[llvm] [SimplifyCFG] Avoid threading for loop headers (PR #151142)
Arne Stenkrona via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 29 08:21:56 PDT 2025
https://github.com/ArneStenkrona2 updated https://github.com/llvm/llvm-project/pull/151142
>From 507d8000c3b92752da381b074e7de8e408b5491d Mon Sep 17 00:00:00 2001
From: Arne Stenkrona <arne.stenkrona at arm.com>
Date: Thu, 8 May 2025 16:19:35 +0200
Subject: [PATCH 1/2] [SimplifyCFG] Avoid threading for loop headers
Updates SimplifyCFG to avoid jump threading through loop headers if
-keep-loops is requested. Canonical loop form requires a loop header
that dominates all blocks in the loop. If we thread through a header,
we risk breaking its domination of the loop. This change avoids this
issue by conservatively avoiding threading through headers entirely.
---
llvm/lib/Transforms/Utils/SimplifyCFG.cpp | 10 ++++-
.../CodeGen/ARM/2013-05-05-IfConvertBug.ll | 6 +--
.../2008-07-13-InfLoopMiscompile.ll | 3 +-
.../2025-07-29-non-canoncial-loop.ll | 37 +++++++++++++++++++
.../SimplifyCFG/branch-phi-thread.ll | 2 +-
.../Transforms/SimplifyCFG/jump-threading.ll | 2 +-
.../SimplifyCFG/two-entry-phi-return.ll | 2 +-
7 files changed, 52 insertions(+), 10 deletions(-)
create mode 100644 llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll
diff --git a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
index 94b0ab892f2dd..d8385beb349d6 100644
--- a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -8030,8 +8030,14 @@ bool SimplifyCFGOpt::simplifyCondBranch(BranchInst *BI, IRBuilder<> &Builder) {
// If this is a branch on something for which we know the constant value in
// predecessors (e.g. a phi node in the current block), thread control
// through this block.
- if (foldCondBranchOnValueKnownInPredecessor(BI, DTU, DL, Options.AC))
- return requestResimplify();
+ // Note: If BB is a loop header then there is a risk that threading introduces
+ // a non-canonical loop by moving a back edge. So we avoid this optimization
+ // for loop headers if NeedCanonicalLoop is set.
+ bool InHeader = !LoopHeaders.empty() && is_contained(LoopHeaders, BB);
+ bool AvoidThreading = Options.NeedCanonicalLoop && InHeader;
+ if (!AvoidThreading)
+ if (foldCondBranchOnValueKnownInPredecessor(BI, DTU, DL, Options.AC))
+ return requestResimplify();
// Scan predecessor blocks for conditional branches.
for (BasicBlock *Pred : predecessors(BB))
diff --git a/llvm/test/CodeGen/ARM/2013-05-05-IfConvertBug.ll b/llvm/test/CodeGen/ARM/2013-05-05-IfConvertBug.ll
index 344bb15d2a8b8..8f798fac06f54 100644
--- a/llvm/test/CodeGen/ARM/2013-05-05-IfConvertBug.ll
+++ b/llvm/test/CodeGen/ARM/2013-05-05-IfConvertBug.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 | FileCheck %s
-; RUN: llc < %s -mtriple=thumbv8 | FileCheck -check-prefix=CHECK-V8 %s
-; RUN: llc < %s -mtriple=thumbv7 -arm-restrict-it | FileCheck -check-prefix=CHECK-RESTRICT-IT %s
+; RUN: llc -keep-loops="false" < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 | FileCheck %s
+; RUN: llc -keep-loops="false" < %s -mtriple=thumbv8 | FileCheck -check-prefix=CHECK-V8 %s
+; RUN: llc -keep-loops="false" < %s -mtriple=thumbv7 -arm-restrict-it | FileCheck -check-prefix=CHECK-RESTRICT-IT %s
define i32 @t1(i32 %a, i32 %b, ptr %retaddr) {
; CHECK-LABEL: t1:
diff --git a/llvm/test/Transforms/SimplifyCFG/2008-07-13-InfLoopMiscompile.ll b/llvm/test/Transforms/SimplifyCFG/2008-07-13-InfLoopMiscompile.ll
index 2e9e7b19c73e2..44d92e1a1c210 100644
--- a/llvm/test/Transforms/SimplifyCFG/2008-07-13-InfLoopMiscompile.ll
+++ b/llvm/test/Transforms/SimplifyCFG/2008-07-13-InfLoopMiscompile.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 -S | FileCheck %s
+; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 -keep-loops="false" -S | FileCheck %s
; PR2540
; Outval should end up with a select from 0/2, not all constants.
@@ -52,4 +52,3 @@ func_1.exit: ; preds = %cowblock, %entry
}
declare i32 @printf(ptr, ...) nounwind
-
diff --git a/llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll b/llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll
new file mode 100644
index 0000000000000..a64108f6346b9
--- /dev/null
+++ b/llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll
@@ -0,0 +1,37 @@
+; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 -S | FileCheck --check-prefix=NO-THREADING %s
+; Checks that we do not thread the control flow through the loop header bb1 as
+; that will introduce a non-canonical loop
+
+; NO-THREADING-LABEL: define void @__start
+; NO-THREADING: bb3:
+; NO-THREADING-NEXT: br i1 %cond, label %bb1, label %bb5
+
+; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 --keep-loops="false" -S | FileCheck --check-prefix=THREADING %s
+; Checks that we thread the control flow through the loop header bb1 since we
+; do not request --keep-loops
+
+; THREADING-LABEL: define void @__start
+; THREADING: bb3:
+; THREADING-NEXT: br i1 %cond, label %bb4, label %bb5
+
+define void @__start(i1 %cond) {
+entry:
+ br label %bb1
+
+bb1: ; preds = %bb3, %entry
+ br i1 %cond, label %bb4, label %bb2
+
+bb2: ; preds = %bb1
+ %_0_ = add i16 0, 0
+ br label %bb3
+
+bb3: ; preds = %bb4, %bb2
+ br i1 %cond, label %bb1, label %bb5
+
+bb4: ; preds = %bb1
+ %_1_ = add i32 0, 1
+ br label %bb3
+
+bb5: ; preds = %bb3
+ ret void
+}
diff --git a/llvm/test/Transforms/SimplifyCFG/branch-phi-thread.ll b/llvm/test/Transforms/SimplifyCFG/branch-phi-thread.ll
index 0afec05ecbd6a..ec9423bd81675 100644
--- a/llvm/test/Transforms/SimplifyCFG/branch-phi-thread.ll
+++ b/llvm/test/Transforms/SimplifyCFG/branch-phi-thread.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -passes=simplifycfg,adce -simplifycfg-require-and-preserve-domtree=1 -S | FileCheck %s
+; RUN: opt < %s -passes=simplifycfg,adce -simplifycfg-require-and-preserve-domtree=1 -keep-loops="false" -S | FileCheck %s
declare void @f1()
diff --git a/llvm/test/Transforms/SimplifyCFG/jump-threading.ll b/llvm/test/Transforms/SimplifyCFG/jump-threading.ll
index 50a32413a0551..a4073ae6eb0b4 100644
--- a/llvm/test/Transforms/SimplifyCFG/jump-threading.ll
+++ b/llvm/test/Transforms/SimplifyCFG/jump-threading.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -S -passes=simplifycfg < %s | FileCheck %s
+; RUN: opt -S -passes=simplifycfg -keep-loops="false" < %s | FileCheck %s
declare void @foo()
declare void @bar()
diff --git a/llvm/test/Transforms/SimplifyCFG/two-entry-phi-return.ll b/llvm/test/Transforms/SimplifyCFG/two-entry-phi-return.ll
index 57930c91b9796..f6d71ddda74fe 100644
--- a/llvm/test/Transforms/SimplifyCFG/two-entry-phi-return.ll
+++ b/llvm/test/Transforms/SimplifyCFG/two-entry-phi-return.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 -S | FileCheck %s
+; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 -keep-loops="false" -S | FileCheck %s
define i1 @qux(ptr %m, ptr %n, ptr %o, ptr %p) nounwind {
; CHECK-LABEL: @qux(
>From e6c922727d473eb4290c5e5349bf5de71cb34caf Mon Sep 17 00:00:00 2001
From: Arne Stenkrona <arne.stenkrona at arm.com>
Date: Tue, 29 Jul 2025 16:02:38 +0200
Subject: [PATCH 2/2] Move threading check, run update_test_checks.py
---
llvm/lib/Transforms/Utils/SimplifyCFG.cpp | 29 ++++----
.../2025-07-29-non-canoncial-loop.ll | 73 +++++++++++++------
2 files changed, 65 insertions(+), 37 deletions(-)
diff --git a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
index d8385beb349d6..89ff74ed73f68 100644
--- a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -286,6 +286,7 @@ class SimplifyCFGOpt {
bool simplifyBranch(BranchInst *Branch, IRBuilder<> &Builder);
bool simplifyUncondBranch(BranchInst *BI, IRBuilder<> &Builder);
bool simplifyCondBranch(BranchInst *BI, IRBuilder<> &Builder);
+ bool foldCondBranchOnValueKnownInPredecessor(BranchInst *BI);
bool tryToSimplifyUncondBranchWithICmpInIt(ICmpInst *ICI,
IRBuilder<> &Builder);
@@ -3604,15 +3605,23 @@ foldCondBranchOnValueKnownInPredecessorImpl(BranchInst *BI, DomTreeUpdater *DTU,
return false;
}
-static bool foldCondBranchOnValueKnownInPredecessor(BranchInst *BI,
- DomTreeUpdater *DTU,
- const DataLayout &DL,
- AssumptionCache *AC) {
+#include <iostream>
+
+bool SimplifyCFGOpt::foldCondBranchOnValueKnownInPredecessor(BranchInst *BI) {
+ // Note: If BB is a loop header then there is a risk that threading introduces
+ // a non-canonical loop by moving a back edge. So we avoid this optimization
+ // for loop headers if NeedCanonicalLoop is set.
+ bool InHeader = is_contained(LoopHeaders, BI->getParent());
+ bool AvoidThreading = Options.NeedCanonicalLoop && InHeader;
+ if (AvoidThreading) {
+ return false;
+ }
+
std::optional<bool> Result;
bool EverChanged = false;
do {
// Note that None means "we changed things, but recurse further."
- Result = foldCondBranchOnValueKnownInPredecessorImpl(BI, DTU, DL, AC);
+ Result = foldCondBranchOnValueKnownInPredecessorImpl(BI, DTU, DL, Options.AC);
EverChanged |= Result == std::nullopt || *Result;
} while (Result == std::nullopt);
return EverChanged;
@@ -8030,14 +8039,8 @@ bool SimplifyCFGOpt::simplifyCondBranch(BranchInst *BI, IRBuilder<> &Builder) {
// If this is a branch on something for which we know the constant value in
// predecessors (e.g. a phi node in the current block), thread control
// through this block.
- // Note: If BB is a loop header then there is a risk that threading introduces
- // a non-canonical loop by moving a back edge. So we avoid this optimization
- // for loop headers if NeedCanonicalLoop is set.
- bool InHeader = !LoopHeaders.empty() && is_contained(LoopHeaders, BB);
- bool AvoidThreading = Options.NeedCanonicalLoop && InHeader;
- if (!AvoidThreading)
- if (foldCondBranchOnValueKnownInPredecessor(BI, DTU, DL, Options.AC))
- return requestResimplify();
+ if (foldCondBranchOnValueKnownInPredecessor(BI))
+ return requestResimplify();
// Scan predecessor blocks for conditional branches.
for (BasicBlock *Pred : predecessors(BB))
diff --git a/llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll b/llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll
index a64108f6346b9..322dd98f48df1 100644
--- a/llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll
+++ b/llvm/test/Transforms/SimplifyCFG/2025-07-29-non-canoncial-loop.ll
@@ -1,37 +1,62 @@
-; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 -S | FileCheck --check-prefix=NO-THREADING %s
-; Checks that we do not thread the control flow through the loop header bb1 as
-; that will introduce a non-canonical loop
-
-; NO-THREADING-LABEL: define void @__start
-; NO-THREADING: bb3:
-; NO-THREADING-NEXT: br i1 %cond, label %bb1, label %bb5
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 --keep-loops="true" -S | FileCheck --check-prefix=NO-THREADING %s
+; Checks that we do not thread the control flow through the loop header loop_header as
+; that will introduce a non-canonical loop.
; RUN: opt < %s -passes=simplifycfg -simplifycfg-require-and-preserve-domtree=1 --keep-loops="false" -S | FileCheck --check-prefix=THREADING %s
-; Checks that we thread the control flow through the loop header bb1 since we
-; do not request --keep-loops
-
-; THREADING-LABEL: define void @__start
-; THREADING: bb3:
-; THREADING-NEXT: br i1 %cond, label %bb4, label %bb5
+; Checks that we thread the control flow through the loop header loop_header since we
+; do not request --keep-loops.
define void @__start(i1 %cond) {
+; NO-THREADING-LABEL: define void @__start(
+; NO-THREADING-SAME: i1 [[COND:%.*]]) {
+; NO-THREADING-NEXT: [[ENTRY:.*:]]
+; NO-THREADING-NEXT: br label %[[LOOP_HEADER:.*]]
+; NO-THREADING: [[LOOP_HEADER]]:
+; NO-THREADING-NEXT: br i1 [[COND]], label %[[LOOP_BODY_1:.*]], label %[[LOOP_BODY_0:.*]]
+; NO-THREADING: [[LOOP_BODY_0]]:
+; NO-THREADING-NEXT: [[_0_:%.*]] = add i16 0, 0
+; NO-THREADING-NEXT: br label %[[LOOP_EXIT:.*]]
+; NO-THREADING: [[LOOP_BODY_1]]:
+; NO-THREADING-NEXT: [[_1_:%.*]] = add i32 0, 1
+; NO-THREADING-NEXT: br label %[[LOOP_EXIT]]
+; NO-THREADING: [[LOOP_EXIT]]:
+; NO-THREADING-NEXT: br i1 [[COND]], label %[[LOOP_HEADER]], label %[[EXIT:.*]]
+; NO-THREADING: [[EXIT]]:
+; NO-THREADING-NEXT: ret void
+;
+; THREADING-LABEL: define void @__start(
+; THREADING-SAME: i1 [[COND:%.*]]) {
+; THREADING-NEXT: [[ENTRY:.*:]]
+; THREADING-NEXT: br i1 [[COND]], label %[[LOOP_BODY_1:.*]], label %[[LOOP_BODY_0:.*]]
+; THREADING: [[LOOP_BODY_0]]:
+; THREADING-NEXT: [[_0_:%.*]] = add i16 0, 0
+; THREADING-NEXT: br label %[[LOOP_EXIT:.*]]
+; THREADING: [[LOOP_BODY_1]]:
+; THREADING-NEXT: [[_1_:%.*]] = add i32 0, 1
+; THREADING-NEXT: br label %[[LOOP_EXIT]]
+; THREADING: [[LOOP_EXIT]]:
+; THREADING-NEXT: br i1 [[COND]], label %[[LOOP_BODY_1]], label %[[EXIT:.*]]
+; THREADING: [[EXIT]]:
+; THREADING-NEXT: ret void
+;
entry:
- br label %bb1
+ br label %loop_header
-bb1: ; preds = %bb3, %entry
- br i1 %cond, label %bb4, label %bb2
+loop_header: ; preds = %loop_exit, %entry
+ br i1 %cond, label %loop_body_1, label %loop_body_0
-bb2: ; preds = %bb1
+loop_body_0: ; preds = %loop_header
%_0_ = add i16 0, 0
- br label %bb3
+ br label %loop_exit
-bb3: ; preds = %bb4, %bb2
- br i1 %cond, label %bb1, label %bb5
-
-bb4: ; preds = %bb1
+loop_body_1: ; preds = %loop_header
%_1_ = add i32 0, 1
- br label %bb3
+ br label %loop_exit
+
+loop_exit: ; preds = %loop_body_1, %loop_body_0
+ br i1 %cond, label %loop_header, label %exit
-bb5: ; preds = %bb3
+exit: ; preds = %loop_exit
ret void
}
More information about the llvm-commits
mailing list