compnerd created this revision.
compnerd added reviewers: vsk, rnk.
Herald added subscribers: llvm-commits, cfe-commits, dang, hiraditya.
Herald added projects: clang, LLVM.
compnerd requested review of this revision.
In order for the hot/cold splitting pass to graduate out of
experimental status, users need some way to safely enable it.
The current method of passing -mllvm -hot-cold-split=true to clang is
not safe, because directly setting a `cl::opt` cannot interact well with
other CC1 options (e.g. -O0, or `-disable-llvm-passes`).
This patch adds -f[no-]split-cold-code CC1 options to clang so that the
splitting pass can be toggled/combined with other options without issue.
This makes it possible to deploy the new pass on a large scale.
Patch by Vedant Kumar <v...@apple.com>!
This is extracted from the patches from the Swift contributed changes to
LLVM at https://github.com/llvm/llvm-project-staging/.
The few test changes here are to allow the tests to continue working
unperturbed.
This has been shipping with the Apple toolchain and has been tested.
The known deficiencies of the outlining here are the incorrect handling
for Windows EH unwind pads which are sometimes duplicately outlined
incorrectly.
Repository:
rG LLVM Github Monorepo
https://reviews.llvm.org/D89078
Files:
clang/include/clang/Basic/CodeGenOptions.def
clang/include/clang/Driver/Options.td
clang/lib/CodeGen/BackendUtil.cpp
clang/lib/Frontend/CompilerInvocation.cpp
clang/test/CodeGen/split-cold-code.c
clang/test/CodeGenCXX/microsoft-abi-typeid.cpp
clang/test/CodeGenCXX/nrvo.cpp
clang/test/CodeGenObjC/synchronized.m
clang/test/CodeGenObjCXX/exceptions-legacy.mm
llvm/include/llvm/Passes/PassBuilder.h
llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
llvm/lib/Passes/PassBuilder.cpp
llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
Index: llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
===================================================================
--- llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -194,6 +194,7 @@
VerifyInput = false;
VerifyOutput = false;
MergeFunctions = false;
+ SplitColdCode = false;
PrepareForLTO = false;
EnablePGOInstrGen = false;
EnablePGOCSInstrGen = false;
@@ -865,7 +866,8 @@
// See comment in the new PM for justification of scheduling splitting at
// this stage (\ref buildModuleSimplificationPipeline).
- if (EnableHotColdSplit && !(PrepareForLTO || PrepareForThinLTO))
+ if ((EnableHotColdSplit || SplitColdCode) &&
+ !(PrepareForLTO || PrepareForThinLTO))
MPM.add(createHotColdSplittingPass());
if (MergeFunctions)
@@ -1089,7 +1091,7 @@
legacy::PassManagerBase &PM) {
// See comment in the new PM for justification of scheduling splitting at
// this stage (\ref buildLTODefaultPipeline).
- if (EnableHotColdSplit)
+ if (EnableHotColdSplit || SplitColdCode)
PM.add(createHotColdSplittingPass());
// Delete basic blocks, which optimization passes may have killed.
Index: llvm/lib/Passes/PassBuilder.cpp
===================================================================
--- llvm/lib/Passes/PassBuilder.cpp
+++ llvm/lib/Passes/PassBuilder.cpp
@@ -1231,7 +1231,7 @@
// Split out cold code. Splitting is done late to avoid hiding context from
// other optimizations and inadvertently regressing performance. The tradeoff
// is that this has a higher code size cost than splitting early.
- if (EnableHotColdSplit && !LTOPreLink)
+ if ((EnableHotColdSplit || SplitColdCode) && !LTOPreLink)
MPM.addPass(HotColdSplittingPass());
// LoopSink pass sinks instructions hoisted by LICM, which serves as a
@@ -1620,7 +1620,7 @@
// Enable splitting late in the FullLTO post-link pipeline. This is done in
// the same stage in the old pass manager (\ref addLateLTOOptimizationPasses).
- if (EnableHotColdSplit)
+ if (EnableHotColdSplit || SplitColdCode)
MPM.addPass(HotColdSplittingPass());
// Add late LTO optimization passes.
@@ -2817,6 +2817,10 @@
return Error::success();
}
+void PassBuilder::setEnableHotColdSplitting(bool Enabled) {
+ SplitColdCode = Enabled;
+}
+
bool PassBuilder::isAAPassName(StringRef PassName) {
#define MODULE_ALIAS_ANALYSIS(NAME, CREATE_PASS) \
if (PassName == NAME) \
Index: llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
===================================================================
--- llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
+++ llvm/include/llvm/Transforms/IPO/PassManagerBuilder.h
@@ -167,6 +167,7 @@
bool VerifyInput;
bool VerifyOutput;
bool MergeFunctions;
+ bool SplitColdCode;
bool PrepareForLTO;
bool PrepareForThinLTO;
bool PerformThinLTO;
Index: llvm/include/llvm/Passes/PassBuilder.h
===================================================================
--- llvm/include/llvm/Passes/PassBuilder.h
+++ llvm/include/llvm/Passes/PassBuilder.h
@@ -684,6 +684,10 @@
const std::function<bool(ModulePassManager &, ArrayRef<PipelineElement>,
bool VerifyEachPass, bool DebugLogging)> &C);
+ /// Enable or disable the hot/cold splitting optimization. By default, it is
+ /// disabled.
+ void setEnableHotColdSplitting(bool Enabled);
+
/// Add PGOInstrumenation passes for O0 only.
void addPGOInstrPassesForO0(ModulePassManager &MPM, bool DebugLogging,
bool RunProfileGen, bool IsCS,
@@ -786,6 +790,9 @@
// AA callbacks
SmallVector<std::function<bool(StringRef Name, AAManager &AA)>, 2>
AAParsingCallbacks;
+
+ // Tunable passes
+ bool SplitColdCode = false;
};
/// This utility template takes care of adding require<> and invalidate<>
Index: clang/test/CodeGenObjCXX/exceptions-legacy.mm
===================================================================
--- clang/test/CodeGenObjCXX/exceptions-legacy.mm
+++ clang/test/CodeGenObjCXX/exceptions-legacy.mm
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -triple i386-apple-darwin10 -fobjc-runtime=macosx-fragile-10.5 -emit-llvm -fexceptions -fobjc-exceptions -O2 -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple i386-apple-darwin10 -fno-split-cold-code -fobjc-runtime=macosx-fragile-10.5 -emit-llvm -fexceptions -fobjc-exceptions -O2 -o - %s | FileCheck %s
// Test we maintain at least a basic amount of interoperation between
// ObjC and C++ exceptions in the legacy runtime.
Index: clang/test/CodeGenObjC/synchronized.m
===================================================================
--- clang/test/CodeGenObjC/synchronized.m
+++ clang/test/CodeGenObjC/synchronized.m
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -emit-llvm -triple i686-apple-darwin9 -fobjc-runtime=macosx-fragile-10.5 -o - %s -O2 | FileCheck %s
+// RUN: %clang_cc1 -emit-llvm -triple i686-apple-darwin9 -fno-split-cold-code -fobjc-runtime=macosx-fragile-10.5 -o - %s -O2 | FileCheck %s
@interface MyClass
{
Index: clang/test/CodeGenCXX/nrvo.cpp
===================================================================
--- clang/test/CodeGenCXX/nrvo.cpp
+++ clang/test/CodeGenCXX/nrvo.cpp
@@ -1,6 +1,6 @@
-// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm -O1 -fno-experimental-new-pass-manager -o - %s | FileCheck %s
-// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm -O1 -fno-experimental-new-pass-manager -fcxx-exceptions -fexceptions -std=c++03 -o - %s | FileCheck --check-prefixes=CHECK-EH,CHECK-EH-03 %s
-// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm -O1 -fno-experimental-new-pass-manager -fcxx-exceptions -fexceptions -std=c++11 -o - %s | FileCheck --check-prefixes=CHECK-EH,CHECK-EH-11 %s
+// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm -O1 -fno-split-cold-code -fno-experimental-new-pass-manager -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm -O1 -fno-split-cold-code -fno-experimental-new-pass-manager -fcxx-exceptions -fexceptions -std=c++03 -o - %s | FileCheck --check-prefixes=CHECK-EH,CHECK-EH-03 %s
+// RUN: %clang_cc1 -triple i386-unknown-unknown -emit-llvm -O1 -fno-split-cold-code -fno-experimental-new-pass-manager -fcxx-exceptions -fexceptions -std=c++11 -o - %s | FileCheck --check-prefixes=CHECK-EH,CHECK-EH-11 %s
// Test code generation for the named return value optimization.
class X {
Index: clang/test/CodeGenCXX/microsoft-abi-typeid.cpp
===================================================================
--- clang/test/CodeGenCXX/microsoft-abi-typeid.cpp
+++ clang/test/CodeGenCXX/microsoft-abi-typeid.cpp
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -emit-llvm -O1 -o - -triple=i386-pc-win32 %s -fexceptions -fcxx-exceptions | FileCheck %s
+// RUN: %clang_cc1 -emit-llvm -O1 -o - -triple=i386-pc-win32 %s -fno-split-cold-code -fexceptions -fcxx-exceptions | FileCheck %s
struct type_info;
namespace std { using ::type_info; }
Index: clang/test/CodeGen/split-cold-code.c
===================================================================
--- /dev/null
+++ clang/test/CodeGen/split-cold-code.c
@@ -0,0 +1,81 @@
+// === Old PM ===
+// No splitting at -O0.
+// RUN: %clang_cc1 -O0 -fsplit-cold-code -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-NO-SPLIT %s
+//
+// No splitting at -Oz.
+// RUN: %clang_cc1 -Oz -fsplit-cold-code -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-NO-SPLIT %s
+//
+// Split by default.
+// RUN: %clang_cc1 -O3 -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-SPLIT %s
+//
+// No splitting when it's explicitly disabled.
+// RUN: %clang_cc1 -O3 -fno-split-cold-code -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-NO-SPLIT %s
+//
+// No splitting when LLVM passes are disabled.
+// RUN: %clang_cc1 -O3 -fsplit-cold-code -disable-llvm-passes -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-NO-SPLIT %s
+//
+// Split at -O1.
+// RUN: %clang_cc1 -O1 -fsplit-cold-code -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-SPLIT %s
+//
+// Split at -Os.
+// RUN: %clang_cc1 -Os -fsplit-cold-code -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-SPLIT %s
+//
+// Split at -O2.
+// RUN: %clang_cc1 -O2 -fsplit-cold-code -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-SPLIT %s
+//
+// Split at -O3.
+// RUN: %clang_cc1 -O3 -fsplit-cold-code -mllvm -debug-pass=Structure \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=OLDPM-SPLIT %s
+
+// OLDPM-NO-SPLIT-NOT: Hot Cold Split
+
+// OLDPM-SPLIT: Hot Cold Split
+
+// === New PM (ditto) ===
+// No splitting at -O0.
+// RUN: %clang_cc1 -O0 -fsplit-cold-code -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-NO-SPLIT %s
+//
+// No splitting at -Oz.
+// RUN: %clang_cc1 -Oz -fsplit-cold-code -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-NO-SPLIT %s
+//
+// Split by default.
+// RUN: %clang_cc1 -O3 -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-SPLIT %s
+//
+// No splitting when it's explicitly disabled.
+// RUN: %clang_cc1 -O3 -fno-split-cold-code -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-NO-SPLIT %s
+//
+// No splitting when LLVM passes are disabled.
+// RUN: %clang_cc1 -O3 -fsplit-cold-code -disable-llvm-passes -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-NO-SPLIT %s
+//
+// Split at -O1.
+// RUN: %clang_cc1 -O1 -fsplit-cold-code -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-SPLIT %s
+//
+// Split at -Os.
+// RUN: %clang_cc1 -Os -fsplit-cold-code -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-SPLIT %s
+//
+// Split at -O2.
+// RUN: %clang_cc1 -O2 -fsplit-cold-code -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-SPLIT %s
+//
+// Split at -O3.
+// RUN: %clang_cc1 -O3 -fsplit-cold-code -fexperimental-new-pass-manager -fdebug-pass-manager \
+// RUN: -emit-llvm -o /dev/null %s 2>&1 | FileCheck --check-prefix=NEWPM-SPLIT %s
+
+// NEWPM-NO-SPLIT-NOT: HotColdSplit
+
+// NEWPM-SPLIT: HotColdSplit
Index: clang/lib/Frontend/CompilerInvocation.cpp
===================================================================
--- clang/lib/Frontend/CompilerInvocation.cpp
+++ clang/lib/Frontend/CompilerInvocation.cpp
@@ -1454,6 +1454,13 @@
Opts.DefaultFunctionAttrs = Args.getAllArgValues(OPT_default_function_attr);
+ // -f[no-]split-cold-code
+ // This may only be enabled when optimizing, and when small code size
+ // increases are tolerable.
+ Opts.SplitColdCode =
+ (Opts.OptimizationLevel > 0) && (Opts.OptimizeSize != 2) &&
+ Args.hasFlag(OPT_fsplit_cold_code, OPT_fno_split_cold_code, true);
+
Opts.PassPlugins = Args.getAllArgValues(OPT_fpass_plugin_EQ);
Opts.SymbolPartition =
Index: clang/lib/CodeGen/BackendUtil.cpp
===================================================================
--- clang/lib/CodeGen/BackendUtil.cpp
+++ clang/lib/CodeGen/BackendUtil.cpp
@@ -643,6 +643,7 @@
// enabled when loop unrolling is enabled.
PMBuilder.LoopsInterleaved = CodeGenOpts.UnrollLoops;
PMBuilder.MergeFunctions = CodeGenOpts.MergeFunctions;
+ PMBuilder.SplitColdCode = CodeGenOpts.SplitColdCode;
PMBuilder.PrepareForThinLTO = CodeGenOpts.PrepareForThinLTO;
PMBuilder.PrepareForLTO = CodeGenOpts.PrepareForLTO;
PMBuilder.RerollLoops = CodeGenOpts.RerollLoops;
@@ -1272,6 +1273,9 @@
// configure the pipeline.
PassBuilder::OptimizationLevel Level = mapToLevel(CodeGenOpts);
+ // -f[no-]split-cold-code
+ PB.setEnableHotColdSplitting(CodeGenOpts.SplitColdCode);
+
// If we reached here with a non-empty index file name, then the index
// file was empty and we are not performing ThinLTO backend compilation
// (used in testing in a distributed build environment). Drop any the type
Index: clang/include/clang/Driver/Options.td
===================================================================
--- clang/include/clang/Driver/Options.td
+++ clang/include/clang/Driver/Options.td
@@ -3782,6 +3782,10 @@
HelpText<"Dump the layouts of all vtables that will be emitted in a translation unit">;
def fmerge_functions : Flag<["-"], "fmerge-functions">,
HelpText<"Permit merging of identical functions when optimizing.">;
+def fsplit_cold_code : Flag<["-"], "fsplit-cold-code">,
+ HelpText<"Permit splitting of cold code when optimizing (off by default).">;
+def fno_split_cold_code : Flag<["-"], "fno-split-cold-code">,
+ HelpText<"Disable splitting of cold code when optimizing.">;
def femit_coverage_notes : Flag<["-"], "femit-coverage-notes">,
HelpText<"Emit a gcov coverage notes file when compiling.">;
def femit_coverage_data: Flag<["-"], "femit-coverage-data">,
Index: clang/include/clang/Basic/CodeGenOptions.def
===================================================================
--- clang/include/clang/Basic/CodeGenOptions.def
+++ clang/include/clang/Basic/CodeGenOptions.def
@@ -151,6 +151,7 @@
///< linker.
CODEGENOPT(MergeAllConstants , 1, 1) ///< Merge identical constants.
CODEGENOPT(MergeFunctions , 1, 0) ///< Set when -fmerge-functions is enabled.
+CODEGENOPT(SplitColdCode , 1, 0) ///< Set when -fsplit-cold-code is enabled.
CODEGENOPT(MemProf , 1, 0) ///< Set when -fmemory-profile is enabled.
CODEGENOPT(MSVolatile , 1, 0) ///< Set when /volatile:ms is enabled.
CODEGENOPT(NoCommon , 1, 0) ///< Set when -fno-common or C++ is enabled.
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
