[InstCombine] Handle vector compares in foldGEPIcmp()

Summary:
This is to fix PR38984 "InstCombine assertion at vector gep/icmp folding":
https://bugs.llvm.org/show_bug.cgi?id=38984

Reviewers: majnemer, spatel, lattner, lebedev.ri

Reviewed By: lebedev.ri

Subscribers: lebedev.ri, llvm-commits

Differential Revision: https://reviews.llvm.org/D52263

llvm-svn: 342647

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 0cb92e0..dd3fed7 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -976,7 +976,7 @@ Instruction *InstCombiner::foldGEPICmp(GEPOperator *GEPLHS, Value *RHS,
 
       if (NumDifferences == 0)   // SAME GEP?
         return replaceInstUsesWith(I, // No comparison is needed here.
-                             Builder.getInt1(ICmpInst::isTrueWhenEqual(Cond)));
+          ConstantInt::get(I.getType(), ICmpInst::isTrueWhenEqual(Cond)));
 
       else if (NumDifferences == 1 && GEPsInBounds) {
         Value *LHSV = GEPLHS->getOperand(DiffOperand);

diff --git a/llvm/test/Transforms/InstCombine/pr38984.ll b/llvm/test/Transforms/InstCombine/pr38984.ll
new file mode 100644 (file)
index 0000000..2da2f9f
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/pr38984.ll
@@ -0,0 +1,25 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -instcombine -S | FileCheck %s
+target datalayout = "p:16:16"
+
+@offsets = external dso_local global [4 x i16], align 1
+
+define void @PR38984() {
+; CHECK-LABEL: @PR38984(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %0 = load i16, i16* getelementptr ([4 x i16], [4 x i16]* @offsets, i16 0, i16 undef), align 1
+  %1 = insertelement <4 x i16> undef, i16 %0, i32 3
+  %2 = sub <4 x i16> zeroinitializer, %1
+  %3 = sext <4 x i16> %2 to <4 x i32>
+  %4 = getelementptr inbounds i64, i64* null, <4 x i32> %3
+  %5 = ptrtoint <4 x i64*> %4 to <4 x i32>
+  %6 = getelementptr inbounds i64, i64* null, <4 x i16> %2
+  %7 = ptrtoint <4 x i64*> %6 to <4 x i32>
+  %8 = icmp eq <4 x i32> %5, %7
+  %9 = select <4 x i1> %8, <4 x i16> zeroinitializer, <4 x i16> <i16 1, i16 1, i16 1, i16 1>
+  %10 = sext <4 x i16> %9 to <4 x i32>
+  ret void
+}