11 files changed, 374 insertions, 4 deletions
diff --git a/test/Transforms/LoopUnroll/2011-08-09-IVSimplify.ll b/test/Transforms/LoopUnroll/2011-08-09-IVSimplify.ll
index 59551d5..a43a4ff 100644
--- a/test/Transforms/LoopUnroll/2011-08-09-IVSimplify.ll
+++ b/test/Transforms/LoopUnroll/2011-08-09-IVSimplify.ll
@@ -1,4 +1,4 @@
-; RUN: opt -S < %s -loop-unroll -unroll-count=4 -enable-iv-rewrite=false | FileCheck %s
+; RUN: opt -S < %s -loop-unroll -unroll-count=4 | FileCheck %s
 ;
 ; Test induction variable simplify after loop unrolling. It should
 ; expose nice opportunities for GVN.
diff --git a/test/Transforms/LoopUnroll/2012-04-09-unroll-indirectbr.ll b/test/Transforms/LoopUnroll/2012-04-09-unroll-indirectbr.ll
new file mode 100644
index 0000000..8946a23
--- /dev/null
+++ b/test/Transforms/LoopUnroll/2012-04-09-unroll-indirectbr.ll
@@ -0,0 +1,40 @@
+; RUN: opt < %s -S -loop-unroll -simplifycfg | FileCheck %s
+; PR12513: Loop unrolling breaks with indirect branches.
+; If loop unrolling attempts to transform this loop, it replaces the
+; indirectbr successors. SimplifyCFG then considers them to be unreachable.
+declare void @subtract() nounwind uwtable
+
+; CHECK-NOT: unreachable
+define i32 @main(i32 %argc, i8** nocapture %argv) nounwind uwtable {
+entry:
+  %vals19 = alloca [5 x i32], align 16
+  %x20 = alloca i32, align 4
+  store i32 135, i32* %x20, align 4
+  br label %for.body
+
+for.body:                                         ; preds = ; %call2_termjoin, %call3_termjoin
+  %indvars.iv = phi i64 [ 0, %entry ], [ %joinphi15.in.in, %call2_termjoin ]
+  %a6 = call coldcc i8* @funca(i8* blockaddress(@main, %for.body_code), i8*
+blockaddress(@main, %for.body_codeprime)) nounwind
+  indirectbr i8* %a6, [label %for.body_code, label %for.body_codeprime]
+
+for.body_code:                                    ; preds = %for.body
+  call void @subtract()
+  br label %call2_termjoin
+
+call2_termjoin:                                   ; preds = %for.body_codeprime, %for.body_code
+  %joinphi15.in.in = add i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %joinphi15.in.in, 5
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:                                          ; preds = %call2_termjoin
+  ret i32 0
+
+for.body_codeprime:                               ; preds = %for.body
+  call void @subtract_v2(i64 %indvars.iv)
+  br label %call2_termjoin
+}
+
+declare coldcc i8* @funca(i8*, i8*) readonly
+
+declare void @subtract_v2(i64) nounwind uwtable
diff --git a/test/Transforms/LoopUnroll/dg.exp b/test/Transforms/LoopUnroll/dg.exp
deleted file mode 100644
index f200589..0000000
--- a/test/Transforms/LoopUnroll/dg.exp
+++ /dev/null
@@ -1,3 +0,0 @@
-load_lib llvm.exp
-
-RunLLVMTests [lsort [glob -nocomplain $srcdir/$subdir/*.{ll,c,cpp}]]
diff --git a/test/Transforms/LoopUnroll/lit.local.cfg b/test/Transforms/LoopUnroll/lit.local.cfg
new file mode 100644
index 0000000..19eebc0
--- /dev/null
+++ b/test/Transforms/LoopUnroll/lit.local.cfg
@@ -0,0 +1 @@
+config.suffixes = ['.ll', '.c', '.cpp']
diff --git a/test/Transforms/LoopUnroll/partial-unroll-optsize.ll b/test/Transforms/LoopUnroll/partial-unroll-optsize.ll
new file mode 100644
index 0000000..3179d55e
--- /dev/null
+++ b/test/Transforms/LoopUnroll/partial-unroll-optsize.ll
@@ -0,0 +1,35 @@
+; RUN: opt < %s -S -loop-unroll -unroll-allow-partial | FileCheck %s
+; Loop size = 3, when the function has the optsize attribute, the
+; OptSizeUnrollThreshold, i.e. 50, is used, hence the loop should be unrolled
+; by 16 times because 3 * 16 < 50.
+define void @unroll_opt_for_size() nounwind optsize {
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i32 [ 0, %entry ], [ %inc, %loop ]
+  %inc = add i32 %iv, 1
+  %exitcnd = icmp uge i32 %inc, 1024
+  br i1 %exitcnd, label %exit, label %loop
+
+exit:
+  ret void
+}
+
+; CHECK:      add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: add
+; CHECK-NEXT: icmp
diff --git a/test/Transforms/LoopUnroll/pr11361.ll b/test/Transforms/LoopUnroll/pr11361.ll
new file mode 100644
index 0000000..7ce7f5f
--- /dev/null
+++ b/test/Transforms/LoopUnroll/pr11361.ll
@@ -0,0 +1,42 @@
+; RUN: opt -loop-unroll -disable-output
+; PR11361
+
+; This tests for an iterator invalidation issue.
+
+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-unknown-linux-gnu"
+
+define void @func_1() nounwind uwtable {
+entry:
+  br label %for.cond8.preheader
+
+for.cond8.preheader:                              ; preds = %for.inc15, %entry
+  %l_1264.04 = phi i32 [ 0, %entry ], [ %add.i, %for.inc15 ]
+  %l_1330.0.03 = phi i80 [ undef, %entry ], [ %ins.lcssa, %for.inc15 ]
+  br label %for.body9
+
+for.body9:                                        ; preds = %for.body9, %for.cond8.preheader
+  %l_1330.0.12 = phi i80 [ %l_1330.0.03, %for.cond8.preheader ], [ %ins, %for.body9 ]
+  %storemerge1 = phi i32 [ 7, %for.cond8.preheader ], [ %sub, %for.body9 ]
+  %tmp = lshr i80 %l_1330.0.12, 8
+  %tmp1 = trunc i80 %tmp to i8
+  %inc12 = add i8 %tmp1, 1
+  %tmp2 = zext i8 %inc12 to i80
+  %tmp3 = shl nuw nsw i80 %tmp2, 8
+  %mask = and i80 %l_1330.0.12, -65281
+  %ins = or i80 %tmp3, %mask
+  %sub = add nsw i32 %storemerge1, -1
+  %tobool = icmp eq i32 %sub, 0
+  br i1 %tobool, label %for.inc15, label %for.body9
+
+for.inc15:                                        ; preds = %for.body9
+  %ins.lcssa = phi i80 [ %ins, %for.body9 ]
+  %sext = shl i32 %l_1264.04, 24
+  %conv.i = ashr exact i32 %sext, 24
+  %add.i = add nsw i32 %conv.i, 1
+  %cmp = icmp slt i32 %add.i, 3
+  br i1 %cmp, label %for.cond8.preheader, label %for.end16
+
+for.end16:                                        ; preds = %for.inc15
+  ret void
+}
diff --git a/test/Transforms/LoopUnroll/runtime-loop.ll b/test/Transforms/LoopUnroll/runtime-loop.ll
new file mode 100644
index 0000000..d8bbea9
--- /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 0000000..ad99b8c
--- /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 0000000..cbc7af5
--- /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 0000000..55cf223
--- /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
+}
+
diff --git a/test/Transforms/LoopUnroll/unloop.ll b/test/Transforms/LoopUnroll/unloop.ll
index 217c8ce..5a9cacd 100644
--- a/test/Transforms/LoopUnroll/unloop.ll
+++ b/test/Transforms/LoopUnroll/unloop.ll
@@ -427,3 +427,44 @@ if.end2413:                                       ; preds = %defchar
 return:                                           ; preds = %sw.bb304
   ret void
 }
+
+; PR11335: the most deeply nested block should be removed from the outer loop.
+; CHECK: @removeSubloopBlocks2
+; CHECK: for.cond3:
+; CHECK-NOT: br
+; CHECK: ret void
+define void @removeSubloopBlocks2() nounwind {
+entry:
+  %tobool.i = icmp ne i32 undef, 0
+  br label %lbl_616
+
+lbl_616.loopexit:                                 ; preds = %for.cond
+  br label %lbl_616
+
+lbl_616:                                          ; preds = %lbl_616.loopexit, %entry
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.cond3, %lbl_616
+  br i1 false, label %for.cond1.preheader, label %lbl_616.loopexit
+
+for.cond1.preheader:                              ; preds = %for.cond
+  br label %for.cond1
+
+for.cond1.loopexit:                               ; preds = %for.cond.i
+  br label %for.cond1
+
+for.cond1:                                        ; preds = %for.cond1.loopexit, %for.cond1.preheader
+  br i1 false, label %for.body2, label %for.cond3
+
+for.body2:                                        ; preds = %for.cond1
+  br label %for.cond.i
+
+for.cond.i:                                       ; preds = %for.cond.i, %for.body2
+  br i1 %tobool.i, label %for.cond.i, label %for.cond1.loopexit
+
+for.cond3:                                        ; preds = %for.cond1
+  br i1 false, label %for.cond, label %if.end
+
+if.end:                                           ; preds = %for.cond3
+  ret void
+}