[PATCH] D140208: [AMDGPU] Improved wide multiplies

[Thomas Symalla via Phabricator via llvm-commits]

tsymalla added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:2892-2897
+void AMDGPULegalizerInfo::buildMultiply(LegalizerHelper &Helper,
+                                        MutableArrayRef<Register> Accum,
+                                        ArrayRef<Register> Src0,
+                                        ArrayRef<Register> Src1,
+                                        bool UsePartialMad64_32,
+                                        bool SeparateOddAlignedProducts) const {
----------------
OutOfCache wrote:
> nhaehnle wrote:
> > Did you run clang-format on this? Usually it chooses a different layout.
> I did. It even caused failing pre-merge checks if I remember correctly. I ran clang-format again and this is still the result.
You can try clang-format -style=file:path and see if this changes something. I think you can also manually invoke git-clang-format to see if anything would have been changed by clang-format.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D140208/new/

https://reviews.llvm.org/D140208