[llvm] 5d7cf50 - [SLP]Fix PR108421: Correctly deduce VF from the masks

[Alexey Bataev via llvm-commits]

Author: Alexey Bataev
Date: 2024-09-12T13:43:44-07:00
New Revision: 5d7cf504ce02f387660ceaedf890c35cfd0ad55f

URL: https://github.com/llvm/llvm-project/commit/5d7cf504ce02f387660ceaedf890c35cfd0ad55f
DIFF: https://github.com/llvm/llvm-project/commit/5d7cf504ce02f387660ceaedf890c35cfd0ad55f.diff

LOG: [SLP]Fix PR108421: Correctly deduce VF from the masks

Need to select the max of CommonMask and V1 Mask size to correctly
perform reshuffling of the vectors, otherwise incorrect result is
generated.

Fixes https://github.com/llvm/llvm-project/issues/108421

Added: 
    

Modified: 
    llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
    llvm/test/Transforms/SLPVectorizer/X86/multi-extracts-bv-combined.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 00d9f2909d71e2..ac59ed3875c1e4 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -12486,11 +12486,12 @@ class BoUpSLP::ShuffleInstructionBuilder final : public BaseShuffleAnalysis {
           V = createShuffle(InVectors.front(), nullptr, CommonMask);
           transformMaskAfterShuffle(CommonMask, CommonMask);
         }
+        unsigned VF = std::max(CommonMask.size(), Mask.size());
         for (unsigned Idx = 0, Sz = CommonMask.size(); Idx < Sz; ++Idx)
           if (CommonMask[Idx] == PoisonMaskElem && Mask[Idx] != PoisonMaskElem)
             CommonMask[Idx] =
                 V->getType() != V1->getType()
-                    ? Idx + Sz
+                    ? Idx + VF
                     : Mask[Idx] + cast<FixedVectorType>(V1->getType())
                                       ->getNumElements();
         if (V->getType() != V1->getType())

diff  --git a/llvm/test/Transforms/SLPVectorizer/X86/multi-extracts-bv-combined.ll b/llvm/test/Transforms/SLPVectorizer/X86/multi-extracts-bv-combined.ll
index 18964a0824d5ee..e6a166c27ac494 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/multi-extracts-bv-combined.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/multi-extracts-bv-combined.ll
@@ -6,7 +6,7 @@ define i32 @foo() {
 ; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
 ; CHECK-NEXT:    [[D:%.*]] = load i32, ptr null, align 4
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> <i32 0, i32 undef, i32 1, i32 undef>, i32 [[D]], i32 1
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> <i32 0, i32 undef, i32 1, i32 0>, i32 [[D]], i32 1
 ; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    [[TMP2:%.*]] = or <8 x i32> zeroinitializer, [[TMP1]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = add <8 x i32> zeroinitializer, [[TMP1]]