[PATCH] D93594: [X86] Pass to transform amx intrinsics to scalar operation.

Mon Dec 21 04:05:10 PST 2020

LuoYuanke added inline comments.

================
Comment at: llvm/lib/Target/X86/X86TargetMachine.cpp:415
+
+  if (TM->getOptLevel() == CodeGenOpt::None)
+    addPass(createX86LowerAMXIntrinsicsPass());
----------------
craig.topper wrote:
> I don't think you can detect O0 this way. A function can have the optnone attribute in the non-O0 pipeline and won't be optimized by the middle end.
> 
> This can occur if you mix an 00 translation unit and an O3 translation unit in LTO and use O3 for the LTO pipeline.
@craig.topper, thank you! How about to check "optnone" attribute in X86LowerAMXIntrinsicsPass and determine if the amx intrinsics in the function need to be scalarized?

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D93594/new/

https://reviews.llvm.org/D93594