swung0x48/MobileGL
1
0
Fork 0
mirror of https://github.com/MobileGL-Dev/MobileGL synced 2026-11-08 10:33:24 +09:00
Code Issues Packages Projects Releases Wiki Activity
Files
7520e53b5ed7441e0224d8c2fbe8b4cf48ad4635
MobileGL/MobileGL/MG_Backend/DirectVulkan/Renderer/WireDraw.inc
T

875 lines
54 KiB
C++
Raw Blame History

// Server-owned draw/dispatch setup. The legacy setup remains the monolith implementation.
#if MOBILEGL_BUILD_DISAGGREGATED
static MagmaProgramSource WireProgramSource(MG_Pipe::MGPipeHandle handle) {
auto& state = MG_Pipe::MGPipeApplier();
const Bool composite = handle.Slot >= MG_Pipe::kMGPipeShaderCsoCompositeSlotBase;
const auto& records = composite ? state.CompositeShaderCsos : state.ShaderCsos;
const SizeT index = composite ? handle.Slot - MG_Pipe::kMGPipeShaderCsoCompositeSlotBase : handle.Slot;
if (MG_Pipe::MGPipeHandleIsNull(handle) || index >= records.size() ||
!records[index].Live || records[index].Gen != handle.Gen || !records[index].Archive)
MagmaWireFatal("program-record");
return MagmaProgramSource(handle, records[index]);
}
// Through the same seam as MagmaWireFatal, and for the same reason (P7 wave 0). The family
// stays RoleViolation: reaching the legacy buffer arm inside a Magma server is a role
// invariant the two halves must hold, not a verb the wire failed to migrate.
[[noreturn]] static void WireBufferLegacyFatal() {
MG_Pipe::MGPipeSessionFail(
MG_Pipe::MGPipeFatalFamily::RoleViolation,
"MGPipe: Fatal{RoleViolation, \"buffer-legacy-arm\"} (Magma P7 buffer consumer)");
}
static const MG_Pipe::MGPStreamOutputBegin& WireXfbSpan() {
const auto& state = MG_Pipe::MGPipeApplier();
const auto found = state.StreamOutputSpans.find(state.BoundStreamOutputLifetimeId);
if (found == state.StreamOutputSpans.end()) MagmaWireFatal("xfb-span-record");
return found->second;
}
Bool VulkanRenderer::BeginWireXfbCaptureForDraw(FrameContext::FrameData& frame) {
const auto& span = WireXfbSpan();
const auto program = WireProgramSource(span.CaptureProgram);
const Uint32 count = static_cast<Uint32>(std::min<SizeT>(program.GetTransformFeedbackBufferCount(), 4));
if (!count || !program.GetTransformFeedbackVaryingCount()) return false;
VkBuffer buffers[4]{};
VkDeviceSize offsets[4]{};
VkDeviceSize sizes[4]{};
Bool hasTarget = false;
for (Uint32 i = 0; i < count; ++i) {
// A leading gl_NextBuffer leaves a hole in the binding indices. No
// output names that zero-stride target, and GL need not bind a buffer.
if (!program.GetTransformFeedbackStride(i)) continue;
const auto& target = span.Targets[i];
BufferSlice slice{};
if (MG_Pipe::MGPipeHandleIsNull(target.Res) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Vertex, target.Res, slice))
MagmaWireFatal("xfb-buffer-resource");
if (target.Offset >= slice.size) return false;
const Uint64 size = target.Size == 0 || target.Size == MG_Pipe::kMGPipeWholeBuffer
? slice.size - target.Offset : target.Size;
if (!size || size > slice.size - target.Offset) return false;
buffers[i] = slice.buffer;
offsets[i] = slice.offset + target.Offset;
sizes[i] = size;
hasTarget = true;
// The server owns the storage. Publish dirtiness through the existing
// reverse channel so CPU readback does not reuse the client's old shadow.
m_bufferManager.MarkWireBufferGpuWritten(target.Res, target.Offset, size);
}
if (!hasTarget) return false;
return BeginXfbCaptureWithBuffers(frame, count, buffers, offsets, sizes);
}
static Bool ConvertWireVertexStream(const MGPVertexAttribWire& attr,
VertexInputStateFactory::VertexStreamConversion conversion, const Uint8* source,
SizeT stride, SizeT count, Vector<Uint8>& output) {
using Conversion = VertexInputStateFactory::VertexStreamConversion;
const auto type = static_cast<DataType>(attr.Type);
const SizeT elementBytes = VertexInputStateFactory::GetAttributeByteSize(type, attr.Size, attr.IsBgra);
if (conversion == Conversion::Repack) {
output.resize(count * elementBytes);
for (SizeT i = 0; i < count; ++i)
Memcpy(output.data() + i * elementBytes, source + i * stride, elementBytes);
return true;
}
output.resize(count * attr.Size * sizeof(Float));
const auto convert = [&]<typename T>() {
for (SizeT i = 0; i < count; ++i) {
for (SizeT component = 0; component < attr.Size; ++component) {
T value{};
Memcpy(&value, source + i * stride + component * sizeof(T), sizeof(T));
const Float converted = static_cast<Float>(value);
Memcpy(output.data() + (i * attr.Size + component) * sizeof(Float), &converted, sizeof(Float));
}
}
return true;
};
switch (type) {
case DataType::Float64: return convert.template operator()<Double>();
case DataType::Int8: return convert.template operator()<Int8>();
case DataType::Uint8: return convert.template operator()<Uint8>();
case DataType::Int16: return convert.template operator()<Int16>();
case DataType::Uint16: return convert.template operator()<Uint16>();
case DataType::Int32: return convert.template operator()<Int32>();
case DataType::Uint32: return convert.template operator()<Uint32>();
default: return false;
}
}
void VulkanRenderer::DestroyWireDrawPass() {
// Only shutdown/swapchain replacement calls this, after device idle.
if (m_wireDrawPass && m_frameContext.GetFrameCount() != 0) {
auto& frame = m_frameContext.GetCurrent();
if (frame.isCommandRecording && VkRenderPassManager::GetActiveRenderPass())
VkRenderPassManager::EndRenderPass(frame.commandBuffer);
}
m_wireDrawPass.reset();
for (const auto view : m_wireDrawViews) vkDestroyImageView(m_device, view, nullptr);
m_wireDrawViews.clear();
m_wireDrawPassKey = {};
}
void VulkanRenderer::RetireWireObjects(WireRetiredObjects objects) {
// The current recording is the next graphics submission. Do not use a
// frame number: mid-frame flushes and readbacks can split one frame.
objects.submitIndex = m_submitCounter + 1;
m_wireRetiredObjects.push_back(Move(objects));
}
void VulkanRenderer::RetireWireDrawPass() {
if (!m_wireDrawPass) return;
auto& frame = m_frameContext.GetCurrent();
if (frame.isCommandRecording && VkRenderPassManager::GetActiveRenderPass())
VkRenderPassManager::EndRenderPass(frame.commandBuffer);
const Uint32 frameIndex = m_frameContext.GetCurrentFrameIndex();
if (m_wireDrawPassCaches.size() < m_frameContext.GetFrameCount())
m_wireDrawPassCaches.resize(m_frameContext.GetFrameCount());
auto& cache = m_wireDrawPassCaches[frameIndex];
// Bound a present-less stream of distinct framebuffer configurations.
// Overflow retains the original submit-index retirement path.
constexpr SizeT kMaxCachedWirePassesPerFrame = 32;
if (cache.size() < kMaxCachedWirePassesPerFrame) {
cache.push_back({Move(m_wireDrawPassKey), Move(m_wireDrawPass), Move(m_wireDrawViews)});
return;
}
WireRetiredObjects retired{};
retired.drawPass = Move(m_wireDrawPass);
retired.imageViews = Move(m_wireDrawViews);
RetireWireObjects(Move(retired));
m_wireDrawPassKey = {};
}
Bool VulkanRenderer::AcquireCachedWireDrawPass(const WireDrawPassKey& key) {
const Uint32 frameIndex = m_frameContext.GetCurrentFrameIndex();
if (frameIndex >= m_wireDrawPassCaches.size()) return false;
auto& cache = m_wireDrawPassCaches[frameIndex];
for (auto it = cache.begin(); it != cache.end(); ++it) {
// Exact values, not a compatibility hash: two FBOs with the same
// formats can name different images, windows or draw-buffer slots.
if (!(it->key == key)) continue;
m_wireDrawPassKey = Move(it->key);
m_wireDrawPass = Move(it->pass);
m_wireDrawViews = Move(it->views);
cache.erase(it);
return true;
}
return false;
}
void VulkanRenderer::ClearWireDrawPassCache(Uint32 frameIndex) {
if (frameIndex >= m_wireDrawPassCaches.size()) return;
auto& cache = m_wireDrawPassCaches[frameIndex];
for (auto& entry : cache) {
entry.pass.reset();
for (const auto view : entry.views) vkDestroyImageView(m_device, view, nullptr);
}
cache.clear();
}
void VulkanRenderer::ClearAllWireDrawPassCaches() {
for (Uint32 frameIndex = 0; frameIndex < m_wireDrawPassCaches.size(); ++frameIndex)
ClearWireDrawPassCache(frameIndex);
}
void VulkanRenderer::CollectWireObjects(Uint64 completedSubmit, Bool all) {
SizeT retained = 0;
for (SizeT index = 0; index < m_wireRetiredObjects.size(); ++index) {
auto& entry = m_wireRetiredObjects[index];
if (!all && entry.submitIndex > completedSubmit) {
if (retained != index) m_wireRetiredObjects[retained] = Move(entry);
++retained;
continue;
}
// Framebuffers/descriptor sets stop naming their views first.
entry.drawPass.reset();
for (const auto pool : entry.descriptorPools) vkDestroyDescriptorPool(m_device, pool, nullptr);
for (const auto framebuffer : entry.framebuffers) vkDestroyFramebuffer(m_device, framebuffer, nullptr);
for (const auto pass : entry.renderPasses) vkDestroyRenderPass(m_device, pass, nullptr);
for (const auto view : entry.imageViews) vkDestroyImageView(m_device, view, nullptr);
}
// Erase once: repeated front erases move the whole remaining cohort for
// every draw retired by a fence, turning a batch retirement quadratic.
m_wireRetiredObjects.resize(retained);
}
struct WirePreparationScope {
Uint32& depth;
explicit WirePreparationScope(Uint32& value) : depth(value) { ++depth; }
~WirePreparationScope() { --depth; }
};
Bool VulkanRenderer::SetupWireDraw(FrameContext::FrameData& frame, GLenum mode,
Flags<DrawSetupAspect> aspects, const DrawCmdParam& drawParams, const IndexBufferView* indices) {
auto& state = MG_Pipe::MGPipeApplier();
const auto program = WireProgramSource(state.BoundShaderCso);
if (!program.GetLinkStatus() || !program.GetSpirvStatus()) {
MGL_WIRE_DECLINE_AT(ProgramLinkOrSpirv, "program is not linked or carries no SPIR-V");
return false;
}
// P8-D: the wire arm's own indirect draw (DrawWireIndirectNative) is the one caller that
// may pass this aspect; a monolith indirect entry point reached here is still the role
// violation.
if ((aspects & DrawSetupAspect::IndirectDrawBuffer) && !m_wireNativeIndirectDraw)
WireBufferLegacyFatal();
MakeXfbWritesVisible();
const auto* fbo = state.DrawFramebuffer();
if (!fbo) MagmaWireFatal("draw-framebuffer-record");
RetireWireDrawPass();
// CPU preparation may synchronize GPU-produced vertex/index bytes. Do
// not rewind an arena while this draw owns as-yet-unrecorded slices.
WirePreparationScope preparing(m_wirePreparationDepth);
ProgramFactory::CompileOptionFlags flags =
ProgramFactory::CompileOptionFlags(GetBaseTransformFlagsRaw(fbo->IsDefault));
if (m_transformFeedbackFeatureEnabled && MGB_CTX->IsTransformFeedbackActive() &&
program.GetTransformFeedbackVaryingCount() > 0)
flags |= ProgramFactory::CompileOptionBit::XfbCapture;
const auto* programObject = &m_programFactory->GetOrCreateProgram(program, flags);
if (!(aspects & DrawSetupAspect::IndexBuffer) && programObject->readsBaseVertexBuiltin) {
flags |= ProgramFactory::CompileOptionBit::ZeroBaseVertex;
programObject = &m_programFactory->GetOrCreateProgram(program, flags);
}
if (programObject->pointSizeCapabilityUnsupported) {
MGL_WIRE_DECLINE_AT(PointSizeCapability, "the program writes gl_PointSize and the device cannot express it");
return false;
}
const auto& programObj = *programObject;
m_currentDrawXfbCaptureDeclined = programObj.xfbCaptureDeclined;
if (!m_uniformManager->PrepareWireTextureResources(program, programObj)) {
MGL_WIRE_DECLINE_AT(TextureResourcesUnprepared, "a sampled/storage image could not be made ready; see the Tex* tally");
return false;
}
// Shared images another session writes: acquired ahead of the recording that samples them
// (WireSharedImage.inc).
AcquireNotedSharedImages();
// Lazy image uploads/promotions can submit the old recording. Resolve
// ALL attachments before descriptor binding captures the current cmd.
for (Uint32 i = 0; i < MG_Pipe::kMGPipeMaxColorAttachments; ++i) {
const Int32 slot = fbo->DrawBuffers[i];
if (slot >= 0) (void)ResolveWireImage(*fbo, fbo->Color[slot], VK_IMAGE_ASPECT_COLOR_BIT);
}
if (fbo->IsDefault || fbo->Depth.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
(void)ResolveWireImage(*fbo, fbo->Depth, VK_IMAGE_ASPECT_DEPTH_BIT);
else if (fbo->Stencil.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
(void)ResolveWireImage(*fbo, fbo->Stencil, VK_IMAGE_ASPECT_STENCIL_BIT);
m_textureManager->FlushPendingUploads();
const auto vaoHandle = state.BoundVertexElements;
if (MG_Pipe::MGPipeHandleIsNull(vaoHandle)) MagmaWireFatal("vertex-elements-record");
if (vaoHandle.Slot >= state.VertexElementsCsos.size()) MagmaWireFatal("vertex-elements-record");
const auto& vao = state.VertexElementsCsos[vaoHandle.Slot];
if (!vao.Live || vao.Gen != vaoHandle.Gen) MagmaWireFatal("vertex-elements-generation");
VertexInputStateFactory::BackendVertexInputState input{};
// P7 wave 2 package C, CONTRACT-P7 §3.2: THE `vertex-layout` ROW IS RETIRED AND SPLIT.
//
// A false is now ONE reason and only one - `buffer-window`, an enabled attribute the
// program reads whose slot lies outside the window set_vertex_buffers published. That
// is a disagreement about what crossed, not about what this device can express, so it
// keeps a named Fatal through the hook (MGPipeSessionFail -> Session::Fail, which is
// what rule I asks of a refusal that must stay a refusal). It is the check that caught
// the Redmi VAO hash collision fixed in 376c04be, which is why it is not softened.
// The P7 marker is gone from the detail string with the abort: this is a permanent
// protocol error, not a shape the split path has yet to migrate, so it must not keep
// counting against the census of unmigrated refusals (scripts/ci/fatal_census.py
// counts the marker literally, which is also why no comment in this package spells it).
if (!m_vertexInputStateFactory->BuildWireVertexInput(vao, state,
programObj.activeVertexInputLocationMask, input))
MagmaWireFatal("vertex-layout-buffer-window");
// The seven device/format reasons are now MASKED OUT of the vertex input state, and
// this is the monolith arm's pre-flight for them, statement for statement
// (VulkanRenderer.cpp's SetupDraw: "Fail loudly rather than render wrong pixels"). An
// enabled array with no usable VkFormat never reaches the vertex input state, which
// makes it indistinguishable from a DISABLED one - and a disabled one is answered
// below by uploading the current attribute value, so without this check the draw would
// quietly feed the shader a constant in place of the application's vertex data.
//
// A DECLINE, NOT A FATAL (rule I (a)): the draw is skipped, the reason is named once,
// and the observable is the monolith lane's for the same VAO on the same device.
// BuildWireVertexInput only considers attributes the program reads, so a masked bit is
// always an active one and this predicate is the whole of the difference.
if ((input.unsupportedAttribMask & programObj.activeVertexInputLocationMask) != 0) {
MGLOG_E_ONCE("Magma wire draw skipped: program=%u reads vertex attribute location "
"mask 0x%x whose enabled array has no supported vertex format",
program.GetExternalIndex(),
input.unsupportedAttribMask & programObj.activeVertexInputLocationMask);
WireDeclineTally::Count(WireDeclineSite::VertexFormatUnsupported);
return false;
}
Vector<BufferSlice> vertexSlices(input.bindings.size());
for (SizeT binding = 0; binding < input.bindings.size(); ++binding) {
const Uint32 location = input.bindingAttributeLocations[binding];
const auto& attr = vao.Attributes[location];
const auto& resource = state.VertexBuffers[location];
// P8-F: A RECORD INVARIANT, NOT AN UNMIGRATED VERB (it carried a P8 phase tag).
// The client turns every enabled client-memory array into an owned buffer before the
// draw record is built, or refuses the draw itself (MG_Impl/Pipe/OwnedDrawInputs.h),
// so an attribute the program reads with no buffer handle is a foreign peer's record.
if (MG_Pipe::MGPipeHandleIsNull(resource.Res))
MG_Pipe::MGPipeSessionFail(MG_Pipe::MGPipeFatalFamily::ProtocolCorruption,
"MGPipe: Fatal{ProtocolCorruption, \"Magma:client-vertex-array\"} location=%u: an "
"attribute the program reads carries no buffer handle", location);
BufferSlice slice{};
if (!m_bufferManager.AcquireWireSlice(BufferKind::Vertex, resource.Res, slice)) {
// A buffer with no data store is legal GL to bind (glGenBuffers + glBindBuffer, no
// glBufferData), and the client mints its handle at construction while the create
// only crosses with the first respecify (PipeFill.cpp's M-1) - so the handle may be
// one this server never saw, or one it holds with zero bytes. Either way the draw
// reads no storage: it is declined, as the GL draws nothing defined from it.
static Bool s_described = false;
if (!s_described && !m_bufferManager.IsKnownWireBuffer(resource.Res)) {
s_described = true;
m_bufferManager.DescribeWireBufferHistory(resource.Res);
}
MGL_WIRE_DECLINE_AT(VertexAttributeWindow, "an enabled attribute's buffer has no storage");
return false;
}
const VkDeviceSize offset = input.bindingBaseOffsets[binding];
const auto type = static_cast<DataType>(attr.Type);
const SizeT elementSize = VertexInputStateFactory::GetAttributeByteSize(type, attr.Size, attr.IsBgra);
if (offset > slice.size || elementSize > slice.size - offset) {
MGL_WIRE_DECLINE_AT(VertexAttributeWindow, "an enabled attribute's first element lies outside its buffer");
return false;
}
const auto conversion = input.bindingConversions[binding];
if (conversion != VertexInputStateFactory::VertexStreamConversion::None) {
const SizeT stride = static_cast<SizeT>(attr.Stride);
SizeT count = stride ? 1 + (static_cast<SizeT>(slice.size - offset) - elementSize) / stride : 1;
// Direct non-indexed draws bound the conversion; indexed/multi-draw may
// name arbitrary vertices, so preserve the entire valid source stream. So may an
// indirect draw (P8-D): its vertex range is in GPU words nobody read.
if (stride && !(aspects & DrawSetupAspect::IndexBuffer) &&
!(aspects & DrawSetupAspect::IndirectDrawBuffer) && !resource.Divisor)
count = std::min<SizeT>(count, static_cast<SizeT>(drawParams.firstVertex) + drawParams.vertexCount);
if (!count) {
MGL_WIRE_DECLINE_AT(VertexStreamCountZero, "the converted vertex stream would hold no elements");
return false;
}
Vector<Uint8> source((count - 1) * stride + elementSize);
if (!m_bufferManager.ReadWireBuffer(resource.Res, offset, source.size(), source.data())) {
MGL_WIRE_DECLINE_AT(VertexStreamRead, "the vertex bytes to convert could not be read back");
return false;
}
Vector<Uint8> converted;
// P7 wave 2 package C, CONTRACT-P7 §3.2 `vertex-format-conversion`: DECLINE.
// The converter is asked only for a conversion BuildWireVertexInput already
// chose, so a refusal here means the two disagree about what is convertible -
// a MobileGL-internal defect, not a peer's malformed record and not a verb the
// split path has yet to migrate. Killing the session for it told the peer
// "protocol corruption" about a bug on this side; skipping the draw and naming
// it once is the honest answer and is what the row asks for. The packed
// converter that would make the refusal unreachable is the row's optional half
// and is not taken here.
if (!ConvertWireVertexStream(attr, conversion, source.data(), stride, count, converted)) {
MGLOG_E_ONCE("Magma wire draw skipped: no vertex stream converter for "
"location=%u type=%u size=%u conversion=%d",
location, attr.Type, static_cast<Uint32>(attr.Size),
static_cast<Int>(conversion));
WireDeclineTally::Count(WireDeclineSite::VertexStreamConverter);
return false;
}
if (!m_bufferManager.UploadTransient(BufferKind::Vertex, m_frameContext.GetCurrentFrameIndex(),
converted.data(), converted.size(), 16, vertexSlices[binding])) {
MGL_WIRE_DECLINE_AT(VertexTransientUpload, "the converted vertex stream did not fit the transient arena");
return false;
}
} else {
slice.offset += offset;
slice.size -= offset;
vertexSlices[binding] = slice;
}
}
BufferSlice indexSlice{};
VkIndexType indexType = VK_INDEX_TYPE_MAX_ENUM;
if (aspects & DrawSetupAspect::IndexBuffer) {
if (!indices) {
MGL_WIRE_DECLINE_AT(IndexViewMissing, "an indexed draw arrived with no index view");
return false;
}
const SizeT width = MG_Util::GetGLTypeSize(indices->indexType);
if (width != 1 && width != 2 && width != 4) {
MGL_WIRE_DECLINE_AT(IndexTypeWidth, "the index type is not 1, 2 or 4 bytes wide");
return false;
}
indexType = width == 4 ? VK_INDEX_TYPE_UINT32 : width == 2 ? VK_INDEX_TYPE_UINT16 : VK_INDEX_TYPE_UINT8;
const auto& restart = MGB_CTX->GetRenderStateParameters();
const Uint32 fixed = MG_Util::FixedRestartIndexForGLType(indices->indexType);
const Bool replaceRestart = restart.PrimitiveRestartEnabled && !restart.PrimitiveRestartFixedIndexEnabled &&
restart.PrimitiveRestartIndex < fixed;
const Bool expandByte = width == 1 && !m_indexTypeUint8ExtensionEnabled;
const Bool cpuIndices = indices->forceClientMemory || MG_Pipe::MGPipeHandleIsNull(state.IndexBuffer.Res);
Vector<Uint8> copied;
const void* bytes = nullptr;
if (cpuIndices) bytes = reinterpret_cast<const void*>(indices->indexByteOffset);
else {
if (!m_bufferManager.AcquireWireSlice(BufferKind::Index, state.IndexBuffer.Res, indexSlice)) {
// As for a vertex buffer: a bound element buffer with no data store yet.
static Bool s_described = false;
if (!s_described && !m_bufferManager.IsKnownWireBuffer(state.IndexBuffer.Res)) {
s_described = true;
m_bufferManager.DescribeWireBufferHistory(state.IndexBuffer.Res);
}
MGL_WIRE_DECLINE_AT(IndexWindow, "the element buffer has no storage");
return false;
}
const Uint64 offset = state.IndexBuffer.Offset + indices->indexByteOffset;
if (offset < state.IndexBuffer.Offset || offset > indexSlice.size ||
indices->indexByteSize > indexSlice.size - offset) {
MGL_WIRE_DECLINE_AT(IndexWindow, "the index range lies outside its buffer");
return false;
}
if (replaceRestart || expandByte || offset % width) {
copied.resize(indices->indexByteSize);
if (!m_bufferManager.ReadWireBuffer(state.IndexBuffer.Res, offset, copied.size(), copied.data())) {
MGL_WIRE_DECLINE_AT(IndexStreamRead, "the indices to rewrite could not be read back");
return false;
}
bytes = copied.data();
}
indexSlice.offset += offset;
indexSlice.size = indices->indexByteSize;
}
if (bytes) {
Vector<Uint8> rewritten;
SizeT uploadSize = indices->indexByteSize;
if (replaceRestart || expandByte) {
const SizeT outWidth = expandByte ? 2 : width;
rewritten.resize(uploadSize / width * outWidth);
for (SizeT i = 0; i < uploadSize / width; ++i) {
Uint32 value = 0;
Memcpy(&value, static_cast<const Uint8*>(bytes) + i * width, width);
if (replaceRestart && value == restart.PrimitiveRestartIndex) value = fixed;
if (expandByte && ResolvePrimitiveRestartEnable(aspects, indices) && value == fixed) value = 0xffffu;
Memcpy(rewritten.data() + i * outWidth, &value, outWidth);
}
bytes = rewritten.data();
uploadSize = rewritten.size();
if (expandByte) indexType = VK_INDEX_TYPE_UINT16;
}
if (!m_bufferManager.UploadTransient(BufferKind::Index, m_frameContext.GetCurrentFrameIndex(),
bytes, uploadSize, 16, indexSlice)) {
MGL_WIRE_DECLINE_AT(IndexTransientUpload, "the rewritten indices did not fit the transient arena");
return false;
}
}
if (!indexSlice.IsValid()) {
MGL_WIRE_DECLINE_AT(IndexSliceInvalid, "no usable index slice was resolved");
return false;
}
}
if (!frame.isCommandRecording) m_frameContext.BeginCommandRecording();
// Descriptor resolution can upgrade a view's root image to STORAGE usage.
// Resolve it before constructing framebuffer views so both roles of that image
// name the same allocation even on its first storage-image use.
if (!m_uniformManager->BindProgramUniformBuffers(frame.commandBuffer, program, programObj,
m_frameContext.GetCurrentFrameIndex(), VK_PIPELINE_BIND_POINT_GRAPHICS)) {
MGL_WIRE_DECLINE_AT(UniformBufferBinding, "the program's uniform/storage bindings could not be bound");
return false;
}
Vector<VkAttachmentDescription> attachments;
Vector<VkImageViewCreateInfo> viewInfos;
Vector<VkAttachmentReference> colors;
VkAttachmentReference depth{VK_ATTACHMENT_UNUSED, VK_IMAGE_LAYOUT_GENERAL};
VkExtent2D extent{~0u, ~0u};
Uint32 layers = ~0u;
VkSampleCountFlagBits samples = VK_SAMPLE_COUNT_1_BIT;
Uint64 passHash = 0;
WireDrawPassKey passKey{};
passKey.isDefault = fbo->IsDefault;
passKey.framebufferSrgb = MGB_CTX->IsCapabilityEnabled(CapabilityInput::FramebufferSrgb);
if (fbo->IsDefault) {
passKey.swapchain = m_swapchainObject.GetHandle();
// A drawing pass on the default framebuffer is what makes the freshly acquired
// swapchain image the one GL addresses (see m_defaultFramebufferImageIndex); the
// attachments below resolve the same index, so this key has to be taken after it.
passKey.swapchainImageIndex = DefaultFramebufferWriteIndex(true);
}
const auto add = [&](const MG_Pipe::MGPSurface& surface, VkImageAspectFlags aspect) -> Uint32 {
WireImage image = ResolveWireImage(*fbo, surface, aspect, /*isWriteTarget=*/true);
if (!image.image) return VK_ATTACHMENT_UNUSED;
m_textureManager->FlushPendingUploads();
if (aspect == VK_IMAGE_ASPECT_COLOR_BIT)
image.format = ResolveSrgbAttachmentWriteFormat(image.format,
MGB_CTX->IsCapabilityEnabled(CapabilityInput::FramebufferSrgb));
const VkImageLayout layout = aspect == VK_IMAGE_ASPECT_COLOR_BIT ?
VK_IMAGE_LAYOUT_GENERAL : VK_IMAGE_LAYOUT_GENERAL;
TransitionWireImage(image, layout);
VkImageViewCreateInfo info{VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO};
info.image = image.image;
info.viewType = image.viewType;
info.format = image.format;
info.subresourceRange = {aspect, image.level, 1, image.layer, image.layers};
if (image.format == VK_FORMAT_D24_UNORM_S8_UINT || image.format == VK_FORMAT_D32_SFLOAT_S8_UINT)
info.subresourceRange.aspectMask = VK_IMAGE_ASPECT_DEPTH_BIT | VK_IMAGE_ASPECT_STENCIL_BIT;
viewInfos.push_back(info);
passKey.attachments.push_back({image.storage, static_cast<Uint32>(surface.Kind), image.image,
image.viewType, image.format, info.subresourceRange.aspectMask, aspect,
image.level, image.layer, image.layers, image.levels, image.extent.width, image.extent.height,
image.samples});
VkAttachmentDescription description{};
description.format = image.format;
description.samples = image.samples;
description.loadOp = description.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_LOAD;
description.storeOp = description.stencilStoreOp = VK_ATTACHMENT_STORE_OP_STORE;
description.initialLayout = description.finalLayout = layout;
attachments.push_back(description);
extent.width = std::min(extent.width, image.extent.width);
extent.height = std::min(extent.height, image.extent.height);
layers = std::min(layers, image.layers);
samples = image.samples;
passHash = XXH64(&description, sizeof(description), passHash);
if (!image.isDefault && surface.Kind == MG_Pipe::kMGPipeSurfaceKindTexture)
m_textureManager->MarkWireTextureGpuWritten(image.storage, image.level, image.layer, image.layers);
if (image.isDefault) {
if (aspect == VK_IMAGE_ASPECT_COLOR_BIT) m_swapchainObject.SetImageContentDefined(image.swapchainImageIndex, true);
else m_swapchainObject.SetDepthStencilContentDefined(image.swapchainImageIndex, true);
}
return static_cast<Uint32>(attachments.size() - 1);
};
for (Uint32 i = 0; i < MG_Pipe::kMGPipeMaxColorAttachments; ++i) {
const Int32 slot = fbo->DrawBuffers[i];
const Uint32 index = slot < 0 ? VK_ATTACHMENT_UNUSED : add(fbo->Color[slot], VK_IMAGE_ASPECT_COLOR_BIT);
colors.push_back({index, VK_IMAGE_LAYOUT_GENERAL});
}
while (!colors.empty() && colors.back().attachment == VK_ATTACHMENT_UNUSED) colors.pop_back();
if (fbo->IsDefault || fbo->Depth.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
depth.attachment = add(fbo->Depth, VK_IMAGE_ASPECT_DEPTH_BIT);
else if (fbo->Stencil.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
depth.attachment = add(fbo->Stencil, VK_IMAGE_ASPECT_STENCIL_BIT);
if (attachments.empty()) {
MGL_WIRE_DECLINE_AT(NoAttachments, "the draw framebuffer resolved to no attachments");
return false;
}
passKey.width = extent.width;
passKey.height = extent.height;
passKey.layers = layers;
passKey.depthReference = depth.attachment;
for (const auto& color : colors) passKey.colorReferences.push_back(color.attachment);
// A native handle can be recycled after image replacement or death.
// Sample epochs after every lazy resolve, then compare them with the key.
passKey.textureImageEpoch = m_textureManager->GetTextureImageEpoch();
passKey.resourceEraseEpoch = m_textureManager->GetResourceEraseEpoch();
VkSubpassDescription subpass{};
subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
subpass.colorAttachmentCount = static_cast<Uint32>(colors.size());
subpass.pColorAttachments = colors.data();
subpass.pDepthStencilAttachment = depth.attachment != VK_ATTACHMENT_UNUSED ? &depth : nullptr;
VkRenderPassCreateInfo passInfo{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO};
passInfo.attachmentCount = static_cast<Uint32>(attachments.size());
passInfo.pAttachments = attachments.data();
passInfo.subpassCount = 1;
passInfo.pSubpasses = &subpass;
if (!AcquireCachedWireDrawPass(passKey)) {
m_wireDrawPassKey = Move(passKey);
Vector<VkImageView> views;
views.reserve(viewInfos.size());
for (const auto& info : viewInfos) {
VkImageView view = VK_NULL_HANDLE;
VK_VERIFY(vkCreateImageView(m_device, &info, nullptr, &view));
m_wireDrawViews.push_back(view);
views.push_back(view);
}
m_wireDrawPass = MakeUnique<RenderPassEntry>();
auto& created = *m_wireDrawPass;
VK_VERIFY(vkCreateRenderPass(m_device, &passInfo, nullptr, &created.renderPass));
VkFramebufferCreateInfo fbInfo{VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO};
fbInfo.renderPass = created.renderPass;
fbInfo.attachmentCount = static_cast<Uint32>(views.size());
fbInfo.pAttachments = views.data();
fbInfo.width = extent.width; fbInfo.height = extent.height; fbInfo.layers = layers;
VK_VERIFY(vkCreateFramebuffer(m_device, &fbInfo, nullptr, &created.framebuffer));
created.attachmentCount = static_cast<Uint32>(attachments.size());
created.colorAttachmentCount = static_cast<Uint32>(colors.size());
created.hasDepthStencilAttachment = depth.attachment != VK_ATTACHMENT_UNUSED;
created.sampleCount = samples;
created.extent = {static_cast<Int>(extent.width), static_cast<Int>(extent.height)};
created.layers = layers;
created.hash = created.compatibilityHash = XXH64(colors.data(), colors.size() * sizeof(colors[0]), passHash);
}
auto& pass = *m_wireDrawPass;
WireRenderPassCompatibilityKey pipelinePassKey{};
for (const auto& attachment : attachments)
pipelinePassKey.attachmentFormatsAndSamples.push_back(
(static_cast<Uint64>(attachment.format) << 32) | static_cast<Uint32>(attachment.samples));
for (const auto& color : colors) pipelinePassKey.colorReferences.push_back(color.attachment);
pipelinePassKey.depthReference = depth.attachment;
const Uint64 compatibilityId = m_wireRenderPassCompatibility.Intern(pipelinePassKey);
const auto pipeline = GetOrCreatePipelineWithInput(mode, program, programObj, flags, input, pass,
ResolvePrimitiveRestartEnable(aspects, indices), compatibilityId);
if (pipeline == VK_NULL_HANDLE) {
MGL_WIRE_DECLINE_AT(PipelineUnavailable, "no graphics pipeline could be created for this draw");
return false;
}
for (Uint32 i = 0; i < vertexSlices.size(); ++i)
vkCmdBindVertexBuffers(frame.commandBuffer, i, 1, &vertexSlices[i].buffer, &vertexSlices[i].offset);
Uint32 binding = static_cast<Uint32>(vertexSlices.size());
for (Uint32 location = 0; location < kMaxVertexAttribs; ++location) {
if (!(programObj.activeVertexInputLocationMask & (1u << location)) ||
(input.attributeLocationMask & (1u << location))) continue;
VkFormat format = VK_FORMAT_UNDEFINED;
const void* data = nullptr;
VkDeviceSize size = 0;
if (!TryGetCurrentVertexAttributeUploadPayload(MGB_CTX->GetCurrentVertexAttribute(location),
programObj.vertexInputTypes[location], format, data, size)) {
MGL_WIRE_DECLINE_AT(CurrentAttributePayload, "a disabled array's current attribute value has no upload payload");
return false;
}
BufferSlice slice{};
if (!m_bufferManager.UploadTransient(BufferKind::Vertex, m_frameContext.GetCurrentFrameIndex(),
data, size, 16, slice)) {
MGL_WIRE_DECLINE_AT(CurrentAttributeUpload, "the current attribute value did not fit the transient arena");
return false;
}
vkCmdBindVertexBuffers(frame.commandBuffer, binding++, 1, &slice.buffer, &slice.offset);
}
if (indexSlice.IsValid()) vkCmdBindIndexBuffer(frame.commandBuffer, indexSlice.buffer, indexSlice.offset, indexType);
if (!VkRenderPassManager::BeginRenderPass(frame.commandBuffer, pass)) {
MGL_WIRE_DECLINE_AT(BeginRenderPass, "the render pass for this draw could not be begun");
return false;
}
vkCmdBindPipeline(frame.commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, pipeline);
ApplyDynamicDrawStateTail(frame, pass.extent, fbo->IsDefault,
ResolveDrawViewportCount(programObj.writesViewportIndexBuiltin));
if (MG_Util::PipeStats::Enabled()) MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::Draws, 1);
return true;
}
// ---- P8-D: THE WIRE ARM'S INDIRECT DRAWS READ THEIR WORDS ON THE GPU ----------------------
//
// The shape the monolith arm records (VulkanRenderer.cpp's MultiDraw{Elements,Arrays}Indirect
// and MultiDrawElementsIndirectCount), with the wire store's own VkBuffer in place of the
// frontend buffer's resident slice. Before this, every wire indirect draw read its commands
// through ReadWireBuffer and expanded them on the CPU, and a store a shader had written made
// that read a whole-GPU wait (WaitForWireBufferHostAccess) per draw.
//
// THE ONE FALSE: a COUNT form this device cannot issue - the monolith arm's own condition for
// vkCmdDrawIndexedIndirectCount (MultiDrawElementsIndirectCount), extended to the non-indexed
// twin the monolith never loads. Everything else is issued here or declined by name.
Bool VulkanRenderer::DrawWireIndirectNative(GLenum mode, GLenum type, Uint64 offset, GLsizei drawcount,
GLsizei stride, Bool indexed, Bool counted, Uint64 countOffset) {
if (drawcount <= 0) return true;
if (counted) {
const auto countEntry = indexed ? s_vkCmdDrawIndexedIndirectCount : s_vkCmdWireDrawIndirectCount;
if (!m_drawIndirectCountExtensionEnabled || countEntry == nullptr ||
(!m_multiDrawIndirectFeatureEnabled && drawcount != 1))
return false;
}
const auto& state = MG_Pipe::MGPipeApplier();
// GL's command sizes (GL 4.6 10.3.10), which are also Vulkan's.
const Uint64 commandSize = indexed ? 5 * sizeof(Uint32) : 4 * sizeof(Uint32);
if (stride == 0) stride = static_cast<GLsizei>(commandSize);
BufferSlice commands{};
if (MG_Pipe::MGPipeHandleIsNull(state.VerbIndirectBuffer) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Indirect, state.VerbIndirectBuffer, commands)) {
MGL_WIRE_DECLINE_AT(IndirectBufferUnbound, "an indirect draw names no live indirect buffer store");
return true;
}
const Uint64 span = static_cast<Uint64>(stride) * static_cast<Uint64>(drawcount - 1) + commandSize;
// GL refuses a stride that is not a multiple of four (INVALID_VALUE), and Vulkan requires
// it for drawCount > 1; a peer's record that breaks either is declined, not issued.
if (stride < static_cast<GLsizei>(commandSize) || (stride & 3) != 0 || (offset & 3u) != 0 ||
offset > commands.size || span > commands.size - offset) {
MGL_WIRE_DECLINE_AT(IndirectCommandRange, "the indirect commands lie outside their store or are misaligned");
return true;
}
BufferSlice parameters{};
if (counted) {
if (MG_Pipe::MGPipeHandleIsNull(state.VerbIndirectParameterBuffer) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Indirect, state.VerbIndirectParameterBuffer, parameters) ||
(countOffset & 3u) != 0 || countOffset > parameters.size || parameters.size - countOffset < sizeof(Uint32)) {
MGL_WIRE_DECLINE_AT(IndirectCountRange, "the indirect draw count lies outside its parameter store");
return true;
}
}
// The index view is the WHOLE bound element store past its binding offset, as the monolith
// arm binds it: the commands name their own firstIndex, which only the GPU reads.
IndexBufferView indices{};
DrawCmdParam vertexRange{};
vertexRange.instanceCount = 1;
Flags<DrawSetupAspect> aspects = DrawSetupAspect::IndirectDrawBuffer;
if (indexed) {
const SizeT width = MG_Util::GetGLTypeSize(type);
BufferSlice elements{};
if (width == 0 || MG_Pipe::MGPipeHandleIsNull(state.IndexBuffer.Res) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Index, state.IndexBuffer.Res, elements) ||
state.IndexBuffer.Offset > elements.size) {
MGL_WIRE_DECLINE_AT(IndirectIndexStore, "an indexed indirect draw names no usable element store");
return true;
}
indices.indexType = type;
indices.indexByteOffset = 0;
indices.indexByteSize = static_cast<SizeT>(elements.size - state.IndexBuffer.Offset);
vertexRange.vertexCount = static_cast<Uint32>(indices.indexByteSize / width);
aspects |= DrawSetupAspect::IndexBuffer;
}
// A shader write the store was marked with (MarkWireBufferGpuWritten) is made visible to
// the indirect read here, once per write, so a program that omits GL_COMMAND_BARRIER_BIT
// is not left racing a read the old CPU path used to take after a whole-GPU wait. The
// application's own glMemoryBarrier is BuildMemoryBarrierForGlBarriers, as on the monolith
// arm; transfer writes carry their own MEMORY_READ after-barrier (VkBufferManager.cpp).
const Bool commandsWritten = m_bufferManager.TakeWireIndirectReadBarrier(state.VerbIndirectBuffer);
const Bool countWritten = counted && m_bufferManager.TakeWireIndirectReadBarrier(state.VerbIndirectParameterBuffer);
if (commandsWritten || countWritten) {
RetireWireDrawPass();
auto& barrierFrame = m_frameContext.GetCurrent();
if (!barrierFrame.isCommandRecording) m_frameContext.BeginCommandRecording();
if (VkRenderPassManager::GetActiveRenderPass() != nullptr)
VkRenderPassManager::EndRenderPass(barrierFrame.commandBuffer);
VkMemoryBarrier barrier{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
barrier.srcAccessMask = VK_ACCESS_MEMORY_WRITE_BIT;
barrier.dstAccessMask = VK_ACCESS_INDIRECT_COMMAND_READ_BIT;
vkCmdPipelineBarrier(barrierFrame.commandBuffer, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT, 0, 1, &barrier, 0, nullptr, 0, nullptr);
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectBarriers, 1);
}
auto& frame = m_frameContext.GetCurrent();
m_wireNativeIndirectDraw = true;
const Bool ready = SetupDraw(frame, mode, aspects, vertexRange, indexed ? &indices : nullptr);
m_wireNativeIndirectDraw = false;
if (!ready) return true;
MOBILEGL_ASSERT(frame.isCommandRecording, "%s: frame recording was not started", __func__);
const VkCommandBuffer commandBuffer = frame.commandBuffer;
const VkDeviceSize first = commands.offset + offset;
const Uint32 count = static_cast<Uint32>(drawcount);
const Uint32 byteStride = static_cast<Uint32>(stride);
if (counted) {
const auto countEntry = indexed ? s_vkCmdDrawIndexedIndirectCount : s_vkCmdWireDrawIndirectCount;
countEntry(commandBuffer, commands.buffer, first, parameters.buffer, parameters.offset + countOffset,
count, byteStride);
} else if (count == 1 || (!m_multiDrawForceUnrollIndirect && m_multiDrawIndirectFeatureEnabled)) {
// maxDrawIndirectCount bounds one call; GL's drawcount does not.
const Uint32 limit = std::max<Uint32>(1u, m_physicalDevice.properties.limits.maxDrawIndirectCount);
for (Uint32 base = 0; base < count; base += limit) {
const Uint32 chunk = std::min(count - base, limit);
const VkDeviceSize at = first + static_cast<VkDeviceSize>(base) * byteStride;
if (indexed) vkCmdDrawIndexedIndirect(commandBuffer, commands.buffer, at, chunk, byteStride);
else vkCmdDrawIndirect(commandBuffer, commands.buffer, at, chunk, byteStride);
}
} else {
// No multiDrawIndirect: one indirect draw per command, still read by the GPU
// (the monolith arm's own fallback).
for (Uint32 i = 0; i < count; ++i) {
const VkDeviceSize at = first + static_cast<VkDeviceSize>(i) * byteStride;
if (indexed) vkCmdDrawIndexedIndirect(commandBuffer, commands.buffer, at, 1, 0);
else vkCmdDrawIndirect(commandBuffer, commands.buffer, at, 1, 0);
}
}
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectNativeDraws, 1);
return true;
}
void VulkanRenderer::DispatchWireCompute(GLuint x, GLuint y, GLuint z) {
RetireWireDrawPass();
auto& frame = m_frameContext.GetCurrent();
const auto program = WireProgramSource(MG_Pipe::MGPipeApplier().DispatchProgram);
if (!program.GetLinkStatus() || !program.GetSpirvStatus()) {
MGL_WIRE_DECLINE_AT(ComputeProgramLinkOrSpirv, "the compute program is not linked or carries no SPIR-V");
return;
}
const auto& programObj = m_programFactory->GetOrCreateProgram(program, {});
if (!m_uniformManager->PrepareWireTextureResources(program, programObj)) {
MGL_WIRE_DECLINE_AT(ComputeTextureResourcesUnprepared, "a sampled/storage image could not be made ready for the dispatch");
return;
}
AcquireNotedSharedImages(); // shared images another session writes (WireSharedImage.inc)
const auto pipeline = GetOrCreateComputePipeline(programObj);
if (!pipeline) {
MGL_WIRE_DECLINE_AT(ComputePipelineUnavailable, "no compute pipeline could be created for this dispatch");
return;
}
if (!frame.isCommandRecording) m_frameContext.BeginCommandRecording();
if (!m_uniformManager->BindProgramUniformBuffers(frame.commandBuffer, program, programObj,
m_frameContext.GetCurrentFrameIndex(), VK_PIPELINE_BIND_POINT_COMPUTE)) {
MGL_WIRE_DECLINE_AT(ComputeUniformBufferBinding, "the dispatch's uniform/storage bindings could not be bound");
return;
}
vkCmdBindPipeline(frame.commandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, pipeline);
vkCmdDispatch(frame.commandBuffer, x, y, z);
}
// ---- P8-SV: THE WIRE ARM'S INDIRECT DISPATCH READS ITS GROUP COUNTS ON THE GPU ----------
//
// The monolith arm's shape (VulkanRenderer.cpp's DispatchComputeIndirect) with the wire
// store's own VkBuffer in place of the frontend buffer's resident slice. Before this the wire
// arm read the three words through ReadWireBuffer and dispatched them from the CPU, and a store
// a shader had written made that read a whole-GPU wait (WaitForWireBufferHostAccess) per call.
// There is no shape the device cannot issue, so there is no CPU path left: a record whose
// store or words are unusable is declined by name.
//
// The barrier is P8-D's draw rule (DrawWireIndirectNative): a store marked shader-written gets
// one MEMORY_WRITE -> INDIRECT_COMMAND_READ barrier before its next indirect read, whether or
// not the application issued GL_COMMAND_BARRIER_BIT; DRAW_INDIRECT is the stage that consumes
// VkDispatchIndirectCommand too. It is TAKEN before the bindings below, because binding this
// dispatch's own storage buffers marks them written, and a store that is both this dispatch's
// parameters and one of its outputs must keep that mark for the next reader.
void VulkanRenderer::DispatchWireComputeIndirect(GLintptr offset) {
RetireWireDrawPass();
const auto& state = MG_Pipe::MGPipeApplier();
constexpr Uint64 kCommandSize = 3 * sizeof(Uint32); // GL 4.6 10.3.10 / VkDispatchIndirectCommand
BufferSlice parameters{};
if (MG_Pipe::MGPipeHandleIsNull(state.VerbDispatchIndirectBuffer) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Indirect, state.VerbDispatchIndirectBuffer, parameters)) {
MGL_WIRE_DECLINE_AT(DispatchIndirectBufferUnbound, "an indirect dispatch names no live dispatch-indirect store");
return;
}
// GL refuses an offset that is negative or not a multiple of four (INVALID_VALUE) and a
// command past the end of the buffer (INVALID_OPERATION); a peer's record that breaks
// either is declined, not issued.
if (offset < 0 || (static_cast<Uint64>(offset) & 3u) != 0 || static_cast<Uint64>(offset) > parameters.size ||
parameters.size - static_cast<Uint64>(offset) < kCommandSize) {
MGL_WIRE_DECLINE_AT(DispatchIndirectRange, "the dispatch group counts lie outside their store or are misaligned");
return;
}
auto& frame = m_frameContext.GetCurrent();
if (m_bufferManager.TakeWireIndirectReadBarrier(state.VerbDispatchIndirectBuffer)) {
if (!frame.isCommandRecording) m_frameContext.BeginCommandRecording();
if (VkRenderPassManager::GetActiveRenderPass() != nullptr)
VkRenderPassManager::EndRenderPass(frame.commandBuffer);
VkMemoryBarrier barrier{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
barrier.srcAccessMask = VK_ACCESS_MEMORY_WRITE_BIT;
barrier.dstAccessMask = VK_ACCESS_INDIRECT_COMMAND_READ_BIT;
vkCmdPipelineBarrier(frame.commandBuffer, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT, 0, 1, &barrier, 0, nullptr, 0, nullptr);
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectBarriers, 1);
}
const auto program = WireProgramSource(state.DispatchProgram);
if (!program.GetLinkStatus() || !program.GetSpirvStatus()) {
MGL_WIRE_DECLINE_AT(ComputeProgramLinkOrSpirv, "the compute program is not linked or carries no SPIR-V");
return;
}
const auto& programObj = m_programFactory->GetOrCreateProgram(program, {});
if (!m_uniformManager->PrepareWireTextureResources(program, programObj)) {
MGL_WIRE_DECLINE_AT(ComputeTextureResourcesUnprepared, "a sampled/storage image could not be made ready for the dispatch");
return;
}
AcquireNotedSharedImages(); // shared images another session writes (WireSharedImage.inc)
const auto pipeline = GetOrCreateComputePipeline(programObj);
if (!pipeline) {
MGL_WIRE_DECLINE_AT(ComputePipelineUnavailable, "no compute pipeline could be created for this dispatch");
return;
}
// PrepareWireTextureResources may have flushed and begun a new recording.
auto& dispatchFrame = m_frameContext.GetCurrent();
if (!dispatchFrame.isCommandRecording) m_frameContext.BeginCommandRecording();
if (!m_uniformManager->BindProgramUniformBuffers(dispatchFrame.commandBuffer, program, programObj,
m_frameContext.GetCurrentFrameIndex(), VK_PIPELINE_BIND_POINT_COMPUTE)) {
MGL_WIRE_DECLINE_AT(ComputeUniformBufferBinding, "the dispatch's uniform/storage bindings could not be bound");
return;
}
vkCmdBindPipeline(dispatchFrame.commandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, pipeline);
vkCmdDispatchIndirect(dispatchFrame.commandBuffer, parameters.buffer,
parameters.offset + static_cast<VkDeviceSize>(offset));
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectNativeDispatches, 1);
}
#endif
Reference in New Issue View Git Blame Copy Permalink