[SVE] Fix TypeSize warning in llvm::getGEPInductionOperand

We do not need to use the implicit cast here. We can instead can rely on
a comparison between two TypeSize objects instead. This algorithm will
work fine with scalable vectors.

Reviewed By: DavidTruby

Differential Revision: https://reviews.llvm.org/D90146

diff --git a/llvm/lib/Analysis/VectorUtils.cpp b/llvm/lib/Analysis/VectorUtils.cpp
index 79be29c..e865087 100644 (file)
--- a/llvm/lib/Analysis/VectorUtils.cpp
+++ b/llvm/lib/Analysis/VectorUtils.cpp
@@ -136,7 +136,7 @@ Intrinsic::ID llvm::getVectorIntrinsicIDForCall(const CallInst *CI,
 unsigned llvm::getGEPInductionOperand(const GetElementPtrInst *Gep) {
   const DataLayout &DL = Gep->getModule()->getDataLayout();
   unsigned LastOperand = Gep->getNumOperands() - 1;
-  unsigned GEPAllocSize = DL.getTypeAllocSize(Gep->getResultElementType());
+  TypeSize GEPAllocSize = DL.getTypeAllocSize(Gep->getResultElementType());
 
   // Walk backwards and try to peel off zeros.
   while (LastOperand > 1 && match(Gep->getOperand(LastOperand), m_Zero())) {

diff --git a/llvm/test/Analysis/LoopAccessAnalysis/gep-induction-operand-typesize-warning.ll b/llvm/test/Analysis/LoopAccessAnalysis/gep-induction-operand-typesize-warning.ll
new file mode 100644 (file)
index 0000000..7e4e5ba
--- /dev/null
+++ b/llvm/test/Analysis/LoopAccessAnalysis/gep-induction-operand-typesize-warning.ll
@@ -0,0 +1,25 @@
+; RUN: opt -loop-load-elim -mtriple=aarch64--linux-gnu -mattr=+sve < %s 2>%t
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s < %t
+
+; This regression test is verifying that a GEP instruction performed on a
+; scalable vector does not produce a 'assumption that TypeSize is not scalable'
+; warning in the llvm::getGEPInductionOperand function.
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; WARN-NOT: warning: {{.*}}TypeSize is not scalable
+
+define void @get_gep_induction_operand_typesize_warning(i64 %n, <vscale x 4 x i32>* %a) {
+entry:
+  br label %loop.body
+
+loop.body:
+  %0 = phi i64 [ 0, %entry ], [ %1, %loop.body ]
+  %idx = getelementptr <vscale x 4 x i32>, <vscale x 4 x i32>* %a, i64 %0
+  store <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32>* %idx
+  %1 = add i64 %0, 1
+  %2 = icmp eq i64 %1, %n
+  br i1 %2, label %loop.end, label %loop.body
+
+loop.end:
+  ret void
+}