Enable unroll for constant bound loops when TripCount is not modulo of unroll factor...

Commit for Evgeny Stupachenko (evstupac@gmail.com)

Differential Revision: http://reviews.llvm.org/D18290

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@265337 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Scalar/LoopUnrollPass.cpp b/lib/Transforms/Scalar/LoopUnrollPass.cpp
index c3761dc..fa6214f 100644 (file)
--- a/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -639,6 +639,16 @@ static bool tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI,
       Count = (std::max(UP.PartialThreshold, 3u) - 2) / (LoopSize - 2);
       while (Count != 0 && TripCount % Count != 0)
         Count--;
+      if (Count <= 1) {
+        // If there is no Count that is modulo of TripCount, set Count to
+        // largest power-of-two factor that satisfies the threshold limit.
+        Count = (std::max(UP.PartialThreshold, 3u) - 2) / (LoopSize - 2);
+        UnrolledSize = (LoopSize - 2) * Count + 2;
+        while (Count != 0 && UnrolledSize > UP.PartialThreshold) {
+          Count >>= 1;
+          UnrolledSize = (LoopSize - 2) * Count + 2;
+        }
+      }
     }
   } else if (Unrolling == Runtime) {
     if (!AllowRuntime && !CountSetExplicitly) {

diff --git a/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll b/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
new file mode 100644 (file)
index 0000000..04bee11
--- /dev/null
+++ b/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
@@ -0,0 +1,29 @@
+; RUN: opt < %s -S -unroll-threshold=20 -loop-unroll -unroll-allow-partial | FileCheck %s
+
+; The Loop TripCount is 9. However unroll factors 3 or 9 exceed given threshold.
+; The test checks that we choose a smaller, power-of-two, unroll count and do not give up on unrolling.
+
+; CHECK: for.body:
+; CHECK: store
+; CHECK: for.body.1:
+; CHECK: store
+
+define void @foo(i32* nocapture %a, i32* nocapture readonly %b) nounwind uwtable {
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %for.body, %entry
+  %indvars.iv = phi i64 [ 1, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+  %ld = load i32, i32* %arrayidx, align 4
+  %idxprom1 = sext i32 %ld to i64
+  %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %idxprom1
+  %st = trunc i64 %indvars.iv to i32
+  store i32 %st, i32* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 10
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body
+  ret void
+}