[PATCH] D156647: [AMDGPU] Extend f32 support for llvm.amdgcn.update.dpp intrinsic

Mon Jul 31 13:45:17 PDT 2023

arsenm requested changes to this revision.
arsenm added a comment.
This revision now requires changes to proceed.

Did you run the clang tests? I expect this would break the builtin test

================
Comment at: llvm/test/CodeGen/AMDGPU/llvm.amdgcn.update.dpp.ll:114
+define amdgpu_kernel void @dpp_test_f32(ptr addrspace(1) %out, float %in1, float %in2) {
+  %tmp0 = call float @llvm.amdgcn.update.dpp.f32(float %in1, float %in2, i32 1, i32 1, i32 1, i1 0) #0
+  store float %tmp0, ptr addrspace(1) %out
----------------
Add tests with the different immediate operands exercised

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156647/new/

https://reviews.llvm.org/D156647