[SVE][CodeGen] Fix InlineFunction for scalable vectors

[david-arm]

Summary

When inlining functions containing allocas of scalable vectors we
cannot specify the size in the lifetime markers, since we don't
know this at compile time.

Added new test here:

test/Transforms/Inline/AArch64/sve-alloca-merge.ll

[kmclaughlin]

LGTM

llvm/lib/Transforms/Utils/InlineFunction.cpp

for (unsigned ai = 0, ae = IFI.StaticAllocas.size(); ai != ae; ++ai) {
         continue;
 
       // Try to determine the size of the allocation.
       ConstantInt *AllocaSize = nullptr;
       if (ConstantInt *AIArraySize =
           dyn_cast<ConstantInt>(AI->getArraySize())) {
         auto &DL = Caller->getParent()->getDataLayout();
         Type *AllocaType = AI->getAllocatedType();
-        uint64_t AllocaTypeSize = DL.getTypeAllocSize(AllocaType);
+        TypeSize AllocaTypeSize = DL.getTypeAllocSize(AllocaType);
         uint64_t AllocaArraySize = AIArraySize->getLimitedValue();
 
         // Don't add markers for zero-sized allocas.
         if (AllocaArraySize == 0)
           continue;
 
         // Check that array size doesn't saturate uint64_t and doesn't
         // overflow when it's multiplied by type size.
-        if (AllocaArraySize != std::numeric_limits<uint64_t>::max() &&
+        if (!AllocaTypeSize.isScalable() &&
+            AllocaArraySize != std::numeric_limits<uint64_t>::max() &&
             std::numeric_limits<uint64_t>::max() / AllocaArraySize >=
-                AllocaTypeSize) {
+                AllocaTypeSize.getFixedSize()) {
           AllocaSize = ConstantInt::get(Type::getInt64Ty(AI->getContext()),
                                         AllocaArraySize * AllocaTypeSize);
         }
       }
 
       builder.CreateLifetimeStart(AI, AllocaSize);
       for (ReturnInst *RI : Returns) {
         // Don't insert llvm.lifetime.end calls between a musttail or deoptimize

llvm/test/Transforms/Inline/AArch64/sve-alloca-merge.ll

+; RUN: opt -mtriple=aarch64--linux-gnu -mattr=+sve < %s -inline -S | FileCheck %s
+
+define void @bar(<vscale x 2 x i64>* %a) {
+entry:
+  %b = alloca <vscale x 2 x i64>, align 16
+  store <vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64>* %b, align 16
+  %c = load <vscale x 2 x i64>, <vscale x 2 x i64>* %a, align 16
+  %d = load <vscale x 2 x i64>, <vscale x 2 x i64>* %b, align 16
+  %e = add <vscale x 2 x i64> %c, %d
+  %f = add <vscale x 2 x i64> %e, %c
+  store <vscale x 2 x i64> %f, <vscale x 2 x i64>* %a, align 16
+  ret void
+}
+
+define i64 @foo() {
+; CHECK-LABEL: @foo(
+; CHECK: %0 = bitcast <vscale x 2 x i64>* %{{.*}} to i8*
+; CHECK-NEXT: call void @llvm.lifetime.start.p0i8(i64 -1, i8* %0)
+; CHECK: %1 = bitcast <vscale x 2 x i64>* %{{.*}} to i8*
+; CHECK-NEXT: call void @llvm.lifetime.end.p0i8(i64 -1, i8* %1)
+entry:
+  %a = alloca <vscale x 2 x i64>, align 16
+  store <vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64>* %a, align 16
+  %a1 = bitcast <vscale x 2 x i64>* %a to i64*
+  store i64 1, i64* %a1, align 8
+  call void @bar(<vscale x 2 x i64>* %a)
+  %el = load i64, i64* %a1
+  ret i64 %el
+}