[PATCH] D141544: [AMDGPU] Mark wmma intrinsics as source of divergence

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
rampitec added reviewers: arsenm, foad.
Herald added subscribers: kosarev, StephenFan, kerbowa, hiraditya, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
rampitec requested review of this revision.
Herald added a subscriber: wdng.
Herald added a project: LLVM.

I do not believe any code can hit this, but these do not give
a uniform answer with all unifirm sources.


https://reviews.llvm.org/D141544

Files:
  llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td


Index: llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
+++ llvm/lib/Target/AMDGPU/AMDGPUSearchableTables.td
@@ -362,6 +362,12 @@
 def : SourceOfDivergence<int_amdgcn_smfmac_f32_32x32x32_bf8_fp8>;
 def : SourceOfDivergence<int_amdgcn_smfmac_f32_32x32x32_fp8_bf8>;
 def : SourceOfDivergence<int_amdgcn_smfmac_f32_32x32x32_fp8_fp8>;
+def : SourceOfDivergence<int_amdgcn_wmma_f32_16x16x16_f16>;
+def : SourceOfDivergence<int_amdgcn_wmma_f32_16x16x16_bf16>;
+def : SourceOfDivergence<int_amdgcn_wmma_f16_16x16x16_f16>;
+def : SourceOfDivergence<int_amdgcn_wmma_bf16_16x16x16_bf16>;
+def : SourceOfDivergence<int_amdgcn_wmma_i32_16x16x16_iu8>;
+def : SourceOfDivergence<int_amdgcn_wmma_i32_16x16x16_iu4>;
 
 // The dummy boolean output is divergent from the IR's perspective,
 // but the mask results are uniform. These produce a divergent and


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D141544.488362.patch
Type: text/x-patch
Size: 960 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230111/47b54b37/attachment.bin>