[PATCH] D148628: [NewPM][AMDGPU] Port amdgpu-atomic-optimizer

[Pravin Jagtap via Phabricator via llvm-commits]

pravinjagtap added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/global-atomic-scan.ll:2
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN:  opt -S -mtriple=amdgcn-- -passes=amdgpu-atomic-optimizer -verify-machineinstrs %s | FileCheck -check-prefix=IR %s
+
----------------
arsenm wrote:
> Don't know why this is introducing a new test. also drop -verify-machineinstrs, it won't do anything for opt 
> Don't know why this is introducing a new test

Currently there are no tests for atomic optimizer which runs in isolation i.e., only `amdgpu-atomic-optimizer` pass alone. All existing tests runs complete pipeline.




Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D148628/new/

https://reviews.llvm.org/D148628