LoopVectorize: Do not vectorize loops with tiny constant trip counts.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@167101 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoopVectorize.cpp b/lib/Transforms/Vectorize/LoopVectorize.cpp
index e82dfa2454fc9926ee89351db07673396e49f4e6..fd728bd6168ed02db8c3da1ba5d92ea3441e5393 100644 (file)
--- a/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -1145,6 +1145,14 @@ bool LoopVectorizationLegality::canVectorize() {
     return false;
   }
 
+  // Do not loop-vectorize loops with a tiny trip count.
+  unsigned TC = SE->getSmallConstantTripCount(TheLoop, BB);
+  if (TC > 0 && TC < 16) {
+    DEBUG(dbgs() << "LV: Found a loop with a very small trip count. " <<
+          "This loop is not worth vectorizing.\n");
+    return false;
+  }
+
   DEBUG(dbgs() << "LV: We can vectorize this loop!\n");
 
   // Okay! We can vectorize. At this point we don't have any other mem analysis

diff --git a/test/Transforms/LoopVectorize/small-loop.ll b/test/Transforms/LoopVectorize/small-loop.ll
new file mode 100644 (file)
index 0000000..4a6e4b2
--- /dev/null
+++ b/test/Transforms/LoopVectorize/small-loop.ll
@@ -0,0 +1,33 @@
+; RUN: opt < %s  -loop-vectorize -force-vector-width=4 -dce -instcombine -licm -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+@a = common global [2048 x i32] zeroinitializer, align 16
+@b = common global [2048 x i32] zeroinitializer, align 16
+@c = common global [2048 x i32] zeroinitializer, align 16
+
+;CHECK: @example1
+;CHECK-NOT: load <4 x i32>
+;CHECK: ret void
+define void @example1() 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]* @b, i64 0, i64 %indvars.iv
+  %3 = load i32* %2, align 4
+  %4 = getelementptr inbounds [2048 x i32]* @c, i64 0, i64 %indvars.iv
+  %5 = load i32* %4, align 4
+  %6 = add nsw i32 %5, %3
+  %7 = getelementptr inbounds [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
+  %exitcond = icmp eq i32 %lftr.wideiv, 8  ;   <-----  A really small trip count.
+  br i1 %exitcond, label %8, label %1
+
+; <label>:8                                       ; preds = %1
+  ret void
+}
+