[PATCH] D127904: [AMDGPU] gfx11 new dot instruction codegen support

[Joe Nash via Phabricator via llvm-commits]

Joe_Nash added inline comments.


================
Comment at: llvm/include/llvm/IR/IntrinsicsAMDGPU.td:1926
 
+// f16 %r = llvm.amdgcn.fdot2.f16.f16(v2f16 %a, v2f16 %b, f16 %c, i1 %clamp)
+//   %r = %a[0] * %b[0] + %a[1] * %b[1] + %c
----------------
rampitec wrote:
> I do not see clamp in the definition. Make a separate comment for the last 2?
I removed clamp from the comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.fdot2.f16.f16.ll:2
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=GFX11
+
----------------
arsenm wrote:
> Is there actually a reason to split the globalisel and DAG tests? I expect tests this simple to be identical
Ok, I have combined the tests and they are identical.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D127904/new/

https://reviews.llvm.org/D127904