[LV] Clamp the VF to the trip count

Summary:
When the MaxVectorSize > ConstantTripCount, we should just clamp the
vectorization factor to be the ConstantTripCount.
This vectorizes loops where the TinyTripCountThreshold >= TripCount < MaxVF.

Earlier we were finding the maximum vector width, which could be greater than
the trip count itself. The Loop vectorizer does all the work for generating a
vectorizable loop, but in the end we would always choose the scalar loop (since
the VF > trip count). This allows us to choose the VF keeping in mind the trip
count if available.

This is a fix on top of rL312472.

Reviewers: Ayal, zvi, hfinkel, dneilson

Reviewed by: Ayal

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D37702

llvm-svn: 313046

1 files changed, 26 insertions, 0 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll b/llvm/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
index a32cc46e913..4e7880d09d6 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/vector_max_bandwidth.ll
@@ -46,3 +46,29 @@ for.body:
   %exitcond = icmp eq i64 %indvars.iv.next, 1000
   br i1 %exitcond, label %for.cond.cleanup, label %for.body
 }
+
+; We should not choose a VF larger than the constant TC.
+; VF chosen should be atmost 16 (not the max possible vector width = 32 for AVX2)
+define void @not_too_small_tc(i8* noalias nocapture %A, i8* noalias nocapture readonly %B) {
+; CHECK-LABEL: not_too_small_tc
+; CHECK-AVX2: LV: Selecting VF: 16.
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i8, i8* %B, i64 %indvars.iv
+  %l1 = load i8, i8* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+  %arrayidx2 = getelementptr inbounds i8, i8* %A, i64 %indvars.iv
+  %l2 = load i8, i8* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %add = add i8 %l1, %l2
+  store i8 %add, i8* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 16
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !4
+
+for.end:
+  ret void
+}
+!3 = !{!3}
+!4 = !{!4}