summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp10
-rw-r--r--llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll29
2 files changed, 39 insertions, 0 deletions
diff --git a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
index c3761dcf4e8..fa6214f89f0 100644
--- a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/llvm/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/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll b/llvm/test/Transforms/LoopUnroll/partial-unroll-const-bounds.ll
new file mode 100644
index 00000000000..04bee115c2b
--- /dev/null
+++ b/llvm/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
+}
OpenPOWER on IntegriCloud