diff options
| author | macurtis-amd <macurtis@amd.com> | 2025-10-21 05:47:26 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-10-21 05:47:26 -0500 |
| commit | 5440cfc4505ffd242d3a75633b92c355c245bcae (patch) | |
| tree | 93a84f00313c4bc164b57fcc3341907eef161f35 /clang/lib/Frontend/InitPreprocessor.cpp | |
| parent | 8d29d09309654541fb2861524276ada6a3ebf84c (diff) | |
[clang] Add support for cluster sync scope (#162575)
From Sam Liu:
>CUDA supports thread block clusters
https://docs.nvidia.com/cuda/cuda-c-programming-guide/#thread-block-clusters
>
>In their atomic intrinsics, cluster scope is supported
https://docs.nvidia.com/cuda/cuda-c-programming-guide/#nv-atomic-fetch-add-and-nv-atomic-add
>
>For compatibility, clang and hip needs to support cluster scope.
Diffstat (limited to 'clang/lib/Frontend/InitPreprocessor.cpp')
| -rw-r--r-- | clang/lib/Frontend/InitPreprocessor.cpp | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/clang/lib/Frontend/InitPreprocessor.cpp b/clang/lib/Frontend/InitPreprocessor.cpp index baad63179d89..47f1d5a6b636 100644 --- a/clang/lib/Frontend/InitPreprocessor.cpp +++ b/clang/lib/Frontend/InitPreprocessor.cpp @@ -585,6 +585,7 @@ static void InitializeStandardPredefinedMacros(const TargetInfo &TI, Builder.defineMacro("__HIP_MEMORY_SCOPE_WORKGROUP", "3"); Builder.defineMacro("__HIP_MEMORY_SCOPE_AGENT", "4"); Builder.defineMacro("__HIP_MEMORY_SCOPE_SYSTEM", "5"); + Builder.defineMacro("__HIP_MEMORY_SCOPE_CLUSTER", "6"); if (LangOpts.HIPStdPar) { Builder.defineMacro("__HIPSTDPAR__"); if (LangOpts.HIPStdParInterposeAlloc) { @@ -873,6 +874,7 @@ static void InitializePredefinedMacros(const TargetInfo &TI, Builder.defineMacro("__MEMORY_SCOPE_WRKGRP", "2"); Builder.defineMacro("__MEMORY_SCOPE_WVFRNT", "3"); Builder.defineMacro("__MEMORY_SCOPE_SINGLE", "4"); + Builder.defineMacro("__MEMORY_SCOPE_CLUSTR", "5"); // Define macros for the OpenCL memory scope. // The values should match AtomicScopeOpenCLModel::ID enum. |