[PATCH] D107364: [VectorCombine] Limit scalarization known non-poison indices.

[Florian Hahn via Phabricator via llvm-commits]

fhahn updated this revision to Diff 364440.
fhahn added a comment.

rebased after adding additional tests in 8d2a8ced00dc45605cb85 <https://reviews.llvm.org/rG8d2a8ced00dc45605cb856845385d289e8cc45ed>.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D107364/new/

https://reviews.llvm.org/D107364

Files:
  llvm/lib/Transforms/Vectorize/VectorCombine.cpp
  llvm/test/Transforms/VectorCombine/load-insert-store.ll


Index: llvm/test/Transforms/VectorCombine/load-insert-store.ll
===================================================================
--- llvm/test/Transforms/VectorCombine/load-insert-store.ll
+++ llvm/test/Transforms/VectorCombine/load-insert-store.ll
@@ -310,9 +310,10 @@
 define void @insert_store_nonconst_index_known_valid_by_and_but_may_be_poison(<16 x i8>* %q, i8 zeroext %s, i32 %idx) {
 ; CHECK-LABEL: @insert_store_nonconst_index_known_valid_by_and_but_may_be_poison(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i8>, <16 x i8>* [[Q:%.*]], align 16
 ; CHECK-NEXT:    [[IDX_CLAMPED:%.*]] = and i32 [[IDX:%.*]], 7
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[Q:%.*]], i32 0, i32 [[IDX_CLAMPED]]
-; CHECK-NEXT:    store i8 [[S:%.*]], i8* [[TMP0]], align 1
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <16 x i8> [[TMP0]], i8 [[S:%.*]], i32 [[IDX_CLAMPED]]
+; CHECK-NEXT:    store <16 x i8> [[VECINS]], <16 x i8>* [[Q]], align 16
 ; CHECK-NEXT:    ret void
 ;
 entry:
@@ -412,9 +413,10 @@
 define void @insert_store_nonconst_index_known_valid_by_urem_but_may_be_poison(<16 x i8>* %q, i8 zeroext %s, i32 %idx) {
 ; CHECK-LABEL: @insert_store_nonconst_index_known_valid_by_urem_but_may_be_poison(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i8>, <16 x i8>* [[Q:%.*]], align 16
 ; CHECK-NEXT:    [[IDX_CLAMPED:%.*]] = urem i32 [[IDX:%.*]], 16
-; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[Q:%.*]], i32 0, i32 [[IDX_CLAMPED]]
-; CHECK-NEXT:    store i8 [[S:%.*]], i8* [[TMP0]], align 1
+; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <16 x i8> [[TMP0]], i8 [[S:%.*]], i32 [[IDX_CLAMPED]]
+; CHECK-NEXT:    store <16 x i8> [[VECINS]], <16 x i8>* [[Q]], align 16
 ; CHECK-NEXT:    ret void
 ;
 entry:
Index: llvm/lib/Transforms/Vectorize/VectorCombine.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/VectorCombine.cpp
+++ llvm/lib/Transforms/Vectorize/VectorCombine.cpp
@@ -781,6 +781,9 @@
   if (auto *C = dyn_cast<ConstantInt>(Idx))
     return C->getValue().ult(VecTy->getNumElements());
 
+  if (!isGuaranteedNotToBePoison(Idx, &AC))
+    return false;
+
   APInt Zero(Idx->getType()->getScalarSizeInBits(), 0);
   APInt MaxElts(Idx->getType()->getScalarSizeInBits(), VecTy->getNumElements());
   ConstantRange ValidIndices(Zero, MaxElts);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D107364.364440.patch
Type: text/x-patch
Size: 2418 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210805/b373041e/attachment.bin>