[PATCH] D85446: [InstCombine] Add vector support to mul(add(x,c),negpow2) -> mul(sub(-c,x),pow2) folds

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri added inline comments.


================
Comment at: llvm/test/Transforms/InstCombine/mul.ll:976
 ; CHECK-LABEL: @muladd2_vec(
-; CHECK-NEXT:    [[TMP1:%.*]] = mul <2 x i32> [[A0:%.*]], <i32 -4, i32 -4>
-; CHECK-NEXT:    [[MUL:%.*]] = add <2 x i32> [[TMP1]], <i32 -64, i32 -64>
+; CHECK-NEXT:    [[SUBC_NEG:%.*]] = mul <2 x i32> [[A0:%.*]], <i32 -4, i32 -4>
+; CHECK-NEXT:    [[MUL:%.*]] = add <2 x i32> [[SUBC_NEG]], <i32 -64, i32 -64>
----------------
And another example that we need something like Negator-driven hoisting.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D85446/new/

https://reviews.llvm.org/D85446