Files
MobileGL/MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FixIterationRPBarrierPass.h
T
swung0x48 c09045fe59 [Fix, Test] (DirectVulkan, ShaderTranspiler, TraceReplay): repair iterationRP's missing reduction barrier
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.
2026-08-19 23:42:17 -04:00

29 lines
1.3 KiB
C++

// MobileGL - MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FixIterationRPBarrierPass.h
// Copyright (c) 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"
namespace MobileGL::MG_Util::ShaderTranspiler {
// Repairs iterationRP Program 203's missing workgroup rendezvous between two
// reductions that reuse prefixSumCache. The first phase broadcasts its result
// through prefixSumCache[0], but the second phase may overwrite that element before
// every invocation has read it. The pass fingerprints that exact two-scan,
// 512-invocation shape and inserts one Workgroup control barrier immediately before
// the second scan. Unrelated modules and already-repaired modules are byte-identical.
class FixIterationRPBarrierPass : public spvtools::opt::Pass {
public:
const char* name() const override { return "fix-iterationrp-barrier"; }
Status Process() override;
static spvtools::Optimizer::PassToken CreateFixIterationRPBarrierPass();
};
} // namespace MobileGL::MG_Util::ShaderTranspiler