summaryrefslogtreecommitdiff
path: root/test
diff options
context:
space:
mode:
authorAndrew Trick <atrick@apple.com>2011-12-09 06:19:40 +0000
committerAndrew Trick <atrick@apple.com>2011-12-09 06:19:40 +0000
commit5d73448bb7f3d326f310e6f35030821b103b1cdb (patch)
tree559f8f027346d2270472463686fa54187721d8d5 /test
parent9c181a92d8bc7af36839520c3e145bf11a6193fa (diff)
downloadllvm-5d73448bb7f3d326f310e6f35030821b103b1cdb.tar.gz
llvm-5d73448bb7f3d326f310e6f35030821b103b1cdb.tar.bz2
llvm-5d73448bb7f3d326f310e6f35030821b103b1cdb.tar.xz
Add -unroll-runtime for unrolling loops with run-time trip counts.
Patch by Brendon Cahoon! This extends the existing LoopUnroll and LoopUnrollPass. Brendon measured no regressions in the llvm test suite with -unroll-runtime enabled. This implementation works by using the existing loop unrolling code to unroll the loop by a power-of-two (default 8). It generates an if-then-else sequence of code prior to the loop to execute the extra iterations before entering the unrolled loop. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146245 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
-rw-r--r--test/Transforms/LoopUnroll/runtime-loop.ll109
-rw-r--r--test/Transforms/LoopUnroll/runtime-loop1.ll30
-rw-r--r--test/Transforms/LoopUnroll/runtime-loop2.ll31
-rw-r--r--test/Transforms/LoopUnroll/runtime-loop3.ll44
4 files changed, 214 insertions, 0 deletions
diff --git a/test/Transforms/LoopUnroll/runtime-loop.ll b/test/Transforms/LoopUnroll/runtime-loop.ll
new file mode 100644
index 0000000000..d8bbea9f10
--- /dev/null
+++ b/test/Transforms/LoopUnroll/runtime-loop.ll
@@ -0,0 +1,109 @@
+; RUN: opt < %s -S -loop-unroll -unroll-runtime=true | FileCheck %s
+
+; Tests for unrolling loops with run-time trip counts
+
+; CHECK: unr.cmp{{.*}}:
+; CHECK: for.body.unr{{.*}}:
+; CHECK: for.body:
+; CHECK: br i1 %exitcond.7, label %for.end.loopexit{{.*}}, label %for.body
+
+define i32 @test(i32* nocapture %a, i32 %n) nounwind uwtable readonly {
+entry:
+ %cmp1 = icmp eq i32 %n, 0
+ br i1 %cmp1, label %for.end, label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+ %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+ %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+ %0 = load i32* %arrayidx, align 4
+ %add = add nsw i32 %0, %sum.02
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, %n
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
+ ret i32 %sum.0.lcssa
+}
+
+
+; Still try to completely unroll loops with compile-time trip counts
+; even if the -unroll-runtime is specified
+
+; CHECK: for.body:
+; CHECK-NOT: for.body.unr:
+
+define i32 @test1(i32* nocapture %a) nounwind uwtable readonly {
+entry:
+ br label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %sum.01 = phi i32 [ 0, %entry ], [ %add, %for.body ]
+ %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+ %0 = load i32* %arrayidx, align 4
+ %add = add nsw i32 %0, %sum.01
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, 5
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret i32 %add
+}
+
+; This is test 2007-05-09-UnknownTripCount.ll which can be unrolled now
+; if the -unroll-runtime option is turned on
+
+; CHECK: bb72.2:
+
+define void @foo(i32 %trips) {
+entry:
+ br label %cond_true.outer
+
+cond_true.outer:
+ %indvar1.ph = phi i32 [ 0, %entry ], [ %indvar.next2, %bb72 ]
+ br label %bb72
+
+bb72:
+ %indvar.next2 = add i32 %indvar1.ph, 1
+ %exitcond3 = icmp eq i32 %indvar.next2, %trips
+ br i1 %exitcond3, label %cond_true138, label %cond_true.outer
+
+cond_true138:
+ ret void
+}
+
+
+; Test run-time unrolling for a loop that counts down by -2.
+
+; CHECK: for.body.unr:
+; CHECK: br i1 %cmp.7, label %for.cond.for.end_crit_edge{{.*}}, label %for.body
+
+define zeroext i16 @down(i16* nocapture %p, i32 %len) nounwind uwtable readonly {
+entry:
+ %cmp2 = icmp eq i32 %len, 0
+ br i1 %cmp2, label %for.end, label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %p.addr.05 = phi i16* [ %incdec.ptr, %for.body ], [ %p, %entry ]
+ %len.addr.04 = phi i32 [ %sub, %for.body ], [ %len, %entry ]
+ %res.03 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+ %incdec.ptr = getelementptr inbounds i16* %p.addr.05, i64 1
+ %0 = load i16* %p.addr.05, align 2
+ %conv = zext i16 %0 to i32
+ %add = add i32 %conv, %res.03
+ %sub = add nsw i32 %len.addr.04, -2
+ %cmp = icmp eq i32 %sub, 0
+ br i1 %cmp, label %for.cond.for.end_crit_edge, label %for.body
+
+for.cond.for.end_crit_edge: ; preds = %for.body
+ %phitmp = trunc i32 %add to i16
+ br label %for.end
+
+for.end: ; preds = %for.cond.for.end_crit_edge, %entry
+ %res.0.lcssa = phi i16 [ %phitmp, %for.cond.for.end_crit_edge ], [ 0, %entry ]
+ ret i16 %res.0.lcssa
+}
diff --git a/test/Transforms/LoopUnroll/runtime-loop1.ll b/test/Transforms/LoopUnroll/runtime-loop1.ll
new file mode 100644
index 0000000000..ad99b8cd9c
--- /dev/null
+++ b/test/Transforms/LoopUnroll/runtime-loop1.ll
@@ -0,0 +1,30 @@
+; RUN: opt < %s -S -loop-unroll -unroll-runtime -unroll-count=4 | FileCheck %s
+
+; This tests that setting the unroll count works
+
+; CHECK: unr.cmp:
+; CHECK: for.body.unr:
+; CHECK: for.body:
+; CHECK: br i1 %exitcond.3, label %for.end.loopexit{{.*}}, label %for.body
+; CHECK-NOT: br i1 %exitcond.4, label %for.end.loopexit{{.*}}, label %for.body
+
+define i32 @test(i32* nocapture %a, i32 %n) nounwind uwtable readonly {
+entry:
+ %cmp1 = icmp eq i32 %n, 0
+ br i1 %cmp1, label %for.end, label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+ %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+ %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+ %0 = load i32* %arrayidx, align 4
+ %add = add nsw i32 %0, %sum.02
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, %n
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
+ ret i32 %sum.0.lcssa
+}
diff --git a/test/Transforms/LoopUnroll/runtime-loop2.ll b/test/Transforms/LoopUnroll/runtime-loop2.ll
new file mode 100644
index 0000000000..cbc7af58ff
--- /dev/null
+++ b/test/Transforms/LoopUnroll/runtime-loop2.ll
@@ -0,0 +1,31 @@
+; RUN: opt < %s -S -loop-unroll -unroll-threshold=50 -unroll-runtime -unroll-count=8 | FileCheck %s
+
+; Choose a smaller, power-of-two, unroll count if the loop is too large.
+; This test makes sure we're not unrolling 'odd' counts
+
+; CHECK: unr.cmp:
+; CHECK: for.body.unr:
+; CHECK: for.body:
+; CHECK: br i1 %exitcond.3, label %for.end.loopexit{{.*}}, label %for.body
+; CHECK-NOT: br i1 %exitcond.4, label %for.end.loopexit{{.*}}, label %for.body
+
+define i32 @test(i32* nocapture %a, i32 %n) nounwind uwtable readonly {
+entry:
+ %cmp1 = icmp eq i32 %n, 0
+ br i1 %cmp1, label %for.end, label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
+ %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ]
+ %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv
+ %0 = load i32* %arrayidx, align 4
+ %add = add nsw i32 %0, %sum.02
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, %n
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body, %entry
+ %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ]
+ ret i32 %sum.0.lcssa
+}
diff --git a/test/Transforms/LoopUnroll/runtime-loop3.ll b/test/Transforms/LoopUnroll/runtime-loop3.ll
new file mode 100644
index 0000000000..55cf22373e
--- /dev/null
+++ b/test/Transforms/LoopUnroll/runtime-loop3.ll
@@ -0,0 +1,44 @@
+; RUN: opt < %s -disable-output -stats -loop-unroll -unroll-runtime -unroll-threshold=400 -info-output-file - | FileCheck %s --check-prefix=STATS
+
+; Test that nested loops can be unrolled. We need to increase threshold to do it
+
+; STATS: 2 loop-unroll - Number of loops unrolled (completely or otherwise)
+
+define i32 @nested(i32* nocapture %a, i32 %n, i32 %m) nounwind uwtable readonly {
+entry:
+ %cmp11 = icmp sgt i32 %n, 0
+ br i1 %cmp11, label %for.cond1.preheader.lr.ph, label %for.end7
+
+for.cond1.preheader.lr.ph: ; preds = %entry
+ %cmp28 = icmp sgt i32 %m, 0
+ br label %for.cond1.preheader
+
+for.cond1.preheader: ; preds = %for.inc5, %for.cond1.preheader.lr.ph
+ %indvars.iv16 = phi i64 [ 0, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next17, %for.inc5 ]
+ %sum.012 = phi i32 [ 0, %for.cond1.preheader.lr.ph ], [ %sum.1.lcssa, %for.inc5 ]
+ br i1 %cmp28, label %for.body3, label %for.inc5
+
+for.body3: ; preds = %for.cond1.preheader, %for.body3
+ %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 0, %for.cond1.preheader ]
+ %sum.19 = phi i32 [ %add4, %for.body3 ], [ %sum.012, %for.cond1.preheader ]
+ %0 = add nsw i64 %indvars.iv, %indvars.iv16
+ %arrayidx = getelementptr inbounds i32* %a, i64 %0
+ %1 = load i32* %arrayidx, align 4
+ %add4 = add nsw i32 %1, %sum.19
+ %indvars.iv.next = add i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, %m
+ br i1 %exitcond, label %for.inc5, label %for.body3
+
+for.inc5: ; preds = %for.body3, %for.cond1.preheader
+ %sum.1.lcssa = phi i32 [ %sum.012, %for.cond1.preheader ], [ %add4, %for.body3 ]
+ %indvars.iv.next17 = add i64 %indvars.iv16, 1
+ %lftr.wideiv18 = trunc i64 %indvars.iv.next17 to i32
+ %exitcond19 = icmp eq i32 %lftr.wideiv18, %n
+ br i1 %exitcond19, label %for.end7, label %for.cond1.preheader
+
+for.end7: ; preds = %for.inc5, %entry
+ %sum.0.lcssa = phi i32 [ 0, %entry ], [ %sum.1.lcssa, %for.inc5 ]
+ ret i32 %sum.0.lcssa
+}
+