We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent d257cd8 commit 2f89c1cCopy full SHA for 2f89c1c
llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
@@ -906,11 +906,7 @@ unsigned getWavefrontSize(const MCSubtargetInfo *STI) {
906
}
907
908
unsigned getLocalMemorySize(const MCSubtargetInfo *STI) {
909
- unsigned BytesPerCU = 0;
910
- if (STI->getFeatureBits().test(FeatureLocalMemorySize32768))
911
- BytesPerCU = 32768;
912
- if (STI->getFeatureBits().test(FeatureLocalMemorySize65536))
913
- BytesPerCU = 65536;
+ unsigned BytesPerCU = getAddressableLocalMemorySize(STI);
914
915
// "Per CU" really means "per whatever functional block the waves of a
916
// workgroup must share". So the effective local memory size is doubled in
0 commit comments