where nothing is acquired
-        // and nothing is signaled - skips the bookkeeping.
-        if (result != VK_SUCCESS && result != VK_SUBOPTIMAL_KHR) {
+        if (result != VK_SUCCESS) {
             return result;
         }
 
         frame.imageAvailableSemaphoreConsumed = false;
-        const VkResult resetResult = vkResetFences(device, 1, &frame.imageInFlightFence);
-        // Hand the acquire's own code back so the caller can schedule a rebuild.
-        return resetResult == VK_SUCCESS ? result : resetResult;
+        return vkResetFences(device, 1, &frame.imageInFlightFence);
     }
 
     Uint32 FrameContext::GetCurrentFrameIndex() const {
@@ -293,9 +264,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (result != VK_SUCCESS) {
             return result;
         }
-        // lastSubmitIndex was just written by the renderer for the submission
-        // that carried this command buffer.
-        frame.retiredCommandBuffers.push_back({frame.commandBuffer, frame.lastSubmitIndex});
+        frame.retiredCommandBuffers.push_back(frame.commandBuffer);
         frame.commandBuffer = replacement;
         return VK_SUCCESS;
     }
@@ -305,40 +274,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return;
         }
         if (m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE) {
-            for (const auto& retired : frame.retiredCommandBuffers) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1, &retired.commandBuffer);
-            }
+            vkFreeCommandBuffers(m_device, m_commandPool, static_cast<Uint32>(frame.retiredCommandBuffers.size()),
+                                 frame.retiredCommandBuffers.data());
         }
         frame.retiredCommandBuffers.clear();
     }
 
-    void FrameContext::FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex) {
-        if (m_device == VK_NULL_HANDLE || m_commandPool == VK_NULL_HANDLE) {
-            return;
-        }
-        for (auto& frame : m_frames) {
-            // Retired buffers are appended in submit order, so the completed
-            // ones form a prefix.
-            SizeT completedCount = 0;
-            while (completedCount < frame.retiredCommandBuffers.size() &&
-                   frame.retiredCommandBuffers[completedCount].submitIndex <= completedSubmitIndex) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1,
-                                     &frame.retiredCommandBuffers[completedCount].commandBuffer);
-                ++completedCount;
-            }
-            if (completedCount > 0) {
-                frame.retiredCommandBuffers.erase(frame.retiredCommandBuffers.begin(),
-                                                  frame.retiredCommandBuffers.begin() + completedCount);
-            }
-        }
-    }
-
-    void FrameContext::FreeAllRetiredCommandBuffers() {
-        for (auto& frame : m_frames) {
-            FreeRetiredCommandBuffers(frame);
-        }
-    }
-
     void FrameContext::AssertValidFrameIndex(Uint32 frameIndex) const {
         MOBILEGL_ASSERT(frameIndex < m_frames.size(), "FrameContext index out of range");
     }

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.h

@@ -40,16 +40,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkPresentInfoKHR presentInfo{VK_STRUCTURE_TYPE_PRESENT_INFO_KHR};
         };
 
-        // A command buffer submitted mid-frame (FlushPendingCommands), tagged
-        // with the submit-tracker index it was submitted under so it can be
-        // freed as soon as that submission is observed complete - without
-        // waiting for the slot's fence to be waited again (present-less flush
-        // loops never wait it).
-        struct RetiredCommandBuffer {
-            VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
-            Uint64 submitIndex = 0;
-        };
-
         struct FrameData {
             VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
             VkSemaphore imageAvailableSemaphore = VK_NULL_HANDLE;
@@ -57,10 +47,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Bool isCommandRecording = false;
             Bool hasCommandBufferRecorded = false;
             Bool imageAvailableSemaphoreConsumed = false;
-            // Command buffers submitted mid-frame (FlushPendingCommands),
-            // appended in submit order; freed once their submission is known
-            // complete (fence wait or completion poll).
-            Vector<RetiredCommandBuffer> retiredCommandBuffers;
+            // Command buffers submitted mid-frame (FlushPendingCommands) whose
+            // execution is only known complete once this slot's fence has been
+            // waited again; freed at that point.
+            Vector<VkCommandBuffer> retiredCommandBuffers;
             // Submit-tracker index of this slot's most recent queue submission
             // (written by the renderer at submit time).
             Uint64 lastSubmitIndex = 0;
@@ -89,19 +79,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Parks the current (already ended and submitted) command buffer on the
         // slot's retired list and installs a freshly allocated one, so recording
         // can restart while the submitted buffer is still executing. Retired
-        // buffers are freed after the slot's fence is next waited, or as soon
-        // as their submission is observed complete.
+        // buffers are freed after the slot's fence is next waited.
         VkResult RetireCurrentCommandBuffer();
 
-        // Frees every retired command buffer whose tagged submission index is
-        // known complete. Driven by the renderer's submit tracker on completion
-        // events (fence waits and non-blocking polls), so present-less flush
-        // loops reclaim their buffers without any extra wait.
-        void FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex);
-        // Frees every slot's retired command buffers. Only valid when the
-        // caller has proven every queue submission complete.
-        void FreeAllRetiredCommandBuffers();
-
         Uint32 GetCurrentFrameIndex() const;
         Uint32 GetFrameCount() const;
 

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.cpp

@@ -8,7 +8,6 @@
 
 #include "PipelineFactory.h"
 
-#include <algorithm>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     static const char* PrimitiveTopologyToString(VkPrimitiveTopology topology) {
@@ -244,108 +243,23 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const HashType hash = ComputeHash(payload);
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
-            it->second.lastUsedFrame = m_frameCounter;
-            return it->second.pipeline;
+            return it->second;
         }
 
         VkPipeline pipeline = CreatePipeline(payload);
-        m_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash, payload.renderPass,
-                                                 m_frameCounter});
+        m_cache.emplace(hash, pipeline);
         return pipeline;
     }
 
     void PipelineFactory::DestroyAll() {
         for (auto& pair : m_cache) {
-            if (pair.second.pipeline != VK_NULL_HANDLE) {
-                vkDestroyPipeline(m_device, pair.second.pipeline, nullptr);
+            if (pair.second != VK_NULL_HANDLE) {
+                vkDestroyPipeline(m_device, pair.second, nullptr);
             }
         }
         m_cache.clear();
     }
 
-    Uint32 PipelineFactory::OnFrameBoundary() {
-        ++m_frameCounter;
-
-        // Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
-        // idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
-        // any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
-        // so immediate vkDestroyPipeline is safe. The caller must drop its "last
-        // pipeline" memo when this returns non-zero: the memo can return a cached
-        // handle without touching this cache, so an evicted pipeline may still be
-        // memoized (present-less flush loops never reset the memo per frame).
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeFrames = 1024;
-        if ((m_frameCounter % kSweepInterval) != 0) {
-            return 0;
-        }
-
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::OnFrameBoundary: evicted %u idle pipelines (%zu remain)", evicted,
-                    m_cache.size());
-        }
-        return evicted;
-    }
-
-    Uint32 PipelineFactory::EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses) {
-        if (renderPasses.empty() || m_cache.empty()) {
-            return 0;
-        }
-        // Sorted-batch membership test keeps a mass eviction (shader-pack switch,
-        // dimension exit) at one O(cache * log batch) scan instead of one full scan
-        // per dying pass.
-        Vector<VkRenderPass> sortedPasses = renderPasses;
-        std::sort(sortedPasses.begin(), sortedPasses.end());
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (std::binary_search(sortedPasses.begin(), sortedPasses.end(), it->second.renderPass)) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::EvictByRenderPasses: evicted %u pipelines for %zu destroyed render passes",
-                    evicted, sortedPasses.size());
-        }
-        return evicted;
-    }
-
-    Uint32 PipelineFactory::EvictByProgramHash(HashType programHash) {
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (it->second.programHash == programHash) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::EvictByProgramHash: evicted %u pipelines for program hash 0x%llx",
-                    evicted, static_cast<unsigned long long>(programHash));
-        }
-        return evicted;
-    }
-
     VkPipeline PipelineFactory::CreatePipeline(const PipelineCreatePayload& payload) const {
         MOBILEGL_ASSERT(payload.stages != nullptr && !payload.stages->empty(), "PipelineFactory: stages are empty");
         MOBILEGL_ASSERT(payload.vertexInputState != nullptr, "PipelineFactory: vertexInputState is null");

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.h

@@ -65,26 +65,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkPipeline GetOrCreatePipeline(const PipelineCreatePayload& payload);
         void DestroyAll();
 
-        // Frame boundary hook: ages the pipeline cache and destroys long-unused entries
-        // (their command buffers retired many frames ago), mirroring
-        // VkRenderPassManager::OnPresent's sweep. Returns the number of pipelines
-        // destroyed so the caller can drop any memoized VkPipeline handle.
-        Uint32 OnFrameBoundary();
-        // Destroys every cached pipeline hashed on one of `renderPasses`. Only safe
-        // when the caller guarantees GPU idleness for them - the render-pass manager
-        // calls this (via the renderer) for passes its own >1024-boundary-idle sweep
-        // just evicted, and a pipeline hashed on those handles is only ever bound by
-        // draws that also hit the render-pass entries. Also closes the handle-recycling
-        // hazard: a recycled VkRenderPass value must never serve a stale pipeline.
-        // Batched: one cache scan regardless of how many passes died in the sweep.
-        // Returns the number destroyed (callers invalidate memos when non-zero).
-        Uint32 EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses);
-        // Destroys every cached pipeline built from the program with content hash
-        // `programHash`. Called from the ProgramFactory eviction path, which proves the
-        // same >1024-boundary idleness (the program's pipelines are only bound by draws
-        // that stamp its factory entry). Returns the number destroyed.
-        Uint32 EvictByProgramHash(HashType programHash);
-
         // Driver quirk: suppress depth writes on accumulation-blended pipelines. Multi-pass
         // depth-equality rendering (a blended prepass writes depth that later passes re-test
         // with an equality-inclusive compare on the re-rasterized geometry) requires
@@ -107,26 +87,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         static Bool ShouldSuppressDepthWrite(const PipelineCreatePayload& payload);
 
     private:
-        struct PipelineCacheEntry {
-            VkPipeline pipeline = VK_NULL_HANDLE;
-            // The hashed inputs the eviction paths key on: programHash ties the entry to
-            // its ProgramFactory entry, renderPass records the exact handle the hash
-            // folded in (the hash is one-way, so targeted eviction needs them verbatim).
-            HashType programHash = 0;
-            VkRenderPass renderPass = VK_NULL_HANDLE;
-            // Frame-boundary counter value of the last GetOrCreatePipeline hit; drives
-            // cache eviction (see OnFrameBoundary).
-            Uint64 lastUsedFrame = 0;
-        };
-
         VkPipeline CreatePipeline(const PipelineCreatePayload& payload) const;
 
         VkDevice m_device = VK_NULL_HANDLE;
         const VulkanRendererConfig& m_config;
         VkPipelineCache m_pipelineCache = VK_NULL_HANDLE;
-        UnorderedMap<HashType, PipelineCacheEntry> m_cache;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameCounter = 0;
+        UnorderedMap<HashType, VkPipeline> m_cache;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
         static inline Bool s_suppressBlendedDepthWrite = false;
     };

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.cpp

@@ -12,10 +12,7 @@
 #include "MG_Util/ShaderTranspiler/ShaderCompiler.h"
 #include "MG_Util/ShaderTranspiler/SpvcSession.h"
 #include "MG_Util/ShaderTranspiler/Types.h"
-#include <cmath>
-#include <cstdio>
 #include <cstring>
-#include <unordered_set>
 #include <spirv-tools/libspirv.h>
 #include <spirv-tools/optimizer.hpp>
 #include <source/opt/build_module.h>
@@ -926,610 +923,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             ProgramFactory::CompileOptionFlags m_transformFlags;
         };
 
-        // Adreno 650 (driver 512.502) faults the GPU on an implicit-LOD sample of a full-screen
-        // colour render target: the texture unit's derivative path reads outside the image's
-        // allocation even though the sampler clamps LOD to 0 and the mapping is 1:1. MobileGL's
-        // own default-framebuffer blit shader works around it with textureLod, but an
-        // application's shader (Minecraft's blit.fsh is `texture(InSampler, texCoord)`) cannot be
-        // edited - so rewrite the sample at the SPIR-V level instead.
-        //
-        // The rewrite is only requested for draws whose every sampler binding is clamped to one
-        // mip level, where explicit LOD 0 is exactly what the implicit form must already produce:
-        // lambda' = clamp(lambda + bias, minLod, maxLod) with minLod = maxLod = 0. Bias and MinLod
-        // operands are therefore dropped rather than translated.
-        class ForceExplicitLod0SamplePass final : public spvtools::opt::Pass {
-        public:
-            const char* name() const override { return "force-explicit-lod0-sample"; }
-
-            Status Process() override {
-                Bool isFragment = false;
-                for (auto& entryPoint : get_module()->entry_points()) {
-                    if (entryPoint.opcode() != spv::Op::OpEntryPoint) continue;
-                    if (static_cast<spv::ExecutionModel>(entryPoint.GetSingleWordInOperand(0)) ==
-                        spv::ExecutionModel::Fragment) {
-                        isFragment = true;
-                        break;
-                    }
-                }
-                if (!isFragment) return Status::SuccessWithoutChange;
-
-                // Plan first, mutate second. Materializing the LOD constant is itself a module
-                // change, so it must not happen unless at least one rewrite is going to follow -
-                // otherwise the pass would grow the binary while reporting SuccessWithoutChange.
-                Vector<RewritePlan> plans;
-                for (auto& function : *get_module()) {
-                    for (auto& block : function) {
-                        for (auto& inst : block) {
-                            RewritePlan plan{};
-                            if (PlanRewrite(&inst, plan)) plans.push_back(Move(plan));
-                        }
-                    }
-                }
-                if (plans.empty()) return Status::SuccessWithoutChange;
-
-                const Uint32 zeroId = GetFloatZeroId();
-                if (zeroId == 0) return Status::SuccessWithoutChange;
-
-                for (auto& plan : plans) {
-                    plan.operands.push_back({SPV_OPERAND_TYPE_ID, {zeroId}});
-                    for (auto& operand : plan.trailingOperands) {
-                        plan.operands.push_back(operand);
-                    }
-                    plan.instruction->SetOpcode(plan.opcode);
-                    plan.instruction->SetInOperands(Move(plan.operands));
-                }
-                // Opcodes and operand lists changed underneath every cached analysis.
-                context()->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisNone);
-                return Status::SuccessWithChange;
-            }
-
-        private:
-            struct RewritePlan {
-                spvtools::opt::Instruction* instruction = nullptr;
-                spv::Op opcode = spv::Op::OpNop;
-                // Everything up to and including the Image Operands mask; the Lod id and the
-                // trailing operand values are appended once the constant exists.
-                Vector<spvtools::opt::Operand> operands;
-                Vector<spvtools::opt::Operand> trailingOperands;
-            };
-
-            // Image Operands bits that may accompany an implicit-LOD sample, in the canonical
-            // ascending order SPIR-V requires the operand values to appear in.
-            static constexpr Uint32 kBias = 0x1;
-            static constexpr Uint32 kLod = 0x2;
-            static constexpr Uint32 kGrad = 0x4;
-            static constexpr Uint32 kConstOffset = 0x8;
-            static constexpr Uint32 kOffset = 0x10;
-            static constexpr Uint32 kConstOffsets = 0x20;
-            static constexpr Uint32 kSample = 0x40;
-            static constexpr Uint32 kMinLod = 0x80;
-            static constexpr Uint32 kKnownMask = 0xFF;
-
-            Uint32 GetFloatZeroId() {
-                // Reuse a 32-bit float type already in the module; a shader that samples always has
-                // one, and looking it up avoids depending on type-creation API details.
-                Uint32 floatTypeId = 0;
-                for (auto& inst : get_module()->types_values()) {
-                    if (inst.opcode() == spv::Op::OpTypeFloat && inst.NumInOperands() >= 1 &&
-                        inst.GetSingleWordInOperand(0) == 32) {
-                        floatTypeId = inst.result_id();
-                        break;
-                    }
-                }
-                if (floatTypeId == 0) return 0;
-
-                const auto* floatType = context()->get_type_mgr()->GetType(floatTypeId);
-                if (floatType == nullptr) return 0;
-                const auto zeroBits = std::bit_cast<Uint32>(0.0f);
-                const auto* zeroConst = context()->get_constant_mgr()->GetConstant(floatType, {zeroBits});
-                if (zeroConst == nullptr) return 0;
-                auto* zeroInst = context()->get_constant_mgr()->GetDefiningInstruction(zeroConst);
-                return zeroInst != nullptr ? zeroInst->result_id() : 0;
-            }
-
-            static Bool MapOpcode(spv::Op op, spv::Op& outOpcode, Uint32& outFixedOperandCount) {
-                switch (op) {
-                case spv::Op::OpImageSampleImplicitLod:
-                    outOpcode = spv::Op::OpImageSampleExplicitLod;
-                    outFixedOperandCount = 2; // sampled image, coordinate
-                    return true;
-                case spv::Op::OpImageSampleProjImplicitLod:
-                    outOpcode = spv::Op::OpImageSampleProjExplicitLod;
-                    outFixedOperandCount = 2;
-                    return true;
-                case spv::Op::OpImageSampleDrefImplicitLod:
-                    outOpcode = spv::Op::OpImageSampleDrefExplicitLod;
-                    outFixedOperandCount = 3; // sampled image, coordinate, Dref
-                    return true;
-                case spv::Op::OpImageSampleProjDrefImplicitLod:
-                    outOpcode = spv::Op::OpImageSampleProjDrefExplicitLod;
-                    outFixedOperandCount = 3;
-                    return true;
-                default:
-                    return false;
-                }
-            }
-
-            static Bool PlanRewrite(spvtools::opt::Instruction* inst, RewritePlan& outPlan) {
-                spv::Op newOpcode = spv::Op::OpNop;
-                Uint32 fixedCount = 0;
-                if (!MapOpcode(inst->opcode(), newOpcode, fixedCount)) return false;
-                if (inst->NumInOperands() < fixedCount) return false;
-
-                Uint32 mask = 0;
-                Uint32 next = fixedCount;
-                if (inst->NumInOperands() > fixedCount) {
-                    mask = inst->GetSingleWordInOperand(fixedCount);
-                    next = fixedCount + 1;
-                }
-                // An operand this pass does not model would be silently reordered or dropped, and
-                // Grad cannot legally accompany an implicit-LOD sample: leave such an instruction be.
-                if ((mask & ~kKnownMask) != 0 || (mask & kGrad) != 0) return false;
-
-                Vector<spvtools::opt::Operand> fixedOperands;
-                fixedOperands.reserve(fixedCount + 1);
-                for (Uint32 i = 0; i < fixedCount; ++i) {
-                    fixedOperands.push_back(inst->GetInOperand(i));
-                }
-
-                // Collect the surviving operand values in the same ascending-bit order they were
-                // encoded in, so the rebuilt list stays canonical.
-                Uint32 keptMask = kLod;
-                Vector<spvtools::opt::Operand> keptOperands;
-                static constexpr Uint32 kOrderedBits[] = {kBias,   kLod,          kGrad,   kConstOffset,
-                                                          kOffset, kConstOffsets, kSample, kMinLod};
-                for (const Uint32 bit : kOrderedBits) {
-                    if ((mask & bit) == 0) continue;
-                    if (next >= inst->NumInOperands()) return false;
-                    const spvtools::opt::Operand value = inst->GetInOperand(next++);
-                    // Bias and MinLod only shift a lambda that is already clamped to 0, and any
-                    // original Lod is replaced by the constant the caller appends.
-                    if (bit == kBias || bit == kMinLod || bit == kLod) continue;
-                    keptMask |= bit;
-                    keptOperands.push_back(value);
-                }
-
-                fixedOperands.push_back({SPV_OPERAND_TYPE_IMAGE, {keptMask}});
-                outPlan.instruction = inst;
-                outPlan.opcode = newOpcode;
-                outPlan.operands = Move(fixedOperands);
-                outPlan.trailingOperands = Move(keptOperands);
-                return true;
-            }
-        };
-
-        spvtools::Optimizer::PassToken CreateForceExplicitLod0SamplePass() {
-            return spvtools::Optimizer::PassToken(MakeUnique<ForceExplicitLod0SamplePass>());
-        }
-
-        // TEMP-PERFDIAG: measure what fragment-stage fp32 costs on this GPU. Desktop GLSL carries
-        // no precision qualifiers, so everything reaches the driver as full fp32 while Adreno runs
-        // fp16 at twice the rate. Decorating every float-typed result in a fragment entry point
-        // with RelaxedPrecision is the blunt "all mediump" upper bound - it changes results, so it
-        // is a probe, not a shipping transform. Toggled by /sdcard/MG/exp_relaxed_precision.
-        class RelaxedPrecisionProbePass final : public spvtools::opt::Pass {
-        public:
-            const char* name() const override { return "relaxed-precision-probe"; }
-
-            Status Process() override {
-                Bool isFragment = false;
-                for (auto& entryPoint : get_module()->entry_points()) {
-                    if (entryPoint.opcode() != spv::Op::OpEntryPoint) continue;
-                    if (static_cast<spv::ExecutionModel>(entryPoint.GetSingleWordInOperand(0)) ==
-                        spv::ExecutionModel::Fragment) {
-                        isFragment = true;
-                        break;
-                    }
-                }
-                if (!isFragment) return Status::SuccessWithoutChange;
-
-                // Every 32-bit-float scalar/vector/matrix type in the module. Anything wider (f64)
-                // or narrower is left alone: RelaxedPrecision only has meaning for 32-bit floats.
-                std::unordered_set<Uint32> relaxableTypes;
-                for (auto& type : get_module()->types_values()) {
-                    const Uint32 typeId = type.result_id();
-                    if (typeId == 0) continue;
-                    switch (type.opcode()) {
-                    case spv::Op::OpTypeFloat:
-                        if (type.GetSingleWordInOperand(0) == 32) relaxableTypes.insert(typeId);
-                        break;
-                    case spv::Op::OpTypeVector:
-                    case spv::Op::OpTypeMatrix:
-                        if (relaxableTypes.count(type.GetSingleWordInOperand(0)) != 0) {
-                            relaxableTypes.insert(typeId);
-                        }
-                        break;
-                    default:
-                        break;
-                    }
-                }
-                if (relaxableTypes.empty()) return Status::SuccessWithoutChange;
-
-                Vector<Uint32> targets;
-                for (auto& function : *get_module()) {
-                    for (auto& block : function) {
-                        for (auto& inst : block) {
-                            const Uint32 resultId = inst.result_id();
-                            if (resultId == 0) continue;
-                            if (relaxableTypes.count(inst.type_id()) == 0) continue;
-                            targets.push_back(resultId);
-                        }
-                    }
-                }
-                if (targets.empty()) return Status::SuccessWithoutChange;
-
-                for (const Uint32 id : targets) {
-                    context()->get_decoration_mgr()->AddDecoration(
-                        id, static_cast<Uint32>(spv::Decoration::RelaxedPrecision));
-                }
-                context()->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisNone);
-                return Status::SuccessWithChange;
-            }
-        };
-
-        // Relax fragment-stage arithmetic that provably came out of a texture read. Desktop GLSL
-        // has no precision qualifiers, so every fragment value reaches the driver as fp32 while
-        // Adreno runs fp16 at twice the rate - and a texel is at most 8 bits per channel, which
-        // fp16's 11-bit mantissa carries exactly. Seeding at image reads and propagating only
-        // through operations whose every input is already relaxed keeps everything the shader
-        // computes from other sources (screen coordinates, depth, wide-range uniforms) at full
-        // precision, which is where fp16 would actually go wrong: fp16 cannot even represent a
-        // 3044-pixel gl_FragCoord.x exactly.
-        class RelaxTextureDerivedPrecisionPass final : public spvtools::opt::Pass {
-        public:
-            const char* name() const override { return "relax-texture-derived-precision"; }
-
-            Status Process() override {
-                if (!IsFragmentEntryPoint()) return Status::SuccessWithoutChange;
-                // A shader that drives depth or coverage itself is out of scope: those values must
-                // stay exact, and proving which computations feed them is not worth it here.
-                if (WritesDepthOrSampleMask()) return Status::SuccessWithoutChange;
-
-                CollectRelaxableFloatTypes();
-                if (m_relaxableTypes.empty()) return Status::SuccessWithoutChange;
-
-                // Whitelisting from texture reads captures nothing in practice: MC's fragment
-                // shaders multiply every texel by an interpolated colour and a UBO value, so one
-                // un-relaxed operand vetoes the whole expression (measured: no fps change).
-                // Taint the few genuinely precision-critical sources instead and relax the rest.
-                std::unordered_set<Uint32> tainted;
-                CollectPrecisionCriticalSeeds(tainted);
-                Bool grew = true;
-                while (grew) {
-                    grew = false;
-                    for (auto& function : *get_module()) {
-                        for (auto& block : function) {
-                            for (auto& inst : block) {
-                                const Uint32 resultId = inst.result_id();
-                                if (resultId == 0 || tainted.count(resultId) != 0) continue;
-                                if (!AnyOperandTainted(inst, tainted)) continue;
-                                tainted.insert(resultId);
-                                grew = true;
-                            }
-                        }
-                    }
-                }
-
-                std::unordered_set<Uint32> relaxed;
-                for (auto& function : *get_module()) {
-                    for (auto& block : function) {
-                        for (auto& inst : block) {
-                            const Uint32 resultId = inst.result_id();
-                            if (resultId == 0 || tainted.count(resultId) != 0) continue;
-                            if (m_relaxableTypes.count(inst.type_id()) == 0) continue;
-                            relaxed.insert(resultId);
-                        }
-                    }
-                }
-                if (relaxed.empty()) return Status::SuccessWithoutChange;
-
-                for (const Uint32 id : relaxed) {
-                    context()->get_decoration_mgr()->AddDecoration(
-                        id, static_cast<Uint32>(spv::Decoration::RelaxedPrecision));
-                }
-                context()->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisNone);
-                return Status::SuccessWithChange;
-            }
-
-        private:
-            std::unordered_set<Uint32> m_relaxableTypes;
-
-            Bool IsFragmentEntryPoint() const {
-                for (auto& entryPoint : get_module()->entry_points()) {
-                    if (entryPoint.opcode() != spv::Op::OpEntryPoint) continue;
-                    if (static_cast<spv::ExecutionModel>(entryPoint.GetSingleWordInOperand(0)) ==
-                        spv::ExecutionModel::Fragment) {
-                        return true;
-                    }
-                }
-                return false;
-            }
-
-            Bool WritesDepthOrSampleMask() const {
-                for (auto& annotation : get_module()->annotations()) {
-                    if (annotation.opcode() != spv::Op::OpDecorate) continue;
-                    if (static_cast<spv::Decoration>(annotation.GetSingleWordInOperand(1)) !=
-                        spv::Decoration::BuiltIn) {
-                        continue;
-                    }
-                    const auto builtIn = static_cast<spv::BuiltIn>(annotation.GetSingleWordInOperand(2));
-                    if (builtIn == spv::BuiltIn::FragDepth || builtIn == spv::BuiltIn::SampleMask) {
-                        return true;
-                    }
-                }
-                return false;
-            }
-
-            void CollectRelaxableFloatTypes() {
-                m_relaxableTypes.clear();
-                for (auto& type : get_module()->types_values()) {
-                    const Uint32 typeId = type.result_id();
-                    if (typeId == 0) continue;
-                    switch (type.opcode()) {
-                    case spv::Op::OpTypeFloat:
-                        if (type.GetSingleWordInOperand(0) == 32) m_relaxableTypes.insert(typeId);
-                        break;
-                    case spv::Op::OpTypeVector:
-                        if (m_relaxableTypes.count(type.GetSingleWordInOperand(0)) != 0) {
-                            m_relaxableTypes.insert(typeId);
-                        }
-                        break;
-                    default:
-                        break;
-                    }
-                }
-            }
-
-            void CollectImageReadSeeds(std::unordered_set<Uint32>& relaxed) const {
-                for (auto& function : *get_module()) {
-                    for (auto& block : function) {
-                        for (auto& inst : block) {
-                            const Uint32 resultId = inst.result_id();
-                            if (resultId == 0 || m_relaxableTypes.count(inst.type_id()) == 0) continue;
-                            // Interpolated user varyings seed too, or propagation dies at the
-                            // first `texel * vertexColour`: the load of an Input can never be
-                            // relaxed by the rule below (its operand is a pointer), so a single
-                            // varying vetoes every downstream operation. This is what ESSL's
-                            // mediump varyings already mean. Built-ins are excluded - gl_FragCoord
-                            // carries pixel coordinates that fp16 cannot represent exactly.
-                            if (inst.opcode() == spv::Op::OpLoad && IsNonBuiltInFragmentInput(inst)) {
-                                relaxed.insert(resultId);
-                                continue;
-                            }
-                            switch (inst.opcode()) {
-                            case spv::Op::OpImageSampleImplicitLod:
-                            case spv::Op::OpImageSampleExplicitLod:
-                            case spv::Op::OpImageSampleProjImplicitLod:
-                            case spv::Op::OpImageSampleProjExplicitLod:
-                            case spv::Op::OpImageSampleDrefImplicitLod:
-                            case spv::Op::OpImageSampleDrefExplicitLod:
-                            case spv::Op::OpImageFetch:
-                            case spv::Op::OpImageRead:
-                            case spv::Op::OpImageGather:
-                                relaxed.insert(resultId);
-                                break;
-                            default:
-                                break;
-                            }
-                        }
-                    }
-                }
-            }
-
-            // OpLoad straight out of a fragment Input variable that carries no BuiltIn decoration.
-            // Only a direct load counts: a load through an access chain could be indexing a
-            // structure whose other members are not interpolated colour data.
-            Bool IsNonBuiltInFragmentInput(const spvtools::opt::Instruction& load) const {
-                const Uint32 pointerId = load.GetSingleWordInOperand(0);
-                const auto* pointer = context()->get_def_use_mgr()->GetDef(pointerId);
-                if (pointer == nullptr || pointer->opcode() != spv::Op::OpVariable) return false;
-                if (static_cast<spv::StorageClass>(pointer->GetSingleWordInOperand(0)) !=
-                    spv::StorageClass::Input) {
-                    return false;
-                }
-                Bool isBuiltIn = false;
-                context()->get_decoration_mgr()->ForEachDecoration(
-                    pointerId, static_cast<Uint32>(spv::Decoration::BuiltIn),
-                    [&isBuiltIn](const spvtools::opt::Instruction&) { isBuiltIn = true; });
-                return !isBuiltIn;
-            }
-
-            // A float constant small enough that fp16 represents it without surprise. Colour math
-            // constants (0, 1, 0.5, 255, gamma exponents) all live here; anything larger is
-            // treated as unknown so it stops propagation.
-            Bool IsBoundedFloatConstant(Uint32 id) const {
-                const auto* constant = context()->get_constant_mgr()->FindDeclaredConstant(id);
-                if (constant == nullptr) return false;
-                if (const auto* scalar = constant->AsFloatConstant()) {
-                    const float value = scalar->GetFloat();
-                    return std::isfinite(value) && std::fabs(value) <= 1024.0f;
-                }
-                if (const auto* composite = constant->AsVectorConstant()) {
-                    for (const auto* component : composite->GetComponents()) {
-                        const auto* scalar = component->AsFloatConstant();
-                        if (scalar == nullptr) return false;
-                        const float value = scalar->GetFloat();
-                        if (!std::isfinite(value) || std::fabs(value) > 1024.0f) return false;
-                    }
-                    return true;
-                }
-                return false;
-            }
-
-            // Precision-critical sources: a built-in fragment input. gl_FragCoord is the one that
-            // matters - fp16 cannot represent a 3044-pixel x coordinate exactly, and anything
-            // derived from it (screen-space effects, manual depth reconstruction) would visibly
-            // quantise. Everything else a fragment shader reads is colour-range data.
-            void CollectPrecisionCriticalSeeds(std::unordered_set<Uint32>& tainted) const {
-                for (auto& function : *get_module()) {
-                    for (auto& block : function) {
-                        for (auto& inst : block) {
-                            if (inst.opcode() != spv::Op::OpLoad || inst.result_id() == 0) continue;
-                            if (IsBuiltInInputLoad(inst)) tainted.insert(inst.result_id());
-                        }
-                    }
-                }
-            }
-
-            Bool IsBuiltInInputLoad(const spvtools::opt::Instruction& load) const {
-                const Uint32 pointerId = load.GetSingleWordInOperand(0);
-                const auto* pointer = context()->get_def_use_mgr()->GetDef(pointerId);
-                if (pointer == nullptr || pointer->opcode() != spv::Op::OpVariable) return false;
-                if (static_cast<spv::StorageClass>(pointer->GetSingleWordInOperand(0)) !=
-                    spv::StorageClass::Input) {
-                    return false;
-                }
-                Bool isBuiltIn = false;
-                context()->get_decoration_mgr()->ForEachDecoration(
-                    pointerId, static_cast<Uint32>(spv::Decoration::BuiltIn),
-                    [&isBuiltIn](const spvtools::opt::Instruction&) { isBuiltIn = true; });
-                return isBuiltIn;
-            }
-
-            Bool AnyOperandTainted(const spvtools::opt::Instruction& inst,
-                                   const std::unordered_set<Uint32>& tainted) const {
-                const Uint32 operandCount = inst.NumInOperands();
-                for (Uint32 i = 0; i < operandCount; ++i) {
-                    const auto& operand = inst.GetInOperand(i);
-                    if (!spvIsIdType(operand.type)) continue;
-                    if (IsNonNumericOperand(inst, i)) continue;
-                    if (tainted.count(operand.words[0]) != 0) return true;
-                }
-                return false;
-            }
-
-            Bool AllValueOperandsRelaxed(const spvtools::opt::Instruction& inst,
-                                         const std::unordered_set<Uint32>& relaxed) const {
-                switch (inst.opcode()) {
-                // Pointer-typed plumbing: relaxing the loaded value would say nothing about the
-                // memory it came from, and the pointer operand can never be in the set.
-                case spv::Op::OpLoad:
-                case spv::Op::OpStore:
-                case spv::Op::OpAccessChain:
-                case spv::Op::OpInBoundsAccessChain:
-                case spv::Op::OpFunctionCall:
-                    return false;
-                default:
-                    break;
-                }
-
-                Bool sawValueOperand = false;
-                Bool allRelaxed = true;
-                const Uint32 operandCount = inst.NumInOperands();
-                for (Uint32 i = 0; i < operandCount; ++i) {
-                    const auto& operand = inst.GetInOperand(i);
-                    if (!spvIsIdType(operand.type)) continue; // literals: selectors, swizzle indices
-                    const Uint32 id = operand.words[0];
-                    // OpPhi's block labels, OpSelect's condition and OpExtInst's instruction-set id
-                    // are ids that carry no numeric precision; skip them rather than let them veto.
-                    if (IsNonNumericOperand(inst, i)) continue;
-                    sawValueOperand = true;
-                    if (relaxed.count(id) != 0) continue;
-                    if (IsBoundedFloatConstant(id)) continue;
-                    allRelaxed = false;
-                    break;
-                }
-                return sawValueOperand && allRelaxed;
-            }
-
-            static Bool IsNonNumericOperand(const spvtools::opt::Instruction& inst, Uint32 index) {
-                switch (inst.opcode()) {
-                case spv::Op::OpPhi:
-                    return (index % 2) == 1; // parent block labels
-                case spv::Op::OpSelect:
-                    return index == 0; // condition
-                case spv::Op::OpExtInst:
-                    return index == 0; // extended instruction set
-                default:
-                    return false;
-                }
-            }
-        };
-
-        // TEMP-PERFDIAG: A/B switch between the scoped transform and the all-float upper bound.
-        Bool PerfDiagRelaxAllPrecision() {
-            static const Bool enabled = [] {
-                std::FILE* probe = std::fopen("/sdcard/MG/exp_relaxed_precision_all", "rb");
-                if (probe == nullptr) return false;
-                std::fclose(probe);
-                MGLOG_I("[PERFDIAG] fragment RelaxedPrecision: ALL floats (upper-bound probe)");
-                return true;
-            }();
-            return enabled;
-        }
-
-        // TEMP-PERFDIAG: lets a run turn the transform off entirely for an A/B baseline.
-        Bool PerfDiagRelaxedPrecisionEnabled() {
-            static const Bool disabled = [] {
-                std::FILE* probe = std::fopen("/sdcard/MG/exp_no_relaxed_precision", "rb");
-                if (probe == nullptr) return false;
-                std::fclose(probe);
-                MGLOG_I("[PERFDIAG] fragment RelaxedPrecision DISABLED");
-                return true;
-            }();
-            return !disabled;
-        }
-
-        Bool TransformSpirvForExplicitLod0Sampling(const Vector<Uint>& input, Vector<Uint>& output) {
-            if (input.empty()) {
-                output.clear();
-                return true;
-            }
-            spvtools::Optimizer optimizer(SPV_ENV_VULKAN_1_3);
-            spvtools::OptimizerOptions options;
-            // Matches the position-fix pass: this build of spirv-tools asserts rather than
-            // reporting, so validation stays off in the shipping path.
-            options.set_run_validator(false);
-            optimizer.SetMessageConsumer([](spv_message_level_t, const char*, const spv_position_t&,
-                                            const char* message) {
-                MGLOG_E("Vulkan: explicit-LOD0 pass: %s", message != nullptr ? message : "");
-            });
-            optimizer.RegisterPass(CreateForceExplicitLod0SamplePass());
-
-            const Bool success = optimizer.Run(input.data(), input.size(), &output, options);
-            if (!success) {
-                MGLOG_E("Vulkan: explicit-LOD0 sampling pass failed; keeping the original module");
-                output = input;
-            }
-            return success;
-        }
-
         spvtools::Optimizer::PassToken CreateGlToVulkanPositionFixPass(
             ProgramFactory::CompileOptionFlags transformFlags) {
             return spvtools::Optimizer::PassToken(MakeUnique<GlToVulkanPositionFixPass>(transformFlags));
         }
 
-        // TEMP-PERFDIAG
-        Bool TransformSpirvForRelaxedPrecisionProbe(const Vector<Uint>& input, Vector<Uint>& output) {
-            if (input.empty()) {
-                output.clear();
-                return true;
-            }
-            spvtools::Optimizer optimizer(SPV_ENV_VULKAN_1_3);
-            spvtools::OptimizerOptions options;
-            options.set_run_validator(false);
-            optimizer.SetMessageConsumer([](spv_message_level_t, const char*, const spv_position_t&,
-                                            const char* message) {
-                MGLOG_E("Vulkan: relaxed-precision probe: %s", message != nullptr ? message : "");
-            });
-            // SSA promotion first: glslang emits function-local variables with stores and loads,
-            // and a load can never be relaxed (its operand is a pointer), so without this the
-            // propagation below dies at the first temporary.
-            optimizer.RegisterPass(spvtools::CreateLocalMultiStoreElimPass());
-            if (PerfDiagRelaxAllPrecision()) {
-                optimizer.RegisterPass(spvtools::Optimizer::PassToken(MakeUnique<RelaxedPrecisionProbePass>()));
-            } else {
-                optimizer.RegisterPass(
-                    spvtools::Optimizer::PassToken(MakeUnique<RelaxTextureDerivedPrecisionPass>()));
-            }
-            const Bool success = optimizer.Run(input.data(), input.size(), &output, options);
-            if (!success) {
-                MGLOG_E("Vulkan: relaxed-precision probe failed; keeping the original module");
-                output = input;
-            }
-            return success;
-        }
-
         Bool TransformSpirvForVulkanPositionFix(const Vector<Uint>& input, Vector<Uint>& output,
                                                 ProgramFactory::CompileOptionFlags transformFlags) {
             if (input.empty()) {
@@ -2552,17 +1950,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
-            // Every draw/dispatch funnels through this lookup (the renderer memos only
-            // skip re-hashing, never the factory lookup), so an actively-used entry is
-            // stamped at least once per frame boundary and can never be aged out while
-            // any in-flight command buffer still references it.
-            it->second.lastUsedFrame = m_frameCounter;
             return it->second;
         }
 
         auto& entry = m_cache[hash];
         entry.hash = hash;
-        entry.lastUsedFrame = m_frameCounter;
         auto& shaders = program.GetAttachedShaders();
         auto& spirv = program.GetGeneratedSpirv();
         Vector<Vector<Uint>> moduleSpirvs(spirv.size());
@@ -2580,23 +1972,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 moduleSpirvs[i] = spv;
             }
 
-            if ((flags & ProgramFactory::CompileOptionBit::ExplicitLod0Sampling) && shaders[i] &&
-                shaders[i]->GetShaderStage() == ShaderStage::Fragment) {
-                Vector<Uint> explicitLodSpirv;
-                if (TransformSpirvForExplicitLod0Sampling(moduleSpirvs[i], explicitLodSpirv)) {
-                    moduleSpirvs[i] = Move(explicitLodSpirv);
-                }
-            }
-
-            if ((flags & ProgramFactory::CompileOptionBit::RelaxedFragmentPrecision) &&
-                PerfDiagRelaxedPrecisionEnabled() && shaders[i] &&
-                shaders[i]->GetShaderStage() == ShaderStage::Fragment) {
-                Vector<Uint> relaxedSpirv;
-                if (TransformSpirvForRelaxedPrecisionProbe(moduleSpirvs[i], relaxedSpirv)) {
-                    moduleSpirvs[i] = Move(relaxedSpirv);
-                }
-            }
-
             // GL apps depend on cross-program position invariance for multi-pass equality
             // depth tests (MC 26.3's OIT re-draws the cloud geometry with GEQUAL against the
             // depth its own first pass wrote); decorate Position outputs Invariant so
@@ -2693,42 +2068,4 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         return entry;
     }
-
-    void ProgramFactory::OnFrameBoundary() {
-        ++m_frameCounter;
-
-        // Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
-        // idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
-        // any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
-        // so its shader modules and layouts are destroyed immediately - no deferred-
-        // destroy machinery needed. Eviction is content-based, never tied to
-        // glDeleteProgram: the cache is content-hash-shared across GL programs, so a
-        // delete-driven erase could free an entry another live program still resolves.
-        // An evicted entry self-heals - the frontend program keeps its generated
-        // SPIR-V, so the next GetOrCreateProgram rebuilds it (this also covers the
-        // renderer's internal blit/depth-mipmap programs).
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeFrames = 1024;
-        if ((m_frameCounter % kSweepInterval) != 0) {
-            return;
-        }
-
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
-                const HashType hash = it->first;
-                const VkDescriptorSetLayout descriptorSetLayout = it->second.descriptorSetLayout;
-                MGLOG_D("ProgramFactory::OnFrameBoundary: evicting idle program entry hash=0x%llx",
-                        static_cast<unsigned long long>(hash));
-                // erase runs ~VkProgramObject (modules/layouts destroyed); notify after
-                // so an observer never observes a half-destroyed entry through a lookup.
-                // Observers only need the handle values to purge their keyed caches.
-                it = m_cache.erase(it);
-                if (m_evictionObserver != nullptr) {
-                    m_evictionObserver->OnProgramEvicted(hash, descriptorSetLayout);
-                }
-            } else {
-                ++it;
-            }
-        }
-    }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.h

@@ -42,16 +42,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             SurfaceRotate90 = 1 << 2,
             SurfaceRotate180 = 1 << 3,
             SurfaceRotate270 = 1 << 4,
-            // Rewrites the fragment stage's implicit-LOD image samples to explicit LOD 0.
-            // Only ever set for a draw whose every sampler binding is clamped to a single mip
-            // level, which makes the two forms produce identical texels (the implicit lambda is
-            // clamped into [minLod, maxLod] = [0, 0] regardless of derivatives or bias).
-            ExplicitLod0Sampling = 1 << 5,
-            // Fragment arithmetic may run at relaxed (fp16) precision. Only requested for draws
-            // where every sampled texture and every colour attachment is an 8-bit-or-less
-            // normalized format, so nothing the shader reads or writes carries more precision
-            // than fp16 already represents exactly.
-            RelaxedFragmentPrecision = 1 << 6,
         };
         using CompileOptionFlags = Flags<CompileOptionBit>;
         using HashType = Uint64;
@@ -98,9 +88,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             // gl_FragDepth); shader-computed depth is immune to the cross-pipeline
             // position-invariance quirk (see PipelineFactory::ShouldSuppressDepthWrite).
             Bool fragmentReplacesDepth = false;
-            // Frame-boundary counter value of the last GetOrCreateProgram hit; drives
-            // cache eviction (see OnFrameBoundary).
-            Uint64 lastUsedFrame = 0;
 
             static inline VkDevice s_device = VK_NULL_HANDLE;
 
@@ -137,7 +124,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 producerOutputComponentCount = other.producerOutputComponentCount;
                 fragmentInputComponentCount = other.fragmentInputComponentCount;
                 fragmentReplacesDepth = other.fragmentReplacesDepth;
-                lastUsedFrame = other.lastUsedFrame;
                 other.hash = 0;
                 other.descriptorSetLayout = VK_NULL_HANDLE;
                 other.pipelineLayout = VK_NULL_HANDLE;
@@ -149,7 +135,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 other.producerOutputComponentCount = 0;
                 other.fragmentInputComponentCount = 0;
                 other.fragmentReplacesDepth = false;
-                other.lastUsedFrame = 0;
             }
             VkProgramObject& operator=(VkProgramObject&& other) noexcept {
                 if (this == &other) {
@@ -185,7 +170,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 producerOutputComponentCount = other.producerOutputComponentCount;
                 fragmentInputComponentCount = other.fragmentInputComponentCount;
                 fragmentReplacesDepth = other.fragmentReplacesDepth;
-                lastUsedFrame = other.lastUsedFrame;
                 other.hash = 0;
                 other.descriptorSetLayout = VK_NULL_HANDLE;
                 other.pipelineLayout = VK_NULL_HANDLE;
@@ -197,7 +181,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 other.producerOutputComponentCount = 0;
                 other.fragmentInputComponentCount = 0;
                 other.fragmentReplacesDepth = false;
-                other.lastUsedFrame = 0;
                 return *this;
             }
 
@@ -227,18 +210,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             }
         };
 
-        // Notified when the OnFrameBoundary sweep destroys an aged-out cache entry,
-        // carrying the entry's content hash and the VkDescriptorSetLayout it owned.
-        // Dependent caches (compute pipelines, PipelineFactory entries, UniformManager's
-        // per-layout descriptor sets) must purge in the same step: after vkDestroy the
-        // layout handle value may be recycled for an unrelated layout, and the program
-        // hash may be re-inserted by a later rebuild of the same content.
-        class IEvictionObserver {
-        public:
-            virtual ~IEvictionObserver() = default;
-            virtual void OnProgramEvicted(HashType programHash, VkDescriptorSetLayout descriptorSetLayout) = 0;
-        };
-
         explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings = 16,
                                 Bool shaderDrawParametersEnabled = false,
                                 Bool unformattedFloatStorageImagesEnabled = false)
@@ -254,13 +225,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const VkProgramObject& GetOrCreateProgram(
             const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags);
 
-        // Observer may be null (no notifications). Not owned.
-        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
-        // Frame boundary hook: ages the program cache and evicts long-unused entries
-        // (their command buffers retired many frames ago), mirroring
-        // VkRenderPassManager::OnPresent's sweep.
-        void OnFrameBoundary();
-
         static VkShaderStageFlagBits ToVkStage(ShaderStage stage);
         static VkFormat ConvertSpirvImageFormatToVkFormat(SpvImageFormat format);
         static SamplerNumericDomain UniformTypeToSamplerNumericDomain(GLenum glType);
@@ -302,9 +266,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // shaderStorageImageReadWithoutFormat and shaderStorageImageWriteWithoutFormat.
         Bool m_unformattedFloatStorageImagesEnabled = false;
         mutable ProgramLookupCache m_lastLookup;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameCounter = 0;
-        IEvictionObserver* m_evictionObserver = nullptr;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.cpp

@@ -247,11 +247,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_surfaceFormat = {createInfo.imageFormat, createInfo.imageColorSpace};
         m_extent = createInfo.imageExtent;
-        // The surface-space extent this swapchain was built from, i.e. before the
-        // quarter-turn swap above. Out-of-date checks must compare in THIS space: comparing a
-        // freshly queried currentExtent against the swapped m_extent flips axes every rotation
-        // and makes the comparison alternate forever.
-        m_surfaceExtent = defaultFramebufferExtent;
         m_preTransform = createInfo.preTransform;
 
         VK_VERIFY(vkCreateSwapchainKHR(device, &createInfo, nullptr, &m_swapchain));

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.h

@@ -35,9 +35,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkSwapchainKHR GetHandle() const { return m_swapchain; }
         const VkSurfaceFormatKHR& GetSurfaceFormat() const { return m_surfaceFormat; }
         VkExtent2D GetExtent() const { return m_extent; }
-        // Surface-space extent (before the pre-rotation quarter-turn swap) this swapchain was
-        // created from - the value to compare a freshly queried currentExtent against.
-        VkExtent2D GetSurfaceExtent() const { return m_surfaceExtent; }
         VkSurfaceTransformFlagBitsKHR GetPreTransform() const { return m_preTransform; }
         const Vector<VkImage>& GetImages() const { return m_images; }
         const Vector<VkImageView>& GetImageViews() const { return m_imageViews; }
@@ -66,7 +63,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkSwapchainKHR m_swapchain = VK_NULL_HANDLE;
         VkSurfaceFormatKHR m_surfaceFormat{};
         VkExtent2D m_extent{};
-        VkExtent2D m_surfaceExtent{};
         VkSurfaceTransformFlagBitsKHR m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
         Vector<VkImage> m_images;
         Vector<VkImageView> m_imageViews;

MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.cpp

@@ -16,7 +16,6 @@
 #include "MG_Util/Converters/GLToMG/TextureEnumConverter.h"
 #include "MG_Util/Converters/MGToStr/FramebufferEnumConverter.h"
 #include "MG_Util/Converters/MGToVk/TextureEnumConverter.h"
-#include <vulkan/utility/vk_format_utils.h>
 #include "MG_Util/Metrics/TextureMetrics.h"
 #include <Config.h>
 #include <cstdio>
@@ -212,40 +211,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     }
 
-    void UniformManager::OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout) {
-        SizeT purgedSets = 0;
-        for (auto& frame : m_frames) {
-            const auto it = frame.descriptorSetCacheByLayout.find(descriptorSetLayout);
-            if (it == frame.descriptorSetCacheByLayout.end()) {
-                continue;
-            }
-            // Free the sets back to their pools and credit the bucket accounting, so
-            // program churn recycles pool capacity instead of abandoning the slots.
-            // GPU-safe: the layout only dies after >1024 idle frame boundaries, so no
-            // in-flight command buffer references these sets.
-            for (const auto& cached : it->second.sets) {
-                if (cached.set == VK_NULL_HANDLE) {
-                    continue;
-                }
-                vkFreeDescriptorSets(m_device, cached.pool, 1, &cached.set);
-                const auto bucket = std::find_if(
-                    frame.descriptorPools.begin(), frame.descriptorPools.end(),
-                    [&cached](const DescriptorPoolBucket& candidate) { return candidate.handle == cached.pool; });
-                if (bucket != frame.descriptorPools.end() && bucket->allocatedSets > 0) {
-                    --bucket->allocatedSets;
-                }
-            }
-            purgedSets += it->second.sets.size();
-            frame.descriptorSetCacheByLayout.erase(it);
-        }
-        if (purgedSets > 0) {
-            // The per-draw reuse memo folds the layout handle into its signature; drop
-            // it so a recycled handle value cannot revive a purged set mid-frame.
-            m_hasLastDescriptor = false;
-            MGLOG_D("UniformDescriptorBinder: freed %zu descriptor sets for destroyed layout", purgedSets);
-        }
-    }
-
     Bool UniformManager::ResolveSamplerDescriptor(VkCommandBuffer commandBuffer,
                                                             const MG_State::GLState::ProgramObject& program,
                                                             const ProgramFactory::VkProgramObject& programObj,
@@ -385,28 +350,24 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const Uint16 samplerVersion = samplerToUse->GetVersion();
             const Uint64 textureLifetimeId = texture->GetLifetimeId();
             const Uint16 textureParamsVersion = texture->GetTextureParamsVersion();
-            // The sampler's LOD clamp depends on how many levels the sampled view exposes, and that
-            // follows uploads as well as GL parameters - so it belongs in the memo key too.
-            const Uint32 viewLevelCount = resource->sampledLevelCount;
             if (memo.valid && memo.samplerLifetimeId == samplerLifetimeId && memo.samplerVersion == samplerVersion &&
                 memo.textureLifetimeId == textureLifetimeId && memo.textureParamsVersion == textureParamsVersion &&
-                memo.forceNearestFiltering == forceNearestFiltering && memo.viewLevelCount == viewLevelCount) {
+                memo.forceNearestFiltering == forceNearestFiltering) {
                 resolvedSampler = memo.sampler;
             } else {
-                resolvedSampler = m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture,
-                                                                       forceNearestFiltering, viewLevelCount);
+                resolvedSampler =
+                    m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering);
                 memo.samplerLifetimeId = samplerLifetimeId;
                 memo.samplerVersion = samplerVersion;
                 memo.textureLifetimeId = textureLifetimeId;
                 memo.textureParamsVersion = textureParamsVersion;
                 memo.forceNearestFiltering = forceNearestFiltering;
-                memo.viewLevelCount = viewLevelCount;
                 memo.sampler = resolvedSampler;
                 memo.valid = true;
             }
         } else {
-            resolvedSampler = m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering,
-                                                                   resource->sampledLevelCount);
+            resolvedSampler =
+                m_samplerManager->GetOrCreateSampler(*samplerToUse, *texture, forceNearestFiltering);
         }
         outImageInfo = {
             .sampler = resolvedSampler,
@@ -447,106 +408,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return outImageInfo.sampler != VK_NULL_HANDLE;
     }
 
-    namespace {
-        // fp16 carries an 11-bit mantissa, so an 8-bit normalized channel round-trips exactly.
-        // Anything wider - 16-bit normalized, half float, full float, and every packed HDR
-        // encoding - holds precision or range that relaxing the arithmetic would throw away.
-        Bool IsLowPrecisionNormalizedFormat(VkFormat format) {
-            if (format == VK_FORMAT_UNDEFINED) return false;
-            if (!vkuFormatIsUNORM(format) && !vkuFormatIsSNORM(format) && !vkuFormatIsSRGB(format)) {
-                return false;
-            }
-            const struct VKU_FORMAT_INFO info = vkuGetFormatInfo(format);
-            for (Uint32 i = 0; i < info.component_count; ++i) {
-                if (info.components[i].size > 8) return false;
-            }
-            return info.component_count > 0;
-        }
-    } // namespace
-
-    Bool UniformManager::DrawTargetIsLowPrecision(const MG_State::GLState::FramebufferObject* drawFramebuffer) {
-        // Default framebuffer: the swapchain is an 8-bit normalized surface.
-        if (drawFramebuffer == nullptr) return true;
-
-        Bool sawColour = false;
-        for (Int i = static_cast<Int>(FramebufferAttachmentType::Color0);
-             i < static_cast<Int>(FramebufferAttachmentType::FramebufferAttachmentTypeCount);
-             ++i) {
-            const auto& attachment =
-                drawFramebuffer->GetAttachment(static_cast<FramebufferAttachmentType>(i));
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            if (const auto& texture = attachment.GetTexture()) {
-                format = MG_Util::ConvertTextureInternalFormatToVkEnum(texture->GetFormat());
-            } else if (const auto& renderbuffer = attachment.GetRenderbuffer()) {
-                format = MG_Util::ConvertTextureInternalFormatToVkEnum(
-                    renderbuffer->GetInternalFormat());
-            } else {
-                continue;
-            }
-            if (!IsLowPrecisionNormalizedFormat(format)) return false;
-            sawColour = true;
-        }
-        return sawColour;
-    }
-
-    Bool UniformManager::ProgramSamplesOnlyLowPrecisionTextures(
-        const MG_State::GLState::ProgramObject& program, const ProgramFactory::VkProgramObject& programObj) {
-        for (Uint32 binding = 0; binding < programObj.bindingKinds.size(); ++binding) {
-            if (programObj.bindingKinds[binding] != ProgramFactory::DescriptorBindingKind::CombinedImageSampler) {
-                continue;
-            }
-            const auto* texture = ResolveSamplerTextureRaw(program, programObj, binding);
-            // An unresolvable binding is unknown territory, not licence to relax.
-            if (texture == nullptr) return false;
-            const VkFormat format =
-                MG_Util::ConvertTextureInternalFormatToVkEnum(texture->GetFormat());
-            if (!IsLowPrecisionNormalizedFormat(format)) return false;
-        }
-        return true;
-    }
-
-    Bool UniformManager::ProgramSamplesOnlySingleLevelTextures(
-        const MG_State::GLState::ProgramObject& program, const ProgramFactory::VkProgramObject& programObj) {
-        Bool sawSampler = false;
-        for (Uint32 binding = 0; binding < programObj.bindingKinds.size(); ++binding) {
-            if (programObj.bindingKinds[binding] != ProgramFactory::DescriptorBindingKind::CombinedImageSampler) {
-                continue;
-            }
-            const auto* texture = ResolveSamplerTextureRaw(program, programObj, binding);
-            if (texture == nullptr) return false;
-            const auto& levelRange = texture->GetLevelRange();
-            if (levelRange.x() != levelRange.y()) return false;
-
-            // An explicit-LOD sample is a single filtered tap, so it also gives up anisotropic
-            // filtering - which a single-level view can still have. Resolve the sampler exactly
-            // the way ResolveSamplerDescriptor does and bail if anisotropy would apply.
-            const Int location = programObj.samplerUniformLocationByBinding[binding];
-            const Int unit = ResolveSamplerUnitIndex(program, location, binding);
-            const auto& samplerOverride = MG_State::pGLContext->GetTextureUnitObject(unit).GetSamplerObject();
-            const auto* effectiveSampler =
-                samplerOverride ? samplerOverride.get() : texture->GetSamplerObject().get();
-            if (effectiveSampler == nullptr) return false;
-            if (effectiveSampler->GetMaxAnisotropy() > 1.0f &&
-                effectiveSampler->GetMinFilter() == SamplerFilterMode::Linear &&
-                effectiveSampler->GetMagFilter() == SamplerFilterMode::Linear) {
-                return false;
-            }
-
-            // An explicit LOD 0 makes lambda exactly 0, which is the magnification side of the
-            // min/mag decision. That only matches the implicit form when lambda could not have been
-            // positive anyway (the LOD clamp already pins it at or below 0), or when the two
-            // filters are the same and the choice cannot be observed.
-            const Float effectiveMaxLod = effectiveSampler->GetMipmapMode() == SamplerMipmapMode::None
-                                              ? 0.0f
-                                              : effectiveSampler->GetMaxLod();
-            if (effectiveMaxLod > 0.0f && effectiveSampler->GetMinFilter() != effectiveSampler->GetMagFilter()) {
-                return false;
-            }
-            sawSampler = true;
-        }
-        return sawSampler;
-    }
-
     Bool UniformManager::ResolveSamplerTexture(const MG_State::GLState::ProgramObject& program,
                                                          const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
                                                          SharedPtr<MG_State::GLState::ITextureObject>& outTexture) {
@@ -1050,11 +911,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         VkDescriptorPoolCreateInfo poolInfo{};
         poolInfo.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO;
-        // FREE_DESCRIPTOR_SET_BIT lets a destroyed layout's cached sets be freed back
-        // (OnDescriptorSetLayoutDestroyed) so program churn recycles pool capacity.
-        // The cost is on set allocation only, which happens when a layout's per-frame
-        // cache grows - never on the per-draw reuse path.
-        poolInfo.flags = VK_DESCRIPTOR_POOL_CREATE_FREE_DESCRIPTOR_SET_BIT;
         poolInfo.maxSets = maxSets;
         poolInfo.poolSizeCount = static_cast<Uint32>(std::size(poolSizes));
         poolInfo.pPoolSizes = poolSizes;
@@ -1134,7 +990,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         auto& frame = m_frames[frameIndex];
         auto& cache = frame.descriptorSetCacheByLayout[programObj.descriptorSetLayout];
         if (cache.cursor < cache.sets.size()) {
-            outDescriptorSet = cache.sets[cache.cursor++].set;
+            outDescriptorSet = cache.sets[cache.cursor++];
         } else {
             VkResult allocResult = AllocateDescriptorSetsFromActivePool(frameIndex, programObj, outDescriptorSet);
             if (allocResult == VK_ERROR_OUT_OF_POOL_MEMORY || allocResult == VK_ERROR_FRAGMENTED_POOL) {
@@ -1148,9 +1004,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 return allocResult;
             }
 
-            // The successful allocation came from the bucket the alloc helper left
-            // active; record it so a layout-destroyed purge can free the set back.
-            cache.sets.push_back({outDescriptorSet, frame.descriptorPools[frame.activeDescriptorPoolIndex].handle});
+            cache.sets.push_back(outDescriptorSet);
             ++cache.cursor;
             MGLOG_D("UniformDescriptorBinder: cached descriptor set count for frame=%u grew to %zu", frameIndex,
                     cache.sets.size());

MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.h

@@ -39,17 +39,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void Shutdown();
 
         void BeginFrame(Uint32 frameIndex);
-        // A ProgramFactory eviction just destroyed this layout: purge every frame
-        // slot's cached descriptor sets for it, so a recycled handle value can never
-        // stale-hit sets written for the dead layout's bindings. The sets are
-        // vkFreeDescriptorSets'd back to their pools (created with
-        // FREE_DESCRIPTOR_SET_BIT) and the pool accounting is credited, so program
-        // churn recycles pool capacity instead of abandoning it. GPU-safe: the layout
-        // only dies after >1024 idle frame boundaries, so no in-flight command buffer
-        // references its sets. This is the only eviction path for the per-layout
-        // caches - a live layout's entry must never be purged (its sets would be
-        // unreachable pool slots), so there is deliberately no age-based sweep here.
-        void OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout);
         Bool CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
                                     const ProgramFactory::VkProgramObject& programObj,
                                     Vector<MG_State::GLState::ITextureObject*>& outTextures);
@@ -69,25 +58,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         static VkFormat ResolveStorageImageViewFormat(VkFormat reflectedFormat, GLenum bindingFormat,
                                                       VkFormat resourceFormat, Bool useBindingFormat);
 
-        // True when the program reads at least one sampler and every one of them is bound to a
-        // texture whose GL level range is a single level. Such a sampler resolves to
-        // minLod = maxLod = 0 (see VkSamplerManager::GetOrCreateSampler), so an implicit-LOD sample
-        // and an explicit LOD 0 sample must read the same texel - which is what makes the
-        // ExplicitLod0Sampling SPIR-V rewrite safe to request. Deliberately conservative: it reads
-        // only GL state, so a texture that ends up single-level for another reason (one uploaded
-        // level under a wide level range) merely misses the rewrite.
-        // True when every texture this program samples is an 8-bit-or-less normalized format, so
-        // relaxing the fragment stage to fp16 cannot lose a bit the texel ever carried. Says
-        // nothing about the render target - the caller must check that too.
-        static Bool ProgramSamplesOnlyLowPrecisionTextures(const MG_State::GLState::ProgramObject& program,
-                                                          const ProgramFactory::VkProgramObject& programObj);
-        // True when every colour attachment the draw writes is an 8-bit-or-less normalized
-        // format (nullptr = default framebuffer, which is). Blending happens at attachment
-        // precision, so a wider target must keep the fragment stage at full precision.
-        static Bool DrawTargetIsLowPrecision(const MG_State::GLState::FramebufferObject* drawFramebuffer);
-        static Bool ProgramSamplesOnlySingleLevelTextures(const MG_State::GLState::ProgramObject& program,
-                                                          const ProgramFactory::VkProgramObject& programObj);
-
     private:
         struct DescriptorPoolBucket {
             VkDescriptorPool handle = VK_NULL_HANDLE;
@@ -95,16 +65,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint32 allocatedSets = 0;
         };
 
-        // A cached descriptor set together with the pool it was allocated from, so a
-        // layout-destroyed purge can vkFreeDescriptorSets it back and credit the
-        // owning bucket's accounting.
-        struct CachedDescriptorSet {
-            VkDescriptorSet set = VK_NULL_HANDLE;
-            VkDescriptorPool pool = VK_NULL_HANDLE;
-        };
-
         struct DescriptorSetCacheEntry {
-            Vector<CachedDescriptorSet> sets;
+            Vector<VkDescriptorSet> sets;
             Uint32 cursor = 0;
         };
 
@@ -210,7 +172,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             Uint64 samplerLifetimeId = 0;
             Uint64 textureLifetimeId = 0;
             VkSampler sampler = VK_NULL_HANDLE;
-            Uint32 viewLevelCount = 0;
             Uint16 samplerVersion = 0;
             Uint16 textureParamsVersion = 0;
             Bool forceNearestFiltering = false;

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.cpp

@@ -32,13 +32,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsBgra, sizeof(attr.IsBgra)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Divisor, sizeof(attr.Divisor)));
 
-            // The buffer's heap address is an identity component of the key: a freed
-            // buffer's reused address can alias an old cache entry, but only under a
-            // byte-identical attribute layout - and the entry payload is a pure function
-            // of the hashed inputs, with the draw path re-resolving bindingBufferKeys
-            // against the live VAO attribute pointers, so an aliased hit returns exactly
-            // what a rebuild would. Address drift only grows the map; the OnFrameBoundary
-            // aging sweep bounds that.
             const SizeT bufferKey = reinterpret_cast<SizeT>(attr.Buffer.get());
             XXHASH_VERIFY(XXH64_update(m_hashState, &bufferKey, sizeof(bufferKey)));
         }
@@ -65,7 +58,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const MG_State::GLState::VertexArrayObject& vao, HashType hash) {
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
-            it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
             return it->second;
         }
 
@@ -174,7 +166,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         auto& entry = m_cache[hash];
         entry.hash = hash;
-        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
         entry.bindings = builder.GetBindings();
         entry.attributes = builder.GetAttributes();
         entry.bindingBufferKeys = std::move(bindingBufferKeys);
@@ -189,30 +180,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return entry;
     }
 
-    void VertexInputStateFactory::OnFrameBoundary() {
-        ++m_frameBoundaryCounter;
-
-        // Sweep occasionally; evict entries whose last hit is far in the past.
-        // Erasure happens only here, never mid-frame: the draw path holds a
-        // reference into the current entry across its setup, and unordered_map
-        // erase would invalidate it. Entries are CPU-side only, so no GPU-idle
-        // proof is needed; an evicted entry that is used again is simply rebuilt
-        // from the VAO state (same hash, same content).
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeBoundaries = 1024;
-        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
-            return;
-        }
-
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (m_frameBoundaryCounter - it->second.lastUsedFrameBoundary > kRetireAgeBoundaries) {
-                it = m_cache.erase(it);
-            } else {
-                ++it;
-            }
-        }
-    }
-
     VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger,
                                                        Bool isBgra) {
         if (isBgra) {

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.h

@@ -27,9 +27,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         struct BackendVertexInputState {
             HashType hash = 0;
-            // Frame boundary of the last cache hit; entries idle past the
-            // OnFrameBoundary retirement age are evicted (CPU heap only).
-            Uint64 lastUsedFrameBoundary = 0;
             Vector<VkVertexInputBindingDescription> bindings;
             Vector<VkVertexInputAttributeDescription> attributes;
             Vector<SizeT> bindingBufferKeys;
@@ -58,14 +55,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const BackendVertexInputState& GetOrCreateVertexInputState(
             const MG_State::GLState::VertexArrayObject& vao, HashType hash);
         const BackendVertexInputState& GetOrCreateVertexInputState(const MG_State::GLState::VertexArrayObject& vao);
-        // Frame boundary hook: ages the cache and evicts entries not hit for many
-        // frames. The key mixes buffer heap addresses, so buffer/VAO churn keeps
-        // minting fresh keys; without eviction the map grows for the whole session.
-        // Entries hold no Vulkan handles (pipeline creation copies the descriptions)
-        // and the draw path's entry reference never spans a frame boundary, so
-        // eviction here needs no GPU-idle proof. Self-gated: one counter bump and
-        // compare except on sweep boundaries.
-        void OnFrameBoundary();
         static SizeT GetComponentSize(DataType type);
         // Tightly-packed byte size of one vertex element for this attribute: componentSize * size for
         // normal types, and 4 (one packed word) for the 2_10_10_10 types and GL_BGRA. Returns 0 for
@@ -81,8 +70,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const VulkanRendererConfig& m_config;
         VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
         UnorderedMap<HashType, BackendVertexInputState> m_cache;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameBoundaryCounter = 0;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.cpp

@@ -141,15 +141,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_transientUploadArena.BeginFrame(frameIndex);
     }
 
-    void VkBufferManager::CollectAllDeferredReleases() {
-        for (Uint32 frameIndex = 0; frameIndex < m_deferredBufferReleases.size(); ++frameIndex) {
-            CollectDeferredReleases(frameIndex);
-        }
-        for (Uint32 frameIndex = 0; frameIndex < m_transientUploadArena.GetFrameCount(); ++frameIndex) {
-            m_transientUploadArena.CollectDeferredReleases(frameIndex);
-        }
-    }
-
     void VkBufferManager::NotifyDeviceIdle() {
         // Everything submitted so far has completed. Work recorded for the
         // current frame has not been submitted yet, so the current serial

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.h

@@ -77,11 +77,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Recreate all per-frame transient arenas
         Bool RecreateTransientArenas(Uint32 frameCount);
         void BeginFrame(Uint32 frameIndex);
-        // Drains every frame slot's deferred buffer/resource releases (and the
-        // transient arena's parked superseded blocks). Only valid when the
-        // caller has proven every queue submission complete; used by the
-        // present-less frame-boundary drain.
-        void CollectAllDeferredReleases();
         // All previously submitted GPU work has completed (vkDeviceWaitIdle).
         void NotifyDeviceIdle();
         // A frame slot's submission fence has been waited: every serial up to

MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp

@@ -180,7 +180,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         sampleCount = VK_SAMPLE_COUNT_1_BIT;
         internalFormat = TextureInternalFormat::Unknown;
         samples = 0;
-        deadSinceFrame = kNeverObservedDead;
     }
 
     VkRenderPassManager::VkRenderPassManager(VkDevice device,
@@ -207,7 +206,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             resource.Destroy(m_device, m_allocator);
         }
         m_renderbufferResources.clear();
-        CollectDeferredRenderbufferReleases(/*destroyAll=*/true); // caller guarantees device idle
         m_pendingRenderbufferClears.clear();
         RenderPassEntry::s_textureResourcesScratch.clear();
         s_activeRenderPass = {};
@@ -215,75 +213,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_rpFastValid = false;
     }
 
-    Uint64 VkRenderPassManager::RetireAgeFrames() const {
-        // MaxFramesInFlight + 2 covers the frame ring plus one boundary for the
-        // recording-to-submit gap and one because OnPresent runs ahead of Present's
-        // fence wait; the floor of 8 keeps a margin over the default ring of 3 while
-        // still releasing multi-MB attachment memory promptly (the render-pass cache's
-        // 1024-frame retirement would pin it for no additional safety).
-        return std::max<Uint64>(8, static_cast<Uint64>(m_config.MaxFramesInFlight) + 2);
-    }
-
-    void VkRenderPassManager::DeferRenderbufferBackingRelease(RenderbufferResource& resource) {
-        // The superseded backing may still be referenced by in-flight command buffers
-        // (glRenderbufferStorage can respecify a renderbuffer drawn this very frame),
-        // so it is parked and destroyed only after RetireAgeFrames() boundaries.
-        if (resource.image == VK_NULL_HANDLE && resource.view == VK_NULL_HANDLE) {
-            return;
-        }
-        m_deferredRenderbufferReleases.push_back({resource.image, resource.allocation, resource.view, m_frameCounter});
-        resource.image = VK_NULL_HANDLE;
-        resource.allocation = nullptr;
-        resource.view = VK_NULL_HANDLE;
-    }
-
-    void VkRenderPassManager::CollectDeferredRenderbufferReleases(Bool destroyAll) {
-        if (m_deferredRenderbufferReleases.empty()) {
-            return;
-        }
-        const Uint64 retireAgeFrames = RetireAgeFrames();
-        std::erase_if(m_deferredRenderbufferReleases, [&](DeferredRenderbufferRelease& release) {
-            if (!destroyAll && m_frameCounter - release.deferredAtFrame < retireAgeFrames) {
-                return false;
-            }
-            if (release.view != VK_NULL_HANDLE) {
-                vkDestroyImageView(m_device, release.view, nullptr);
-            }
-            if (release.image != VK_NULL_HANDLE) {
-                vmaDestroyImage(m_allocator, release.image, release.allocation);
-            }
-            return true;
-        });
-    }
-
     void VkRenderPassManager::CollectRenderbufferGarbage() {
-        // Two-phase reclamation: a dead renderbuffer's VkImage may still be referenced by
-        // command buffers submitted up to frames-in-flight frames ago (it was legally
-        // attached and drawn right up to its deletion), so the first observation of an
-        // expired weak reference only stamps the current frame counter; Destroy runs once
-        // enough frame boundaries have passed that the stamping frame's submission fence
-        // has provably been waited (see RetireAgeFrames).
-        const Uint64 retireAgeFrames = RetireAgeFrames();
-        for (auto it = m_renderbufferResources.begin(); it != m_renderbufferResources.end();) {
-            auto& resource = it->second;
+        Vector<MG_State::GLState::RenderbufferObject*> deadRenderbuffers;
+        deadRenderbuffers.reserve(m_renderbufferResources.size());
+        for (auto& [renderbuffer, resource] : m_renderbufferResources) {
             const auto liveRenderbuffer = resource.renderbuffer.lock();
-            if (liveRenderbuffer && liveRenderbuffer.get() == it->first) {
-                resource.deadSinceFrame = RenderbufferResource::kNeverObservedDead;
-                ++it;
-                continue;
+            if (!liveRenderbuffer || liveRenderbuffer.get() != renderbuffer) {
+                deadRenderbuffers.emplace_back(renderbuffer);
             }
-            if (resource.deadSinceFrame == RenderbufferResource::kNeverObservedDead) {
-                resource.deadSinceFrame = m_frameCounter;
-                ++it;
-                continue;
+        }
+        for (auto* renderbuffer : deadRenderbuffers) {
+            auto resourceIt = m_renderbufferResources.find(renderbuffer);
+            if (resourceIt != m_renderbufferResources.end()) {
+                resourceIt->second.Destroy(m_device, m_allocator);
+                m_renderbufferResources.erase(resourceIt);
             }
-            if (m_frameCounter - resource.deadSinceFrame < retireAgeFrames) {
-                ++it;
-                continue;
-            }
-            m_pendingRenderbufferClears.erase(it->first);
-            resource.Destroy(m_device, m_allocator);
-            it = m_renderbufferResources.erase(it);
+            m_pendingRenderbufferClears.erase(renderbuffer);
         }
     }
 
@@ -325,15 +270,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             resource.samples != renderbuffer->GetSamples();
         if (!needsCreate) {
             resource.renderbuffer = renderbuffer;
-            // A new renderbuffer at a recycled address may adopt a compatible entry that
-            // was already stamped dead; it is alive again, so cancel the aging.
-            resource.deadSinceFrame = RenderbufferResource::kNeverObservedDead;
             return &resource;
         }
 
-        // Respecify: park the old backing for aged destruction instead of destroying
-        // inline - it may still be referenced by in-flight command buffers.
-        DeferRenderbufferBackingRelease(resource);
         resource.Destroy(m_device, m_allocator);
         resource.renderbuffer = renderbuffer;
 
@@ -1239,14 +1178,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     void VkRenderPassManager::OnPresent() {
         ++m_frameCounter;
 
-        // Runs every frame boundary, ahead of the render-pass sweep gate below: the walk
-        // is O(#renderbuffer resources) — single digits in practice — and per-frame
-        // invocation keeps dead-resource reclaim latency at the aging bound instead of
-        // coupling it to renderbuffer *use* (the GetOrCreateRenderbufferResource call
-        // site never runs again once an app stops using renderbuffers).
-        CollectRenderbufferGarbage();
-        CollectDeferredRenderbufferReleases(/*destroyAll=*/false);
-
         // Sweep occasionally; evict entries whose last use is far past every
         // in-flight frame so their VkRenderPass/VkFramebuffer can be destroyed
         // safely (RenderPassEntry's destructor releases the handles).
@@ -1256,12 +1187,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return;
         }
 
-        // Collect the dying handles and notify once after the loop: pipelines hashed
-        // on them share the entries' >kRetireAgeFrames idleness (they are only bound
-        // by draws that hit those entries), so the observer may destroy them
-        // immediately - and a single batched notification costs one pipeline-cache
-        // scan instead of one per evicted pass.
-        Vector<VkRenderPass> destroyedRenderPasses;
         const Uint64 activeHash = s_hasActiveRenderPass ? s_activeRenderPass.hash : 0;
         for (auto it = m_renderPasses.begin(); it != m_renderPasses.end();) {
             const Bool isActive = s_hasActiveRenderPass && it->first == activeHash;
@@ -1269,15 +1194,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 if (m_rpFastValid && m_rpFastRenderPassHash == it->first) {
                     m_rpFastValid = false;
                 }
-                destroyedRenderPasses.push_back(it->second.renderPass);
                 it = m_renderPasses.erase(it);
             } else {
                 ++it;
             }
         }
-        if (!destroyedRenderPasses.empty() && m_evictionObserver != nullptr) {
-            m_evictionObserver->OnRenderPassesDestroyed(destroyedRenderPasses);
-        }
     }
 
     Bool VkRenderPassManager::BeginRenderPass(VkCommandBuffer commandBuffer, RenderPassEntry& renderPassEntry) {

MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.h

@@ -157,31 +157,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     class VkRenderPassManager {
     public:
         using HashType = Uint64;
-
-        // Notified once per OnPresent sweep with every aged-out entry's VkRenderPass
-        // value: pipelines are hashed on the raw handle, and once destroyed the value
-        // may be recycled for an incompatible pass, so dependent caches must purge
-        // everything keyed on them before any new pass can be created (the sweep and
-        // the notification run back-to-back with no creation in between; observers
-        // compare the values, never dereference them). Batched so a mass-idle cohort
-        // (shader-pack switch, dimension exit) costs the observer one pipeline-cache
-        // scan, not one per dying pass. The wholesale paths
-        // (Shutdown/RecreateSwapchain) do not notify - their callers already drop
-        // every pipeline outright.
-        class IEvictionObserver {
-        public:
-            virtual ~IEvictionObserver() = default;
-            virtual void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) = 0;
-        };
-
         VkRenderPassManager(VkDevice device,
             VkPhysicalDevice physicalDevice, VmaAllocator allocator, const VulkanRendererConfig& config,
             VkClearManager& clearManager, VkTextureManager& textureManager, SwapchainObject& swapchainObject);
         ~VkRenderPassManager();
 
-        // Observer may be null (no notifications). Not owned.
-        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
-
         Bool Initialize();
         void Shutdown();
 
@@ -212,7 +192,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         UnorderedMap<Uint64, RenderPassEntry> m_renderPasses;
         // Monotonic frame counter (bumped in OnPresent) for render-pass cache aging.
         Uint64 m_frameCounter = 0;
-        IEvictionObserver* m_evictionObserver = nullptr;
 
         // Bumped whenever a renderbuffer VkImage is (re)created; together with the texture
         // manager's image epoch this invalidates the render-pass fast path on any attachment
@@ -234,12 +213,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     public:
         struct RenderbufferResource {
-            // deadSinceFrame sentinel: the owning weak reference has not been observed
-            // expired. Dead resources age past every in-flight frame before Destroy
-            // (see CollectRenderbufferGarbage); the GPU may still reference the image
-            // for frames-in-flight frames after the GL object dies.
-            static constexpr Uint64 kNeverObservedDead = UINT64_MAX;
-
             WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
             VkImage image = VK_NULL_HANDLE;
             VmaAllocation allocation = nullptr;
@@ -251,8 +224,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
             TextureInternalFormat internalFormat = TextureInternalFormat::Unknown;
             Int samples = 0;
-            // m_frameCounter value at which the weak reference was first seen expired.
-            Uint64 deadSinceFrame = kNeverObservedDead;
 
             void Destroy(VkDevice device, VmaAllocator allocator);
         };
@@ -270,28 +241,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             ClearAttachmentPayload payload{};
         };
 
-        // A superseded renderbuffer backing (glRenderbufferStorage respecify) parked
-        // until enough frame boundaries have passed that no in-flight command buffer
-        // can still reference it; destroyed in OnPresent (see RetireAgeFrames).
-        struct DeferredRenderbufferRelease {
-            VkImage image = VK_NULL_HANDLE;
-            VmaAllocation allocation = nullptr;
-            VkImageView view = VK_NULL_HANDLE;
-            Uint64 deferredAtFrame = 0;
-        };
-
         UnorderedMap<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
         UnorderedMap<MG_State::GLState::RenderbufferObject*, PendingRenderbufferClear> m_pendingRenderbufferClears;
-        Vector<DeferredRenderbufferRelease> m_deferredRenderbufferReleases;
 
         Bool HasPendingRenderbufferClear(
             const MG_State::GLState::FramebufferAttachmentObject& attachment) const;
         void CollectRenderbufferGarbage();
-        // Frame-boundary margin after which a resource last referenced by a retired
-        // GL object (or superseded backing) is provably past every in-flight frame.
-        Uint64 RetireAgeFrames() const;
-        void DeferRenderbufferBackingRelease(RenderbufferResource& resource);
-        void CollectDeferredRenderbufferReleases(Bool destroyAll);
 
         static inline XXH64_state_t* m_hashState = XXH64_createState();
         static inline ActiveRenderPassInfo s_activeRenderPass{};

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.cpp

@@ -51,18 +51,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Float ResolveEffectiveMinLod(const MG_State::GLState::SamplerObject& sampler, Float effectiveMaxLod) {
             return std::min(sampler.GetMinLod(), effectiveMaxLod);
         }
-
-        // A single-level view can only ever deliver the base level, but the LOD clamp must not be
-        // collapsed to exactly 0: both GL and Vulkan pick magFilter over minFilter from the
-        // *clamped* lambda, so maxLod = 0 would make every fragment magnify and quietly retire the
-        // min filter. 0.25 is the value VkSamplerCreateInfo's own note prescribes for emulating
-        // GL's non-mipmapped minification - large enough for lambda to stay positive, small enough
-        // that a NEAREST mip mode still rounds down to level 0. Clamped rather than assigned, so a
-        // texture whose GL_TEXTURE_MAX_LOD really is 0 keeps magnifying as GL says it must.
-        Float ResolveSingleLevelMaxLod(const MG_State::GLState::SamplerObject& sampler, Bool singleLevelView) {
-            const Float maxLod = ResolveEffectiveMaxLod(sampler);
-            return singleLevelView ? std::min(maxLod, 0.25f) : maxLod;
-        }
     } // namespace
 
     Bool VkSamplerManager::Initialize(const InitInfo& initInfo) {
@@ -101,43 +89,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_device = VK_NULL_HANDLE;
         m_config = nullptr;
-        m_frameBoundaryCounter = 0;
-    }
-
-    void VkSamplerManager::OnFrameBoundary() {
-        ++m_frameBoundaryCounter;
-
-        // Sweep occasionally; destroy samplers whose last use is far past every
-        // in-flight frame. Destroy and erase must stay atomic, or Shutdown would
-        // double-free the handle; an evicted key that recurs simply re-creates
-        // its sampler on the next miss.
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeBoundaries = 1024;
-        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
-            return;
-        }
-
-        for (auto it = m_samplers.begin(); it != m_samplers.end();) {
-            auto& entry = it->second;
-            if (m_frameBoundaryCounter - entry.lastUsedFrameBoundary > kRetireAgeBoundaries) {
-                if (m_device != VK_NULL_HANDLE && entry.handle != VK_NULL_HANDLE) {
-                    vkDestroySampler(m_device, entry.handle, nullptr);
-                }
-                it = m_samplers.erase(it);
-            } else {
-                ++it;
-            }
-        }
     }
 
     Uint64 VkSamplerManager::BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
                                              const MG_State::GLState::ITextureObject& texture,
-                                             Bool forceNearestFiltering, Bool singleLevelView) const {
+                                             Bool forceNearestFiltering) const {
         MOBILEGL_ASSERT(m_config != nullptr, "VkSamplerManager::BuildSamplerKey: m_config is null");
         XXHASH_VERIFY(XXH64_reset(m_hashState, m_config->CacheVersion));
 
         XXHASH_VERIFY(XXH64_update(m_hashState, &forceNearestFiltering, sizeof(forceNearestFiltering)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &singleLevelView, sizeof(singleLevelView)));
 
         const auto minFilter = sampler.GetMinFilter();
         XXHASH_VERIFY(XXH64_update(m_hashState, &minFilter, sizeof(minFilter)));
@@ -151,7 +111,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         XXHASH_VERIFY(XXH64_update(m_hashState, &wrapT, sizeof(wrapT)));
         const auto wrapR = sampler.GetWrapR();
         XXHASH_VERIFY(XXH64_update(m_hashState, &wrapR, sizeof(wrapR)));
-        const auto maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
+        const auto maxLod = ResolveEffectiveMaxLod(sampler);
         const auto minLod = ResolveEffectiveMinLod(sampler, maxLod);
         XXHASH_VERIFY(XXH64_update(m_hashState, &minLod, sizeof(minLod)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &maxLod, sizeof(maxLod)));
@@ -173,20 +133,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     VkSampler VkSamplerManager::GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
                                                    const MG_State::GLState::ITextureObject& texture,
-                                                   Bool forceNearestFiltering, Uint32 viewLevelCount) {
-        // A view that exposes a single mip level has no second level to blend with, so GL's
-        // *_MIPMAP_* minification filters degenerate to plain filtering on the base level -
-        // sampling is unchanged by pinning the Vulkan sampler to NEAREST mip mode at LOD 0.
-        // It is not cosmetic: MobileGL backs such a view with a fully allocated mip chain whose
-        // tail is never written, and a LINEAR mip mode lets the texture unit issue the level+1
-        // fetch anyway. On Adreno that fetch lands in uninitialized UBWC pages (or past the
-        // allocation for a genuinely single-level image) and faults the GPU - the same failure
-        // the default-framebuffer blit shader had to work around with an explicit-LOD sample.
-        const Bool singleLevelView = viewLevelCount == 1;
-        const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering, singleLevelView);
+                                                   Bool forceNearestFiltering) {
+        const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering);
         auto it = m_samplers.find(key);
         if (it != m_samplers.end()) {
-            it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
             return it->second.handle;
         }
 
@@ -194,9 +144,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         samplerInfo.sType = VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO;
         samplerInfo.magFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMagFilter());
         samplerInfo.minFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMinFilter());
-        samplerInfo.mipmapMode = (forceNearestFiltering || singleLevelView)
-                                     ? VK_SAMPLER_MIPMAP_MODE_NEAREST
-                                     : ToVkMipmapMode(sampler.GetMipmapMode());
+        samplerInfo.mipmapMode = forceNearestFiltering ? VK_SAMPLER_MIPMAP_MODE_NEAREST
+                                                       : ToVkMipmapMode(sampler.GetMipmapMode());
         samplerInfo.addressModeU = ToVkAddressMode(sampler.GetWrapS());
         samplerInfo.addressModeV = ToVkAddressMode(sampler.GetWrapT());
         samplerInfo.addressModeW = ToVkAddressMode(sampler.GetWrapR());
@@ -208,8 +157,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         samplerInfo.maxAnisotropy = maxAnisotropy;
         samplerInfo.compareEnable = sampler.GetCompareMode() == SamplerCompareMode::CompareToTexture ? VK_TRUE : VK_FALSE;
         samplerInfo.compareOp = ToVkCompareOp(ResolveCompareFunc(sampler, texture));
-        // Must match BuildSamplerKey's resolution exactly.
-        samplerInfo.maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
+        samplerInfo.maxLod = ResolveEffectiveMaxLod(sampler);
         samplerInfo.minLod = ResolveEffectiveMinLod(sampler, samplerInfo.maxLod);
         samplerInfo.borderColor = ResolveVkBorderColor(sampler, texture);
         samplerInfo.unnormalizedCoordinates = VK_FALSE;
@@ -221,7 +169,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         entry.handle = vkSampler;
         entry.externalIndex = sampler.GetExternalIndex();
         entry.version = sampler.GetVersion();
-        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
         m_samplers[key] = entry;
         return vkSampler;
     }

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.h

@@ -33,38 +33,20 @@ public:
     Bool Initialize(const InitInfo& initInfo);
     void Shutdown();
 
-    // viewLevelCount is the mip-level count of the image view this sampler will be paired
-    // with; 0 means "unknown, do not narrow". See GetOrCreateSampler for why it matters.
     VkSampler GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
                                  const MG_State::GLState::ITextureObject& texture,
-                                 Bool forceNearestFiltering = false,
-                                 Uint32 viewLevelCount = 0);
-    // Frame boundary hook: ages the sampler cache and destroys samplers not used
-    // for many frames. The key hashes continuous float state (lodBias, LOD clamps,
-    // anisotropy), so an app animating those would otherwise mint an unbounded
-    // stream of never-destroyed VkSamplers and eventually exhaust the device's
-    // maxSamplerAllocationCount. A sampler idle for over a thousand frame
-    // boundaries cannot be referenced by any in-flight command buffer (frames in
-    // flight are single digits), and every descriptor set the GPU consumes is
-    // written that same frame with live handles (the per-binding resolve memo and
-    // descriptor-set reuse are both frame-reset), so destruction here needs no
-    // fence wait. Self-gated: one counter bump and compare except on sweep
-    // boundaries.
-    void OnFrameBoundary();
+                                 Bool forceNearestFiltering = false);
 
 private:
     struct SamplerCacheEntry {
         VkSampler handle = VK_NULL_HANDLE;
         Uint externalIndex = 0;
         Uint16 version = 0;
-        // Frame boundary of the last cache hit; entries idle past the
-        // OnFrameBoundary retirement age have their VkSampler destroyed.
-        Uint64 lastUsedFrameBoundary = 0;
     };
 
     Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
                            const MG_State::GLState::ITextureObject& texture,
-                           Bool forceNearestFiltering, Bool singleLevelView) const;
+                           Bool forceNearestFiltering) const;
     static VkFilter ToVkFilter(SamplerFilterMode mode);
     static VkSamplerMipmapMode ToVkMipmapMode(SamplerMipmapMode mode);
     static VkSamplerAddressMode ToVkAddressMode(SamplerWrapMode mode);
@@ -85,8 +67,6 @@ private:
     Bool m_samplerAnisotropySupported = false;
     Float m_maxSamplerAnisotropy = 1.0f;
     UnorderedMap<Uint64, SamplerCacheEntry> m_samplers;
-    // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-    Uint64 m_frameBoundaryCounter = 0;
     static inline XXH64_state_t* m_hashState = XXH64_createState();
 };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.cpp

@@ -587,7 +587,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_allocator = initInfo.allocator;
         m_commandPool = initInfo.commandPool;
         m_graphicsQueue = initInfo.graphicsQueue;
-        m_imageFormatListSupported = initInfo.imageFormatListSupported;
         m_currentFrameIndex = 0;
         m_deferredReleases.clear();
         m_deferredReleases.resize(initInfo.frameCount);
@@ -610,7 +609,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         DestroyDeferredReleases();
         m_textureResources.clear();
         m_aliveObjects.clear();
-        m_storageImageTextures.clear();
 
         m_device = VK_NULL_HANDLE;
         m_physicalDevice = VK_NULL_HANDLE;
@@ -629,26 +627,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         frameIndex, m_deferredViewReleases.size());
         m_currentFrameIndex = frameIndex;
         CollectDeferredReleases(frameIndex);
-
-        // Frame-boundary GC: every 64 frame boundaries (~1 s at 60 fps) bounds the reclaim
-        // latency for dead textures regardless of draw traffic — workloads that churn
-        // textures through clears/readbacks alone never reach the draw-gated
-        // CollectGarbage. Must run after CollectDeferredReleases above: the prune defers
-        // its releases into this frame's slot, which was just drained, so they are
-        // destroyed only after the slot's fence has been waited again one full frame-ring
-        // cycle from now (never while an in-flight frame may still reference them).
-        constexpr Uint32 kGcFrameInterval = 64;
-        ++m_gcFrameCounter;
-        if (m_gcFrameCounter % kGcFrameInterval == 0) {
-            PruneDeadTextures();
-        }
-    }
-
-    void VkTextureManager::CollectAllDeferredReleases() {
-        const SizeT frameCount = std::min(m_deferredReleases.size(), m_deferredViewReleases.size());
-        for (SizeT frameIndex = 0; frameIndex < frameCount; ++frameIndex) {
-            CollectDeferredReleases(static_cast<Uint32>(frameIndex));
-        }
     }
 
     void VkTextureManager::EraseTrackedTexture(const TextureIdentity& identity) {
@@ -658,7 +636,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             m_textureResources.erase(resourceIt);
         }
         m_aliveObjects.erase(identity);
-        m_storageImageTextures.erase(identity);
     }
 
     void VkTextureManager::PruneStaleTextureAliases(MG_State::GLState::ITextureObject* texture) {
@@ -725,22 +702,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // construction introduces a new identity. Doing this unconditionally made every
         // sampled-texture sync scan the entire alive-texture map per draw.
         if (aliveIt == m_aliveObjects.end()) {
-            WeakPtr<MG_State::GLState::ITextureObject> aliveTexture;
             const auto& liveTexture = MG_State::pGLContext->GetTextureObject(texture.GetExternalIndex());
             if (liveTexture && liveTexture.get() == &texture) {
-                aliveTexture = liveTexture;
-            } else {
-                // The name lookup legally fails while the object is alive: the name was
-                // deleted with the texture still attached to an FBO (the attachment's
-                // SharedPtr keeps it alive), or the name was reused by a new texture, or
-                // this is a default texture object (name 0 lives outside the name map).
-                // Register through the object's own control block so the resource created
-                // below still participates in weak-expiry GC instead of becoming an
-                // orphan no reclamation path can reach until Shutdown.
-                aliveTexture = texture.weak_from_this();
-            }
-            if (!aliveTexture.expired()) {
-                m_aliveObjects[identity] = Move(aliveTexture);
+                m_aliveObjects[identity] = WeakPtr<MG_State::GLState::ITextureObject>(liveTexture);
                 PruneStaleTextureAliases(&texture);
             }
         }
@@ -1192,25 +1156,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return ok;
     }
 
-    void VkTextureManager::MarkStorageImageTexture(MG_State::GLState::ITextureObject& texture) {
-        m_storageImageTextures.insert(MakeTextureIdentity(&texture));
-    }
-
-    Bool VkTextureManager::NeedsStorageUsageUpgrade(MG_State::GLState::ITextureObject& texture) const {
-        const TextureIdentity identity = MakeTextureIdentity(&texture);
-        if (m_storageImageTextures.find(identity) == m_storageImageTextures.end()) {
-            return false;
-        }
-        const auto it = m_textureResources.find(identity);
-        // No image yet: the first sync creates it with STORAGE straight away, so there is nothing
-        // to preserve and nothing to order against.
-        return it != m_textureResources.end() && it->second.image != VK_NULL_HANDLE &&
-               !it->second.storageUsageResolved;
-    }
-
     Bool VkTextureManager::NeedsStorageImagePreparation(MG_State::GLState::ITextureObject& texture) const {
-        const TextureIdentity identity = MakeTextureIdentity(&texture);
-        const auto it = m_textureResources.find(identity);
+        const auto it = m_textureResources.find(MakeTextureIdentity(&texture));
         if (it == m_textureResources.end()) {
             return true;
         }
@@ -1218,12 +1165,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (resource.image == VK_NULL_HANDLE || resource.layout != VK_IMAGE_LAYOUT_GENERAL) {
             return true;
         }
-        // The image predates this texture's first image-unit binding, so it was created without
-        // STORAGE usage and has to be recreated - which is illegal inside a render pass.
-        if (!resource.storageUsageResolved &&
-            m_storageImageTextures.find(identity) != m_storageImageTextures.end()) {
-            return true;
-        }
         // Mirror SyncTexture's cross-draw skip condition: any version drift means the sync
         // path may upload or rebuild, both of which need the render pass ended first.
         const auto* mipTexture = MG_State::GLState::AsMipmapTexture(&texture);
@@ -1271,22 +1212,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     SizeT VkTextureManager::CollectGarbage() {
-        // Draw-gated stagger (1 in 256 calls): keeps the per-draw cost at one counter
-        // bump. The guaranteed reclaim path is the frame-boundary prune in BeginFrame;
-        // this remains as a cheap assist so draw-heavy workloads reclaim sooner.
         m_gcCounter++;
         if (m_gcCounter != 0) {
             return 0;
         }
-        return PruneDeadTextures();
-    }
-
-    SizeT VkTextureManager::PruneDeadTextures() {
-        // Erasing entries would dangle the raw TextureResource pointers memoized for the
-        // current draw; every call path (BeginFrame, and CollectGarbage at the top of a
-        // freshly opened draw-sync scope) runs before any memo entry is recorded.
-        MOBILEGL_ASSERT(m_drawSyncedThisDraw.empty(),
-                        "PruneDeadTextures: draw-sync memo holds raw resource pointers an erase would dangle");
 
         Vector<MG_State::GLState::ITextureObject*> expiredTextures;
         expiredTextures.reserve(m_aliveObjects.size());
@@ -1298,25 +1227,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         for (auto* texture : expiredTextures) {
             PruneStaleTextureAliases(texture);
         }
-        SizeT prunedCount = expiredTextures.size();
-
-        // Orphan sweep: after the pass above, m_aliveObjects holds only live entries.
-        // Registration in SyncTextureAndGetDescriptor cannot fail for a SharedPtr-owned
-        // texture (weak_from_this fallback), so a resource whose identity has no alive
-        // entry has no trackable owner: its GL-side object is gone, or was never
-        // shared-owned, in which case recreation on a later sync is the safe fallback.
-        // Destruction goes through the per-frame deferred queues, never immediate.
-        Vector<TextureIdentity> orphanIdentities;
-        for (auto it = m_textureResources.begin(); it != m_textureResources.end(); ++it) {
-            if (m_aliveObjects.find(it->first) == m_aliveObjects.end()) {
-                orphanIdentities.emplace_back(it->first);
-            }
-        }
-        for (const auto& identity : orphanIdentities) {
-            EraseTrackedTexture(identity);
-        }
-        prunedCount += orphanIdentities.size();
-        return prunedCount;
+        return expiredTextures.size();
     }
 
     Bool VkTextureManager::SyncTexture(MG_State::GLState::ITextureObject &texture,
@@ -1330,13 +1241,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const auto* syncingMipTexture = MG_State::GLState::AsMipmapTexture(&texture);
         const Uint32 syncingMipLevelCount =
             syncingMipTexture != nullptr ? syncingMipTexture->GetMipmapLevelCount() : 0u;
-        // A pending storage-usage upgrade also has to bust the skip: nothing about the texture's
-        // content or params changed, but the image itself must be recreated with STORAGE usage
-        // before it can back an image-unit descriptor.
-        const Bool storageUpgradePending =
-            !outResource.storageUsageResolved &&
-            m_storageImageTextures.find(MakeTextureIdentity(&texture)) != m_storageImageTextures.end();
-        if (outResource.image != VK_NULL_HANDLE && !storageUpgradePending &&
+        if (outResource.image != VK_NULL_HANDLE &&
             outResource.syncedContentVersion == syncingContentVersion &&
             outResource.syncedTextureParamsVersion == texture.GetTextureParamsVersion() &&
             outResource.syncedMipLevelCount == syncingMipLevelCount) {
@@ -1447,44 +1352,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const VkImageAspectFlags aspect = GetAspectMaskForFormat(format);
         VkFormatProperties formatProperties{};
         vkGetPhysicalDeviceFormatProperties(m_physicalDevice, format, &formatProperties);
-        // Only textures that have actually been bound to a GL image unit get STORAGE usage (and
-        // the MUTABLE_FORMAT it drags in for format-reinterpreting image views). Requesting it
-        // for every storage-capable colour texture costs real bandwidth: Adreno cannot keep UBWC
-        // compression on an image that may be written through a storage descriptor, so the whole
-        // render target - MC's included - runs uncompressed. MarkStorageImageTexture upgrades a
-        // texture before its first image-unit draw, and the usage below feeds the compatibility
-        // check so the upgrade recreates the image.
-        const Bool markedAsStorageImage =
-            m_storageImageTextures.find(MakeTextureIdentity(
-                const_cast<MG_State::GLState::ITextureObject*>(&texture))) != m_storageImageTextures.end();
-        // Storage-image CAPABILITY (does the format allow it at all) is deliberately separate from
-        // whether this texture actually needs the usage. MUTABLE_FORMAT keys off capability, as
-        // before: format-reinterpreting views are not a storage-only concern - the SAMPLED path
-        // needs them too (GetOrCreateSampledImageView bails out without it, see ~line 892), so
-        // tying MUTABLE_FORMAT to the image-unit mark would break sampled format reinterpretation
-        // for every texture that never becomes a storage image.
-        const Bool storageImageCapable =
+        const Bool supportsStorageImage =
             !isMultisampleTexture &&
             (aspect & VK_IMAGE_ASPECT_COLOR_BIT) != 0 &&
             (formatProperties.optimalTilingFeatures & VK_FORMAT_FEATURE_STORAGE_IMAGE_BIT) != 0;
-        const Bool supportsStorageImage = storageImageCapable && markedAsStorageImage;
         VkImageCreateFlags imageCreateFlags = shapeInfo.imageFlags;
-        if (storageImageCapable && IsMutableStorageImageFormat(format) &&
+        if (supportsStorageImage && IsMutableStorageImageFormat(format) &&
             m_mutableFormatUnsupported.find(format) == m_mutableFormatUnsupported.end()) {
             imageCreateFlags |= VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT;
         }
 
-        VkImageUsageFlags desiredUsage =
-            VK_IMAGE_USAGE_SAMPLED_BIT |
-            (supportsStorageImage ? VK_IMAGE_USAGE_STORAGE_BIT : 0) |
-            ((aspect & VK_IMAGE_ASPECT_COLOR_BIT) ? VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT : 0) |
-            (((aspect & VK_IMAGE_ASPECT_DEPTH_BIT) || (aspect & VK_IMAGE_ASPECT_STENCIL_BIT)) ?
-                 VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT :
-                 0);
-        if (!isMultisampleTexture) {
-            desiredUsage |= VK_IMAGE_USAGE_TRANSFER_DST_BIT | VK_IMAGE_USAGE_TRANSFER_SRC_BIT;
-        }
-
         const Bool compatible = resource.image != VK_NULL_HANDLE && resource.format == format &&
                                 resource.extent.width == static_cast<Uint32>(texelSize.x()) &&
                                 resource.extent.height == static_cast<Uint32>(texelSize.y()) &&
@@ -1493,7 +1370,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                 resource.viewType == shapeInfo.viewType &&
                                 resource.sampleCount == resolvedSampleCount &&
                                 resource.imageCreateFlags == imageCreateFlags &&
-                                resource.usageFlags == desiredUsage &&
                                 resource.mipLevels == backingMipLevels;
         if (compatible) {
             if (resource.perMipViews.size() != backingMipLevels) {
@@ -1502,10 +1378,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             if (resource.perMipSampledViews.size() != backingMipLevels) {
                 resource.perMipSampledViews.resize(backingMipLevels, VK_NULL_HANDLE);
             }
-            // Keeping the image is itself the answer to the mark: either it already carries
-            // STORAGE, or this format can never carry it. Either way there is nothing left to
-            // recreate, so stop reporting the texture as needing preparation.
-            resource.storageUsageResolved = markedAsStorageImage;
             return true;
         }
 
@@ -1520,10 +1392,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             resource.sampleCount == resolvedSampleCount &&
             resource.imageCreateFlags == imageCreateFlags &&
             resolvedSampleCount == VK_SAMPLE_COUNT_1_BIT &&
-            // '<=' rather than '<': a storage-usage upgrade recreates the image with an
-            // unchanged mip count, and its contents (a render target's pixels live only on the
-            // GPU) still have to survive. The vkCmdCopyImage below copies min(mipLevels).
-            resource.mipLevels <= backingMipLevels &&
+            resource.mipLevels < backingMipLevels &&
             resource.layout != VK_IMAGE_LAYOUT_UNDEFINED;
 
         std::unique_ptr<TextureResource> preservedResource;
@@ -1545,37 +1414,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         imageInfo.format = format;
         imageInfo.tiling = VK_IMAGE_TILING_OPTIMAL;
         imageInfo.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-        imageInfo.usage = desiredUsage;
-        imageInfo.samples = resolvedSampleCount;
-
-        // Bound the mutability. A blindly-mutable image has to be laid out so that ANY format in
-        // its compatibility class can be viewed, which costs bandwidth compression on tilers;
-        // naming the exact set instead lets the driver keep it. Only safe when that set really is
-        // exhaustive, so it is restricted to textures that are not image-unit bound: sampled views
-        // can only ever ask for ResolveSampledImageViewFormat's output, whereas glBindImageTexture
-        // may name any compatible format, which nothing here can enumerate ahead of time.
-        Vector<VkFormat> viewFormats;
-        VkImageFormatListCreateInfo formatListInfo{};
-        if (m_imageFormatListSupported && !supportsStorageImage &&
-            (imageInfo.flags & VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT) != 0) {
-            viewFormats.push_back(format);
-            for (const SamplerNumericDomain domain : {SamplerNumericDomain::Float,
-                                                      SamplerNumericDomain::SignedInteger,
-                                                      SamplerNumericDomain::UnsignedInteger}) {
-                const VkFormat viewFormat = ResolveSampledImageViewFormat(format, domain);
-                if (viewFormat == VK_FORMAT_UNDEFINED) {
-                    continue;
-                }
-                if (std::find(viewFormats.begin(), viewFormats.end(), viewFormat) == viewFormats.end()) {
-                    viewFormats.push_back(viewFormat);
-                }
-            }
-            formatListInfo.sType = VK_STRUCTURE_TYPE_IMAGE_FORMAT_LIST_CREATE_INFO;
-            formatListInfo.viewFormatCount = static_cast<Uint32>(viewFormats.size());
-            formatListInfo.pViewFormats = viewFormats.data();
-            imageInfo.pNext = &formatListInfo;
+        imageInfo.usage = VK_IMAGE_USAGE_SAMPLED_BIT |
+                          (supportsStorageImage ? VK_IMAGE_USAGE_STORAGE_BIT : 0) |
+                          ((aspect & VK_IMAGE_ASPECT_COLOR_BIT) ? VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT : 0) |
+                          (((aspect & VK_IMAGE_ASPECT_DEPTH_BIT) || (aspect & VK_IMAGE_ASPECT_STENCIL_BIT)) ?
+                               VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT :
+                               0);
+        if (!isMultisampleTexture) {
+            imageInfo.usage |= VK_IMAGE_USAGE_TRANSFER_DST_BIT | VK_IMAGE_USAGE_TRANSFER_SRC_BIT;
         }
-
+        imageInfo.samples = resolvedSampleCount;
         if (isMultisampleTexture || (imageInfo.flags & VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT) != 0) {
             VkImageFormatProperties imageFormatProperties{};
             VkResult imageFormatResult = vkGetPhysicalDeviceImageFormatProperties(
@@ -1632,8 +1480,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         resource.viewType = shapeInfo.viewType;
         resource.sampleCount = resolvedSampleCount;
         resource.imageCreateFlags = imageCreateFlags;
-        resource.usageFlags = imageInfo.usage;
-        resource.storageUsageResolved = markedAsStorageImage;
         resource.syncedTextureParamsVersion = 0;
 
         if (preservedResource) {

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.h

@@ -53,9 +53,6 @@ public:
         VkCommandPool commandPool = VK_NULL_HANDLE;
         VkQueue graphicsQueue = VK_NULL_HANDLE;
         Uint32 frameCount = 0;
-        // VK_KHR_image_format_list is enabled: MUTABLE_FORMAT images can name the exact set of
-        // formats they will be viewed as, which is what lets a tiler keep them compressed.
-        Bool imageFormatListSupported = false;
     };
 
     struct TextureResource {
@@ -160,17 +157,6 @@ public:
         VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
         VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
         VkImageCreateFlags imageCreateFlags = 0;
-        // Usage the live image was created with. STORAGE is only requested for textures that
-        // have actually been bound to a GL image unit, because on Adreno a storage-capable
-        // image loses UBWC bandwidth compression; a later image binding upgrades the usage
-        // and recreates the image, so the resolved usage has to be part of the compatibility
-        // check that decides whether the existing image can be kept.
-        VkImageUsageFlags usageFlags = 0;
-        // True once this image was (re)resolved while the texture was already marked as an
-        // image-unit texture. Distinguishes "not upgraded yet" from "cannot be upgraded"
-        // (a format whose optimalTilingFeatures lack STORAGE_IMAGE never gains the bit), so
-        // NeedsStorageImagePreparation cannot ask for a recreate that will never happen.
-        Bool storageUsageResolved = false;
         Uint16 syncedTextureParamsVersion = 0;
         // Snapshot of ITextureObject::GetContentVersion() at the last successful sync;
         // lets SyncTexture skip the whole re-check/re-upload when content is unchanged.
@@ -204,8 +190,6 @@ public:
             std::swap(this->viewType, that.viewType);
             std::swap(this->sampleCount, that.sampleCount);
             std::swap(this->imageCreateFlags, that.imageCreateFlags);
-            std::swap(this->usageFlags, that.usageFlags);
-            std::swap(this->storageUsageResolved, that.storageUsageResolved);
             std::swap(this->syncedTextureParamsVersion, that.syncedTextureParamsVersion);
             std::swap(this->syncedContentVersion, that.syncedContentVersion);
             std::swap(this->syncedMipLevelCount, that.syncedMipLevelCount);
@@ -267,8 +251,6 @@ public:
             viewType = VK_IMAGE_VIEW_TYPE_2D;
             sampleCount = VK_SAMPLE_COUNT_1_BIT;
             imageCreateFlags = 0;
-            usageFlags = 0;
-            storageUsageResolved = false;
             syncedTextureParamsVersion = 0;
             syncedContentVersion = 0;
             syncedMipLevelCount = 0;
@@ -285,10 +267,6 @@ public:
     Bool Initialize(const InitInfo& initInfo);
     void Shutdown();
     void BeginFrame(Uint32 frameIndex);
-    // Drains every frame slot's deferred image/view releases. Only valid when
-    // the caller has proven every queue submission complete; used by the
-    // present-less frame-boundary drain.
-    void CollectAllDeferredReleases();
 
     TextureResource* SyncTextureAndGetDescriptor(
         MG_State::GLState::ITextureObject& texture);
@@ -307,17 +285,6 @@ public:
                                                       VkImageLayout newLayout);
     Bool TransitionTextureForSampling(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
     Bool TransitionTextureForStorageImage(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
-    // Records that this texture is bound to a GL image unit, so its image must carry
-    // VK_IMAGE_USAGE_STORAGE_BIT. Must be called before NeedsStorageImagePreparation, and
-    // therefore before the render pass is committed: an image that has to be upgraded is
-    // recreated, which is illegal inside a render pass. Sticky for the texture's lifetime -
-    // GL lets an image binding come and go, and re-creating the image every time it does
-    // would cost far more than the compression it wins back.
-    void MarkStorageImageTexture(MG_State::GLState::ITextureObject& texture);
-    // True when this texture is marked but its live image predates the mark, i.e. the next sync
-    // will recreate it with STORAGE usage and copy the old contents forward. Callers use this to
-    // submit their pending recording first, so that copy cannot read pre-flush content.
-    Bool NeedsStorageUsageUpgrade(MG_State::GLState::ITextureObject& texture) const;
     // Non-mutating probe for the per-draw storage-image fast path: true when preparing this
     // texture as a storage image may need work that is illegal inside a render pass (resource
     // creation, dirty-content upload, or a layout transition to GENERAL). Unknown state reports
@@ -397,20 +364,15 @@ private:
     static TextureIdentity MakeTextureIdentity(MG_State::GLState::ITextureObject* texture);
     void EraseTrackedTexture(const TextureIdentity& identity);
     void PruneStaleTextureAliases(MG_State::GLState::ITextureObject* texture);
-    SizeT PruneDeadTextures();
 
     VkDevice m_device = VK_NULL_HANDLE;
     VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
     VmaAllocator m_allocator = nullptr;
     VkCommandPool m_commandPool = VK_NULL_HANDLE;
     VkQueue m_graphicsQueue = VK_NULL_HANDLE;
-    Bool m_imageFormatListSupported = false;
     Uint32 m_currentFrameIndex = 0;
 
     Uint8 m_gcCounter = 0;
-    // Frame-boundary GC gate: counts BeginFrame calls, not draws, so texture churn
-    // through non-draw paths (FBO clears, readbacks) still reaches the prune.
-    Uint32 m_gcFrameCounter = 0;
     // Active only between BeginDrawSyncScope/EndDrawSyncScope; identities of
     // textures already fully synced in the current draw (small N -> flat scan).
     Bool m_drawSyncScopeActive = false;
@@ -428,8 +390,6 @@ private:
     std::unordered_set<VkFormat> m_mutableFormatUnsupported;
     std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
     std::unordered_map<TextureIdentity, TextureResource, TextureIdentityHash> m_textureResources;
-    // Textures that have been bound to a GL image unit (see MarkStorageImageTexture).
-    std::unordered_set<TextureIdentity, TextureIdentityHash> m_storageImageTextures;
     Vector<Vector<TextureResource>> m_deferredReleases;
     Vector<Vector<VkImageView>> m_deferredViewReleases;
 };

MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp

@@ -1016,18 +1016,7 @@ layout(location = 0) in vec2 vTexCoord;
 layout(location = 0) out vec4 outColor;
 
 void main() {
-    // Explicit LOD, not texture(): a blit reads exactly the selected level, so
-    // derivative-based mip selection has no business here. It is also load-bearing:
-    // on Adreno 650 (driver 512.502) an implicit-LOD sample of this single-mip
-    // UBWC render target through the pre-rotation (ROTATE_90) mapping reads past
-    // the image's allocation - despite the sampler's maxLod=0 and a nominal 1:1
-    // texel mapping whose LOD is 0, so the driver's implicit-LOD path itself is at
-    // fault - and page-faults the GPU once the neighbouring memory is returned to
-    // the kernel (frame 2 of Minecraft 26.2's resource reload; the kernel then
-    // invalidates the context and the next submit dies with EDEADLK ->
-    // VK_ERROR_DEVICE_LOST at Present). Verified on device: texture() faults on
-    // the second frame every run, textureLod survives with identical state.
-    outColor = textureLod(uSource, vTexCoord, 0.0);
+    outColor = texture(uSource, vTexCoord);
 }
 )";
 
@@ -1921,10 +1910,8 @@ void main() {
                 case VK_FORMAT_R16G16_UNORM:          out = {ReadbackSourceClass::Float, 2, 16}; return true;
                 case VK_FORMAT_R16G16B16A16_UNORM:    out = {ReadbackSourceClass::Float, 4, 16}; return true;
                 // --- SRGB (decode to linear like GL readback of sRGB textures) ---
-                // GL GetTexImage/ReadPixels of sRGB textures return the raw sRGB-encoded
-                // bytes (GL 3.3 has no FRAMEBUFFER_SRGB read decode) - do NOT linearize.
-                case VK_FORMAT_R8G8B8A8_SRGB:         out = {ReadbackSourceClass::Float, 4, 8}; return true;
-                case VK_FORMAT_B8G8R8A8_SRGB:         out = {ReadbackSourceClass::Float, 4, 8, false, false, true}; return true;
+                case VK_FORMAT_R8G8B8A8_SRGB:         out = {ReadbackSourceClass::Float, 4, 8, false, true}; return true;
+                case VK_FORMAT_B8G8R8A8_SRGB:         out = {ReadbackSourceClass::Float, 4, 8, false, true, true}; return true;
                 // --- SNORM ---
                 case VK_FORMAT_R8_SNORM:              out = {ReadbackSourceClass::Float, 1, 8, true};  return true;
                 case VK_FORMAT_R8G8_SNORM:            out = {ReadbackSourceClass::Float, 2, 8, true};  return true;
@@ -1962,8 +1949,6 @@ void main() {
                 // --- packed / special ---
                 case VK_FORMAT_A2B10G10R10_UNORM_PACK32:
                 case VK_FORMAT_A2B10G10R10_UINT_PACK32:
-                case VK_FORMAT_A2R10G10B10_UNORM_PACK32:
-                case VK_FORMAT_A2R10G10B10_UINT_PACK32:
                 case VK_FORMAT_B10G11R11_UFLOAT_PACK32:
                 case VK_FORMAT_E5B9G9R9_UFLOAT_PACK32:
                 case VK_FORMAT_R5G6B5_UNORM_PACK16:
@@ -1973,8 +1958,7 @@ void main() {
                 case VK_FORMAT_B5G5R5A1_UNORM_PACK16:
                 case VK_FORMAT_R4G4B4A4_UNORM_PACK16:
                 case VK_FORMAT_B4G4R4A4_UNORM_PACK16:
-                    out.sourceClass = (format == VK_FORMAT_A2B10G10R10_UINT_PACK32 ||
-                                       format == VK_FORMAT_A2R10G10B10_UINT_PACK32) ?
+                    out.sourceClass = format == VK_FORMAT_A2B10G10R10_UINT_PACK32 ?
                         ReadbackSourceClass::UnsignedInt : ReadbackSourceClass::Float;
                     out.special = format;
                     return true;
@@ -2050,15 +2034,6 @@ void main() {
                     rgba[3] = static_cast<Float>((word >> 30) & 0x3u) / 3.0f;
                     return;
                 }
-                case VK_FORMAT_A2R10G10B10_UNORM_PACK32: {
-                    Uint32 word = 0;
-                    Memcpy(&word, source, sizeof(word));
-                    rgba[2] = static_cast<Float>(word & 0x3FFu) / 1023.0f;
-                    rgba[1] = static_cast<Float>((word >> 10) & 0x3FFu) / 1023.0f;
-                    rgba[0] = static_cast<Float>((word >> 20) & 0x3FFu) / 1023.0f;
-                    rgba[3] = static_cast<Float>((word >> 30) & 0x3u) / 3.0f;
-                    return;
-                }
                 case VK_FORMAT_B10G11R11_UFLOAT_PACK32: {
                     Uint32 word = 0;
                     Memcpy(&word, source, sizeof(word));
@@ -2210,13 +2185,6 @@ void main() {
                     rgba[1] = (word >> 10) & 0x3FFu;
                     rgba[2] = (word >> 20) & 0x3FFu;
                     rgba[3] = (word >> 30) & 0x3u;
-                } else if (srcFormat == VK_FORMAT_A2R10G10B10_UINT_PACK32) {
-                    Uint32 word = 0;
-                    Memcpy(&word, source, sizeof(word));
-                    rgba[2] = word & 0x3FFu;
-                    rgba[1] = (word >> 10) & 0x3FFu;
-                    rgba[0] = (word >> 20) & 0x3FFu;
-                    rgba[3] = (word >> 30) & 0x3u;
                 } else {
                     for (Int c = 0; c < desc.channels; ++c) {
                         if (desc.componentBits == 8) {
@@ -2248,9 +2216,8 @@ void main() {
         }
 
         static Bool PackReadbackToClientOrPbo(const Uint8* srcPixels, VkFormat srcFormat, GLsizei width,
-                                              GLsizei sliceHeight, GLsizei sliceCount, GLenum format, GLenum type,
-                                              void* pixels, Bool applyPackImageParams) {
-            if (width <= 0 || sliceHeight <= 0 || sliceCount <= 0) {
+                                              GLsizei height, GLenum format, GLenum type, void* pixels) {
+            if (width <= 0 || height <= 0) {
                 return true;
             }
 
@@ -2263,8 +2230,7 @@ void main() {
 
             Vector<Uint8> wide;
             GLenum wideType = GL_FLOAT;
-            if (!DecodeReadbackRowsToWide(srcPixels, srcFormat, width,
-                                          sliceHeight * sliceCount, wide, wideType)) {
+            if (!DecodeReadbackRowsToWide(srcPixels, srcFormat, width, height, wide, wideType)) {
                 MGLOG_E("DirectVulkan readback skipped: unsupported source format=%d",
                         static_cast<Int>(srcFormat));
                 return false;
@@ -2277,9 +2243,9 @@ void main() {
                 return false;
             }
 
-            return DirectGLES::ReadbackImpl::StoreWideRowsToClient(wide.data(), wideType, width, sliceHeight,
-                                                                   sliceCount, mapping, type, pixels,
-                                                                   applyPackImageParams);
+            return DirectGLES::ReadbackImpl::StoreWideRowsToClient(wide.data(), wideType, width, height,
+                                                                   /*sliceCount=*/1, mapping, type, pixels,
+                                                                   /*applyPackImageParams=*/false);
         }
     } // namespace
 
@@ -2491,7 +2457,7 @@ void main() {
         MOBILEGL_ASSERT(m_textureManager != nullptr, "VkTextureManager creation failed.");
         succeeded = m_textureManager->Initialize(
             {m_device, m_physicalDevice.handle, m_allocator, m_commandPool, m_graphicsQueue,
-             m_frameContext.GetFrameCount(), m_imageFormatListExtensionEnabled});
+             m_frameContext.GetFrameCount()});
         MOBILEGL_ASSERT(succeeded, "VkTextureManager initialization failed.");
         m_clearManager = MakeUnique<VkClearManager>();
         MOBILEGL_ASSERT(m_clearManager != nullptr, "VkClearManager creation failed.");
@@ -2540,11 +2506,6 @@ void main() {
                                                       m_shaderDrawParametersFeatureEnabled,
                                                       m_unformattedFloatStorageImagesEnabled);
         MOBILEGL_ASSERT(m_programFactory != nullptr, "ProgramFactory creation failed.");
-        // Aging evictions (render passes and program entries) must purge the dependent
-        // pipeline / compute-pipeline / descriptor-set caches in the same step; both
-        // sweeps only run from the frame-boundary seams, long after initialization.
-        m_renderPassManager->SetEvictionObserver(this);
-        m_programFactory->SetEvictionObserver(this);
 
         m_samplerManager = MakeUnique<VkSamplerManager>();
         MOBILEGL_ASSERT(m_samplerManager != nullptr, "VkSamplerManager creation failed.");
@@ -2574,20 +2535,11 @@ void main() {
         if (m_swapchainObject.GetHandle() != VK_NULL_HANDLE) {
             VkResult acquireResult =
                 m_frameContext.WaitAndAcquireNextImage(m_device, m_swapchainObject.GetHandle(), m_imageIndexAcquired);
-            if (acquireResult == VK_ERROR_OUT_OF_DATE_KHR) {
-                // Nothing was acquired and no semaphore signal was armed, so
-                // rebuilding and re-acquiring on the same semaphore is safe.
+            if (acquireResult == VK_ERROR_OUT_OF_DATE_KHR || acquireResult == VK_SUBOPTIMAL_KHR) {
                 MGLOG_D("Initialize, vkAcquireNextImageKHR got %d, recreating swapchain", acquireResult);
                 RecreateSwapchain();
                 acquireResult =
                     m_frameContext.WaitAndAcquireNextImage(m_device, m_swapchainObject.GetHandle(), m_imageIndexAcquired);
-            } else if (acquireResult == VK_SUBOPTIMAL_KHR) {
-                // The image is usable, and its acquire signal is already armed on
-                // imageAvailableSemaphore. Re-acquiring here would arm a second signal on a
-                // binary semaphore whose first one nobody has waited on yet; keep the image.
-                // Only a real surface change schedules a rebuild.
-                m_swapchainResizeRequested = m_swapchainResizeRequested || SwapchainIsOutOfDate();
-                acquireResult = VK_SUCCESS;
             }
             VK_VERIFY(acquireResult, "Initialize, WaitAndAcquireNextImage");
         } else {
@@ -2614,15 +2566,6 @@ void main() {
         DestroyDeferredDepthMipmapCleanup();
         DestroyComputePipelines();
 
-        // No sweep runs during teardown, but the observers point at this renderer
-        // and the factories die at different times below; disconnect them first.
-        if (m_renderPassManager) {
-            m_renderPassManager->SetEvictionObserver(nullptr);
-        }
-        if (m_programFactory) {
-            m_programFactory->SetEvictionObserver(nullptr);
-        }
-
         m_pipelineFactory.reset();
         ShutdownBlitResources();
         ShutdownDepthMipmapResources();
@@ -2713,7 +2656,6 @@ void main() {
             DestroyDebugMessenger();
             m_debugMessenger = VK_NULL_HANDLE;
         }
-        DestroyDebugReportCallback();
 
         if (m_instance != VK_NULL_HANDLE) {
             vkDestroyInstance(m_instance, nullptr);
@@ -4193,7 +4135,7 @@ void main() {
     }
 
     Bool VulkanRenderer::PrepareStorageImageTextures(
-        FrameContext::FrameData& frame,
+        VkCommandBuffer commandBuffer,
         const MG_State::GLState::ProgramObject& program,
         const ProgramFactory::VkProgramObject& programObj) {
         if (!programObj.hasStorageImages) {
@@ -4214,18 +4156,9 @@ void main() {
         // keep the render pass alive instead of splitting it on every storage-image draw (on
         // tiled GPUs each split is a full tile load/store). GL makes cross-draw image-store
         // coherence the app's job (glMemoryBarrier), so no implicit barrier is owed here.
-        // Record every image-unit binding before probing anything: a texture whose image was
-        // created without STORAGE usage (the default - it costs UBWC compression on Adreno)
-        // needs a recreate, and the probe below is what ends the render pass so that recreate
-        // lands here rather than mid-pass. This cannot be folded into the probe loop, which
-        // stops at the first texture that needs work and would leave the rest unmarked.
-        for (auto* texture : storageTextures) {
-            MOBILEGL_ASSERT(texture != nullptr, "%s: collected a null storage texture", __func__);
-            m_textureManager->MarkStorageImageTexture(*texture);
-        }
-
         Bool anyNeedsPreparation = false;
         for (auto* texture : storageTextures) {
+            MOBILEGL_ASSERT(texture != nullptr, "%s: collected a null storage texture", __func__);
             if (m_textureManager->NeedsStorageImagePreparation(*texture) ||
                 m_clearManager->HasPendingClear(texture)) {
                 anyNeedsPreparation = true;
@@ -4236,51 +4169,21 @@ void main() {
             return true;
         }
 
-        // A first-time storage-usage upgrade recreates the image and carries the old contents
-        // forward with an out-of-band, immediately-submitted copy (PreserveTextureContentsOnRecreate).
-        // Whatever this frame already recorded into the old image is still sitting unsubmitted in
-        // this command buffer, so that copy would read pre-frame content and this frame's rendering
-        // into the texture would be lost - precisely the render-target-then-image-unit case this
-        // whole path exists for. Submit what is recorded first; the copy then queues behind it.
-        Bool anyNeedsStorageUpgrade = false;
-        for (auto* texture : storageTextures) {
-            if (m_textureManager->NeedsStorageUsageUpgrade(*texture)) {
-                anyNeedsStorageUpgrade = true;
-                break;
-            }
-        }
-        if (anyNeedsStorageUpgrade && HasPendingRecordedWork()) {
-            if (FlushPendingCommands()) {
-                // Fresh command buffer: the sampled-descriptor-set memo describes bindings that
-                // only existed in the retired one. FlushPendingCommands drops the pipeline memo
-                // itself; this is the other command-buffer-scoped cache.
-                m_lastSampledSetValid = false;
-            } else {
-                // Best effort: the upgrade still produces a correct image, only its preserved
-                // contents may predate this frame's writes. Dropping the draw would be worse.
-                MGLOG_E("%s: flush before a storage-usage image upgrade failed; preserved contents "
-                        "may be stale for one frame", __func__);
-            }
-        }
-        if (!frame.isCommandRecording) {
-            m_frameContext.BeginCommandRecording();
-        }
-
         // Image uploads, deferred-clear materialization, and layout barriers are illegal inside
         // a classic render pass. Do this before sampler preparation as well: a texture used by
         // both a sampler and an image must stay in GENERAL, and both descriptors must name that
         // same layout independent of SPIR-V reflection/binding order.
         if (VkRenderPassManager::GetActiveRenderPass() != nullptr) {
-            VkRenderPassManager::EndRenderPass(frame.commandBuffer);
+            VkRenderPassManager::EndRenderPass(commandBuffer);
         }
 
         for (auto* texture : storageTextures) {
-            if (!MaterializePendingClearForTexture(frame.commandBuffer, *texture)) {
+            if (!MaterializePendingClearForTexture(commandBuffer, *texture)) {
                 MGLOG_E("%s: failed to materialize pending clear for storage textureId=%d",
                         __func__, texture->GetExternalIndex());
                 return false;
             }
-            if (!m_textureManager->TransitionTextureForStorageImage(frame.commandBuffer, *texture)) {
+            if (!m_textureManager->TransitionTextureForStorageImage(commandBuffer, *texture)) {
                 MGLOG_E("%s: failed to prepare storage textureId=%d",
                         __func__, texture->GetExternalIndex());
                 return false;
@@ -4306,25 +4209,7 @@ void main() {
         const auto& vao = *MG_State::pGLContext->GetBoundVertexArray();
         const auto& program = *MG_State::pGLContext->GetCurrentProgram();
         ProgramFactory::CompileOptionFlags transformFlags = GetShaderTransformFlags(m_swapchainObject.GetPreTransform());
-        const auto* programObjPtr = &m_programFactory->GetOrCreateProgram(program, transformFlags);
-        // Sampling a colour render target through the driver's implicit-LOD path faults the GPU on
-        // Adreno 650 (see ForceExplicitLod0SamplePass); ask for the explicit-LOD variant when doing
-        // so cannot change a texel, i.e. when every sampler this program reads is pinned to a
-        // single mip level.
-        if (UniformManager::ProgramSamplesOnlySingleLevelTextures(program, *programObjPtr)) {
-            transformFlags |= ProgramFactory::CompileOptionBit::ExplicitLod0Sampling;
-            programObjPtr = &m_programFactory->GetOrCreateProgram(program, transformFlags);
-        }
-        // fp16 fragment arithmetic is only sound when nothing this draw reads or writes carries
-        // more than 8 normalized bits per channel. A shaderpack's HDR gbuffer, or a data texture
-        // holding positions, must keep full precision - and SPIR-V cannot tell, since sampler2D
-        // yields vec4 whatever the bound format is, so the decision has to be made here.
-        if (UniformManager::ProgramSamplesOnlyLowPrecisionTextures(program, *programObjPtr) &&
-            UniformManager::DrawTargetIsLowPrecision(drawFbo.get())) {
-            transformFlags |= ProgramFactory::CompileOptionBit::RelaxedFragmentPrecision;
-            programObjPtr = &m_programFactory->GetOrCreateProgram(program, transformFlags);
-        }
-        const auto& programObj = *programObjPtr;
+        const auto& programObj = m_programFactory->GetOrCreateProgram(program, transformFlags);
 
         // Begin command recording if not yet
         if (!frame.isCommandRecording) {
@@ -4334,7 +4219,7 @@ void main() {
             m_lastSampledSetValid = false;
         }
 
-        if (!PrepareStorageImageTextures(frame, program, programObj)) {
+        if (!PrepareStorageImageTextures(frame.commandBuffer, program, programObj)) {
             MGLOG_E("SetupDraw skipped: storage image preparation failed");
             return false;
         }
@@ -4559,7 +4444,7 @@ void main() {
             VkRenderPassManager::EndRenderPass(frame.commandBuffer);
         }
 
-        if (!PrepareStorageImageTextures(frame, program, programObj)) {
+        if (!PrepareStorageImageTextures(frame.commandBuffer, program, programObj)) {
             MGLOG_E("DispatchCompute skipped: storage image preparation failed");
             return;
         }
@@ -4599,7 +4484,7 @@ void main() {
             VkRenderPassManager::EndRenderPass(frame.commandBuffer);
         }
 
-        if (!PrepareStorageImageTextures(frame, program, programObj)) {
+        if (!PrepareStorageImageTextures(frame.commandBuffer, program, programObj)) {
             MGLOG_E("DispatchComputeIndirect skipped: storage image preparation failed");
             return;
         }
@@ -6296,12 +6181,12 @@ void main() {
 
         frame.hasCommandBufferRecorded = false;
         frame.isCommandRecording = false;
-        // The wait proved every submission complete, so the full frame-boundary
-        // drain applies: descriptor cursors, transient arenas, deferred
-        // texture/buffer releases, retired command buffers and the converted
-        // vertex-stream cache all rewind here, keeping present-less readback
-        // loops bounded (Present is the only other drain point).
-        TryDrainFrameTransients();
+        // The wait proved every descriptor set this slot has in flight idle;
+        // rewind the reuse cursors so present-less readback loops stay
+        // bounded (Present is the only other rewind point).
+        if (m_uniformManager) {
+            m_uniformManager->BeginFrame(m_frameContext.GetCurrentFrameIndex());
+        }
         return true;
     }
 
@@ -6448,8 +6333,7 @@ void main() {
                 if (RemapDefaultFboReadbackToGLOrientation(mapped, swapchainExtent, preTransform,
                                                            sourceTexelSize,
                                                            remapped.data())) {
-                    PackReadbackToClientOrPbo(remapped.data(), srcFormat, width, height, 1, format, type, pixels,
-                                              /*applyPackImageParams=*/false);
+                    PackReadbackToClientOrPbo(remapped.data(), srcFormat, width, height, format, type, pixels);
                     return;
                 }
             }
@@ -6458,8 +6342,7 @@ void main() {
                     width, height, swapchainExtent.width, swapchainExtent.height,
                     static_cast<Int>(preTransform));
         }
-        PackReadbackToClientOrPbo(mapped, srcFormat, width, height, 1, format, type, pixels,
-                                  /*applyPackImageParams=*/false);
+        PackReadbackToClientOrPbo(mapped, srcFormat, width, height, format, type, pixels);
     }
 
     void VulkanRenderer::GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels) {
@@ -6512,17 +6395,6 @@ void main() {
         if (width <= 0 || height <= 0) {
             return;
         }
-        // GetTexImage returns every slice of a 3D level and every layer of an array
-        // level; GL_PACK_IMAGE_HEIGHT / GL_PACK_SKIP_IMAGES apply to the 3D/array
-        // destination layout (GL 3.3 section 6.1.4).
-        const auto imageTextureTarget = textureObject->GetTarget();
-        const Bool is3dImage = imageTextureTarget == TextureTarget::Texture3D;
-        const Bool isArrayImage = imageTextureTarget == TextureTarget::Texture1DArray ||
-                                  imageTextureTarget == TextureTarget::Texture2DArray ||
-                                  imageTextureTarget == TextureTarget::TextureCubeMapArray;
-        const GLsizei depthSlices = is3dImage ? std::max<GLsizei>(texelSize.z(), 1) : 1;
-        const GLsizei arrayLayers = isArrayImage ? static_cast<GLsizei>(resource->arrayLayers) : 1;
-        const GLsizei sliceCount = std::max<GLsizei>(depthSlices * arrayLayers, 1);
         if (bufSize >= 0) {
             const Int dstChannels = GetReadbackChannelCount(format);
             if ((type == GL_UNSIGNED_BYTE || type == GL_FLOAT) && dstChannels > 0) {
@@ -6543,8 +6415,7 @@ void main() {
             return;
         }
         const VkDeviceSize readbackSize = static_cast<VkDeviceSize>(width) *
-                                          static_cast<VkDeviceSize>(height) *
-                                          static_cast<VkDeviceSize>(sliceCount) * sourceTexelSize;
+                                          static_cast<VkDeviceSize>(height) * sourceTexelSize;
         VkBufferObject readback;
         if (!readback.Create({
                 .allocator = m_allocator,
@@ -6572,9 +6443,8 @@ void main() {
         copyRegion.imageSubresource.aspectMask = resource->aspect;
         copyRegion.imageSubresource.mipLevel = static_cast<Uint32>(level);
         copyRegion.imageSubresource.baseArrayLayer = 0;
-        copyRegion.imageSubresource.layerCount = static_cast<Uint32>(arrayLayers);
-        copyRegion.imageExtent = {static_cast<Uint32>(width), static_cast<Uint32>(height),
-                                  static_cast<Uint32>(depthSlices)};
+        copyRegion.imageSubresource.layerCount = 1;
+        copyRegion.imageExtent = {static_cast<Uint32>(width), static_cast<Uint32>(height), 1};
         vkCmdCopyImageToBuffer(frame.commandBuffer, resource->image, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL,
                                readback.GetHandle(), 1, &copyRegion);
 
@@ -6600,8 +6470,7 @@ void main() {
             MGLOG_E("DirectVulkan::GetTextureImage skipped: failed to invalidate readback buffer");
             return;
         }
-        PackReadbackToClientOrPbo(mapped, resource->format, width, height, sliceCount, format, type, pixels,
-                                  /*applyPackImageParams=*/is3dImage || isArrayImage);
+        PackReadbackToClientOrPbo(mapped, resource->format, width, height, format, type, pixels);
     }
 
     void VulkanRenderer::GenerateMipmap(GLenum target) {
@@ -7215,9 +7084,6 @@ void main() {
         }
         m_bufferManager.NotifyDeviceIdle();
         OnSubmitsCompletedUpTo(m_submitCounter);
-        // The queue was just drained; take the free frame-boundary drain when
-        // nothing is recorded (present-less timer-query loops). No-op otherwise.
-        TryDrainFrameTransients();
         return true;
     }
 
@@ -7286,85 +7152,6 @@ void main() {
                 vkDestroyFence(m_device, record.fence, nullptr);
             }
         }
-        // Mid-frame-flushed command buffers whose submission just completed can
-        // be freed now; present-less flush loops have no other reclaim point.
-        m_frameContext.FreeRetiredCommandBuffersCompletedUpTo(m_completedSubmitCounter);
-    }
-
-    Bool VulkanRenderer::TryDrainFrameTransients() {
-        if (m_device == VK_NULL_HANDLE || m_frameContext.GetFrameCount() == 0) {
-            return false;
-        }
-        if (m_completedSubmitCounter != m_submitCounter) {
-            RefreshCompletedSubmits();
-            if (m_completedSubmitCounter != m_submitCounter) {
-                return false;
-            }
-        }
-        if (HasPendingRecordedWork()) {
-            return false;
-        }
-
-        // Every submission is complete and nothing recorded references the
-        // per-frame transients. Pure-reclaim work runs on every drain: it only
-        // releases memory that is provably dead, never invalidates anything a
-        // later draw would have to rebuild. Raise the buffer manager's
-        // completed floor first so busy-tracking reflects the proven idleness.
-        m_bufferManager.NotifyDeviceIdle();
-
-        const Uint32 frameIndex = m_frameContext.GetCurrentFrameIndex();
-        m_frameContext.FreeAllRetiredCommandBuffers();
-        for (Uint32 slot = 0; slot < m_deferredDepthMipmapCleanup.size(); ++slot) {
-            CollectDeferredDepthMipmapCleanup(slot);
-        }
-        if (m_textureManager) {
-            m_textureManager->CollectAllDeferredReleases();
-        }
-        m_bufferManager.CollectAllDeferredReleases();
-        // Descriptor cursors rewind on every drain (the pre-drain readback path
-        // already did exactly this), keeping fence/readback loops' set usage bounded.
-        if (m_uniformManager) {
-            m_uniformManager->BeginFrame(frameIndex);
-        }
-
-        // Frame-boundary-equivalent work - transient arena rewind (which invalidates
-        // the conversion cache) and the cache-aging clocks - is gated to every 8th
-        // drain since the last Present: a presenting app's mid-frame readbacks/waits
-        // must neither force re-conversion/re-upload churn for the rest of the frame
-        // nor multiply the aging rate (which would shrink the 1024-boundary retire
-        // window and thrash periodically-used pipelines/programs), while present-less
-        // loops still rewind the arena and age their caches every 8 iterations -
-        // bounded by 8 iterations' transient usage.
-        ++m_drainsSinceLastPresent;
-        if ((m_drainsSinceLastPresent % 8) != 0) {
-            return true;
-        }
-        if (m_textureManager) {
-            m_textureManager->BeginFrame(frameIndex);
-        }
-        m_bufferManager.BeginFrame(frameIndex);
-        // The cached conversion slices point into the transient arena the
-        // BeginFrame above just rewound; drop them together.
-        m_convertedVertexStreams.clear();
-        if (m_renderPassManager) {
-            m_renderPassManager->OnPresent();
-        }
-        // The pipeline memo can survive across these boundaries (no per-frame reset
-        // on this path), so it must drop whenever the sweep destroys anything.
-        if (m_programFactory) {
-            m_programFactory->OnFrameBoundary();
-        }
-        if (m_pipelineFactory && m_pipelineFactory->OnFrameBoundary() > 0) {
-            m_lastPipelineValid = false;
-            m_lastPipelineResult = VK_NULL_HANDLE;
-        }
-        if (m_vertexInputStateFactory) {
-            m_vertexInputStateFactory->OnFrameBoundary();
-        }
-        if (m_samplerManager) {
-            m_samplerManager->OnFrameBoundary();
-        }
-        return true;
     }
 
     VkFence VulkanRenderer::AcquirePooledSubmitFence() {
@@ -7427,10 +7214,6 @@ void main() {
         if (m_device == VK_NULL_HANDLE || m_graphicsQueue == VK_NULL_HANDLE || m_frameContext.GetFrameCount() == 0) {
             return false;
         }
-        // Non-blocking completion poll: gives flush-only workloads (no sync
-        // objects, no present) a point where finished submissions retire their
-        // pooled fences and mid-frame command buffers.
-        RefreshCompletedSubmits();
         auto& frame = m_frameContext.GetCurrent();
         if (!frame.isCommandRecording && !frame.hasCommandBufferRecorded) {
             return false;
@@ -7455,14 +7238,6 @@ void main() {
             return false;
         }
 
-        // Command-buffer boundary: the pipeline memo must not survive it, or a
-        // pipeline bound only through memo hits is never re-stamped in the factory
-        // cache and the aging sweep could destroy it while the flushed submission
-        // still references it. Mirrors the drops at the readback and Present
-        // boundaries; costs one full pipeline lookup on the next draw.
-        m_lastPipelineValid = false;
-        m_lastPipelineResult = VK_NULL_HANDLE;
-
         // The submitted command buffer may still be executing; recording must
         // restart on a fresh one. If none can be allocated, fall back to
         // draining this submission so reusing the buffer stays legal.
@@ -7514,10 +7289,6 @@ void main() {
                 const VkResult result = vkWaitForFences(m_device, 1, &record.fence, VK_TRUE, timeoutNs);
                 if (result == VK_SUCCESS) {
                     OnSubmitsCompletedUpTo(record.submitIndex);
-                    // The wait already stalled the pipeline; if it happens to
-                    // have drained everything (present-less fence loops), take
-                    // the free frame-boundary drain. No-op otherwise.
-                    TryDrainFrameTransients();
                     return true;
                 }
                 if (result != VK_TIMEOUT) {
@@ -7607,69 +7378,34 @@ void main() {
                 suspendedFrame.isCommandRecording = false;
                 suspendedFrame.hasCommandBufferRecorded = false;
                 m_lastPipelineValid = false;
-                // The dropped recording is never submitted, so once the fence
-                // poll shows the pre-suspension submissions complete the frame
-                // transients (descriptor sets, transient arenas, deferred
-                // releases, conversion caches) can rewind; without this a
-                // minimized-window app accumulates them for the whole
-                // suspension.
-                TryDrainFrameTransients();
                 MGLOG_D("Present skipped: no usable swapchain (zero-area window)");
                 return;
             }
             m_presentSuspended = false;
             const VkResult acquireResult =
                 m_frameContext.WaitAndAcquireNextImage(m_device, m_swapchainObject.GetHandle(), m_imageIndexAcquired);
-            if (acquireResult == VK_SUBOPTIMAL_KHR) {
-                // Usable image with its acquire signal already armed; a rebuild is scheduled
-                // only if the surface genuinely no longer matches (see step 4 of Present).
-                m_swapchainResizeRequested = m_swapchainResizeRequested || SwapchainIsOutOfDate();
-            } else {
+            if (acquireResult != VK_SUBOPTIMAL_KHR) {
                 VK_VERIFY(acquireResult, "Present, deferred first WaitAndAcquireNextImage");
             }
         }
         MOBILEGL_ASSERT(m_imageIndexAcquired < m_swapchainObject.GetImageCount(),
                         "Present, acquired image index out of range");
         m_renderPassManager->OnPresent();
-        // A real presented frame is the canonical aging cadence; mid-frame drains
-        // count against this and only age when presents stop coming.
-        m_drainsSinceLastPresent = 0;
-        // Age the content-addressed caches on the same frame-boundary cadence. Each
-        // keeps its own internal 256-sweep gate, so the per-frame cost is one counter
-        // increment and compare per cache; entries used by this frame's still-
-        // unsubmitted recording were stamped this boundary (every command-buffer
-        // boundary drops the pipeline memo, so the first draw of each recording
-        // performs a real, stamping lookup) and can never age out.
-        m_programFactory->OnFrameBoundary();
-        if (m_pipelineFactory->OnFrameBoundary() > 0) {
-            m_lastPipelineValid = false; // an aged-out pipeline may still be memoized
-            m_lastPipelineResult = VK_NULL_HANDLE;
-        }
-        m_vertexInputStateFactory->OnFrameBoundary();
-        m_samplerManager->OnFrameBoundary();
         auto& frame = m_frameContext.GetCurrent();
         auto* activeRenderPass = VkRenderPassManager::GetActiveRenderPass();
         if (activeRenderPass)
             VkRenderPassManager::EndRenderPass(frame.commandBuffer);
 
-        // Transition while this frame's recording is still open. A frame that
-        // rendered only into FBOs has no default-framebuffer render pass, and that
-        // pass's finalLayout is the only other thing that carries the swapchain
-        // image to PRESENT_SRC_KHR - so closing the buffer first, which made
-        // TransitionToPresent refuse to record, handed the image to
-        // vkQueuePresentKHR in the layout it was acquired in (UNDEFINED on a fresh
-        // swapchain). The SetImageLayout below then made the tracker's
-        // disagreement with reality permanent for that image index.
-        const auto acquiredImageLayout = m_swapchainObject.GetImageLayout(m_imageIndexAcquired);
-        m_frameContext.TransitionToPresent(m_swapchainObject.GetImage(m_imageIndexAcquired), acquiredImageLayout);
-
         if (frame.isCommandRecording) {
             m_frameContext.EndCommandRecording();
             frame.hasCommandBufferRecorded = true;
             m_lastPipelineValid = false; // command-buffer boundary: drop the pipeline memo
         }
 
-        const Bool shouldSubmitCommandBuffer = frame.hasCommandBufferRecorded;
+        const auto acquiredImageLayout = m_swapchainObject.GetImageLayout(m_imageIndexAcquired);
+        const Bool needsLayoutTransitionForPresent =
+            m_frameContext.TransitionToPresent(m_swapchainObject.GetImage(m_imageIndexAcquired), acquiredImageLayout);
+        const Bool shouldSubmitCommandBuffer = frame.hasCommandBufferRecorded || needsLayoutTransitionForPresent;
 
         // 1) Submit current frame work.
         auto submitPacket = m_frameContext.GetSubmitInfo(shouldSubmitCommandBuffer, m_imageIndexAcquired);
@@ -7683,15 +7419,7 @@ void main() {
         // 2) Present current frame.
         auto presentPacket = m_frameContext.GetPresentInfo(m_swapchainObject.GetHandle(), m_imageIndexAcquired);
         auto result = vkQueuePresentKHR(m_presentQueue, &presentPacket.presentInfo);
-        if (result == VK_SUBOPTIMAL_KHR) {
-            // Suboptimal is not a reason to rebuild on its own: a driver may report it for a
-            // surface whose size and orientation still match what we built from (Android does
-            // this routinely), and rebuilding on it alone destroys every pipeline and
-            // reallocates the default framebuffer once per frame - flicker, then garbage.
-            // Defer to the surface-capabilities comparison below.
-            result = VK_SUCCESS;
-        }
-        if (result == VK_ERROR_OUT_OF_DATE_KHR) {
+        if (result == VK_ERROR_OUT_OF_DATE_KHR || result == VK_SUBOPTIMAL_KHR) {
             MGLOG_D("Present, vkQueuePresentKHR got %d, recreating swapchain", result);
             if (!RecreateSwapchain()) {
                 // Window went zero-area (minimize) with the swapchain out of date:
@@ -7705,13 +7433,6 @@ void main() {
             result = VK_SUCCESS;
         }
         VK_VERIFY(result, "Present, vkQueuePresentKHR");
-        // The authoritative check, done here - after the frame is presented, before the next
-        // acquire. This is what makes a launcher-side resolution change take effect: shrinking
-        // the window's buffer (SurfaceHolder.setFixedSize) moves currentExtent, the swapchain
-        // follows, and the compositor scales the smaller image up to the view for free.
-        if (!m_swapchainResizeRequested && SwapchainIsOutOfDate()) {
-            m_swapchainResizeRequested = true;
-        }
         if (m_swapchainResizeRequested) {
             MGLOG_D("Present, processing requested swapchain resize");
             if (!RecreateSwapchain()) {
@@ -7728,16 +7449,7 @@ void main() {
 
         // 4) Wait/reset/acquire for next frame.
         result = m_frameContext.WaitAndAcquireNextImage(m_device, m_swapchainObject.GetHandle(), m_imageIndexAcquired);
-        if (result == VK_SUBOPTIMAL_KHR) {
-            // An image WAS acquired and its signal is armed on this slot's
-            // imageAvailableSemaphore, so the frame proceeds normally. Whether a rebuild is
-            // actually needed is decided by the surface-capabilities comparison at the next
-            // Present - suboptimal alone must not schedule one, or a driver that reports it
-            // every frame would rebuild every frame.
-            m_swapchainResizeRequested = m_swapchainResizeRequested || SwapchainIsOutOfDate();
-            result = VK_SUCCESS;
-        } else if (result == VK_ERROR_OUT_OF_DATE_KHR) {
-            // Nothing acquired, nothing signaled: safe to rebuild and re-acquire.
+        if (result == VK_ERROR_OUT_OF_DATE_KHR || result == VK_SUBOPTIMAL_KHR) {
             MGLOG_D("Present, vkAcquireNextImageKHR got %d, recreating swapchain", result);
             if (!RecreateSwapchain()) {
                 m_presentSuspended = true;
@@ -7785,24 +7497,6 @@ void main() {
 
         m_validationLayersEnabled = m_config.EnableValidationLayers && validationLayerAvailable;
 
-        // The debug messenger is a VK_EXT_debug_utils object, but a driver can ship
-        // the validation layers while exposing only the older VK_EXT_debug_report
-        // (Adreno 650 / Vulkan 1.1.128 does exactly that). Requesting the extension
-        // unconditionally tripped the required-extension assert below, aborting every
-        // validation-enabled build in CreateInstance. Keep the layers - they still
-        // validate, and on Android they report to logcat on their own - and drop only
-        // the messenger.
-        const Bool debugUtilsAvailable =
-            m_validationLayersEnabled && IsExtensionSupported(m_extensions, VK_EXT_DEBUG_UTILS_EXTENSION_NAME);
-        // Without a reporting channel the layers validate but say nothing, so fall
-        // back to VK_EXT_debug_report when debug_utils is missing.
-        const Bool debugReportAvailable = m_validationLayersEnabled && !debugUtilsAvailable &&
-                                          IsExtensionSupported(m_extensions, VK_EXT_DEBUG_REPORT_EXTENSION_NAME);
-        if (m_validationLayersEnabled && !debugUtilsAvailable) {
-            MGLOG_I("%s not available; validation reports via %s instead.", VK_EXT_DEBUG_UTILS_EXTENSION_NAME,
-                    debugReportAvailable ? VK_EXT_DEBUG_REPORT_EXTENSION_NAME : "(no channel)");
-        }
-
         // ---------------- App info -------------------
         VkApplicationInfo appInfo = {};
         appInfo.sType = VK_STRUCTURE_TYPE_APPLICATION_INFO;
@@ -7853,10 +7547,8 @@ void main() {
         }
 #endif
 
-        if (debugUtilsAvailable) {
+        if (m_validationLayersEnabled) {
             exts.push_back(VK_EXT_DEBUG_UTILS_EXTENSION_NAME);
-        } else if (debugReportAvailable) {
-            exts.push_back(VK_EXT_DEBUG_REPORT_EXTENSION_NAME);
         }
 
         MGLOG_I("Enabling %d Vulkan instance extensions:", exts.size());
@@ -7881,8 +7573,7 @@ void main() {
             MGLOG_I("Enabling validation layer...");
             instanceInfo.enabledLayerCount = static_cast<uint32_t>(std::size(s_validationLayerNames));
             instanceInfo.ppEnabledLayerNames = s_validationLayerNames;
-            // Chaining the messenger create-info is only legal with the extension on.
-            instanceInfo.pNext = debugUtilsAvailable ? &debugMessengerCreateInfo : nullptr;
+            instanceInfo.pNext = &debugMessengerCreateInfo;
         } else {
             instanceInfo.enabledLayerCount = 0;
             instanceInfo.pNext = nullptr;
@@ -7890,40 +7581,7 @@ void main() {
 
         VK_VERIFY(vkCreateInstance(&instanceInfo, nullptr, &m_instance), "vkCreateInstance failed");
 
-        if (debugUtilsAvailable) {
-            VK_VERIFY(SetupDebugMessenger());
-        } else if (debugReportAvailable) {
-            VK_VERIFY(SetupDebugReportCallback());
-        }
-    }
-
-    static VKAPI_ATTR VkBool32 VKAPI_CALL DebugReportCallback(VkDebugReportFlagsEXT flags, VkDebugReportObjectTypeEXT,
-                                                              Uint64, size_t, Int32 messageCode, const char* pLayerPrefix,
-                                                              const char* pMessage, void*) {
-        if ((flags & (VK_DEBUG_REPORT_ERROR_BIT_EXT | VK_DEBUG_REPORT_WARNING_BIT_EXT |
-                      VK_DEBUG_REPORT_PERFORMANCE_WARNING_BIT_EXT)) != 0) {
-            MGLOG_F("[Vulkan %s %d] %s", pLayerPrefix ? pLayerPrefix : "?", messageCode, pMessage ? pMessage : "");
-        }
-        return VK_FALSE;
-    }
-
-    VkResult VulkanRenderer::SetupDebugReportCallback() {
-        auto vkCreateDebugReportCallbackEXT =
-            (PFN_vkCreateDebugReportCallbackEXT)vkGetInstanceProcAddr(m_instance, "vkCreateDebugReportCallbackEXT");
-        if (!vkCreateDebugReportCallbackEXT) return VK_ERROR_EXTENSION_NOT_PRESENT;
-        VkDebugReportCallbackCreateInfoEXT createInfo{VK_STRUCTURE_TYPE_DEBUG_REPORT_CALLBACK_CREATE_INFO_EXT};
-        createInfo.flags = VK_DEBUG_REPORT_ERROR_BIT_EXT | VK_DEBUG_REPORT_WARNING_BIT_EXT |
-                           VK_DEBUG_REPORT_PERFORMANCE_WARNING_BIT_EXT;
-        createInfo.pfnCallback = &DebugReportCallback;
-        return vkCreateDebugReportCallbackEXT(m_instance, &createInfo, nullptr, &m_debugReportCallback);
-    }
-
-    void VulkanRenderer::DestroyDebugReportCallback() {
-        if (m_debugReportCallback == VK_NULL_HANDLE) return;
-        auto func = (PFN_vkDestroyDebugReportCallbackEXT)vkGetInstanceProcAddr(m_instance,
-                                                                               "vkDestroyDebugReportCallbackEXT");
-        if (func != nullptr) func(m_instance, m_debugReportCallback, nullptr);
-        m_debugReportCallback = VK_NULL_HANDLE;
+        if (m_validationLayersEnabled) VK_VERIFY(SetupDebugMessenger());
     }
 
     VkResult VulkanRenderer::SetupDebugMessenger() {
@@ -8205,18 +7863,6 @@ void main() {
 
         const Vector<VkExtensionProperties> availableExtensions = EnumerateDeviceExtensions(m_physicalDevice.handle);
         ResolveOptionalDeviceExtensions(availableExtensions, enabledDeviceExtensions);
-
-        // VK_KHR_image_format_list lets a MUTABLE_FORMAT image declare exactly which formats it
-        // may be viewed as. Adreno drops UBWC bandwidth compression on a blindly-mutable image
-        // (measured: 65 -> 80 fps in MC 26.2 once mutability is not requested); an explicit,
-        // compression-compatible format list is the portable way to keep both.
-        m_imageFormatListExtensionEnabled =
-            IsExtensionSupported(availableExtensions, VK_KHR_IMAGE_FORMAT_LIST_EXTENSION_NAME);
-        if (m_imageFormatListExtensionEnabled) {
-            enabledDeviceExtensions.push_back(VK_KHR_IMAGE_FORMAT_LIST_EXTENSION_NAME);
-        }
-        MGLOG_I("VK_KHR_image_format_list enabled: %s",
-                m_imageFormatListExtensionEnabled ? "true" : "false");
         MGLOG_I("VK_KHR_draw_indirect_count enabled: %s", m_drawIndirectCountExtensionEnabled ? "true" : "false");
 
         m_indexTypeUint8ExtensionEnabled = false;
@@ -8681,38 +8327,6 @@ void main() {
         return m_physicalDevice;
     }
 
-    Bool VulkanRenderer::SwapchainIsOutOfDate() {
-        if (m_surface == VK_NULL_HANDLE || m_swapchainObject.GetHandle() == VK_NULL_HANDLE) {
-            return false;
-        }
-        VkSurfaceCapabilitiesKHR surfaceCaps{};
-        if (vkGetPhysicalDeviceSurfaceCapabilitiesKHR(m_physicalDevice.handle, m_surface, &surfaceCaps) !=
-            VK_SUCCESS) {
-            return false;
-        }
-        // A driver-defined currentExtent (UINT32_MAX) means the surface takes its size from the
-        // swapchain, so there is nothing to compare against - the app's requested size wins and
-        // only an explicit RequestSwapchainResize can change it.
-        if (surfaceCaps.currentExtent.width == UINT32_MAX || surfaceCaps.currentExtent.height == UINT32_MAX) {
-            return false;
-        }
-        // Compare in SURFACE space against the extent the live swapchain was created from. Using
-        // the swapchain's own (quarter-turn swapped) extent here would report a difference on
-        // every rotated frame and rebuild forever.
-        const VkExtent2D builtFrom = m_swapchainObject.GetSurfaceExtent();
-        const Bool extentChanged = surfaceCaps.currentExtent.width != builtFrom.width ||
-                                   surfaceCaps.currentExtent.height != builtFrom.height;
-        const Bool transformChanged = surfaceCaps.currentTransform != m_swapchainObject.GetPreTransform();
-        if (!extentChanged && !transformChanged) {
-            return false;
-        }
-        MGLOG_I("Swapchain out of date: surface %ux%u transform %u -> %ux%u transform %u",
-                builtFrom.width, builtFrom.height, static_cast<Uint32>(m_swapchainObject.GetPreTransform()),
-                surfaceCaps.currentExtent.width, surfaceCaps.currentExtent.height,
-                static_cast<Uint32>(surfaceCaps.currentTransform));
-        return true;
-    }
-
     void VulkanRenderer::RequestSwapchainResize(Uint32 width, Uint32 height) {
         width = std::max<Uint32>(width, 1);
         height = std::max<Uint32>(height, 1);
@@ -8809,43 +8423,6 @@ void main() {
         m_computePipelines.clear();
     }
 
-    void VulkanRenderer::OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) {
-        if (m_pipelineFactory == nullptr) {
-            return;
-        }
-        // The render-pass sweep's >1024-boundary idle guarantee covers these pipelines
-        // too (they are only bound by draws that hit the dying entries), so the factory
-        // destroys them immediately. The memo must drop as well: it can hand out a
-        // cached handle without touching the factory.
-        if (m_pipelineFactory->EvictByRenderPasses(renderPasses) > 0) {
-            m_lastPipelineValid = false;
-            m_lastPipelineResult = VK_NULL_HANDLE;
-        }
-    }
-
-    void VulkanRenderer::OnProgramEvicted(ProgramFactory::HashType programHash,
-                                          VkDescriptorSetLayout descriptorSetLayout) {
-        // Same >1024-boundary idleness as the program entry: its compute pipeline is
-        // only dispatched, and its graphics pipelines only bound, through paths that
-        // stamp the entry, so immediate destruction is GPU-safe. (The graphics memo
-        // never holds compute pipelines; it only needs invalidating for the factory
-        // eviction below.)
-        const auto computeIt = m_computePipelines.find(programHash);
-        if (computeIt != m_computePipelines.end()) {
-            if (computeIt->second != VK_NULL_HANDLE && m_device != VK_NULL_HANDLE) {
-                vkDestroyPipeline(m_device, computeIt->second, nullptr);
-            }
-            m_computePipelines.erase(computeIt);
-        }
-        if (m_pipelineFactory != nullptr && m_pipelineFactory->EvictByProgramHash(programHash) > 0) {
-            m_lastPipelineValid = false;
-            m_lastPipelineResult = VK_NULL_HANDLE;
-        }
-        if (m_uniformManager != nullptr) {
-            m_uniformManager->OnDescriptorSetLayoutDestroyed(descriptorSetLayout);
-        }
-    }
-
     VkPipeline VulkanRenderer::GetOrCreateComputePipeline(const ProgramFactory::VkProgramObject& programObj) {
         const auto it = m_computePipelines.find(programObj.hash);
         if (it != m_computePipelines.end()) {

MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.h

@@ -114,10 +114,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     };
 
-    class VulkanRenderer : public IBufferCopyCommandProvider,
-                           public FrameContext::IRecordingObserver,
-                           public VkRenderPassManager::IEvictionObserver,
-                           public ProgramFactory::IEvictionObserver {
+    class VulkanRenderer : public IBufferCopyCommandProvider, public FrameContext::IRecordingObserver {
     public:
         VulkanRenderer(NativeWindowType window, const VulkanRendererConfig& cfg = {});
         ~VulkanRenderer();
@@ -134,20 +131,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // recording, before any render pass.
         void OnFrameCommandRecordingBegan(VkCommandBuffer commandBuffer) override;
 
-        // VkRenderPassManager::IEvictionObserver: the render-pass aging sweep just
-        // destroyed these VkRenderPasses; evict every graphics pipeline hashed on a
-        // dying handle (they share its >1024-boundary idleness, so immediate
-        // destruction is safe) and drop the last-pipeline memo if any went.
-        void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) override;
-
-        // ProgramFactory::IEvictionObserver: an aged-out program entry was
-        // destroyed; evict its compute pipeline and graphics pipelines (same
-        // idleness guarantee - they are only bound through draws/dispatches that
-        // stamp the program entry) and purge the descriptor-set cache entries
-        // keyed by its now-recyclable VkDescriptorSetLayout handle.
-        void OnProgramEvicted(ProgramFactory::HashType programHash,
-                              VkDescriptorSetLayout descriptorSetLayout) override;
-
         Bool SetupDraw(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
                        const DrawCmdParam& drawParams,
                        const IndexBufferView* pIndexBufferView = nullptr);
@@ -274,10 +257,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint64 GetTimerQueryTimestampNs(const VkTimerQueryManager::TimestampRecord& record) const;
 
         void RequestSwapchainResize(Uint32 width, Uint32 height);
-        // Re-query the surface and report whether the live swapchain no longer matches it
-        // (size or orientation). This - not a VK_SUBOPTIMAL_KHR result - is what decides a
-        // rebuild, so a surface the driver merely considers suboptimal cannot thrash.
-        Bool SwapchainIsOutOfDate();
         // Returns false when the surface is zero-area (minimized/hidden window):
         // no new swapchain is installed and presentation must stay suspended.
         Bool RecreateSwapchain();
@@ -366,26 +345,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkFence AcquirePooledSubmitFence();
         void DestroySubmitFencePool();
         Bool HasPendingRecordedWork() const;
-        // Frame-boundary housekeeping for paths that never reach Present's
-        // tail (present-less readback loops, suspended presentation, blocking
-        // sync waits): runs the same per-frame drains Present performs, but
-        // only when every queue submission has been observed complete AND no
-        // recorded-but-unsubmitted commands exist - i.e. when CPU-GPU overlap
-        // is provably already zero. Never blocks (non-blocking fence poll
-        // only), so the presenting path's frames-in-flight pipelining is
-        // untouched. Returns true when the drain ran.
-        Bool TryDrainFrameTransients();
 
         Vector<SubmitRecord> m_inFlightSubmits;
         Vector<VkFence> m_freeSubmitFences;
         Uint64 m_submitCounter = 0;
         Uint64 m_completedSubmitCounter = 0;
-        // Drains since the last Present, gating the drain's frame-boundary-equivalent
-        // work (arena rewind + cache aging): a presenting app's mid-frame
-        // readbacks/waits must neither churn the transient caches nor accelerate the
-        // aging clocks, while present-less loops still cross a boundary every few
-        // iterations. Reset in Present.
-        Uint32 m_drainsSinceLastPresent = 0;
 
         NativeWindowType m_window = 0;
         void* m_platformDisplay = nullptr;
@@ -403,9 +367,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<VkExtensionProperties> m_extensions;
         VkInstance m_instance = VK_NULL_HANDLE;
         VkDebugUtilsMessengerEXT m_debugMessenger = VK_NULL_HANDLE;
-        // Fallback reporting channel for drivers that ship the validation layers but
-        // only expose the older VK_EXT_debug_report (Adreno 650 / Vulkan 1.1.128).
-        VkDebugReportCallbackEXT m_debugReportCallback = VK_NULL_HANDLE;
         PhysicalDevice m_physicalDevice;
         VkDevice m_device = VK_NULL_HANDLE;
         VmaAllocator m_allocator = nullptr;
@@ -556,8 +517,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void CreateInstance();
         VkResult SetupDebugMessenger();
         VkResult DestroyDebugMessenger();
-        VkResult SetupDebugReportCallback();
-        void DestroyDebugReportCallback();
         VkDebugUtilsMessengerCreateInfoEXT PopulateDebugMessengerCreateInfo();
         void CreateSurface();
         void PickPhysicalDevice();
@@ -576,10 +535,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const RenderPassEntry& renderPassEntry);
         VkPipeline GetOrCreateComputePipeline(const ProgramFactory::VkProgramObject& programObj);
         void DestroyComputePipelines();
-        // Takes the frame rather than a command buffer: a first-time storage-usage upgrade has to
-        // flush the pending recording (see the body), which retires the current command buffer.
         Bool PrepareStorageImageTextures(
-            FrameContext::FrameData& frame,
+            VkCommandBuffer commandBuffer,
             const MG_State::GLState::ProgramObject& program,
             const ProgramFactory::VkProgramObject& programObj);
 
@@ -641,10 +598,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                                  const PhysicalDevice& compareWithDevice,
                                                  PhysicalDevice& outBetterDevice);
         static constexpr const char* s_validationLayerNames[] = {"VK_LAYER_KHRONOS_validation"};
-        // VK_KHR_image_format_list: lets MUTABLE_FORMAT images declare their exact view-format
-        // set so the driver can keep bandwidth compression (see CreateLogicalDeviceAndQueues).
-        Bool m_imageFormatListExtensionEnabled = false;
-
         static constexpr const char* s_deviceExtensionNames[] = {VK_KHR_SWAPCHAIN_EXTENSION_NAME};
         static Bool CheckValidationLayerSupport();
 

MobileGL/MG_Impl/CGLImpl/CGLImpl.cpp

@@ -24,7 +24,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
             GLint Samples = 0;
             GLint Profile = kCGLOGLPVersion_3_2_Core;
             GLint RendererId = 0x4d474c;
-            GLint DisplayMask = 0;
         };
 
         struct ContextObject {
@@ -135,9 +134,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
             case kCGLPFARendererID:
                 pixelFormat.RendererId = value;
                 break;
-            case kCGLPFADisplayMask:
-                pixelFormat.DisplayMask = value;
-                break;
             default:
                 break;
             }
@@ -347,9 +343,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
         case kCGLPFARendererID:
             *value = pixelFormat->RendererId;
             return kCGLNoError;
-        case kCGLPFADisplayMask:
-            *value = pixelFormat->DisplayMask;
-            return kCGLNoError;
         case kCGLPFAOpenGLProfile:
             *value = pixelFormat->Profile;
             return kCGLNoError;
@@ -488,32 +481,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
         return it == currentContexts.end() ? nullptr : it->second;
     }
 
-    CGLError SetVirtualScreen(CGLContextObj ctx, GLint screen) {
-        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
-        auto* object = TryGetContext(ctx);
-        if (!object) {
-            return kCGLBadContext;
-        }
-        if (screen != 0) {
-            return kCGLBadValue;
-        }
-        object->VirtualScreen = screen;
-        return kCGLNoError;
-    }
-
-    CGLError GetVirtualScreen(CGLContextObj ctx, GLint* screen) {
-        const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
-        auto* object = TryGetContext(ctx);
-        if (!object) {
-            return kCGLBadContext;
-        }
-        if (!screen) {
-            return kCGLBadAddress;
-        }
-        *screen = object->VirtualScreen;
-        return kCGLNoError;
-    }
-
     CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
         const std::lock_guard<std::recursive_mutex> lock(RegistryMutex());
         auto* object = TryGetContext(ctx);

MobileGL/MG_Impl/CGLImpl/CGLImpl.h

@@ -32,8 +32,6 @@ namespace MobileGL::MG_Impl::CGLImpl {
 
     CGLError SetCurrentContext(CGLContextObj ctx);
     CGLContextObj GetCurrentContext();
-    CGLError SetVirtualScreen(CGLContextObj ctx, GLint screen);
-    CGLError GetVirtualScreen(CGLContextObj ctx, GLint* screen);
     CGLError SetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params);
     CGLError GetParameter(CGLContextObj ctx, CGLContextParameter pname, GLint* params);
     CGLError UpdateContext(CGLContextObj ctx);

MobileGL/MG_Impl/CGLImpl/Exporting/Definitions.cpp

@@ -71,14 +71,6 @@ MOBILEGL_CGL_API CGLContextObj CGLGetCurrentContext(void) {
     return MobileGL::MG_Impl::CGLImpl::GetCurrentContext();
 }
 
-MOBILEGL_CGL_API CGLError CGLSetVirtualScreen(CGLContextObj ctx, GLint screen) {
-    return MobileGL::MG_Impl::CGLImpl::SetVirtualScreen(ctx, screen);
-}
-
-MOBILEGL_CGL_API CGLError CGLGetVirtualScreen(CGLContextObj ctx, GLint* screen) {
-    return MobileGL::MG_Impl::CGLImpl::GetVirtualScreen(ctx, screen);
-}
-
 MOBILEGL_CGL_API CGLError CGLSetParameter(CGLContextObj ctx, CGLContextParameter pname, const GLint* params) {
     return MobileGL::MG_Impl::CGLImpl::SetParameter(ctx, pname, params);
 }

MobileGL/MG_Impl/DyldInterpose/DyldInterpose.cpp

@@ -10,12 +10,8 @@
 
 #if defined(__APPLE__)
 
-#include "MG_Impl/CGLImpl/CGLImpl.h"
 #include "MG_Impl/GetProcAddress.h"
 
-#include <CoreGraphics/CoreGraphics.h>
-#include <CoreVideo/CVDisplayLink.h>
-#include <cstdint>
 #include <dlfcn.h>
 
 namespace {
@@ -51,52 +47,10 @@ namespace {
         return dlsym(handle, symbol);
     }
 
-    CGDirectDisplayID DisplayForMask(GLint displayMask) {
-        constexpr std::uint32_t MaxDisplays = sizeof(CGOpenGLDisplayMask) * 8;
-        CGDirectDisplayID displays[MaxDisplays] = {};
-        std::uint32_t displayCount = 0;
-        if (displayMask != 0 &&
-            CGGetActiveDisplayList(MaxDisplays, displays, &displayCount) == kCGErrorSuccess) {
-            const auto mask = static_cast<CGOpenGLDisplayMask>(displayMask);
-            for (std::uint32_t i = 0; i < displayCount; ++i) {
-                if ((CGDisplayIDToOpenGLDisplayMask(displays[i]) & mask) != 0) {
-                    return displays[i];
-                }
-            }
-        }
-        return CGMainDisplayID();
-    }
-
-#pragma clang diagnostic push
-#pragma clang diagnostic ignored "-Wdeprecated-declarations"
-    CVReturn MobileGLCVDisplayLinkSetCurrentCGDisplayFromOpenGLContext(
-        CVDisplayLinkRef displayLink,
-        CGLContextObj context,
-        CGLPixelFormatObj pixelFormat) {
-        GLint virtualScreen = 0;
-        if (MobileGL::MG_Impl::CGLImpl::GetVirtualScreen(context, &virtualScreen) == kCGLNoError) {
-            GLint displayMask = 0;
-            if (!displayLink ||
-                MobileGL::MG_Impl::CGLImpl::DescribePixelFormat(
-                    pixelFormat, virtualScreen, kCGLPFADisplayMask, &displayMask) != kCGLNoError) {
-                return kCVReturnInvalidArgument;
-            }
-            return CVDisplayLinkSetCurrentCGDisplay(displayLink, DisplayForMask(displayMask));
-        }
-
-        using OriginalFunction = CVReturn (*)(CVDisplayLinkRef, CGLContextObj, CGLPixelFormatObj);
-        static const auto original = reinterpret_cast<OriginalFunction>(
-            dlsym(RTLD_NEXT, "CVDisplayLinkSetCurrentCGDisplayFromOpenGLContext"));
-        return original ? original(displayLink, context, pixelFormat) : kCVReturnError;
-    }
-
     __attribute__((used)) static const DyldInterposeEntry kMobileGLDyldInterpose[]
         __attribute__((section("__DATA,__interpose"))) = {
             {reinterpret_cast<const void*>(MobileGLDlsym), reinterpret_cast<const void*>(dlsym)},
-            {reinterpret_cast<const void*>(MobileGLCVDisplayLinkSetCurrentCGDisplayFromOpenGLContext),
-             reinterpret_cast<const void*>(CVDisplayLinkSetCurrentCGDisplayFromOpenGLContext)},
         };
-#pragma clang diagnostic pop
 } // namespace
 
 #endif

MobileGL/MG_Impl/DyldInterpose/ExportedSymbols.txt

@@ -1,10 +0,0 @@
-# Public CGL entry points.
-_CGL*
-
-# Public EGL entry points.
-_egl*
-
-# Public OpenGL and GLX entry points. OpenGL function names always use an
-# uppercase letter or digit after the "gl" prefix; excluding lowercase here
-# deliberately prevents glslang_* from matching this pattern.
-_gl[A-Z0-9]*

MobileGL/MG_Impl/GLImpl/Sync/GL_Sync.cpp

@@ -133,33 +133,4 @@ namespace MobileGL::MG_Impl::GLImpl {
             values[0] = value;
         }
     }
-
-    void DestroyAllSyncObjects() {
-        // Detach the registry under the lock, release outside it. Entries the app
-        // already deleted were erased by DeleteSync, so nothing here double-frees;
-        // a DeleteSync racing this sweep finds an empty registry and returns. A
-        // thread still blocked inside ClientWaitSync/GetSynciv during teardown
-        // holds a raw SyncObject* these deletes invalidate - the same undefined
-        // race an app-driven DeleteSync already has.
-        UnorderedMap<GLsync, SyncObject*> orphans;
-        {
-            const std::lock_guard<std::mutex> lock(g_syncObjectsMutex);
-            orphans.swap(g_liveSyncObjects);
-        }
-        if (orphans.empty()) {
-            return;
-        }
-        // Both backends' DeleteSync only free the heap wrapper once their GL
-        // context/renderer is gone (generation/current-thread guards), so this is
-        // safe after the backend has released its EGL resources - but not after
-        // the function table itself is cleared.
-        const auto backendDeleteSync = MG_Backend::gBackendFunctionsTable.GL.DeleteSync;
-        for (const auto& [_, syncObject] : orphans) {
-            if (backendDeleteSync && syncObject->backendHandle) {
-                backendDeleteSync(syncObject->backendHandle);
-            }
-            delete syncObject;
-        }
-        MGLOG_D("DestroyAllSyncObjects: reclaimed %zu sync object(s) the app left undeleted", orphans.size());
-    }
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GLImpl/Sync/GL_Sync.h

@@ -16,12 +16,4 @@ namespace MobileGL::MG_Impl::GLImpl {
     void WaitSync(GLsync sync, GLbitfield flags, GLuint64 timeout);
     void DeleteSync(GLsync sync);
     void GetSynciv(GLsync sync, GLenum pname, GLsizei bufSize, GLsizei* length, GLint* values);
-    // Destroys every still-registered sync object exactly as DeleteSync would.
-    // GL requires syncs to die with their context; called only from full library
-    // teardown (DestroyImpl), where no context survives on any thread, so the
-    // process-global registry can be drained wholesale. Must run while the
-    // backend function table is still populated: each backend handle has to be
-    // released by the backend that created it, never by a later re-initialized
-    // one.
-    void DestroyAllSyncObjects();
 } // namespace MobileGL::MG_Impl::GLImpl

MobileGL/MG_Impl/GetProcAddress.cpp

@@ -85,8 +85,6 @@ namespace MobileGL::MG_Impl {
         GETPROC(CGLGetPixelFormat, name);
         GETPROC(CGLSetCurrentContext, name);
         GETPROC(CGLGetCurrentContext, name);
-        GETPROC(CGLSetVirtualScreen, name);
-        GETPROC(CGLGetVirtualScreen, name);
         GETPROC(CGLSetParameter, name);
         GETPROC(CGLGetParameter, name);
         GETPROC(CGLUpdateContext, name);

MobileGL/MG_Impl/NSOpenGLImpl/NSOpenGLImpl.cpp

@@ -29,19 +29,10 @@ namespace MobileGL::MG_Impl::NSOpenGLImpl {
         char kContextViewKey;
         char kContextLayerKey;
 
+        std::once_flag g_installOnce;
         IMP g_pixelFormatDealloc = nullptr;
         IMP g_contextDealloc = nullptr;
 
-        std::mutex& HookInstallMutex() {
-            static auto* mutex = new std::mutex();
-            return *mutex;
-        }
-
-        Bool& HooksInstalled() {
-            static auto* installed = new Bool(false);
-            return *installed;
-        }
-
         template <typename Fn>
         Fn ObjcMsgSend() {
             return reinterpret_cast<Fn>(objc_msgSend);
@@ -440,12 +431,12 @@ namespace MobileGL::MG_Impl::NSOpenGLImpl {
             method_setImplementation(method, replacement);
         }
 
-        Bool InstallHooksOnce() {
+        void InstallHooksOnce() {
             Class pixelFormatClass = objc_getClass("NSOpenGLPixelFormat");
             Class contextClass = objc_getClass("NSOpenGLContext");
             if (!pixelFormatClass || !contextClass) {
                 MGLOG_W("NSOpenGLImpl: NSOpenGL classes are not loaded; hooks not installed");
-                return false;
+                return;
             }
 
             ReplaceInstanceMethod(pixelFormatClass, "initWithAttributes:",
@@ -480,34 +471,11 @@ namespace MobileGL::MG_Impl::NSOpenGLImpl {
             ReplaceInstanceMethod(contextClass, "dealloc", reinterpret_cast<IMP>(ContextDealloc), &g_contextDealloc);
 
             MGLOG_I("NSOpenGLImpl hooks installed");
-            return true;
         }
     } // namespace
 
     void InstallHooks() {
-        const std::lock_guard<std::mutex> lock(HookInstallMutex());
-        if (!HooksInstalled()) {
-            // Do not permanently consume the install attempt when the OpenGL
-            // framework has not registered its Objective-C classes yet. The
-            // dyld bootstrap normally runs after framework dependencies, but
-            // an explicitly loaded/static-linked MobileGL can arrive earlier.
-            HooksInstalled() = InstallHooksOnce();
-        }
+        std::call_once(g_installOnce, InstallHooksOnce);
     }
 } // namespace MobileGL::MG_Impl::NSOpenGLImpl
-
-namespace {
-    // SDL's Cocoa backend creates NSOpenGLPixelFormat/NSOpenGLContext before
-    // its first dlsym("glGetString") or other MobileGL host-API call. Install
-    // only the lightweight Objective-C dispatch hooks while the injected dylib
-    // is loading so those first Cocoa objects are routed through CGLImpl. The
-    // hooked context constructor reaches EGLImpl::GetDisplay(), which performs
-    // the full, thread-safe MobileGL initialization outside this bootstrap.
-    //
-    // There is intentionally no matching destructor: backend teardown remains
-    // owned by the EGL lifecycle and process-exit globals remain leak-at-exit.
-    __attribute__((constructor)) void BootstrapNSOpenGLHooks() {
-        MobileGL::MG_Impl::NSOpenGLImpl::InstallHooks();
-    }
-} // namespace
 #endif

MobileGL/MG_State/GLState/ProgramState/ProgramObject.h

@@ -334,32 +334,16 @@ namespace MobileGL::MG_State::GLState {
         // draw. The memo is keyed by (backendStateVersion, flags); ResetLinkArtifacts and
         // the binding setters below invalidate it by bumping m_backendStateVersion.
         Bool GetBackendHashMemo(Uint flags, Uint64& outHash) const {
-            if (m_backendHashMemoVersion != m_backendStateVersion) return false;
-            for (const auto& slot : m_backendHashMemoSlots) {
-                if (slot.valid && slot.flags == flags) {
-                    outHash = slot.hash;
-                    return true;
-                }
+            if (m_backendHashMemoVersion != m_backendStateVersion || m_backendHashMemoFlags != flags) {
+                return false;
             }
-            return false;
+            outHash = m_backendHashMemo;
+            return true;
         }
         void SetBackendHashMemo(Uint flags, Uint64 hash) const {
-            if (m_backendHashMemoVersion != m_backendStateVersion) {
-                for (auto& slot : m_backendHashMemoSlots) slot.valid = false;
-                m_backendHashMemoVersion = m_backendStateVersion;
-                m_backendHashMemoNextSlot = 0;
-            }
-            for (auto& slot : m_backendHashMemoSlots) {
-                if (slot.valid && slot.flags == flags) {
-                    slot.hash = hash;
-                    return;
-                }
-            }
-            auto& slot = m_backendHashMemoSlots[m_backendHashMemoNextSlot];
-            slot.flags = flags;
-            slot.hash = hash;
-            slot.valid = true;
-            m_backendHashMemoNextSlot = (m_backendHashMemoNextSlot + 1) % kBackendHashMemoSlotCount;
+            m_backendHashMemo = hash;
+            m_backendHashMemoVersion = m_backendStateVersion;
+            m_backendHashMemoFlags = flags;
         }
 
         void SetUniformSamplerOrImageUnitIndex(Uint location, Int unit) {
@@ -543,19 +527,10 @@ namespace MobileGL::MG_State::GLState {
         Uint32 m_backendStateVersion = 0;
 
         // Backend-owned content-hash memo (see GetBackendHashMemo): valid only while
-        // m_backendStateVersion matches. Several slots, not one: a backend may resolve the same
-        // program under more than one compile-flag set within a frame (surface rotation, and the
-        // explicit-LOD sampling variant), and a single slot would then miss on every lookup and
-        // re-hash the program's whole SPIR-V once per draw.
-        static constexpr SizeT kBackendHashMemoSlotCount = 4;
-        struct BackendHashMemoSlot {
-            Uint64 hash = 0;
-            Uint flags = 0;
-            Bool valid = false;
-        };
-        mutable Array<BackendHashMemoSlot, kBackendHashMemoSlotCount> m_backendHashMemoSlots{};
-        mutable SizeT m_backendHashMemoNextSlot = 0;
+        // m_backendStateVersion and the compile flags match the recorded values.
+        mutable Uint64 m_backendHashMemo = 0;
         mutable Uint32 m_backendHashMemoVersion = ~0u;
+        mutable Uint m_backendHashMemoFlags = 0;
         Uint32 m_uboContentVersion = 0;
         Uint32 m_linkVersion = 0;
     };

MobileGL/MG_State/GLState/TextureState/TextureObject.h

@@ -15,11 +15,7 @@
 #include <MG_Util/Math/VectorTypes.h>
 
 namespace MobileGL::MG_State::GLState {
-    // Texture objects are always SharedPtr-owned (TextureState creates every instance via
-    // MakeShared, including the per-target default objects). enable_shared_from_this lets
-    // backends that only receive a reference (e.g. syncing a name-deleted texture kept
-    // alive by an FBO attachment) still register a weak liveness reference for GC.
-    class ITextureObject : public std::enable_shared_from_this<ITextureObject> {
+    class ITextureObject {
     public:
         using TargetEnum = TextureTarget;
         virtual ~ITextureObject() = default;

MobileGL/MG_Test/SanityTest.cpp

@@ -33,7 +33,6 @@
 #include <MG_Util/ShaderTranspiler/ShaderCompiler.h>
 #include <MG_Util/ShaderTranspiler/ShaderSourceProcessor.h>
 #include <MG_Util/Debug/Log.h>
-#include <FastSTL/UnorderedMap.h>
 
 namespace {
     class DynamicParameterBackend final : public MobileGL::MG_Backend::BackendObject {
@@ -1737,61 +1736,3 @@ TEST(DirectGLESStateGuards, DefaultFramebufferBindGoesThroughShadow) {
     FramebufferImpl::BindFramebufferId(GL_DRAW_FRAMEBUFFER, 7); // must reach the driver again
     EXPECT_EQ(mocks.log.Count("BindFramebuffer:"), 3u);
 }
-
-// FastSTL::unordered_map::erase(iterator) regression coverage. The open-addressing
-// iterator constructor snaps forward from a tombstoned slot to the successor, so
-// erase must NOT advance the rebuilt iterator again: the old double-advance skipped
-// one live element per erase, and erasing the element in the highest occupied
-// bucket pushed the returned index past bucket_count where it never compared equal
-// to end() again - erase-while-iterating sweeps (pipeline/program cache eviction)
-// then ran off the bucket array and fed garbage handles to vkDestroyPipeline
-// (device crash on first mass eviction during world load).
-TEST(FastSTLSanity, EraseWhileIteratingVisitsEveryElementExactlyOnce) {
-    FastSTL::unordered_map<MobileGL::Uint64, MobileGL::Uint64> map;
-    constexpr MobileGL::Uint64 kCount = 1000;
-    for (MobileGL::Uint64 key = 0; key < kCount; ++key) {
-        map.emplace(key * 0x9e3779b97f4a7c15ull, key);
-    }
-    ASSERT_EQ(map.size(), kCount);
-
-    MobileGL::SizeT visited = 0;
-    for (auto it = map.begin(); it != map.end();) {
-        it = map.erase(it);
-        ++visited;
-        ASSERT_LE(visited, kCount); // old code: runaway past end / skipped entries
-    }
-    EXPECT_EQ(visited, kCount);
-    EXPECT_EQ(map.size(), 0u);
-}
-
-TEST(FastSTLSanity, EraseReturnsTheSuccessorElement) {
-    FastSTL::unordered_map<MobileGL::Uint32, MobileGL::Uint32> map;
-    for (MobileGL::Uint32 key = 1; key <= 64; ++key) {
-        map.emplace(key, key);
-    }
-
-    // Erasing every other visited element must still visit all 64 exactly once:
-    // the iterator returned by erase names the very next element, not one past it.
-    MobileGL::SizeT visited = 0;
-    MobileGL::SizeT erased = 0;
-    for (auto it = map.begin(); it != map.end();) {
-        ++visited;
-        if ((visited & 1) != 0) {
-            it = map.erase(it);
-            ++erased;
-        } else {
-            ++it;
-        }
-        ASSERT_LE(visited, 64u);
-    }
-    EXPECT_EQ(visited, 64u);
-    EXPECT_EQ(map.size(), 64u - erased);
-}
-
-TEST(FastSTLSanity, ErasingTheOnlyElementReturnsEnd) {
-    FastSTL::unordered_map<MobileGL::Uint32, MobileGL::Uint32> map;
-    map.emplace(42u, 1u);
-    auto next = map.erase(map.begin());
-    EXPECT_EQ(next, map.end());
-    EXPECT_TRUE(map.empty());
-}

MobileGL/MG_Util/Converters/MGToVk/TextureEnumConverter.cpp

@@ -133,11 +133,9 @@ namespace MobileGL {
             case TextureInternalFormat::RGBA8Snorm:
                 return VK_FORMAT_R8G8B8A8_SNORM;
             case TextureInternalFormat::RGB10A2:
-                // GL_UNSIGNED_INT_2_10_10_10_REV puts R in bits 0-9, which is Vulkan's
-                // A2B10G10R10 layout - A2R10G10B10 silently swaps R and B on upload.
-                return VK_FORMAT_A2B10G10R10_UNORM_PACK32;
+                return VK_FORMAT_A2R10G10B10_UNORM_PACK32;
             case TextureInternalFormat::RGB10A2UI:
-                return VK_FORMAT_A2B10G10R10_UINT_PACK32;
+                return VK_FORMAT_A2R10G10B10_UINT_PACK32;
             case TextureInternalFormat::RGBA16:
                 return VK_FORMAT_R16G16B16A16_UNORM;
             case TextureInternalFormat::RGBA16Snorm:

MobileGL/MG_Util/Debug/Log.h

@@ -9,10 +9,14 @@
 #pragma once
 #include <Includes.h>
 
+// Severity-ordered: a build compiled at level X keeps X and everything MORE
+// severe. INFO builds must keep WARN/ERROR/FATAL — the old ordering
+// (WARN=1/ERROR=2 below INFO=3) compiled every warning and error out of
+// release builds and hid real backend failures.
 #define MOBILEGL_LOG_LEVEL_DEBUG 0
-#define MOBILEGL_LOG_LEVEL_WARN 1
-#define MOBILEGL_LOG_LEVEL_ERROR 2
-#define MOBILEGL_LOG_LEVEL_INFO 3
+#define MOBILEGL_LOG_LEVEL_INFO 1
+#define MOBILEGL_LOG_LEVEL_WARN 2
+#define MOBILEGL_LOG_LEVEL_ERROR 3
 #define MOBILEGL_LOG_LEVEL_FATAL 4
 
 #define MOBILEGL_LOG_INTERNAL(levelTag, androidLogLevel, fmt, ...)                                                     \

MobileGL/MG_Util/ShaderTranspiler/ShaderCompiler.cpp

@@ -22,6 +22,9 @@
 #include "SpirvPasses/StripUboMemberRelaxedPrecisionPass.h"
 #include "SpirvPasses/StripNoPerspectivePass.h"
 #include "SpirvPasses/EmulateNoPerspectivePass.h"
+#include "SpirvPasses/FoldConstOffsetFor1DFetchPass.h"
+#include "SpirvPasses/LowerClipDistanceForEsslPass.h"
+#include "SpirvPasses/DefeatConstStructArrayLutPass.h"
 #include "spirv-tools/libspirv.h"
 #include "spirv-tools/optimizer.hpp"
 
@@ -323,6 +326,55 @@ namespace MobileGL {
                 return optimizer.Run(inputBinary.data(), inputBinary.size(), &outputBinary, options);
             }
 
+            bool ShaderCompiler::ClampAccessChainIndicesForEssl(const Vector<Uint32>& inputBinary,
+                                                                Vector<uint32_t>& outputBinary) {
+                using namespace spvtools;
+                OptimizerOptions options;
+                options.set_run_validator(false);
+
+                Optimizer optimizer(SPV_ENV_VULKAN_1_1);
+                optimizer.RegisterPass(CreateGraphicsRobustAccessPass());
+
+                return optimizer.Run(inputBinary.data(), inputBinary.size(), &outputBinary, options);
+            }
+
+            bool ShaderCompiler::FoldConstOffsetFor1DFetchForEssl(const Vector<Uint32>& inputBinary,
+                                                                  Vector<uint32_t>& outputBinary) {
+                using namespace spvtools;
+                OptimizerOptions options;
+                options.set_run_validator(false);
+
+                Optimizer optimizer(SPV_ENV_VULKAN_1_1);
+                optimizer.RegisterPass(FoldConstOffsetFor1DFetchPass::CreateFoldConstOffsetFor1DFetchPass());
+
+                return optimizer.Run(inputBinary.data(), inputBinary.size(), &outputBinary, options);
+            }
+
+            bool ShaderCompiler::LowerClipDistanceForEssl(const Vector<Uint32>& inputBinary,
+                                                          Vector<uint32_t>& outputBinary) {
+                using namespace spvtools;
+                OptimizerOptions options;
+                options.set_run_validator(false);
+
+                Optimizer optimizer(SPV_ENV_VULKAN_1_1);
+                optimizer.RegisterPass(LowerClipDistanceForEsslPass::CreateLowerClipDistanceForEsslPass());
+
+                return optimizer.Run(inputBinary.data(), inputBinary.size(), &outputBinary, options);
+            }
+
+            bool ShaderCompiler::DefeatConstStructArrayLutForEssl(const Vector<Uint32>& inputBinary,
+                                                                  Vector<uint32_t>& outputBinary) {
+                using namespace spvtools;
+                OptimizerOptions options;
+                options.set_run_validator(false);
+
+                Optimizer optimizer(SPV_ENV_VULKAN_1_1);
+                optimizer.RegisterPass(
+                    DefeatConstStructArrayLutPass::CreateDefeatConstStructArrayLutPass());
+
+                return optimizer.Run(inputBinary.data(), inputBinary.size(), &outputBinary, options);
+            }
+
             bool ShaderCompiler::StripUboMemberRelaxedPrecisionForEssl(const Vector<Uint32>& inputBinary,
                                                                        Vector<uint32_t>& outputBinary) {
                 using namespace spvtools;

MobileGL/MG_Util/ShaderTranspiler/ShaderCompiler.h

@@ -27,6 +27,36 @@ namespace MobileGL {
                 // Only for backends without native draw-parameter support (DirectGLES).
                 static bool LowerDrawParametersForEssl(const Vector<Uint32>& inputBinary,
                                                        Vector<uint32_t>& outputBinary);
+                // Clamps every access-chain index to its declared bounds (spirv-tools
+                // GraphicsRobustAccessPass). GL 3.3 only promises undefined *values* for
+                // out-of-bounds indexing, but Adreno's ESSL compiler constant-folds a provably
+                // out-of-bounds local-array index into poison that corrupts the whole shader's
+                // output; clamping restores the "some value from the array" contract. Only for
+                // the DirectGLES transpile path.
+                static bool ClampAccessChainIndicesForEssl(const Vector<Uint32>& inputBinary,
+                                                           Vector<uint32_t>& outputBinary);
+                // Folds the ConstOffset image operand of Dim1D OpImageFetch into the integer
+                // coordinate (texelFetchOffset(t,P,l,o) == texelFetch(t,P+o,l)). SPIRV-Cross
+                // emulates 1D samplers as 2D for ES: it widens the coordinate to ivec2 but keeps
+                // the scalar offset, and ESSL has no texelFetchOffset(sampler2D, ivec2, int,
+                // scalar) overload, so Adreno rejects the shader. Only for the DirectGLES
+                // transpile path.
+                static bool FoldConstOffsetFor1DFetchForEssl(const Vector<Uint32>& inputBinary,
+                                                             Vector<uint32_t>& outputBinary);
+                // Shadows gl_ClipDistance in Private mg_ClipDistance/mg_ClipDistanceIn arrays so
+                // the decompiled ESSL only writes the builtin with literal constant indices
+                // (flush before EmitVertex/return) and only reads gl_in clip distances with
+                // dynamic loop indices (copy loop): the other shapes miscompile or crash
+                // Adreno's ESSL compiler. Vertex/geometry stages; DirectGLES transpile path on
+                // Qualcomm only (quirk-gated). See LowerClipDistanceForEsslPass.
+                static bool LowerClipDistanceForEssl(const Vector<Uint32>& inputBinary,
+                                                     Vector<uint32_t>& outputBinary);
+                // Splits a Function-storage array-of-structs variable's single constant-composite
+                // store into per-element stores so SPIRV-Cross does not hoist it into a global
+                // const struct[] LUT, which Adreno cannot dynamically index. DirectGLES
+                // transpile path on Qualcomm only (quirk-gated). See DefeatConstStructArrayLutPass.
+                static bool DefeatConstStructArrayLutForEssl(const Vector<Uint32>& inputBinary,
+                                                             Vector<uint32_t>& outputBinary);
                 // Drops RelaxedPrecision member decorations from uniform-block structs so
                 // SPIRV-Cross prints the same (highp) member precision in every stage; ES
                 // drivers reject cross-stage uniform blocks whose member precisions differ.

MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DefeatConstStructArrayLutPass.cpp

@@ -0,0 +1,175 @@
+// MobileGL - MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DefeatConstStructArrayLutPass.cpp
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#include "DefeatConstStructArrayLutPass.h"
+
+#include "spirv.hpp"
+#include "source/opt/constants.h"
+#include "source/opt/def_use_manager.h"
+#include "source/opt/instruction.h"
+#include "source/opt/ir_context.h"
+#include "source/opt/module.h"
+#include "source/opt/type_manager.h"
+#include "source/opt/types.h"
+#include "source/util/make_unique.h"
+
+#include <vector>
+
+namespace MobileGL {
+    namespace MG_Util {
+        namespace ShaderTranspiler {
+            namespace {
+                using spvtools::opt::BasicBlock;
+                using spvtools::opt::Function;
+                using spvtools::opt::Instruction;
+                using spvtools::opt::IRContext;
+                using spvtools::opt::Operand;
+                namespace analysis = spvtools::opt::analysis;
+
+                uint32_t PointerTypeTo(IRContext* ctx, uint32_t pointeeId, spv::StorageClass sc) {
+                    analysis::Type* pointee = ctx->get_type_mgr()->GetType(pointeeId);
+                    analysis::Pointer ptr(pointee, sc);
+                    return ctx->get_type_mgr()->GetTypeInstruction(&ptr);
+                }
+
+                uint32_t SignedIntConstant(IRContext* ctx, uint32_t value) {
+                    analysis::Integer i(32, true);
+                    analysis::Type* reg = ctx->get_type_mgr()->GetRegisteredType(&i);
+                    const analysis::Constant* c = ctx->get_constant_mgr()->GetConstant(reg, {value});
+                    return ctx->get_constant_mgr()->GetDefiningInstruction(c)->result_id();
+                }
+
+                // True when |var| (a Function-storage OpVariable) points to an array of structs.
+                // Reports the struct type id on success.
+                bool IsArrayOfStructsVariable(IRContext* ctx, Instruction* var, uint32_t& structTypeId) {
+                    auto* defUse = ctx->get_def_use_mgr();
+                    Instruction* ptrType = defUse->GetDef(var->type_id());
+                    if (ptrType == nullptr || ptrType->opcode() != spv::Op::OpTypePointer) return false;
+                    Instruction* pointee = defUse->GetDef(ptrType->GetSingleWordInOperand(1));
+                    if (pointee == nullptr || pointee->opcode() != spv::Op::OpTypeArray) return false;
+                    Instruction* element = defUse->GetDef(pointee->GetSingleWordInOperand(0));
+                    if (element == nullptr || element->opcode() != spv::Op::OpTypeStruct) return false;
+                    structTypeId = element->result_id();
+                    return true;
+                }
+            } // namespace
+
+            spvtools::opt::Pass::Status DefeatConstStructArrayLutPass::Process() {
+                auto* ctx = context();
+                auto* defUse = ctx->get_def_use_mgr();
+                bool modified = false;
+
+                for (Function& function : *get_module()) {
+                    if (function.begin() == function.end()) continue;
+                    BasicBlock* entryBlock = &*function.begin();
+
+                    // Candidate variables: Function-storage arrays of structs declared in this
+                    // function's entry block (where OpVariables must live).
+                    struct Candidate {
+                        Instruction* var;
+                        uint32_t structTypeId;
+                    };
+                    std::vector<Candidate> candidates;
+                    for (Instruction& inst : *entryBlock) {
+                        if (inst.opcode() != spv::Op::OpVariable) break;
+                        // Variables with initializers keep SPIRV-Cross's initializer path; the
+                        // glslang pattern under attack is initializer-free with one OpStore.
+                        if (inst.NumInOperands() > 1) continue;
+                        uint32_t structTypeId = 0;
+                        if (IsArrayOfStructsVariable(ctx, &inst, structTypeId)) {
+                            candidates.push_back({&inst, structTypeId});
+                        }
+                    }
+
+                    for (const Candidate& candidate : candidates) {
+                        Instruction* var = candidate.var;
+
+                        // The variable qualifies only when its single write is one direct
+                        // OpStore of an OpConstantComposite; any other write shape already
+                        // defeats SPIRV-Cross's LUT promotion, so it is left untouched.
+                        Instruction* singleStore = nullptr;
+                        bool disqualified = false;
+                        defUse->ForEachUser(var, [&](Instruction* user) {
+                            if (user->opcode() == spv::Op::OpStore &&
+                                user->GetSingleWordInOperand(0) == var->result_id()) {
+                                if (singleStore != nullptr) {
+                                    disqualified = true;
+                                } else {
+                                    singleStore = user;
+                                }
+                            } else if (user->opcode() == spv::Op::OpCopyMemory) {
+                                disqualified = true;
+                            } else if (user->opcode() == spv::Op::OpAccessChain ||
+                                       user->opcode() == spv::Op::OpInBoundsAccessChain) {
+                                defUse->ForEachUser(user, [&](Instruction* chainUser) {
+                                    if (chainUser->opcode() == spv::Op::OpStore ||
+                                        chainUser->opcode() == spv::Op::OpCopyMemory) {
+                                        disqualified = true;
+                                    }
+                                });
+                            }
+                        });
+                        if (disqualified || singleStore == nullptr) continue;
+
+                        Instruction* composite = defUse->GetDef(singleStore->GetSingleWordInOperand(1));
+                        if (composite == nullptr ||
+                            composite->opcode() != spv::Op::OpConstantComposite) {
+                            continue;
+                        }
+
+                        // The store must sit in the entry block: that is the only placement
+                        // SPIRV-Cross treats as a LUT initializer.
+                        bool storeInEntryBlock = false;
+                        for (Instruction& inst : *entryBlock) {
+                            if (&inst == singleStore) {
+                                storeInEntryBlock = true;
+                                break;
+                            }
+                        }
+                        if (!storeInEntryBlock) continue;
+
+                        // Split the composite store into one constant-index store per element.
+                        const uint32_t ptrFnStruct =
+                            PointerTypeTo(ctx, candidate.structTypeId, spv::StorageClass::Function);
+                        for (uint32_t element = 0; element < composite->NumInOperands(); ++element) {
+                            const uint32_t elementConstId = composite->GetSingleWordInOperand(element);
+                            const uint32_t chainId = ctx->TakeNextId();
+                            Instruction* chain =
+                                singleStore->InsertBefore(spvtools::MakeUnique<Instruction>(
+                                    ctx, spv::Op::OpAccessChain, ptrFnStruct, chainId,
+                                    std::initializer_list<Operand>{
+                                        {SPV_OPERAND_TYPE_ID, {var->result_id()}},
+                                        {SPV_OPERAND_TYPE_ID, {SignedIntConstant(ctx, element)}}}));
+                            ctx->AnalyzeDefUse(chain);
+                            Instruction* store =
+                                singleStore->InsertBefore(spvtools::MakeUnique<Instruction>(
+                                    ctx, spv::Op::OpStore, 0, 0,
+                                    std::initializer_list<Operand>{
+                                        {SPV_OPERAND_TYPE_ID, {chainId}},
+                                        {SPV_OPERAND_TYPE_ID, {elementConstId}}}));
+                            ctx->AnalyzeDefUse(store);
+                        }
+                        ctx->KillInst(singleStore);
+                        modified = true;
+                    }
+                }
+
+                if (!modified) {
+                    return Status::SuccessWithoutChange;
+                }
+                ctx->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisNone);
+                return Status::SuccessWithChange;
+            }
+
+            spvtools::Optimizer::PassToken
+            DefeatConstStructArrayLutPass::CreateDefeatConstStructArrayLutPass() {
+                return spvtools::Optimizer::PassToken(MakeUnique<DefeatConstStructArrayLutPass>());
+            }
+        } // namespace ShaderTranspiler
+    } // namespace MG_Util
+} // namespace MobileGL

MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DefeatConstStructArrayLutPass.h

@@ -0,0 +1,36 @@
+// MobileGL - MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DefeatConstStructArrayLutPass.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include "source/opt/pass.h"
+#include "spirv-tools/optimizer.hpp"
+
+#include <Includes.h>
+
+namespace MobileGL {
+    namespace MG_Util {
+        namespace ShaderTranspiler {
+            // SPIRV-Cross hoists a Function-storage array variable whose only write is a single
+            // constant-composite store into a global `const struct[]` LUT (variable_is_lut).
+            // Adreno's ESSL compiler cannot dynamically index such a global const struct array
+            // ("Cannot offset into the structure" - device-verified on Adreno 750). Splitting
+            // the one composite store into per-element constant-index stores makes
+            // variable_is_lut fail, so SPIRV-Cross keeps the array as an ordinary local that
+            // Adreno indexes fine. Scalar/vector const arrays are unaffected on Adreno and are
+            // left alone - only arrays OF STRUCTS are rewritten. Only meant for the DirectGLES
+            // transpile path on Qualcomm devices.
+            class DefeatConstStructArrayLutPass : public spvtools::opt::Pass {
+            public:
+                const char* name() const override { return "defeat-const-struct-array-lut"; }
+                Status Process() override;
+
+                static spvtools::Optimizer::PassToken CreateDefeatConstStructArrayLutPass();
+            };
+        } // namespace ShaderTranspiler
+    } // namespace MG_Util
+} // namespace MobileGL

MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FoldConstOffsetFor1DFetchPass.cpp

@@ -0,0 +1,131 @@
+// MobileGL - MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FoldConstOffsetFor1DFetchPass.cpp
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#include "FoldConstOffsetFor1DFetchPass.h"
+
+#include "spirv.hpp"
+#include "source/opt/def_use_manager.h"
+#include "source/opt/instruction.h"
+#include "source/opt/ir_builder.h"
+#include "source/opt/ir_context.h"
+#include "source/opt/module.h"
+#include "source/util/make_unique.h"
+
+#include <vector>
+
+namespace MobileGL {
+    namespace MG_Util {
+        namespace ShaderTranspiler {
+            namespace {
+                using spvtools::opt::Instruction;
+                using spvtools::opt::InstructionBuilder;
+                using spvtools::opt::IRContext;
+                using spvtools::opt::Operand;
+
+                // Number of ImageOperands ids that precede the ConstOffset id: one per
+                // lower-order bit set in the mask, except Grad which carries two ids.
+                uint32_t CountIdsBeforeConstOffset(uint32_t mask) {
+                    uint32_t count = 0;
+                    if (mask & static_cast<uint32_t>(spv::ImageOperandsMask::Bias)) count += 1;
+                    if (mask & static_cast<uint32_t>(spv::ImageOperandsMask::Lod)) count += 1;
+                    if (mask & static_cast<uint32_t>(spv::ImageOperandsMask::Grad)) count += 2;
+                    return count;
+                }
+            } // namespace
+
+            spvtools::opt::Pass::Status FoldConstOffsetFor1DFetchPass::Process() {
+                auto* irContext = context();
+                auto* defUseMgr = irContext->get_def_use_mgr();
+                Bool modified = false;
+
+                constexpr uint32_t kConstOffsetBit =
+                    static_cast<uint32_t>(spv::ImageOperandsMask::ConstOffset);
+
+                for (auto& function : *get_module()) {
+                    for (auto& block : function) {
+                        for (auto& inst : block) {
+                            if (inst.opcode() != spv::Op::OpImageFetch) continue;
+                            // In-operands: image, coordinate, [ImageOperands mask, ids...].
+                            if (inst.NumInOperands() < 3) continue;
+                            const uint32_t operandsMask = inst.GetSingleWordInOperand(2);
+                            if ((operandsMask & kConstOffsetBit) == 0) continue;
+
+                            Instruction* imageInst = defUseMgr->GetDef(inst.GetSingleWordInOperand(0));
+                            if (imageInst == nullptr) continue;
+                            Instruction* imageType = defUseMgr->GetDef(imageInst->type_id());
+                            if (imageType == nullptr || imageType->opcode() != spv::Op::OpTypeImage ||
+                                static_cast<spv::Dim>(imageType->GetSingleWordInOperand(1)) != spv::Dim::Dim1D) {
+                                continue;
+                            }
+
+                            const uint32_t offsetOperandIndex = 3 + CountIdsBeforeConstOffset(operandsMask);
+                            const uint32_t offsetId = inst.GetSingleWordInOperand(offsetOperandIndex);
+
+                            const uint32_t coordId = inst.GetSingleWordInOperand(1);
+                            Instruction* coordType = defUseMgr->GetDef(defUseMgr->GetDef(coordId)->type_id());
+
+                            InstructionBuilder builder(
+                                irContext, &inst,
+                                IRContext::kAnalysisDefUse | IRContext::kAnalysisInstrToBlockMapping);
+
+                            uint32_t newCoordId = 0;
+                            if (coordType->opcode() == spv::Op::OpTypeVector) {
+                                // Arrayed 1D fetch: component 0 is the texel coordinate,
+                                // component 1 the layer - only component 0 takes the offset.
+                                const uint32_t componentTypeId = coordType->GetSingleWordInOperand(0);
+                                Instruction* extracted = builder.AddCompositeExtract(componentTypeId, coordId, {0});
+                                Instruction* sum =
+                                    builder.AddIAdd(componentTypeId, extracted->result_id(), offsetId);
+                                Instruction* inserted = builder.AddInstruction(spvtools::MakeUnique<Instruction>(
+                                    irContext, spv::Op::OpCompositeInsert, coordType->result_id(),
+                                    irContext->TakeNextId(),
+                                    std::initializer_list<Operand>{
+                                        {SPV_OPERAND_TYPE_ID, {sum->result_id()}},
+                                        {SPV_OPERAND_TYPE_ID, {coordId}},
+                                        {SPV_OPERAND_TYPE_LITERAL_INTEGER, {0}}}));
+                                newCoordId = inserted->result_id();
+                            } else {
+                                Instruction* sum = builder.AddIAdd(coordType->result_id(), coordId, offsetId);
+                                newCoordId = sum->result_id();
+                            }
+
+                            const uint32_t newMask = operandsMask & ~kConstOffsetBit;
+                            // 3 fixed operands + the offset id: anything beyond that is another
+                            // image-operand id that must keep the mask word alive.
+                            const Bool otherOperandIdsRemain = inst.NumInOperands() > 4;
+
+                            irContext->ForgetUses(&inst);
+                            std::vector<Operand> newOperands;
+                            newOperands.push_back(inst.GetInOperand(0));
+                            newOperands.push_back({SPV_OPERAND_TYPE_ID, {newCoordId}});
+                            if (newMask != 0 || otherOperandIdsRemain) {
+                                Operand maskOperand = inst.GetInOperand(2);
+                                maskOperand.words[0] = newMask;
+                                newOperands.push_back(maskOperand);
+                                for (uint32_t i = 3; i < inst.NumInOperands(); ++i) {
+                                    if (i == offsetOperandIndex) continue;
+                                    newOperands.push_back(inst.GetInOperand(i));
+                                }
+                            }
+                            inst.SetInOperands(std::move(newOperands));
+                            irContext->AnalyzeUses(&inst);
+
+                            modified = true;
+                        }
+                    }
+                }
+
+                return modified ? Status::SuccessWithChange : Status::SuccessWithoutChange;
+            }
+
+            spvtools::Optimizer::PassToken FoldConstOffsetFor1DFetchPass::CreateFoldConstOffsetFor1DFetchPass() {
+                return spvtools::Optimizer::PassToken(MakeUnique<FoldConstOffsetFor1DFetchPass>());
+            }
+        } // namespace ShaderTranspiler
+    } // namespace MG_Util
+} // namespace MobileGL

MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FoldConstOffsetFor1DFetchPass.h

@@ -0,0 +1,36 @@
+// MobileGL - MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FoldConstOffsetFor1DFetchPass.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include "source/opt/pass.h"
+#include "spirv-tools/optimizer.hpp"
+
+#include <Includes.h>
+
+namespace MobileGL {
+    namespace MG_Util {
+        namespace ShaderTranspiler {
+            // SPIRV-Cross emulates 1D textures as 2D for ES targets: it widens the texelFetch
+            // coordinate to ivec2 but keeps the ConstOffset image operand scalar, and ESSL has
+            // no texelFetchOffset(sampler2D, ivec2, int, scalar-offset) overload, so drivers
+            // (Adreno) reject the transpiled shader. This pass folds the constant offset into
+            // the integer coordinate before the fetch - texelFetchOffset(t, P, l, o) ==
+            // texelFetch(t, P + o, l) per the GLSL spec - and drops the ConstOffset operand,
+            // so SPIRV-Cross emits a plain texelFetch. For arrayed 1D fetches only coordinate
+            // component 0 is offset (component 1 is the layer). Only meant for the DirectGLES
+            // transpile path.
+            class FoldConstOffsetFor1DFetchPass : public spvtools::opt::Pass {
+            public:
+                const char* name() const override { return "fold-const-offset-for-1d-fetch"; }
+                Status Process() override;
+
+                static spvtools::Optimizer::PassToken CreateFoldConstOffsetFor1DFetchPass();
+            };
+        } // namespace ShaderTranspiler
+    } // namespace MG_Util
+} // namespace MobileGL

MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerClipDistanceForEsslPass.cpp

@@ -0,0 +1,613 @@
+// MobileGL - MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerClipDistanceForEsslPass.cpp
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#include "LowerClipDistanceForEsslPass.h"
+
+#include "spirv.hpp"
+#include "source/opt/basic_block.h"
+#include "source/opt/constants.h"
+#include "source/opt/def_use_manager.h"
+#include "source/opt/instruction.h"
+#include "source/opt/ir_context.h"
+#include "source/opt/module.h"
+#include "source/opt/type_manager.h"
+#include "source/opt/types.h"
+#include "source/util/make_unique.h"
+
+#include <memory>
+#include <vector>
+
+namespace MobileGL {
+    namespace MG_Util {
+        namespace ShaderTranspiler {
+            namespace {
+                using spvtools::opt::BasicBlock;
+                using spvtools::opt::Function;
+                using spvtools::opt::Instruction;
+                using spvtools::opt::IRContext;
+                using spvtools::opt::Operand;
+                namespace analysis = spvtools::opt::analysis;
+
+                spv::ExecutionModel EntryExecutionModel(IRContext* ctx) {
+                    for (Instruction& ep : ctx->module()->entry_points()) {
+                        return static_cast<spv::ExecutionModel>(ep.GetSingleWordInOperand(0));
+                    }
+                    return spv::ExecutionModel::Max;
+                }
+
+                uint32_t EntryFunctionId(IRContext* ctx) {
+                    for (Instruction& ep : ctx->module()->entry_points()) {
+                        // OpEntryPoint <model> <function> "name" <interface...>
+                        return ep.GetSingleWordInOperand(1);
+                    }
+                    return 0;
+                }
+
+                uint32_t VariablePointeeType(IRContext* ctx, Instruction* var) {
+                    Instruction* ptrType = ctx->get_def_use_mgr()->GetDef(var->type_id());
+                    // OpTypePointer <storage-class> <pointee>
+                    return ptrType->GetSingleWordInOperand(1);
+                }
+
+                uint32_t PointerTypeTo(IRContext* ctx, uint32_t pointeeId, spv::StorageClass sc) {
+                    analysis::Type* pointee = ctx->get_type_mgr()->GetType(pointeeId);
+                    analysis::Pointer ptr(pointee, sc);
+                    return ctx->get_type_mgr()->GetTypeInstruction(&ptr);
+                }
+
+                uint32_t IntConstant(IRContext* ctx, bool isSigned, uint32_t value) {
+                    analysis::Integer i(32, isSigned);
+                    analysis::Type* reg = ctx->get_type_mgr()->GetRegisteredType(&i);
+                    const analysis::Constant* c = ctx->get_constant_mgr()->GetConstant(reg, {value});
+                    return ctx->get_constant_mgr()->GetDefiningInstruction(c)->result_id();
+                }
+
+                uint32_t UintType(IRContext* ctx) {
+                    analysis::Integer i(32, false);
+                    return ctx->get_type_mgr()->GetTypeInstruction(&i);
+                }
+
+                uint32_t BoolType(IRContext* ctx) {
+                    analysis::Bool b;
+                    return ctx->get_type_mgr()->GetTypeInstruction(&b);
+                }
+
+                // Constant length of OpTypeArray |arrayTypeId| (0 when not a sized constant).
+                uint32_t ArrayLength(IRContext* ctx, uint32_t arrayTypeId) {
+                    Instruction* arrayType = ctx->get_def_use_mgr()->GetDef(arrayTypeId);
+                    if (arrayType == nullptr || arrayType->opcode() != spv::Op::OpTypeArray) {
+                        return 0;
+                    }
+                    Instruction* length = ctx->get_def_use_mgr()->GetDef(arrayType->GetSingleWordInOperand(1));
+                    if (length == nullptr || length->opcode() != spv::Op::OpConstant) {
+                        return 0;
+                    }
+                    return length->GetSingleWordInOperand(0);
+                }
+
+                bool IsConstantWithValue(IRContext* ctx, uint32_t id, uint32_t value) {
+                    Instruction* def = ctx->get_def_use_mgr()->GetDef(id);
+                    return def != nullptr && def->opcode() == spv::Op::OpConstant &&
+                           def->GetSingleWordInOperand(0) == value;
+                }
+
+                bool IsAccessChain(const Instruction* inst) {
+                    return inst->opcode() == spv::Op::OpAccessChain ||
+                           inst->opcode() == spv::Op::OpInBoundsAccessChain;
+                }
+
+                Instruction* AddPrivateVariable(IRContext* ctx, uint32_t pointeeTypeId, const char* name) {
+                    const uint32_t ptrType = PointerTypeTo(ctx, pointeeTypeId, spv::StorageClass::Private);
+                    const uint32_t varId = ctx->TakeNextId();
+                    ctx->AddGlobalValue(spvtools::MakeUnique<Instruction>(
+                        ctx, spv::Op::OpVariable, ptrType, varId,
+                        std::initializer_list<Operand>{
+                            {SPV_OPERAND_TYPE_STORAGE_CLASS,
+                             {static_cast<uint32_t>(spv::StorageClass::Private)}}}));
+                    ctx->AddDebug2Inst(spvtools::MakeUnique<Instruction>(
+                        ctx, spv::Op::OpName, 0, 0,
+                        std::initializer_list<Operand>{
+                            {SPV_OPERAND_TYPE_ID, {varId}},
+                            {SPV_OPERAND_TYPE_LITERAL_STRING, spvtools::utils::MakeVector(name)}}));
+                    return ctx->get_def_use_mgr()->GetDef(varId);
+                }
+
+                // Retargets |chain| onto |newBaseId|, dropping the first |dropIndexCount| index
+                // operands and switching the result pointer's storage class to Private.
+                void RetargetChainToPrivate(IRContext* ctx, Instruction* chain, uint32_t newBaseId,
+                                            uint32_t dropIndexCount) {
+                    Instruction* chainPtrType = ctx->get_def_use_mgr()->GetDef(chain->type_id());
+                    const uint32_t pointeeId = chainPtrType->GetSingleWordInOperand(1);
+                    const uint32_t newPtrType = PointerTypeTo(ctx, pointeeId, spv::StorageClass::Private);
+
+                    ctx->ForgetUses(chain);
+                    std::vector<Operand> newOperands;
+                    newOperands.push_back({SPV_OPERAND_TYPE_ID, {newBaseId}});
+                    for (uint32_t i = 1 + dropIndexCount; i < chain->NumInOperands(); ++i) {
+                        newOperands.push_back(chain->GetInOperand(i));
+                    }
+                    chain->SetResultType(newPtrType);
+                    chain->SetInOperands(std::move(newOperands));
+                    ctx->AnalyzeUses(chain);
+                }
+
+                // ---- Output side --------------------------------------------------------------
+
+                struct OutputTarget {
+                    Instruction* var = nullptr;   // Output gl_PerVertex block or standalone builtin
+                    bool isBlockMember = false;
+                    uint32_t memberIndex = 0;     // valid when isBlockMember
+                    uint32_t arrayTypeId = 0;     // float[N]
+                    uint32_t elemTypeId = 0;      // float
+                    uint32_t arrayLen = 0;        // N
+                };
+
+                // Inserts "gl_ClipDistance[k] = mg_ClipDistance[k]" for every literal k before
+                // |before|. Constant-index writes are the only write shape Adreno links correctly.
+                void InsertFlushBefore(IRContext* ctx, Instruction* before, const OutputTarget& target,
+                                       uint32_t mgVarId) {
+                    const uint32_t ptrPrivElem =
+                        PointerTypeTo(ctx, target.elemTypeId, spv::StorageClass::Private);
+                    const uint32_t ptrOutElem =
+                        PointerTypeTo(ctx, target.elemTypeId, spv::StorageClass::Output);
+                    for (uint32_t k = 0; k < target.arrayLen; ++k) {
+                        const uint32_t kConst = IntConstant(ctx, true, k);
+                        const uint32_t srcChainId = ctx->TakeNextId();
+                        before->InsertBefore(spvtools::MakeUnique<Instruction>(
+                            ctx, spv::Op::OpAccessChain, ptrPrivElem, srcChainId,
+                            std::initializer_list<Operand>{{SPV_OPERAND_TYPE_ID, {mgVarId}},
+                                                           {SPV_OPERAND_TYPE_ID, {kConst}}}));
+                        const uint32_t valId = ctx->TakeNextId();
+                        before->InsertBefore(spvtools::MakeUnique<Instruction>(
+                            ctx, spv::Op::OpLoad, target.elemTypeId, valId,
+                            std::initializer_list<Operand>{{SPV_OPERAND_TYPE_ID, {srcChainId}}}));
+                        const uint32_t dstChainId = ctx->TakeNextId();
+                        std::vector<Operand> dstOperands;
+                        dstOperands.push_back({SPV_OPERAND_TYPE_ID, {target.var->result_id()}});
+                        if (target.isBlockMember) {
+                            dstOperands.push_back(
+                                {SPV_OPERAND_TYPE_ID, {IntConstant(ctx, true, target.memberIndex)}});
+                        }
+                        dstOperands.push_back({SPV_OPERAND_TYPE_ID, {kConst}});
+                        before->InsertBefore(spvtools::MakeUnique<Instruction>(
+                            ctx, spv::Op::OpAccessChain, ptrOutElem, dstChainId, dstOperands));
+                        before->InsertBefore(spvtools::MakeUnique<Instruction>(
+                            ctx, spv::Op::OpStore, 0, 0,
+                            std::initializer_list<Operand>{{SPV_OPERAND_TYPE_ID, {dstChainId}},
+                                                           {SPV_OPERAND_TYPE_ID, {valId}}}));
+                    }
+                }
+
+                bool LowerOutputClipDistance(IRContext* ctx, bool isGeometry) {
+                    auto* defUse = ctx->get_def_use_mgr();
+
+                    // Collect (struct type, member) pairs decorated BuiltIn ClipDistance and
+                    // standalone variables decorated BuiltIn ClipDistance.
+                    std::vector<std::pair<uint32_t, uint32_t>> memberTargets; // (structId, member)
+                    std::vector<uint32_t> plainTargets;                       // variable ids
+                    for (Instruction& ann : ctx->annotations()) {
+                        if (ann.opcode() == spv::Op::OpMemberDecorate && ann.NumInOperands() >= 4 &&
+                            static_cast<spv::Decoration>(ann.GetSingleWordInOperand(2)) ==
+                                spv::Decoration::BuiltIn &&
+                            static_cast<spv::BuiltIn>(ann.GetSingleWordInOperand(3)) ==
+                                spv::BuiltIn::ClipDistance) {
+                            memberTargets.emplace_back(ann.GetSingleWordInOperand(0),
+                                                       ann.GetSingleWordInOperand(1));
+                        } else if (ann.opcode() == spv::Op::OpDecorate && ann.NumInOperands() >= 3 &&
+                                   static_cast<spv::Decoration>(ann.GetSingleWordInOperand(1)) ==
+                                       spv::Decoration::BuiltIn &&
+                                   static_cast<spv::BuiltIn>(ann.GetSingleWordInOperand(2)) ==
+                                       spv::BuiltIn::ClipDistance) {
+                            plainTargets.push_back(ann.GetSingleWordInOperand(0));
+                        }
+                    }
+
+                    std::vector<OutputTarget> targets;
+                    for (Instruction& inst : ctx->module()->types_values()) {
+                        if (inst.opcode() != spv::Op::OpVariable ||
+                            static_cast<spv::StorageClass>(inst.GetSingleWordInOperand(0)) !=
+                                spv::StorageClass::Output) {
+                            continue;
+                        }
+                        const uint32_t pointee = VariablePointeeType(ctx, &inst);
+                        for (const auto& [structId, member] : memberTargets) {
+                            if (pointee != structId) continue;
+                            Instruction* structType = defUse->GetDef(structId);
+                            if (structType == nullptr || member >= structType->NumInOperands()) continue;
+                            OutputTarget target;
+                            target.var = &inst;
+                            target.isBlockMember = true;
+                            target.memberIndex = member;
+                            target.arrayTypeId = structType->GetSingleWordInOperand(member);
+                            target.arrayLen = ArrayLength(ctx, target.arrayTypeId);
+                            targets.push_back(target);
+                        }
+                        for (const uint32_t varId : plainTargets) {
+                            if (inst.result_id() != varId) continue;
+                            OutputTarget target;
+                            target.var = &inst;
+                            target.isBlockMember = false;
+                            target.arrayTypeId = pointee;
+                            target.arrayLen = ArrayLength(ctx, target.arrayTypeId);
+                            targets.push_back(target);
+                        }
+                    }
+
+                    bool changed = false;
+                    for (OutputTarget& target : targets) {
+                        if (target.arrayLen == 0) continue;
+                        Instruction* arrayType = defUse->GetDef(target.arrayTypeId);
+                        target.elemTypeId = arrayType->GetSingleWordInOperand(0);
+
+                        // Collect the accesses to redirect. For the block form only chains whose
+                        // leading index selects the ClipDistance member count; for the standalone
+                        // form every chain plus whole-variable loads/stores.
+                        std::vector<Instruction*> chains;
+                        std::vector<Instruction*> directAccesses;
+                        bool unsupportedUse = false;
+                        defUse->ForEachUser(target.var, [&](Instruction* user) {
+                            if (IsAccessChain(user) &&
+                                user->GetSingleWordInOperand(0) == target.var->result_id()) {
+                                if (target.isBlockMember) {
+                                    if (user->NumInOperands() >= 2 &&
+                                        IsConstantWithValue(ctx, user->GetSingleWordInOperand(1),
+                                                            target.memberIndex)) {
+                                        chains.push_back(user);
+                                    }
+                                } else {
+                                    chains.push_back(user);
+                                }
+                            } else if (!target.isBlockMember) {
+                                if (user->opcode() == spv::Op::OpLoad ||
+                                    (user->opcode() == spv::Op::OpStore &&
+                                     user->GetSingleWordInOperand(0) == target.var->result_id())) {
+                                    directAccesses.push_back(user);
+                                } else if (user->opcode() == spv::Op::OpCopyMemory) {
+                                    unsupportedUse = true;
+                                }
+                            }
+                        });
+                        if (unsupportedUse || (chains.empty() && directAccesses.empty())) {
+                            continue;
+                        }
+
+                        Instruction* mgVar = AddPrivateVariable(ctx, target.arrayTypeId, "mg_ClipDistance");
+                        const uint32_t mgVarId = mgVar->result_id();
+
+                        for (Instruction* chain : chains) {
+                            const uint32_t dropCount = target.isBlockMember ? 1u : 0u;
+                            if (chain->NumInOperands() == 1 + dropCount) {
+                                // Pointer to the whole float[N]: reuse the private variable itself.
+                                ctx->ReplaceAllUsesWith(chain->result_id(), mgVarId);
+                                ctx->KillInst(chain);
+                            } else {
+                                RetargetChainToPrivate(ctx, chain, mgVarId, dropCount);
+                            }
+                        }
+                        for (Instruction* access : directAccesses) {
+                            ctx->ForgetUses(access);
+                            access->SetInOperand(0, {mgVarId});
+                            ctx->AnalyzeUses(access);
+                        }
+
+                        // Flush the shadow into the real builtin: geometry right before every
+                        // EmitVertex, vertex before every return of the entry point. The flush is
+                        // also what keeps the builtin statically used for cross-stage IO matching.
+                        std::vector<Instruction*> flushSites;
+                        if (isGeometry) {
+                            for (Function& function : *ctx->module()) {
+                                function.ForEachInst([&](Instruction* inst) {
+                                    if (inst->opcode() == spv::Op::OpEmitVertex) {
+                                        flushSites.push_back(inst);
+                                    }
+                                });
+                            }
+                        } else {
+                            const uint32_t entryFuncId = EntryFunctionId(ctx);
+                            for (Function& function : *ctx->module()) {
+                                if (function.result_id() != entryFuncId) continue;
+                                function.ForEachInst([&](Instruction* inst) {
+                                    if (inst->opcode() == spv::Op::OpReturn ||
+                                        inst->opcode() == spv::Op::OpReturnValue) {
+                                        flushSites.push_back(inst);
+                                    }
+                                });
+                            }
+                        }
+                        for (Instruction* site : flushSites) {
+                            InsertFlushBefore(ctx, site, target, mgVarId);
+                        }
+
+                        changed = true;
+                    }
+                    return changed;
+                }
+
+                // ---- Input side (geometry gl_in) ----------------------------------------------
+
+                bool LowerInputClipDistance(IRContext* ctx) {
+                    auto* defUse = ctx->get_def_use_mgr();
+                    auto* typeMgr = ctx->get_type_mgr();
+
+                    // Locate the gl_in block member decorated ClipDistance.
+                    Instruction* glInVar = nullptr;
+                    uint32_t memberIndex = 0;
+                    uint32_t arrayTypeId = 0; // float[N]
+                    for (Instruction& ann : ctx->annotations()) {
+                        if (ann.opcode() != spv::Op::OpMemberDecorate || ann.NumInOperands() < 4 ||
+                            static_cast<spv::Decoration>(ann.GetSingleWordInOperand(2)) !=
+                                spv::Decoration::BuiltIn ||
+                            static_cast<spv::BuiltIn>(ann.GetSingleWordInOperand(3)) !=
+                                spv::BuiltIn::ClipDistance) {
+                            continue;
+                        }
+                        const uint32_t structId = ann.GetSingleWordInOperand(0);
+                        const uint32_t member = ann.GetSingleWordInOperand(1);
+                        for (Instruction& inst : ctx->module()->types_values()) {
+                            if (inst.opcode() != spv::Op::OpVariable ||
+                                static_cast<spv::StorageClass>(inst.GetSingleWordInOperand(0)) !=
+                                    spv::StorageClass::Input) {
+                                continue;
+                            }
+                            const uint32_t pointee = VariablePointeeType(ctx, &inst);
+                            Instruction* pointeeType = defUse->GetDef(pointee);
+                            if (pointeeType == nullptr || pointeeType->opcode() != spv::Op::OpTypeArray ||
+                                pointeeType->GetSingleWordInOperand(0) != structId) {
+                                continue;
+                            }
+                            Instruction* structType = defUse->GetDef(structId);
+                            if (structType == nullptr || member >= structType->NumInOperands()) continue;
+                            glInVar = &inst;
+                            memberIndex = member;
+                            arrayTypeId = structType->GetSingleWordInOperand(member);
+                            break;
+                        }
+                        if (glInVar != nullptr) break;
+                    }
+                    if (glInVar == nullptr) {
+                        return false;
+                    }
+
+                    const uint32_t clipCount = ArrayLength(ctx, arrayTypeId);
+                    const uint32_t vertexCount = ArrayLength(ctx, VariablePointeeType(ctx, glInVar));
+                    if (clipCount == 0 || vertexCount == 0) {
+                        return false;
+                    }
+
+                    // Every gl_in chain that selects the ClipDistance member:
+                    // (vertex, member) yields a whole float[N], (vertex, member, k) an element.
+                    std::vector<Instruction*> chains;
+                    defUse->ForEachUser(glInVar, [&](Instruction* user) {
+                        if (IsAccessChain(user) && user->GetSingleWordInOperand(0) == glInVar->result_id() &&
+                            user->NumInOperands() >= 3 &&
+                            IsConstantWithValue(ctx, user->GetSingleWordInOperand(2), memberIndex)) {
+                            chains.push_back(user);
+                        }
+                    });
+                    if (chains.empty()) {
+                        return false;
+                    }
+
+                    Instruction* arrayTypeInst = defUse->GetDef(arrayTypeId);
+                    const uint32_t elemTypeId = arrayTypeInst->GetSingleWordInOperand(0);
+
+                    // Private mg_ClipDistanceIn = float[vertexCount][clipCount].
+                    const uint32_t vertexCountConst = IntConstant(ctx, false, vertexCount);
+                    analysis::Type* innerType = typeMgr->GetType(arrayTypeId);
+                    analysis::Array outerArray(
+                        innerType, analysis::Array::LengthInfo{
+                                       vertexCountConst,
+                                       {analysis::Array::LengthInfo::kConstant, vertexCount}});
+                    const uint32_t outerArrayTypeId = typeMgr->GetTypeInstruction(&outerArray);
+                    Instruction* mgInVar = AddPrivateVariable(ctx, outerArrayTypeId, "mg_ClipDistanceIn");
+                    const uint32_t mgInVarId = mgInVar->result_id();
+
+                    // Copy loop at the top of the entry point:
+                    //   for (uint t = 0; t < vertexCount * clipCount; ++t)
+                    //       mg_ClipDistanceIn[t / clipCount][t % clipCount] =
+                    //           gl_in[t / clipCount].gl_ClipDistance[t % clipCount];
+                    // Both gl_in indices are loop-derived (dynamic): constant-index element reads
+                    // miscompile and whole-array reads crash the Adreno compiler.
+                    const uint32_t entryFuncId = EntryFunctionId(ctx);
+                    Function* entryFn = nullptr;
+                    for (Function& function : *ctx->module()) {
+                        if (function.result_id() == entryFuncId) {
+                            entryFn = &function;
+                            break;
+                        }
+                    }
+                    if (entryFn == nullptr || entryFn->begin() == entryFn->end()) {
+                        return false;
+                    }
+
+                    const uint32_t uintTypeId = UintType(ctx);
+                    const uint32_t boolTypeId = BoolType(ctx);
+                    const uint32_t ptrFnUint = PointerTypeTo(ctx, uintTypeId, spv::StorageClass::Function);
+                    const uint32_t ptrInElem = PointerTypeTo(ctx, elemTypeId, spv::StorageClass::Input);
+                    const uint32_t ptrPrivElem = PointerTypeTo(ctx, elemTypeId, spv::StorageClass::Private);
+                    const uint32_t uint0 = IntConstant(ctx, false, 0);
+                    const uint32_t uint1 = IntConstant(ctx, false, 1);
+                    const uint32_t uintN = IntConstant(ctx, false, clipCount);
+                    const uint32_t uintTotal = IntConstant(ctx, false, vertexCount * clipCount);
+                    const uint32_t memberConst = IntConstant(ctx, true, memberIndex);
+
+                    BasicBlock* entryBlock = &*entryFn->begin();
+                    auto splitPoint = entryBlock->begin();
+                    while (splitPoint != entryBlock->end() &&
+                           splitPoint->opcode() == spv::Op::OpVariable) {
+                        ++splitPoint;
+                    }
+
+                    // Loop counter lives with the other function-local variables.
+                    const uint32_t counterVarId = ctx->TakeNextId();
+                    splitPoint->InsertBefore(spvtools::MakeUnique<Instruction>(
+                        ctx, spv::Op::OpVariable, ptrFnUint, counterVarId,
+                        std::initializer_list<Operand>{
+                            {SPV_OPERAND_TYPE_STORAGE_CLASS,
+                             {static_cast<uint32_t>(spv::StorageClass::Function)}}}));
+
+                    const uint32_t restLabelId = ctx->TakeNextId();
+                    BasicBlock* restBlock = entryBlock->SplitBasicBlock(ctx, restLabelId, splitPoint);
+
+                    const uint32_t headerLabelId = ctx->TakeNextId();
+                    const uint32_t checkLabelId = ctx->TakeNextId();
+                    const uint32_t bodyLabelId = ctx->TakeNextId();
+                    const uint32_t continueLabelId = ctx->TakeNextId();
+
+                    auto makeBlock = [&](uint32_t labelId) {
+                        return spvtools::MakeUnique<BasicBlock>(spvtools::MakeUnique<Instruction>(
+                            ctx, spv::Op::OpLabel, 0, labelId, std::initializer_list<Operand>{}));
+                    };
+                    auto addInst = [&](BasicBlock* block, spv::Op opcode, uint32_t typeId,
+                                       uint32_t resultId, std::vector<Operand> operands) {
+                        block->AddInstruction(spvtools::MakeUnique<Instruction>(
+                            ctx, opcode, typeId, resultId, std::move(operands)));
+                    };
+
+                    // entry: t = 0; branch header
+                    addInst(entryBlock, spv::Op::OpStore, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {counterVarId}}, {SPV_OPERAND_TYPE_ID, {uint0}}});
+                    addInst(entryBlock, spv::Op::OpBranch, 0, 0, {{SPV_OPERAND_TYPE_ID, {headerLabelId}}});
+
+                    // header: structured loop header
+                    auto headerBlock = makeBlock(headerLabelId);
+                    addInst(headerBlock.get(), spv::Op::OpLoopMerge, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {restLabelId}},
+                             {SPV_OPERAND_TYPE_ID, {continueLabelId}},
+                             {SPV_OPERAND_TYPE_LOOP_CONTROL,
+                              {static_cast<uint32_t>(spv::LoopControlMask::MaskNone)}}});
+                    addInst(headerBlock.get(), spv::Op::OpBranch, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {checkLabelId}}});
+
+                    // check: t < vertexCount * clipCount ?
+                    auto checkBlock = makeBlock(checkLabelId);
+                    const uint32_t tCheckId = ctx->TakeNextId();
+                    addInst(checkBlock.get(), spv::Op::OpLoad, uintTypeId, tCheckId,
+                            {{SPV_OPERAND_TYPE_ID, {counterVarId}}});
+                    const uint32_t condId = ctx->TakeNextId();
+                    addInst(checkBlock.get(), spv::Op::OpULessThan, boolTypeId, condId,
+                            {{SPV_OPERAND_TYPE_ID, {tCheckId}}, {SPV_OPERAND_TYPE_ID, {uintTotal}}});
+                    addInst(checkBlock.get(), spv::Op::OpBranchConditional, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {condId}},
+                             {SPV_OPERAND_TYPE_ID, {bodyLabelId}},
+                             {SPV_OPERAND_TYPE_ID, {restLabelId}}});
+
+                    // body: mg_ClipDistanceIn[t / N][t % N] = gl_in[t / N].gl_ClipDistance[t % N]
+                    auto bodyBlock = makeBlock(bodyLabelId);
+                    const uint32_t tBodyId = ctx->TakeNextId();
+                    addInst(bodyBlock.get(), spv::Op::OpLoad, uintTypeId, tBodyId,
+                            {{SPV_OPERAND_TYPE_ID, {counterVarId}}});
+                    const uint32_t vertexIdxId = ctx->TakeNextId();
+                    addInst(bodyBlock.get(), spv::Op::OpUDiv, uintTypeId, vertexIdxId,
+                            {{SPV_OPERAND_TYPE_ID, {tBodyId}}, {SPV_OPERAND_TYPE_ID, {uintN}}});
+                    const uint32_t clipIdxId = ctx->TakeNextId();
+                    addInst(bodyBlock.get(), spv::Op::OpUMod, uintTypeId, clipIdxId,
+                            {{SPV_OPERAND_TYPE_ID, {tBodyId}}, {SPV_OPERAND_TYPE_ID, {uintN}}});
+                    const uint32_t srcChainId = ctx->TakeNextId();
+                    addInst(bodyBlock.get(), spv::Op::OpAccessChain, ptrInElem, srcChainId,
+                            {{SPV_OPERAND_TYPE_ID, {glInVar->result_id()}},
+                             {SPV_OPERAND_TYPE_ID, {vertexIdxId}},
+                             {SPV_OPERAND_TYPE_ID, {memberConst}},
+                             {SPV_OPERAND_TYPE_ID, {clipIdxId}}});
+                    const uint32_t valId = ctx->TakeNextId();
+                    addInst(bodyBlock.get(), spv::Op::OpLoad, elemTypeId, valId,
+                            {{SPV_OPERAND_TYPE_ID, {srcChainId}}});
+                    const uint32_t dstChainId = ctx->TakeNextId();
+                    addInst(bodyBlock.get(), spv::Op::OpAccessChain, ptrPrivElem, dstChainId,
+                            {{SPV_OPERAND_TYPE_ID, {mgInVarId}},
+                             {SPV_OPERAND_TYPE_ID, {vertexIdxId}},
+                             {SPV_OPERAND_TYPE_ID, {clipIdxId}}});
+                    addInst(bodyBlock.get(), spv::Op::OpStore, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {dstChainId}}, {SPV_OPERAND_TYPE_ID, {valId}}});
+                    addInst(bodyBlock.get(), spv::Op::OpBranch, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {continueLabelId}}});
+
+                    // continue: ++t
+                    auto continueBlock = makeBlock(continueLabelId);
+                    const uint32_t tContinueId = ctx->TakeNextId();
+                    addInst(continueBlock.get(), spv::Op::OpLoad, uintTypeId, tContinueId,
+                            {{SPV_OPERAND_TYPE_ID, {counterVarId}}});
+                    const uint32_t tIncId = ctx->TakeNextId();
+                    addInst(continueBlock.get(), spv::Op::OpIAdd, uintTypeId, tIncId,
+                            {{SPV_OPERAND_TYPE_ID, {tContinueId}}, {SPV_OPERAND_TYPE_ID, {uint1}}});
+                    addInst(continueBlock.get(), spv::Op::OpStore, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {counterVarId}}, {SPV_OPERAND_TYPE_ID, {tIncId}}});
+                    addInst(continueBlock.get(), spv::Op::OpBranch, 0, 0,
+                            {{SPV_OPERAND_TYPE_ID, {headerLabelId}}});
+
+                    BasicBlock* headerPtr = entryFn->InsertBasicBlockBefore(std::move(headerBlock), restBlock);
+                    BasicBlock* checkPtr = entryFn->InsertBasicBlockAfter(std::move(checkBlock), headerPtr);
+                    BasicBlock* bodyPtr = entryFn->InsertBasicBlockAfter(std::move(bodyBlock), checkPtr);
+                    entryFn->InsertBasicBlockAfter(std::move(continueBlock), bodyPtr);
+
+                    // Redirect the pre-existing accesses to the shadow copy.
+                    for (Instruction* chain : chains) {
+                        if (chain->NumInOperands() == 3) {
+                            // (vertex, member): whole float[N] of one vertex.
+                            Instruction* chainPtrType = defUse->GetDef(chain->type_id());
+                            const uint32_t pointeeId = chainPtrType->GetSingleWordInOperand(1);
+                            const uint32_t newPtrType =
+                                PointerTypeTo(ctx, pointeeId, spv::StorageClass::Private);
+                            ctx->ForgetUses(chain);
+                            std::vector<Operand> newOperands;
+                            newOperands.push_back({SPV_OPERAND_TYPE_ID, {mgInVarId}});
+                            newOperands.push_back(chain->GetInOperand(1));
+                            chain->SetResultType(newPtrType);
+                            chain->SetInOperands(std::move(newOperands));
+                            ctx->AnalyzeUses(chain);
+                        } else {
+                            // (vertex, member, k, ...): drop the member index.
+                            Instruction* chainPtrType = defUse->GetDef(chain->type_id());
+                            const uint32_t pointeeId = chainPtrType->GetSingleWordInOperand(1);
+                            const uint32_t newPtrType =
+                                PointerTypeTo(ctx, pointeeId, spv::StorageClass::Private);
+                            ctx->ForgetUses(chain);
+                            std::vector<Operand> newOperands;
+                            newOperands.push_back({SPV_OPERAND_TYPE_ID, {mgInVarId}});
+                            newOperands.push_back(chain->GetInOperand(1));
+                            for (uint32_t i = 3; i < chain->NumInOperands(); ++i) {
+                                newOperands.push_back(chain->GetInOperand(i));
+                            }
+                            chain->SetResultType(newPtrType);
+                            chain->SetInOperands(std::move(newOperands));
+                            ctx->AnalyzeUses(chain);
+                        }
+                    }
+
+                    return true;
+                }
+            } // namespace
+
+            spvtools::opt::Pass::Status LowerClipDistanceForEsslPass::Process() {
+                auto* ctx = context();
+                const spv::ExecutionModel model = EntryExecutionModel(ctx);
+                const bool isVertex = model == spv::ExecutionModel::Vertex;
+                const bool isGeometry = model == spv::ExecutionModel::Geometry;
+                if (!isVertex && !isGeometry) {
+                    return Status::SuccessWithoutChange;
+                }
+
+                bool changed = LowerOutputClipDistance(ctx, isGeometry);
+                if (isGeometry) {
+                    changed |= LowerInputClipDistance(ctx);
+                }
+
+                if (!changed) {
+                    return Status::SuccessWithoutChange;
+                }
+                ctx->InvalidateAnalysesExceptFor(spvtools::opt::IRContext::kAnalysisNone);
+                return Status::SuccessWithChange;
+            }
+
+            spvtools::Optimizer::PassToken
+            LowerClipDistanceForEsslPass::CreateLowerClipDistanceForEsslPass() {
+                return spvtools::Optimizer::PassToken(MakeUnique<LowerClipDistanceForEsslPass>());
+            }
+        } // namespace ShaderTranspiler
+    } // namespace MG_Util
+} // namespace MobileGL

MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerClipDistanceForEsslPass.h

@@ -0,0 +1,44 @@
+// MobileGL - MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerClipDistanceForEsslPass.h
+// Copyright (c) 2025-2026 MobileGL-Dev
+// Licensed under the GNU Lesser General Public License v3.0:
+//   https://www.gnu.org/licenses/gpl-3.0.txt
+//   https://www.gnu.org/licenses/lgpl-3.0.txt
+// SPDX-License-Identifier: LGPL-3.0-only
+// End of Source File Header
+
+#pragma once
+#include "source/opt/pass.h"
+#include "spirv-tools/optimizer.hpp"
+
+#include <Includes.h>
+
+namespace MobileGL {
+    namespace MG_Util {
+        namespace ShaderTranspiler {
+            // Adreno's ESSL compiler mishandles gl_ClipDistance (device-verified on Adreno 750):
+            //   - writes through non-constant indices silently fail to link,
+            //   - reads of gl_in[i].gl_ClipDistance[k] with a CONSTANT k >= 1 fail to compile
+            //     ("array indexing out of boundary") while dynamic-index reads work,
+            //   - compiling a whole-array read of gl_in[i].gl_ClipDistance segfaults the
+            //     compiler backend (libllvm-qgl.so).
+            // This pass shadows the builtin so the decompiled ESSL only ever touches it in the
+            // shapes Adreno accepts. Output side (vertex + geometry): all accesses to the
+            // Output ClipDistance (gl_PerVertex member or standalone variable) are redirected
+            // to a Private mg_ClipDistance array, and a flush writing the real builtin with
+            // literal constant indices is inserted before every OpEmitVertex (geometry) or
+            // every return of the entry point (vertex). Input side (geometry): accesses to
+            // gl_in[...].gl_ClipDistance are redirected to a Private mg_ClipDistanceIn
+            // array-of-arrays filled once at the top of the entry point by a structured loop
+            // whose gl_in reads use dynamic (loop-variable) indices. The builtin members stay
+            // statically referenced by the flush/copy so cross-stage IO matching is intact.
+            // Only meant for the DirectGLES transpile path on Qualcomm devices.
+            class LowerClipDistanceForEsslPass : public spvtools::opt::Pass {
+            public:
+                const char* name() const override { return "lower-clip-distance-for-essl"; }
+                Status Process() override;
+
+                static spvtools::Optimizer::PassToken CreateLowerClipDistanceForEsslPass();
+            };
+        } // namespace ShaderTranspiler
+    } // namespace MG_Util
+} // namespace MobileGL

tools/cts/scripts/run_cts.py

@@ -87,7 +87,7 @@ def main():
     ap.add_argument("--device-dir", default="/data/local/tmp/mgcts")
     ap.add_argument("--surface", default="fbo", help="--deqp-surface-type value")
     ap.add_argument("--max-rounds", type=int, default=4000)
-    ap.add_argument("--max-empty-streak", type=int, default=64,
+    ap.add_argument("--max-empty-streak", type=int, default=8,
                     help="abort after this many consecutive chunks that produce no log at all")
     ap.add_argument("--min-mem-kb", type=int, default=400000,
                     help="pause when the device drops below this much available memory")