[PATCH] D27690: [LV] Don't vectorize when we have a static bound on trip count

[Michael Kuperstein via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL289583: [LV] Don't vectorize when we have a small static bound on trip count (authored by mkuper).

Changed prior to commit:
  https://reviews.llvm.org/D27690?vs=81155&id=81285#toc

Repository:
  rL LLVM

https://reviews.llvm.org/D27690

Files:
  llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/trunk/test/Transforms/LoopVectorize/small-loop.ll


Index: llvm/trunk/test/Transforms/LoopVectorize/small-loop.ll
===================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/small-loop.ll
+++ llvm/trunk/test/Transforms/LoopVectorize/small-loop.ll
@@ -30,3 +30,28 @@
   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
+}
Index: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7382,8 +7382,8 @@
 
   // 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)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D27690.81285.patch
Type: text/x-patch
Size: 2083 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20161213/85fb4728/attachment.bin>