diff options
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp index bcc7dedf3229..fa77b94fc22d 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp @@ -432,7 +432,7 @@ std::pair<unsigned, unsigned> AMDGPUSubtarget::getEffectiveWavesPerEU( std::pair<unsigned, unsigned> Default(1, getMaxWavesPerEU()); // If minimum/maximum flat work group sizes were explicitly requested using - // "amdgpu-flat-work-group-size" attribute, then set default minimum/maximum + // "amdgpu-flat-workgroup-size" attribute, then set default minimum/maximum // number of waves per execution unit to values implied by requested // minimum/maximum flat work group sizes. unsigned MinImpliedByFlatWorkGroupSize = @@ -1108,3 +1108,8 @@ void GCNUserSGPRUsageInfo::allocKernargPreloadSGPRs(unsigned NumSGPRs) { unsigned GCNUserSGPRUsageInfo::getNumFreeUserSGPRs() { return AMDGPU::getMaxNumUserSGPRs(ST) - NumUsedUserSGPRs; } + +SmallVector<unsigned> +AMDGPUSubtarget::getMaxNumWorkGroups(const Function &F) const { + return AMDGPU::getIntegerVecAttribute(F, "amdgpu-max-num-workgroups", 3); +} |