[SVE] Fix invalid usage of getNumElements() in InstCombineMulDivRem
Summary:
getLogBase2 tries to iterate over the number of vector elements. Since
the number of elements of a scalable vector is unknown at compile time,
we must return null if the input type is scalable.
Identified by test LLVM.Transforms/InstCombine::nsw.ll
Reviewers: efriedma, fpetrogalli, kmclaughlin, spatel
Reviewed By: efriedma, fpetrogalli
Subscribers: tschuett, hiraditya, rkruppe, psnobl, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D79197
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp b/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
index 5eb281f..775c0e9 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
@@ -96,19 +96,21 @@
/// A helper routine of InstCombiner::visitMul().
///
-/// If C is a scalar/vector of known powers of 2, then this function returns
-/// a new scalar/vector obtained from logBase2 of C.
+/// If C is a scalar/fixed width vector of known powers of 2, then this
+/// function returns a new scalar/fixed width vector obtained from logBase2
+/// of C.
/// Return a null pointer otherwise.
static Constant *getLogBase2(Type *Ty, Constant *C) {
const APInt *IVal;
if (match(C, m_APInt(IVal)) && IVal->isPowerOf2())
return ConstantInt::get(Ty, IVal->logBase2());
- if (!Ty->isVectorTy())
+ // FIXME: We can extract pow of 2 of splat constant for scalable vectors.
+ if (!isa<FixedVectorType>(Ty))
return nullptr;
SmallVector<Constant *, 4> Elts;
- for (unsigned I = 0, E = cast<VectorType>(Ty)->getNumElements(); I != E;
+ for (unsigned I = 0, E = cast<FixedVectorType>(Ty)->getNumElements(); I != E;
++I) {
Constant *Elt = C->getAggregateElement(I);
if (!Elt)
diff --git a/llvm/test/Transforms/InstCombine/udiv-pow2-vscale.ll b/llvm/test/Transforms/InstCombine/udiv-pow2-vscale.ll
new file mode 100644
index 0000000..f8f9315
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/udiv-pow2-vscale.ll
@@ -0,0 +1,27 @@
+; RUN: opt -instcombine -S < %s | FileCheck %s
+
+; This vscale udiv with a power-of-2 spalt on the rhs should not crash opt
+
+; CHECK: define <vscale x 2 x i32> @udiv_pow2_vscale(<vscale x 2 x i32> %lhs)
+define <vscale x 2 x i32> @udiv_pow2_vscale(<vscale x 2 x i32> %lhs) {
+ %splatter = insertelement <vscale x 2 x i32> undef, i32 2, i32 0
+ %rhs = shufflevector <vscale x 2 x i32> %splatter,
+ <vscale x 2 x i32> undef,
+ <vscale x 2 x i32> zeroinitializer
+ %res = udiv <vscale x 2 x i32> %lhs, %rhs
+ ret <vscale x 2 x i32> %res
+}
+
+; This fixed width udiv with a power-of-2 splat on the rhs should also not
+; crash, and instcombine should eliminate the udiv
+
+; CHECK-LABEL: define <2 x i32> @udiv_pow2_fixed(<2 x i32> %lhs)
+; CHECK-NOT: udiv
+define <2 x i32> @udiv_pow2_fixed(<2 x i32> %lhs) {
+ %splatter = insertelement <2 x i32> undef, i32 2, i32 0
+ %rhs = shufflevector <2 x i32> %splatter,
+ <2 x i32> undef,
+ <2 x i32> zeroinitializer
+ %res = udiv <2 x i32> %lhs, %rhs
+ ret <2 x i32> %res
+}