Skip to content

AMDGPU: Add a subtarget feature for fine-grained remote memory support #96442

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 1 commit into from
Jul 10, 2024
Merged

AMDGPU: Add a subtarget feature for fine-grained remote memory support #96442

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
16 changes: 14 additions & 2 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 +788,16 @@ def FeatureFlatAtomicFaddF32Inst
"Has flat_atomic_add_f32 instruction"
>;

def FeatureAgentScopeFineGrainedRemoteMemoryAtomics
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd prefer using "Device" (hardware terminology) instead of "Agent" (terminology from some compute API??) in the hardware feature name. Although I see "agent" is already pervasive in AMDGPUUsage so perhaps that ship has sailed.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I originally went with device and changed it to agent to match the syncscope spelling. This was the HSA name

: SubtargetFeature<"agent-scope-fine-grained-remote-memory-atomics",
"HasAgentScopeFineGrainedRemoteMemoryAtomics",
"true",
"Agent (device) scoped atomic operations, excluding those directly "
"supported by PCIe (i.e. integer atomic add, exchange, and "
"compare-and-swap), are functional for allocations in host or peer "
"device memory."
>;

def FeatureDefaultComponentZero : SubtargetFeature<"default-component-zero",
"HasDefaultComponentZero",
"true",
Expand Down Expand Up @@ -1207,7 +1217,8 @@ def FeatureGFX12 : GCNSubtargetFeatureGeneration<"GFX12",
FeatureUnalignedBufferAccess, FeatureUnalignedDSAccess,
FeatureTrue16BitInsts, FeatureDefaultComponentBroadcast,
FeatureMaxHardClauseLength32,
FeatureAtomicFMinFMaxF32GlobalInsts, FeatureAtomicFMinFMaxF32FlatInsts
FeatureAtomicFMinFMaxF32GlobalInsts, FeatureAtomicFMinFMaxF32FlatInsts,
FeatureAgentScopeFineGrainedRemoteMemoryAtomics
]
>;

Expand Down Expand Up @@ -1415,7 +1426,8 @@ def FeatureISAVersion9_4_Common : FeatureSet<
FeatureBackOffBarrier,
FeatureKernargPreload,
FeatureAtomicFMinFMaxF64GlobalInsts,
FeatureAtomicFMinFMaxF64FlatInsts
FeatureAtomicFMinFMaxF64FlatInsts,
FeatureAgentScopeFineGrainedRemoteMemoryAtomics
]>;

def FeatureISAVersion9_4_0 : FeatureSet<
Expand Down
8 changes: 8 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 @@ -174,6 +174,7 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
bool HasAtomicBufferPkAddBF16Inst = false;
bool HasFlatAtomicFaddF32Inst = false;
bool HasDefaultComponentZero = false;
bool HasAgentScopeFineGrainedRemoteMemoryAtomics = false;
bool HasDefaultComponentBroadcast = false;
/// The maximum number of instructions that may be placed within an S_CLAUSE,
/// which is one greater than the maximum argument to S_CLAUSE. A value of 0
Expand Down Expand Up @@ -871,6 +872,13 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,

bool hasFlatAtomicFaddF32Inst() const { return HasFlatAtomicFaddF32Inst; }

/// \return true if atomic operations targeting fine-grained memory work
/// correctly at device scope, in allocations in host or peer PCIe device
/// memory.
bool supportsAgentScopeFineGrainedRemoteMemoryAtomics() const {
return HasAgentScopeFineGrainedRemoteMemoryAtomics;
}

bool hasDefaultComponentZero() const { return HasDefaultComponentZero; }

bool hasDefaultComponentBroadcast() const {
Expand Down
Loading