[PATCH] D130364: [LV] Recognize store of invariant value to invariant address as uniform

Wed Jul 27 07:43:21 PDT 2022

reames added inline comments.

================
Comment at: llvm/test/Transforms/LoopVectorize/X86/consecutive-ptr-uniforms.ll:96
 ; FORCE-NEXT:    [[TMP2:%.*]] = icmp ule <2 x i32> [[VEC_IND]], <i32 2, i32 2>
+; FORCE-NEXT:    store i32 [[TMP0]], i32* @b, align 1
+; FORCE-NEXT:    store i32 [[TMP1]], i32* @b, align 1
----------------
fhahn wrote:
> reames wrote:
> > david-arm wrote:
> > > Hi @reames, something doesn't look right about this change because each store instruction is storing out a different value.
> > This is correct, but not directly related to the thrust of the patch.  This is a side effect of the change in isScalarWithPredication.  We'd previously been considering these stores to be predicated.  They are unconditional in the original IR, so this should be correct.
> > 
> > If you want, I can split the patch further to do a pre-change with just the change in isScalarWithPredication.  
> Yeah it would probably be good to split off the change to ‘ isPredicatedInst’, especially if it reduces the test changes per patch
Split off as https://reviews.llvm.org/D130637.  Will rebase this once that lands.

This did turn out to be more test churn than I'd realized.  Clearly should have split that from the start.  Oh well.  

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130364/new/

https://reviews.llvm.org/D130364