[LAA] Support memchecks involving loop-invariant addresses

We used to only allow SCEVAddRecExpr for pointer expressions in order to
be able to compute the bounds.  However this is also trivially possible
for loop-invariant addresses (scUnknown) since then the bounds are the
address itself.

Interestingly, we used allow this for the special case when the
loop-invariant address happens to also be an SCEVAddRecExpr (in an outer
loop).

There are a couple more loops that are vectorized in SPEC after this.
My guess is that the main reason we don't see more because for example a
loop-invariant load is vectorized into a splat vector with several
vector-inserts.  This is likely to make the vectorization unprofitable.
I.e. we don't notice that a later LICM will move all of this out of the
loop so the cost estimate should really be 0.

llvm-svn: 264243

1 files changed, 38 insertions, 0 deletions

diff --git a/llvm/test/Analysis/LoopAccessAnalysis/memcheck-for-loop-invariant.ll b/llvm/test/Analysis/LoopAccessAnalysis/memcheck-for-loop-invariant.ll
new file mode 100644
index 00000000000..a39a1741048
--- /dev/null
+++ b/llvm/test/Analysis/LoopAccessAnalysis/memcheck-for-loop-invariant.ll
@@ -0,0 +1,38 @@
+; RUN: opt -loop-accesses -analyze < %s | FileCheck %s
+
+; Handle memchecks involving loop-invariant addresses:
+;
+; extern int *A, *b;
+; for (i = 0; i < N; ++i) {
+;  A[i] = b;
+; }
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+
+; CHECK: Memory dependences are safe with run-time checks
+; CHECK: Run-time memory checks:
+; CHECK-NEXT: Check 0:
+; CHECK-NEXT:   Comparing group ({{.*}}):
+; CHECK-NEXT:     %arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
+; CHECK-NEXT:   Against group ({{.*}}):
+; CHECK-NEXT:   i32* %b
+
+define void @f(i32* %a, i32* %b) {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %ind = phi i64 [ 0, %entry ], [ %inc, %for.body ]
+
+  %arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
+
+  %loadB = load i32, i32* %b, align 4
+  store i32 %loadB, i32* %arrayidxA, align 4
+
+  %inc = add nuw nsw i64 %ind, 1
+  %exitcond = icmp eq i64 %inc, 20
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}