[llvm] 3f3017e - [Loop Peeling] Add possibility to enable peeling on loop nests.
Arkady Shlykov via llvm-commits
llvm-commits at lists.llvm.org
Wed Jan 15 08:29:18 PST 2020
Author: Arkady Shlykov
Date: 2020-01-15T08:25:21-08:00
New Revision: 3f3017e162ec4208399dcf633c99bdac788c06fd
URL: https://github.com/llvm/llvm-project/commit/3f3017e162ec4208399dcf633c99bdac788c06fd
DIFF: https://github.com/llvm/llvm-project/commit/3f3017e162ec4208399dcf633c99bdac788c06fd.diff
LOG: [Loop Peeling] Add possibility to enable peeling on loop nests.
Summary:
Current peeling implementation bails out in case of loop nests.
The patch introduces a field in TargetTransformInfo structure that
certain targets can use to relax the constraints if it's
profitable (disabled by default).
Also additional option is added to enable peeling manually for
experimenting and testing purposes.
Reviewers: fhahn, lebedev.ri, xbolva00
Reviewed By: xbolva00
Subscribers: xbolva00, hiraditya, zzheng, llvm-commits
Differential Revision: https://reviews.llvm.org/D70304
Added:
llvm/test/Transforms/LoopUnroll/peel-loop-nests.ll
Modified:
llvm/include/llvm/Analysis/TargetTransformInfo.h
llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
Removed:
################################################################################
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index 5382d76813a7..4cf00cd46ed5 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -490,6 +490,8 @@ class TargetTransformInfo {
bool UpperBound;
/// Allow peeling off loop iterations.
bool AllowPeeling;
+ /// Allow peeling off loop iterations for loop nests.
+ bool AllowLoopNestsPeeling;
/// Allow unrolling of all the iterations of the runtime loop remainder.
bool UnrollRemainder;
/// Allow unroll and jam. Used to enable unroll and jam for the target.
diff --git a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
index 4c2b079c6bb5..bb0459bfafc6 100644
--- a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -154,6 +154,10 @@ static cl::opt<bool>
cl::desc("Allows loops to be peeled when the dynamic "
"trip count is known to be low."));
+static cl::opt<bool> UnrollAllowLoopNestsPeeling(
+ "unroll-allow-loop-nests-peeling", cl::init(false), cl::Hidden,
+ cl::desc("Allows loop nests to be peeled."));
+
static cl::opt<bool> UnrollUnrollRemainder(
"unroll-remainder", cl::Hidden,
cl::desc("Allow the loop remainder to be unrolled."));
@@ -204,6 +208,7 @@ TargetTransformInfo::UnrollingPreferences llvm::gatherUnrollingPreferences(
UP.Force = false;
UP.UpperBound = false;
UP.AllowPeeling = true;
+ UP.AllowLoopNestsPeeling = false;
UP.UnrollAndJam = false;
UP.PeelProfiledIterations = true;
UP.UnrollAndJamInnerLoopThreshold = 60;
@@ -244,6 +249,8 @@ TargetTransformInfo::UnrollingPreferences llvm::gatherUnrollingPreferences(
UP.UpperBound = false;
if (UnrollAllowPeeling.getNumOccurrences() > 0)
UP.AllowPeeling = UnrollAllowPeeling;
+ if (UnrollAllowLoopNestsPeeling.getNumOccurrences() > 0)
+ UP.AllowLoopNestsPeeling = UnrollAllowLoopNestsPeeling;
if (UnrollUnrollRemainder.getNumOccurrences() > 0)
UP.UnrollRemainder = UnrollUnrollRemainder;
diff --git a/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp b/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
index 7a168ff6f32b..cdf48265eae9 100644
--- a/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp
@@ -289,8 +289,10 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
if (!canPeel(L))
return;
- // Only try to peel innermost loops.
- if (!L->empty())
+ // Only try to peel innermost loops by default.
+ // The constraint can be relaxed by the target in TTI.getUnrollingPreferences
+ // or by the flag -unroll-allow-loop-nests-peeling.
+ if (!UP.AllowLoopNestsPeeling && !L->empty())
return;
// If the user provided a peel count, use that.
diff --git a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
index 5c84884c66de..f0fbf3d6d49b 100644
--- a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
+++ b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
@@ -403,76 +403,11 @@ for.end:
ret void
}
-; In this case we cannot peel the inner loop, because the condition involves
-; the outer induction variable.
-define void @test5(i32 %k) {
-; CHECK-LABEL: @test5(
-; CHECK-NEXT: for.body.lr.ph:
-; CHECK-NEXT: br label [[OUTER_HEADER:%.*]]
-; CHECK: outer.header:
-; CHECK-NEXT: [[J:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH:%.*]] ], [ [[J_INC:%.*]], [[OUTER_INC:%.*]] ]
-; CHECK-NEXT: br label [[FOR_BODY:%.*]]
-; CHECK: for.body:
-; CHECK-NEXT: [[I_05:%.*]] = phi i32 [ 0, [[OUTER_HEADER]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
-; CHECK-NEXT: [[CMP1:%.*]] = icmp ult i32 [[J]], 2
-; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
-; CHECK: if.then:
-; CHECK-NEXT: call void @f1()
-; CHECK-NEXT: br label [[FOR_INC]]
-; CHECK: if.else:
-; CHECK-NEXT: call void @f2()
-; CHECK-NEXT: br label [[FOR_INC]]
-; CHECK: for.inc:
-; CHECK-NEXT: [[INC]] = add nsw i32 [[I_05]], 1
-; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[INC]], [[K:%.*]]
-; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[OUTER_INC]]
-; CHECK: outer.inc:
-; CHECK-NEXT: [[J_INC]] = add nsw i32 [[J]], 1
-; CHECK-NEXT: [[OUTER_CMP:%.*]] = icmp slt i32 [[J_INC]], [[K]]
-; CHECK-NEXT: br i1 [[OUTER_CMP]], label [[OUTER_HEADER]], label [[FOR_END:%.*]]
-; CHECK: for.end:
-; CHECK-NEXT: ret void
-;
-for.body.lr.ph:
- br label %outer.header
-
-outer.header:
- %j = phi i32 [ 0, %for.body.lr.ph ], [ %j.inc, %outer.inc ]
- br label %for.body
-
-for.body:
- %i.05 = phi i32 [ 0, %outer.header ], [ %inc, %for.inc ]
- %cmp1 = icmp ult i32 %j, 2
- br i1 %cmp1, label %if.then, label %if.else
-
-if.then:
- call void @f1()
- br label %for.inc
-
-if.else:
- call void @f2()
- br label %for.inc
-
-for.inc:
- %inc = add nsw i32 %i.05, 1
- %cmp = icmp slt i32 %inc, %k
- br i1 %cmp, label %for.body, label %outer.inc
-
-outer.inc:
- %j.inc = add nsw i32 %j, 1
- %outer.cmp = icmp slt i32 %j.inc, %k
- br i1 %outer.cmp, label %outer.header, label %for.end
-
-
-for.end:
- ret void
-}
-
; In this test, the condition involves 2 AddRecs. Without evaluating both
; AddRecs, we cannot prove that the condition becomes known in the loop body
; after peeling.
-define void @test6(i32 %k) {
-; CHECK-LABEL: @test6(
+define void @test5(i32 %k) {
+; CHECK-LABEL: @test5(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
@@ -521,8 +456,8 @@ for.end:
ret void
}
-define void @test7(i32 %k) {
-; CHECK-LABEL: @test7(
+define void @test6(i32 %k) {
+; CHECK-LABEL: @test6(
; CHECK-NEXT: for.body.lr.ph:
; CHECK-NEXT: br label [[FOR_BODY_PEEL_BEGIN:%.*]]
; CHECK: for.body.peel.begin:
@@ -615,8 +550,8 @@ for.end:
ret void
}
-define void @test8(i32 %k) {
-; CHECK-LABEL: @test8(
+define void @test7(i32 %k) {
+; CHECK-LABEL: @test7(
; CHECK-NEXT: for.body.lr.ph:
; CHECK-NEXT: br label [[FOR_BODY_PEEL_BEGIN:%.*]]
; CHECK: for.body.peel.begin:
@@ -711,8 +646,8 @@ for.end:
; Comparison with non-monotonic predicate due to possible wrapping, loop
; body cannot be simplified.
-define void @test9(i32 %k) {
-; CHECK-LABEL: @test9(
+define void @test8(i32 %k) {
+; CHECK-LABEL: @test8(
; CHECK-NEXT: for.body.lr.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
@@ -751,8 +686,8 @@ for.end:
}
; CHECK-NOT: llvm.loop.unroll.disable
-define void @test_10__peel_first_iter_via_slt_pred(i32 %len) {
-; CHECK-LABEL: @test_10__peel_first_iter_via_slt_pred(
+define void @test_9__peel_first_iter_via_slt_pred(i32 %len) {
+; CHECK-LABEL: @test_9__peel_first_iter_via_slt_pred(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
; CHECK-NEXT: br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
@@ -818,8 +753,8 @@ if.end: ; preds = %if.then, %for.body
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
-define void @test_11__peel_first_iter_via_sgt_pred(i32 %len) {
-; CHECK-LABEL: @test_11__peel_first_iter_via_sgt_pred(
+define void @test_10__peel_first_iter_via_sgt_pred(i32 %len) {
+; CHECK-LABEL: @test_10__peel_first_iter_via_sgt_pred(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
; CHECK-NEXT: br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
@@ -887,8 +822,8 @@ if.end: ; preds = %if.then, %for.body
; NOTE: here we should only peel the first iteration,
; i.e. all calls to sink() must stay in loop.
-define void @test12__peel_first_iter_via_eq_pred(i32 %len) {
-; CHECK-LABEL: @test12__peel_first_iter_via_eq_pred(
+define void @test11__peel_first_iter_via_eq_pred(i32 %len) {
+; CHECK-LABEL: @test11__peel_first_iter_via_eq_pred(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
; CHECK-NEXT: br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
@@ -956,8 +891,8 @@ if.end: ; preds = %if.then, %for.body
; NOTE: here we should only peel the first iteration,
; i.e. all calls to sink() must stay in loop.
-define void @test13__peel_first_iter_via_ne_pred(i32 %len) {
-; CHECK-LABEL: @test13__peel_first_iter_via_ne_pred(
+define void @test12__peel_first_iter_via_ne_pred(i32 %len) {
+; CHECK-LABEL: @test12__peel_first_iter_via_ne_pred(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
; CHECK-NEXT: br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
@@ -1024,8 +959,8 @@ if.end: ; preds = %if.then, %for.body
}
; No peeling is profitable here.
-define void @test14__ivar_mod2_is_1(i32 %len) {
-; CHECK-LABEL: @test14__ivar_mod2_is_1(
+define void @test13__ivar_mod2_is_1(i32 %len) {
+; CHECK-LABEL: @test13__ivar_mod2_is_1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
; CHECK-NEXT: br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
@@ -1074,8 +1009,8 @@ if.end: ; preds = %if.then, %for.body
}
; No peeling is profitable here.
-define void @test15__ivar_mod2_is_0(i32 %len) {
-; CHECK-LABEL: @test15__ivar_mod2_is_0(
+define void @test14__ivar_mod2_is_0(i32 %len) {
+; CHECK-LABEL: @test14__ivar_mod2_is_0(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP5:%.*]] = icmp sgt i32 [[LEN:%.*]], 0
; CHECK-NEXT: br i1 [[CMP5]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
@@ -1123,10 +1058,10 @@ if.end: ; preds = %if.then, %for.body
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
-; Similar to @test7, we need to peel one extra iteration, and we can't do that
+; Similar to @test6, we need to peel one extra iteration, and we can't do that
; as per the -unroll-peel-max-count=4, so this shouldn't be peeled at all.
-define void @test16(i32 %k) {
-; CHECK-LABEL: @test16(
+define void @test15(i32 %k) {
+; CHECK-LABEL: @test15(
; CHECK-NEXT: for.body.lr.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
@@ -1164,10 +1099,10 @@ for.end:
ret void
}
-; Similar to @test8, we need to peel one extra iteration, and we can't do that
+; Similar to @test7, we need to peel one extra iteration, and we can't do that
; as per the -unroll-peel-max-count=4, so this shouldn't be peeled at all.
-define void @test17(i32 %k) {
-; CHECK-LABEL: @test17(
+define void @test16(i32 %k) {
+; CHECK-LABEL: @test16(
; CHECK-NEXT: for.body.lr.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
diff --git a/llvm/test/Transforms/LoopUnroll/peel-loop-nests.ll b/llvm/test/Transforms/LoopUnroll/peel-loop-nests.ll
new file mode 100644
index 000000000000..65d1977c60fa
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/peel-loop-nests.ll
@@ -0,0 +1,155 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -S -loop-unroll -unroll-peel-max-count=4 -verify-dom-info | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -unroll-peel-max-count=4 -unroll-allow-loop-nests-peeling -verify-dom-info | FileCheck %s --check-prefix PEELED
+
+declare void @f1()
+declare void @f2()
+
+; In this case we cannot peel the inner loop, because the condition involves
+; the outer induction variable.
+; Peel the loop nest if allowed by the flag -unroll-allow-loop-nests-peeling.
+define void @test1(i32 %k) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT: for.body.lr.ph:
+; CHECK-NEXT: br label [[OUTER_HEADER:%.*]]
+; CHECK: outer.header:
+; CHECK-NEXT: [[J:%.*]] = phi i32 [ 0, [[FOR_BODY_LR_PH:%.*]] ], [ [[J_INC:%.*]], [[OUTER_INC:%.*]] ]
+; CHECK-NEXT: br label [[FOR_BODY:%.*]]
+; CHECK: for.body:
+; CHECK-NEXT: [[I_05:%.*]] = phi i32 [ 0, [[OUTER_HEADER]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
+; CHECK-NEXT: [[CMP1:%.*]] = icmp ult i32 [[J]], 2
+; CHECK-NEXT: br i1 [[CMP1]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; CHECK: if.then:
+; CHECK-NEXT: call void @f1()
+; CHECK-NEXT: br label [[FOR_INC]]
+; CHECK: if.else:
+; CHECK-NEXT: call void @f2()
+; CHECK-NEXT: br label [[FOR_INC]]
+; CHECK: for.inc:
+; CHECK-NEXT: [[INC]] = add nsw i32 [[I_05]], 1
+; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[INC]], [[K:%.*]]
+; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[OUTER_INC]]
+; CHECK: outer.inc:
+; CHECK-NEXT: [[J_INC]] = add nsw i32 [[J]], 1
+; CHECK-NEXT: [[OUTER_CMP:%.*]] = icmp slt i32 [[J_INC]], [[K]]
+; CHECK-NEXT: br i1 [[OUTER_CMP]], label [[OUTER_HEADER]], label [[FOR_END:%.*]], !llvm.loop !{{.*}}
+; CHECK: for.end:
+; CHECK-NEXT: ret void
+;
+; PEELED-LABEL: @test1(
+; PEELED-NEXT: for.body.lr.ph:
+; PEELED-NEXT: br label [[OUTER_HEADER_PEEL_BEGIN:%.*]]
+; PEELED: outer.header.peel.begin:
+; PEELED-NEXT: br label [[OUTER_HEADER_PEEL:%.*]]
+; PEELED: outer.header.peel:
+; PEELED-NEXT: br label [[FOR_BODY_PEEL:%.*]]
+; PEELED: for.body.peel:
+; PEELED-NEXT: [[I_05_PEEL:%.*]] = phi i32 [ 0, [[OUTER_HEADER_PEEL]] ], [ [[INC_PEEL:%.*]], [[FOR_INC_PEEL:%.*]] ]
+; PEELED-NEXT: [[CMP1_PEEL:%.*]] = icmp ult i32 0, 2
+; PEELED-NEXT: br i1 [[CMP1_PEEL]], label [[IF_THEN_PEEL:%.*]], label [[IF_ELSE_PEEL:%.*]]
+; PEELED: if.else.peel:
+; PEELED-NEXT: call void @f2()
+; PEELED-NEXT: br label [[FOR_INC_PEEL]]
+; PEELED: if.then.peel:
+; PEELED-NEXT: call void @f1()
+; PEELED-NEXT: br label [[FOR_INC_PEEL]]
+; PEELED: for.inc.peel:
+; PEELED-NEXT: [[INC_PEEL]] = add nsw i32 [[I_05_PEEL]], 1
+; PEELED-NEXT: [[CMP_PEEL:%.*]] = icmp slt i32 [[INC_PEEL]], [[K:%.*]]
+; PEELED-NEXT: br i1 [[CMP_PEEL]], label [[FOR_BODY_PEEL]], label [[OUTER_INC_PEEL:%.*]]
+; PEELED: outer.inc.peel:
+; PEELED-NEXT: [[J_INC_PEEL:%.*]] = add nsw i32 0, 1
+; PEELED-NEXT: [[OUTER_CMP_PEEL:%.*]] = icmp slt i32 [[J_INC_PEEL]], [[K]]
+; PEELED-NEXT: br i1 [[OUTER_CMP_PEEL]], label [[OUTER_HEADER_PEEL_NEXT:%.*]], label [[FOR_END:%[^,]*]]
+; Verify that MD_loop metadata is dropped.
+; PEELED-NOT: , !llvm.loop !{{[0-9]*}}
+; PEELED: outer.header.peel.next:
+; PEELED-NEXT: br label [[OUTER_HEADER_PEEL2:%.*]]
+; PEELED: outer.header.peel2:
+; PEELED-NEXT: br label [[FOR_BODY_PEEL3:%.*]]
+; PEELED: for.body.peel3:
+; PEELED-NEXT: [[I_05_PEEL4:%.*]] = phi i32 [ 0, [[OUTER_HEADER_PEEL2]] ], [ [[INC_PEEL9:%.*]], [[FOR_INC_PEEL8:%.*]] ]
+; PEELED-NEXT: [[CMP1_PEEL5:%.*]] = icmp ult i32 [[J_INC_PEEL]], 2
+; PEELED-NEXT: br i1 [[CMP1_PEEL5]], label [[IF_THEN_PEEL7:%.*]], label [[IF_ELSE_PEEL6:%.*]]
+; PEELED: if.else.peel6:
+; PEELED-NEXT: call void @f2()
+; PEELED-NEXT: br label [[FOR_INC_PEEL8]]
+; PEELED: if.then.peel7:
+; PEELED-NEXT: call void @f1()
+; PEELED-NEXT: br label [[FOR_INC_PEEL8]]
+; PEELED: for.inc.peel8:
+; PEELED-NEXT: [[INC_PEEL9]] = add nsw i32 [[I_05_PEEL4]], 1
+; PEELED-NEXT: [[CMP_PEEL10:%.*]] = icmp slt i32 [[INC_PEEL9]], [[K]]
+; PEELED-NEXT: br i1 [[CMP_PEEL10]], label [[FOR_BODY_PEEL3]], label [[OUTER_INC_PEEL11:%.*]]
+; PEELED: outer.inc.peel11:
+; PEELED-NEXT: [[J_INC_PEEL12:%.*]] = add nsw i32 [[J_INC_PEEL]], 1
+; PEELED-NEXT: [[OUTER_CMP_PEEL13:%.*]] = icmp slt i32 [[J_INC_PEEL12]], [[K]]
+; PEELED-NEXT: br i1 [[OUTER_CMP_PEEL13]], label [[OUTER_HEADER_PEEL_NEXT1:%.*]], label [[FOR_END]]
+; Verify that MD_loop metadata is dropped.
+; PEELED-NOT: , !llvm.loop !{{[0-9]*}}
+; PEELED: outer.header.peel.next1:
+; PEELED-NEXT: br label [[OUTER_HEADER_PEEL_NEXT14:%.*]]
+; PEELED: outer.header.peel.next14:
+; PEELED-NEXT: br label [[FOR_BODY_LR_PH_PEEL_NEWPH:%.*]]
+; PEELED: for.body.lr.ph.peel.newph:
+; PEELED-NEXT: br label [[OUTER_HEADER:%.*]]
+; PEELED: outer.header:
+; PEELED-NEXT: [[J:%.*]] = phi i32 [ [[J_INC_PEEL12]], [[FOR_BODY_LR_PH_PEEL_NEWPH]] ], [ [[J_INC:%.*]], [[OUTER_INC:%.*]] ]
+; PEELED-NEXT: br label [[FOR_BODY:%.*]]
+; PEELED: for.body:
+; PEELED-NEXT: [[I_05:%.*]] = phi i32 [ 0, [[OUTER_HEADER]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ]
+; PEELED-NEXT: br i1 false, label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; PEELED: if.then:
+; PEELED-NEXT: call void @f1()
+; PEELED-NEXT: br label [[FOR_INC]]
+; PEELED: if.else:
+; PEELED-NEXT: call void @f2()
+; PEELED-NEXT: br label [[FOR_INC]]
+; PEELED: for.inc:
+; PEELED-NEXT: [[INC]] = add nsw i32 [[I_05]], 1
+; PEELED-NEXT: [[CMP:%.*]] = icmp slt i32 [[INC]], [[K]]
+; PEELED-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[OUTER_INC]]
+; PEELED: outer.inc:
+; PEELED-NEXT: [[J_INC]] = add nuw nsw i32 [[J]], 1
+; PEELED-NEXT: [[OUTER_CMP:%.*]] = icmp slt i32 [[J_INC]], [[K]]
+; PEELED-NEXT: br i1 [[OUTER_CMP]], label [[OUTER_HEADER]], label [[FOR_END_LOOPEXIT:%.*]], !llvm.loop !{{.*}}
+; PEELED: for.end.loopexit:
+; PEELED-NEXT: br label [[FOR_END]]
+; PEELED: for.end:
+; PEELED-NEXT: ret void
+;
+for.body.lr.ph:
+ br label %outer.header
+
+outer.header:
+ %j = phi i32 [ 0, %for.body.lr.ph ], [ %j.inc, %outer.inc ]
+ br label %for.body
+
+for.body:
+ %i.05 = phi i32 [ 0, %outer.header ], [ %inc, %for.inc ]
+ %cmp1 = icmp ult i32 %j, 2
+ br i1 %cmp1, label %if.then, label %if.else
+
+if.then:
+ call void @f1()
+ br label %for.inc
+
+if.else:
+ call void @f2()
+ br label %for.inc
+
+for.inc:
+ %inc = add nsw i32 %i.05, 1
+ %cmp = icmp slt i32 %inc, %k
+ br i1 %cmp, label %for.body, label %outer.inc
+
+outer.inc:
+ %j.inc = add nsw i32 %j, 1
+ %outer.cmp = icmp slt i32 %j.inc, %k
+ br i1 %outer.cmp, label %outer.header, label %for.end, !llvm.loop !0
+
+for.end:
+ ret void
+}
+
+!0 = distinct !{!0}
\ No newline at end of file
More information about the llvm-commits
mailing list