Index: lib/IR/ConstantFold.cpp =================================================================== --- lib/IR/ConstantFold.cpp +++ lib/IR/ConstantFold.cpp @@ -534,7 +534,8 @@ // If the cast operand is a constant expression, there's a few things we can // do to try to simplify it. - if (ConstantExpr *CE = dyn_cast(V)) { + ConstantExpr *CE = dyn_cast(V); + if (CE && !DestTy->isVectorTy()) { if (CE->isCast()) { // Try hard to fold cast of cast because they are often eliminable. if (unsigned newOpc = foldConstantCastPair(opc, CE, DestTy)) Index: test/Transforms/LoopVectorize/X86/constant-fold.ll =================================================================== --- test/Transforms/LoopVectorize/X86/constant-fold.ll +++ test/Transforms/LoopVectorize/X86/constant-fold.ll @@ -2,7 +2,6 @@ ; RUN: opt -loop-vectorize -S -mtriple=x86_64-- -o - %s | FileCheck %s ; Testcase that point out faulty bitcast that cast between different sizes. -; See "bitcast ([1 x %rec8]* @a to <2 x i16*>)" in checks below %rec8 = type { i16 } @@ -28,7 +27,7 @@ ; CHECK-NEXT: [[TMP3:%.*]] = getelementptr [2 x i16*], [2 x i16*]* @b, i16 0, i64 [[TMP2]] ; CHECK-NEXT: [[TMP4:%.*]] = getelementptr i16*, i16** [[TMP3]], i32 0 ; CHECK-NEXT: [[TMP5:%.*]] = bitcast i16** [[TMP4]] to <2 x i16*>* -; CHECK-NEXT: store <2 x i16*> bitcast ([1 x %rec8]* @a to <2 x i16*>), <2 x i16*>* [[TMP5]], align 8 +; CHECK-NEXT: store <2 x i16*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i16> zeroinitializer, <2 x i64> zeroinitializer), i32 0), i32 0, i32 0), i16* getelementptr inbounds (%rec8, %rec8* extractelement (<2 x %rec8*> getelementptr ([1 x %rec8], [1 x %rec8]* @a, <2 x i16> zeroinitializer, <2 x i64> zeroinitializer), i32 1), i32 0, i32 0)>, <2 x i16*>* [[TMP5]], align 8 ; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 2 ; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], 2 ; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0