[LV] Don't vectorize when we have a small static bound on trip count

We currently check if the exact trip count is known and is smaller than the
"tiny loop" bound. We should be checking the maximum bound on the trip count
instead.

Differential Revision: https://reviews.llvm.org/D27690

llvm-svn: 289583

2 files changed, 27 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index a7f20051818..33f269d51b7 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7382,8 +7382,8 @@ bool LoopVectorizePass::processLoop(Loop *L) {
 
   // Check the loop for a trip count threshold:
   // do not vectorize loops with a tiny trip count.
-  const unsigned TC = SE->getSmallConstantTripCount(L);
-  if (TC > 0u && TC < TinyTripCountVectorThreshold) {
+  const unsigned MaxTC = SE->getSmallConstantMaxTripCount(L);
+  if (MaxTC > 0u && MaxTC < TinyTripCountVectorThreshold) {
     DEBUG(dbgs() << "LV: Found a loop with a very small trip count. "
                  << "This loop is not worth vectorizing.");
     if (Hints.getForce() == LoopVectorizeHints::FK_Enabled)
diff --git a/llvm/test/Transforms/LoopVectorize/small-loop.ll b/llvm/test/Transforms/LoopVectorize/small-loop.ll
index 01bf54b87af..9a5dc4aa1b7 100644
--- a/llvm/test/Transforms/LoopVectorize/small-loop.ll
+++ b/llvm/test/Transforms/LoopVectorize/small-loop.ll
@@ -30,3 +30,28 @@ define void @example1() nounwind uwtable ssp {
   ret void
 }
 
+;CHECK-LABEL: @bound1(
+;CHECK-NOT: load <4 x i32>
+;CHECK: ret void
+define void @bound1(i32 %k) nounwind uwtable ssp {
+  br label %1
+
+; <label>:1                                       ; preds = %1, %0
+  %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
+  %2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %indvars.iv
+  %3 = load i32, i32* %2, align 4
+  %4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %indvars.iv
+  %5 = load i32, i32* %4, align 4
+  %6 = add nsw i32 %5, %3
+  %7 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %indvars.iv
+  store i32 %6, i32* %7, align 4
+  %indvars.iv.next = add i64 %indvars.iv, 1
+  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+  %large = icmp sge i32 %lftr.wideiv, 8
+  %exitcond = icmp eq i32 %lftr.wideiv, %k
+  %realexit = or i1 %large, %exitcond 
+  br i1 %realexit, label %8, label %1
+
+; <label>:8                                       ; preds = %1
+  ret void
+}