diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp --- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp +++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp @@ -11831,6 +11831,11 @@ PreExtendType != MVT::i32) return SDValue(); + bool IsAssert = + ExtendOpcode == ISD::AssertSext || ExtendOpcode == ISD::AssertZext; + if (IsAssert && Extend.getValueType() == MVT::i64) + return SDValue(); + EVT PreExtendVT = TargetType.changeVectorElementType(PreExtendType); if (PreExtendVT.getVectorElementCount() != TargetType.getVectorElementCount()) diff --git a/llvm/test/CodeGen/AArch64/aarch64-dup-ext-crash.ll b/llvm/test/CodeGen/AArch64/aarch64-dup-ext-crash.ll new file mode 100644 --- /dev/null +++ b/llvm/test/CodeGen/AArch64/aarch64-dup-ext-crash.ll @@ -0,0 +1,33 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -o -| FileCheck %s + +target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128" +target triple = "aarch64-unknown-linux-gnu" + +; This test covers a case where an AArch64 DUP instruction is generated with an +; invalid encoding, resulting in a crash. We don't care about the specific output +; here, only that this case no longer causes said crash. +define dso_local i32 @dupext_crashtest(i32 %e) local_unnamed_addr { +; CHECK-LABEL: dupext_crashtest: +for.body.lr.ph: + %conv314 = zext i32 %e to i64 + br label %vector.memcheck + +vector.memcheck: ; preds = %for.body.lr.ph + br label %vector.ph + +vector.ph: ; preds = %vector.memcheck + %broadcast.splatinsert = insertelement <2 x i64> poison, i64 %conv314, i32 0 + %broadcast.splat = shufflevector <2 x i64> %broadcast.splatinsert, <2 x i64> poison, <2 x i32> zeroinitializer + br label %vector.body + +vector.body: ; preds = %vector.body, %vector.ph + %wide.load = load <2 x i32>, <2 x i32>* undef, align 4 + %0 = zext <2 x i32> %wide.load to <2 x i64> + %1 = mul nuw <2 x i64> %broadcast.splat, %0 + %2 = trunc <2 x i64> %1 to <2 x i32> + %3 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> %2 + %4 = bitcast i32* undef to <2 x i32>* + store <2 x i32> %3, <2 x i32>* %4, align 4 + br label %vector.body +} \ No newline at end of file