Program 203 reuses prefixSumCache for a second subgroup reduction before every workgroup invocation has consumed the first result. Add a fingerprint-gated SPIR-V pass that inserts the missing Workgroup acquire-release barrier while preserving native subgroup operations.
Keep the repair opt-in behind MOBILEGL_ITERATIONRP_FIX_BARRIER, cover insertion, pass-through, and idempotence, and enable it together with the existing iterationRP subgroup repairs for the matching Linux and Android CI retraces.
iterationRP's Program 203 declares shared vec2 prefixSumCache[32] for a
512-invocation workgroup indexed by gl_SubgroupID; any device narrower
than 16 lanes partitions into more than 32 subgroups and the pack writes
shared memory out of bounds (heap corruption on lavapipe's CPU
rasterizer, ssim 0.028 on the CI retrace). Fix it where the fault lies -
in the fixture - and keep the GL contract sound everywhere else:
- FixIterationRPSubgroupScratchPass: fingerprint-gated SPIR-V pass that
grows exactly that array to ceil(invocations/width) entries on sub-16-lane devices; every other module passes through byte-identical.
- DeriveNumSubgroupsPass stays default-on for the Adreno topology bug
and is made spec-sound: pipelines request REQUIRE_FULL_SUBGROUPS
whenever the workgroup shape makes the flag legal (computeFullSubgroups
enabled, local_size_x a multiple of the native width, subgroup count
within maxComputeWorkgroupSubgroups).
- EmulateSubgroupsPass: 32-lane virtual-subgroup lowering kept in-tree
as a last resort, enabled only by MOBILEGL_MAGMA_EMULATE_SUBGROUP=1 on
devices with no native subgroup support; fails closed on extended
subgroup instructions and on modules whose added scratch would exceed
maxComputeSharedMemorySize.
- IterationRPFirstReductionScenario skips gracefully outside the pack's
16..256-lane source domain; the new IterationRPScratchFixScenario runs
the fixture-shaped reduction on any width and asserts the exact
width-independent total. DriverPost keeps reporting FAIL on
out-of-domain devices.
- Program203 -> IterationRP rename throughout; the per-trace
num_subgroups_quirk plumbing is removed from the trace replayer, JNI
chain, and CI workflows.
Moves snapshot capture entirely into the apitrace retrace layer (glReadPixels + PNG encode). Drops the MOBILEGL_PRESENT_DUMP_PATH / MOBILEGL_PRESENT_STATS / MOBILEGL_PRESENT_DUMP_CALL / MOBILEGL_PRESENT_CURRENT_CALL / MOBILEGL_TRACE_CURRENT_CALL_OVERRIDE plumbing from Config, ConfigLoader, VulkanRenderer (GetPresentedDumpPixel/WritePresentedDumpPpm + present-stats readback), the EGL/GLX/Android ws shims, and the Android trace_replay_core PPM reader.
DirectVulkan ReadPixels on the default framebuffer now remaps raw swapchain pixels (top-left origin, preTransform-rotated) to GL orientation (bottom-left origin) so the retrace snapshot matches the golden; SwapchainObject also resizes the default-FBO stencil attachment to the swapchain extent to fix GL_INVALID_FRAMEBUFFER_OPERATION under the glReadPixels completeness check.
- compare actual output against primary and alternate golden images
- record the matched golden path in trace replay results
- allow APK and Linux retrace fixtures to pass alternate golden paths
- keep nostalgia validation accepting both Mesa and PC goldens
swung0x48
