Skip to content

AMDGPU: Add subtarget feature for global atomic fadd denormal support #96443

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Jul 10, 2024
Merged

AMDGPU: Add subtarget feature for global atomic fadd denormal support #96443

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
709e791
AMDGPU: Add subtarget feature for global atomic fadd denormal support
arsenm Jun 23, 2024
9d38cff
Add to gfx11.
arsenm Jun 24, 2024
43dc4f2
Rename
arsenm Jun 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 14 additions & 3 deletions llvm/lib/Target/AMDGPU/AMDGPU.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -788,6 +788,13 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;

def FeatureMemoryAtomicFAddF32DenormalSupport
: SubtargetFeature<"memory-atomic-fadd-f32-denormal-support",
"HasMemoryAtomicFaddF32DenormalSupport",
"true",
"global/flat/buffer atomic fadd for float supports denormal handling"
>;

def FeatureAgentScopeFineGrainedRemoteMemoryAtomics
: SubtargetFeature<"agent-scope-fine-grained-remote-memory-atomics",
"HasAgentScopeFineGrainedRemoteMemoryAtomics",
Expand Down Expand Up @@ -1427,7 +1434,8 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureKernargPreload,
FeatureAtomicFMinFMaxF64GlobalInsts,
FeatureAtomicFMinFMaxF64FlatInsts,
FeatureAgentScopeFineGrainedRemoteMemoryAtomics
FeatureAgentScopeFineGrainedRemoteMemoryAtomics,
FeatureMemoryAtomicFAddF32DenormalSupport
]>;

def FeatureISAVersion9_4_0 : FeatureSet<
Expand Down Expand Up @@ -1539,7 +1547,8 @@ def FeatureISAVersion11_Common : FeatureSet<
FeatureFlatAtomicFaddF32Inst,
FeatureImageInsts,
FeaturePackedTID,
FeatureVcmpxPermlaneHazard]>;
FeatureVcmpxPermlaneHazard,
FeatureMemoryAtomicFAddF32DenormalSupport]>;

// There are few workarounds that need to be
// added to all targets. This pessimizes codegen
Expand Down Expand Up @@ -1631,7 +1640,9 @@ def FeatureISAVersion12 : FeatureSet<
FeatureScalarDwordx3Loads,
FeatureDPPSrc1SGPR,
FeatureMaxHardClauseLength32,
Feature1_5xVGPRs]>;
Feature1_5xVGPRs,
FeatureMemoryAtomicFAddF32DenormalSupport
]>;

def FeatureISAVersion12_Generic: FeatureSet<
!listconcat(FeatureISAVersion12.Features,
Expand Down
7 changes: 7 additions & 0 deletions llvm/lib/Target/AMDGPU/GCNSubtarget.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,6 +167,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool HasAtomicFlatPkAdd16Insts = false;
bool HasAtomicFaddRtnInsts = false;
bool HasAtomicFaddNoRtnInsts = false;
bool HasMemoryAtomicFaddF32DenormalSupport = false;
bool HasAtomicBufferGlobalPkAddF16NoRtnInsts = false;
bool HasAtomicBufferGlobalPkAddF16Insts = false;
bool HasAtomicCSubNoRtnInsts = false;
Expand Down Expand Up @@ -872,6 +873,12 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,

bool hasFlatAtomicFaddF32Inst() const { return HasFlatAtomicFaddF32Inst; }

/// \return true if the target's flat, global, and buffer atomic fadd for
/// float supports denormal handling.
bool hasMemoryAtomicFaddF32DenormalSupport() const {
return HasMemoryAtomicFaddF32DenormalSupport;
}

/// \return true if atomic operations targeting fine-grained memory work
/// correctly at device scope, in allocations in host or peer PCIe device
/// memory.
Expand Down
Loading