shifathosn
/
AnyPS5
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #3472 from oneandonlydean/up4/fix-bda-note-write-nvidia-hang 

fix(shader): set a BDA-written page's bit inside the slot probe loop
This commit is contained in:
Adrià 2026-10-11 13:51:42 +02:00 committed by GitHub
parent 23f274e785 e7b4c05549
commit 6f7a12b0ee
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 11 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
core/shader/recompiler/SpirvBackend/src/SpirvBdaLookup.cpp
View File

@ -132,17 +132,13 @@ static std::uint32_t DefineBdaNoteWrite(SpirvEmitterState& state) {
state.module.AddFunction(spv::OpVariable, TypePointer(state, spv::StorageClassFunction, boolean), done, spv::StorageClassFunction);
const auto counter = state.module.AllocateId();
state.module.AddFunction(spv::OpVariable, TypePointer(state, spv::StorageClassFunction, u32), counter, spv::StorageClassFunction);
const auto held = state.module.AllocateId();
state.module.AddFunction(spv::OpVariable, TypePointer(state, spv::StorageClassFunction, u32), held, spv::StorageClassFunction);
state.module.AddFunction(spv::OpStore, done, ConstantBool(state, false));
state.module.AddFunction(spv::OpStore, counter, constant(0u));
state.module.AddFunction(spv::OpStore, held, constant(0u));
const auto u64 = TypeScalarU64(state);
const auto key = binary(spv::OpIAdd, u32, Unary(state, spv::OpUConvert, u32, binary(spv::OpShiftRightLogical, u64, address, BdaConstant(state, BdaAbi::WrittenChunkShift))), constant(1));
const auto page = binary(spv::OpBitwiseAnd, u32, Unary(state, spv::OpUConvert, u32, binary(spv::OpShiftRightLogical, u64, address, BdaConstant(state, BdaAbi::WrittenPageShift))), constant(BdaAbi::WrittenChunkPages - 1u));
const auto bit = binary(spv::OpShiftLeftLogical, u32, constant(1u), page);
const auto hash = binary(spv::OpShiftRightLogical, u32, binary(spv::OpIMul, u32, key, constant(0x9e3779b1u)), constant(32u - static_cast<std::uint32_t>(std::countr_zero(BdaAbi::WrittenPageSlots))));
const auto keyWordOf = [&](std::uint32_t slot) { return binary(spv::OpIAdd, u32, constant(BdaAbi::WrittenSlotsWord), binary(spv::OpShiftLeftLogical, u32, slot, constant(1u))); };
const auto scope = constant(spv::ScopeDevice);
const auto relaxed = constant(spv::MemorySemanticsMaskNone);
const auto header = state.module.AllocateId();
@ -160,8 +156,7 @@ static std::uint32_t DefineBdaNoteWrite(SpirvEmitterState& state) {
state.module.AddFunction(spv::OpBranchConditional, searching, body, merge);
EmitLabel(state, body);
const auto slot = binary(spv::OpBitwiseAnd, u32, binary(spv::OpIAdd, u32, hash, probe), constant(BdaAbi::WrittenPageSlots - 1u));
const auto keyWord = keyWordOf(slot);
state.module.AddFunction(spv::OpStore, held, slot);
const auto keyWord = binary(spv::OpIAdd, u32, constant(BdaAbi::WrittenSlotsWord), binary(spv::OpShiftLeftLogical, u32, slot, constant(1u)));
const auto current = state.module.AllocateId();
state.module.AddFunction(spv::OpAtomicLoad, u32, current, BdaWord(state, state.faultBufferVariable, keyWord), scope, relaxed);
const auto same = binary(spv::OpIEqual, boolean, current, key);
@ -177,6 +172,16 @@ static std::uint32_t DefineBdaNoteWrite(SpirvEmitterState& state) {
state.module.AddFunction(spv::OpAtomicStore, BdaWord(state, state.faultBufferVariable, binary(spv::OpIAdd, u32, constant(BdaAbi::WrittenListWord), index)), scope, relaxed, slot);
});
});
const auto holds = state.module.AllocateId();
state.module.AddFunction(spv::OpLoad, boolean, holds, done);
EmitIfCondition(state, holds, [&] {
const auto maskWord = binary(spv::OpIAdd, u32, keyWord, constant(1u));
const auto mask = state.module.AllocateId();
state.module.AddFunction(spv::OpAtomicLoad, u32, mask, BdaWord(state, state.faultBufferVariable, maskWord), scope, relaxed);
EmitIfCondition(state, binary(spv::OpIEqual, boolean, binary(spv::OpBitwiseAnd, u32, mask, bit), constant(0u)), [&] {
state.module.AddFunction(spv::OpAtomicOr, u32, state.module.AllocateId(), BdaWord(state, state.faultBufferVariable, maskWord), scope, relaxed, bit);
});
});
state.module.AddFunction(spv::OpBranch, continuation);
EmitLabel(state, continuation);
state.module.AddFunction(spv::OpStore, counter, binary(spv::OpIAdd, u32, probe, constant(1u)));
@ -184,16 +189,6 @@ static std::uint32_t DefineBdaNoteWrite(SpirvEmitterState& state) {
EmitLabel(state, merge);
const auto noted = state.module.AllocateId();
state.module.AddFunction(spv::OpLoad, boolean, noted, done);
EmitIfCondition(state, noted, [&] {
const auto heldSlot = state.module.AllocateId();
state.module.AddFunction(spv::OpLoad, u32, heldSlot, held);
const auto maskWord = binary(spv::OpIAdd, u32, keyWordOf(heldSlot), constant(1u));
const auto mask = state.module.AllocateId();
state.module.AddFunction(spv::OpAtomicLoad, u32, mask, BdaWord(state, state.faultBufferVariable, maskWord), scope, relaxed);
EmitIfCondition(state, binary(spv::OpIEqual, boolean, binary(spv::OpBitwiseAnd, u32, mask, bit), constant(0u)), [&] {
state.module.AddFunction(spv::OpAtomicOr, u32, state.module.AllocateId(), BdaWord(state, state.faultBufferVariable, maskWord), scope, relaxed, bit);
});
});
EmitIfCondition(state, Unary(state, spv::OpLogicalNot, boolean, noted), [&] {
state.module.AddFunction(spv::OpAtomicStore, BdaWord(state, state.faultBufferVariable, constant(BdaAbi::WrittenOverflowWord)), scope, relaxed, constant(1u));
});