[llvm-branch-commits] [llvm] AMDGPU: Increase the LDS size to support to 160 KB for gfx950 (PR #116309)

[Jay Foad via llvm-branch-commits]

================
@@ -1494,7 +1494,8 @@ def FeatureISAVersion9_5_Common : FeatureSet<
   [FeatureFP8Insts,
    FeatureFP8ConversionInsts,
    FeatureCvtFP8VOP1Bug,
-   FeatureGFX950Insts
+   FeatureGFX950Insts,
+   FeatureAddressableLocalMemorySize163840
----------------
jayfoad wrote:

This means that gfx950 has both `FeatureAddressableLocalMemorySize65536` and 
`FeatureAddressableLocalMemorySize163840`, which seems like it should be 
disallowed in `GCNSubtarget::checkSubtargetFeatures`.

https://github.com/llvm/llvm-project/pull/116309
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits