[SLP]Fix PR58863: Mask index beyond mask size for non-power-2 insertelement analysis.

Need to check if the insertelement mask size is reached during cost analysis to avoid compiler crash.

Differential Revision: https://reviews.llvm.org/D137639

diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 1449cec..2f0a93a 100644 (file)
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -6702,7 +6702,8 @@ InstructionCost BoUpSLP::getEntryCost(const TreeEntry *E,
           if (Mask[I] != UndefMaskElem)
             Mask[I] = I + VecSz;
         for (unsigned I = OffsetEnd + 1 - Offset; I < VecSz; ++I)
-          Mask[I] = InMask.test(I) ? UndefMaskElem : I;
+          Mask[I] =
+              ((I >= InMask.size()) || InMask.test(I)) ? UndefMaskElem : I;
         Cost += TTI->getShuffleCost(TTI::SK_PermuteTwoSrc, InsertVecTy, Mask);
       }
     }

diff --git a/llvm/test/Transforms/SLPVectorizer/slp-non-pow-2-insertelement.ll b/llvm/test/Transforms/SLPVectorizer/slp-non-pow-2-insertelement.ll
new file mode 100644 (file)
index 0000000..379022d
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/slp-non-pow-2-insertelement.ll
@@ -0,0 +1,19 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -passes=slp-vectorizer < %s | FileCheck %s
+
+define void @PR58863() {
+; CHECK-LABEL: @PR58863(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[MUL_I:%.*]] = fmul float poison, poison
+; CHECK-NEXT:    [[MUL11_I:%.*]] = fmul float poison, poison
+; CHECK-NEXT:    [[I:%.*]] = insertelement <3 x float> <float poison, float 0.000000e+00, float poison>, float [[MUL_I]], i64 0
+; CHECK-NEXT:    [[I1:%.*]] = insertelement <3 x float> [[I]], float [[MUL11_I]], i64 2
+; CHECK-NEXT:    ret void
+;
+entry:
+  %mul.i = fmul float poison, poison
+  %mul11.i = fmul float poison, poison
+  %i = insertelement <3 x float> <float poison, float 0.000000e+00, float poison>, float %mul.i, i64 0
+  %i1 = insertelement <3 x float> %i, float %mul11.i, i64 2
+  ret void
+}