[PATCH] D155995: [AMDGPU]: Allow combining into v_dot4

[Jeffrey Byrnes via Phabricator via llvm-commits]

jrbyrnes added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:12364-12365
+      };
+      auto Match = std::find_if(Srcs.begin(), Srcs.end(), MatchesSecond);
+      if (Match != Srcs.end()) {
+        Match->second = addPermMasks(SecondMask, Match->second);
----------------
arsenm wrote:
> is_contained
We use the found value here


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:12493-12496
+        (LHS.getOpcode() == AMDGPUISD::MUL_I24 ||
+         LHS.getOpcode() == AMDGPUISD::MUL_U24 || LHS.getOpcode() == ISD::MUL)
+            ? 0
+            : 1;
----------------
arsenm wrote:
> Don't understand what you are doing with this opcode to index check
It is a convenience which allows getting the mul operand without having to do operand checks every time.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D155995/new/

https://reviews.llvm.org/D155995