https://github.com/minglotus-6 updated
https://github.com/llvm/llvm-project/pull/75954
>From 4936920fbbe5e70a47be35b057200de3b07a087f Mon Sep 17 00:00:00 2001
From: mingmingl <mingmi...@google.com>
Date: Mon, 18 Dec 2023 20:21:40 -0800
Subject: [PATCH 1/2] Reapply "Reland "[PGO][GlobalValue][LTO]In
GlobalValues::getGlobalIdentifier, use semicolon as delimiter for
local-linkage varibles. "" (#75888)
This reverts commit 6ce23ea0ab6370c944f5e426a20217f93f41aa15.
---
compiler-rt/test/profile/CMakeLists.txt | 2 +-
...trprof-thinlto-indirect-call-promotion.cpp | 115 ++++++++++++++++++
llvm/include/llvm/IR/GlobalValue.h | 4 +
llvm/include/llvm/ProfileData/InstrProf.h | 26 ++--
llvm/lib/IR/Globals.cpp | 12 +-
llvm/lib/ProfileData/InstrProf.cpp | 36 ++++--
llvm/lib/ProfileData/InstrProfReader.cpp | 9 +-
.../thinlto-function-summary-originalnames.ll | 10 +-
llvm/test/ThinLTO/X86/memprof-basic.ll | 26 ++--
.../X86/memprof-duplicate-context-ids.ll | 10 +-
.../ThinLTO/X86/memprof-funcassigncloning.ll | 6 +-
llvm/test/ThinLTO/X86/memprof-indirectcall.ll | 32 ++---
llvm/test/ThinLTO/X86/memprof-inlined.ll | 14 +--
.../Inputs/thinlto_indirect_call_promotion.ll | 16 ---
.../thinlto_indirect_call_promotion.profraw | Bin 0 -> 528 bytes
..._thinlto_indirect_call_promotion_inputs.sh | 62 ++++++++++
.../thinlto_indirect_call_promotion.ll | 105 +++++++++++-----
llvm/unittests/ProfileData/InstrProfTest.cpp | 4 +-
18 files changed, 362 insertions(+), 127 deletions(-)
create mode 100644
compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
delete mode 100644
llvm/test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.ll
create mode 100644
llvm/test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.profraw
create mode 100755
llvm/test/Transforms/PGOProfile/Inputs/update_thinlto_indirect_call_promotion_inputs.sh
diff --git a/compiler-rt/test/profile/CMakeLists.txt
b/compiler-rt/test/profile/CMakeLists.txt
index 975e4c42f4b640..eebe0469efebe0 100644
--- a/compiler-rt/test/profile/CMakeLists.txt
+++ b/compiler-rt/test/profile/CMakeLists.txt
@@ -6,7 +6,7 @@ set(PROFILE_TESTSUITES)
set(PROFILE_TEST_DEPS ${SANITIZER_COMMON_LIT_TEST_DEPS} compiler-rt-headers)
list(APPEND PROFILE_TEST_DEPS profile)
if(NOT COMPILER_RT_STANDALONE_BUILD)
- list(APPEND PROFILE_TEST_DEPS llvm-profdata llvm-cov)
+ list(APPEND PROFILE_TEST_DEPS llvm-cov llvm-dis llvm-lto llvm-profdata opt)
if(NOT APPLE AND COMPILER_RT_HAS_LLD AND "lld" IN_LIST LLVM_ENABLE_PROJECTS)
list(APPEND PROFILE_TEST_DEPS lld)
endif()
diff --git
a/compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
b/compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
new file mode 100644
index 00000000000000..82ca1cd7d0a564
--- /dev/null
+++ b/compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
@@ -0,0 +1,115 @@
+// This is a regression test for ThinLTO indirect-call-promotion when candidate
+// callees need to be imported from another IR module. In the C++ test case,
+// `main` calls `global_func` which is defined in another module. `global_func`
+// has two indirect callees, one has external linkage and one has local
linkage.
+// All three functions should be imported into the IR module of main.
+
+// What the test does:
+// - Generate raw profiles from executables and convert it to indexed profiles.
+// During the conversion, a profiled callee address in raw profiles will be
+// converted to function hash in indexed profiles.
+// - Run IRPGO profile use and ThinTLO prelink pipeline and get LLVM bitcodes
+// for both cpp files in the C++ test case.
+// - Generate ThinLTO summary file with LLVM bitcodes, and run
`function-import` pass.
+// - Run `pgo-icall-prom` pass for the IR module which needs to import callees.
+
+// Use lld as linker for more robust test. We need to REQUIRE LLVMgold.so for
+// LTO if default linker is GNU ld or gold anyway.
+// REQUIRES: lld-available
+
+// Test should fail where linkage-name and mangled-name diverges, see issue
https://github.com/llvm/llvm-project/issues/74565).
+// Currently, this name divergence happens on Mach-O object file format, or on
+// many (but not all) 32-bit Windows systems.
+//
+// XFAIL: system-darwin
+//
+// Mark 32-bit Windows as UNSUPPORTED for now as opposed to XFAIL. This test
+// should fail on many (but not all) 32-bit Windows systems and succeed on the
+// rest. The flexibility in triple string parsing makes it tricky to capture
+// both sets accurately. i[3-9]86 specifies arch as Triple::ArchType::x86,
(win32|windows)
+// specifies OS as Triple::OS::Win32
+//
+// UNSUPPORTED: target={{i.86.*windows.*}}
+
+// RUN: rm -rf %t && split-file %s %t && cd %t
+
+// Do setup work for all below tests.
+// Generate raw profiles from real programs and convert it into indexed
profiles.
+// Use clangxx_pgogen for IR level instrumentation for C++.
+// RUN: %clangxx_pgogen -fuse-ld=lld -O2 lib.cpp main.cpp -o main
+// RUN: env LLVM_PROFILE_FILE=main.profraw %run ./main
+// RUN: llvm-profdata merge main.profraw -o main.profdata
+
+// Use profile on lib and get bitcode, test that local function callee0 has
+// expected !PGOFuncName metadata and external function callee1 doesn't have
+// !PGOFuncName metadata. Explicitly skip ICP pass to test ICP happens as
+// expected in the IR module that imports functions from lib.
+// RUN: %clang -mllvm -disable-icp -fprofile-use=main.profdata -flto=thin -O2
-c lib.cpp -o lib.bc
+// RUN: llvm-dis lib.bc -o - | FileCheck %s --check-prefix=PGOName
+
+// Use profile on main and get bitcode.
+// RUN: %clang -fprofile-use=main.profdata -flto=thin -O2 -c main.cpp -o
main.bc
+
+// Run llvm-lto to get summary file.
+// RUN: llvm-lto -thinlto -o summary main.bc lib.bc
+
+// Test the imports of functions. Default import thresholds would work but do
+// explicit override to be more futureproof. Note all functions have one basic
+// block with a function-entry-count of one, so they are actually hot functions
+// per default profile summary hotness cutoff.
+// RUN: opt -passes=function-import -import-instr-limit=100
-import-cold-multiplier=1 -summary-file summary.thinlto.bc main.bc -o
main.import.bc -print-imports 2>&1 | FileCheck %s --check-prefix=IMPORTS
+// Test that '_Z11global_funcv' has indirect calls annotated with value
profiles.
+// RUN: llvm-dis main.import.bc -o - | FileCheck %s --check-prefix=IR
+
+// Test that both candidates are ICP'ed and there is no `!VP` in the IR.
+// RUN: opt main.import.bc -icp-lto -passes=pgo-icall-prom -S
-pass-remarks=pgo-icall-prom 2>&1 | FileCheck %s
--check-prefixes=ICP-IR,ICP-REMARK --implicit-check-not="!VP"
+
+// IMPORTS: main.cpp: Import _Z7callee1v
+// IMPORTS: main.cpp: Import _ZL7callee0v.llvm.[[#]]
+// IMPORTS: main.cpp: Import _Z11global_funcv
+
+// PGOName: define {{(dso_local )?}}void @_Z7callee1v() #[[#]] !prof ![[#]] {
+// PGOName: define internal void @_ZL7callee0v() #[[#]] !prof ![[#]]
!PGOFuncName ![[#MD:]] {
+// PGOName: ![[#MD]] = !{!"{{.*}}lib.cpp;_ZL7callee0v"}
+
+// IR-LABEL: define available_externally {{.*}} void @_Z11global_funcv()
{{.*}} !prof ![[#]] {
+// IR-NEXT: entry:
+// IR-NEXT: %0 = load ptr, ptr @calleeAddrs
+// IR-NEXT: tail call void %0(), !prof ![[#PROF1:]]
+// IR-NEXT: %1 = load ptr, ptr getelementptr inbounds ([2 x ptr], ptr
@calleeAddrs,
+// IR-NEXT: tail call void %1(), !prof ![[#PROF2:]]
+
+// The GUID of indirect callee is the MD5 hash of
`/path/to/lib.cpp;_ZL7callee0v`
+// that depends on the directory. Use [[#]] for its MD5 hash.
+// Use {{.*}} for integer types so the test works on 32-bit and 64-bit systems.
+// IR: ![[#PROF1]] = !{!"VP", i32 0, {{.*}} 1, {{.*}} [[#]], {{.*}} 1}
+// IR: ![[#PROF2]] = !{!"VP", i32 0, {{.*}} 1, {{.*}} -3993653843325621743,
{{.*}} 1}
+
+// ICP-REMARK: Promote indirect call to _ZL7callee0v.llvm.[[#]] with count 1
out of 1
+// ICP-REMARK: Promote indirect call to _Z7callee1v with count 1 out of 1
+
+// ICP-IR: br i1 %[[#]], label %if.true.direct_targ, label
%if.false.orig_indirect, !prof ![[#BRANCH_WEIGHT1:]]
+// ICP-IR: br i1 %[[#]], label %if.true.direct_targ1, label
%if.false.orig_indirect2, !prof ![[#BRANCH_WEIGHT1]]
+// ICP-IR: ![[#BRANCH_WEIGHT1]] = !{!"branch_weights", i32 1, i32 0}
+
+//--- lib.h
+void global_func();
+
+//--- lib.cpp
+#include "lib.h"
+static void callee0() {}
+void callee1() {}
+typedef void (*FPT)();
+FPT calleeAddrs[] = {callee0, callee1};
+// `global_func`` might call one of two indirect callees. callee0 has internal
+// linkage and callee1 has external linkage.
+void global_func() {
+ FPT fp = calleeAddrs[0];
+ fp();
+ fp = calleeAddrs[1];
+ fp();
+}
+
+//--- main.cpp
+#include "lib.h"
+int main() { global_func(); }
diff --git a/llvm/include/llvm/IR/GlobalValue.h
b/llvm/include/llvm/IR/GlobalValue.h
index d1891c157099d4..e97a7f2b963606 100644
--- a/llvm/include/llvm/IR/GlobalValue.h
+++ b/llvm/include/llvm/IR/GlobalValue.h
@@ -41,6 +41,10 @@ namespace Intrinsic {
typedef unsigned ID;
} // end namespace Intrinsic
+// Choose ';' as the delimiter. ':' was used once but it doesn't work well for
+// Objective-C functions which commonly have :'s in their names.
+inline constexpr char kGlobalIdentifierDelimiter = ';';
+
class GlobalValue : public Constant {
public:
/// An enumeration for the kinds of linkage for global values.
diff --git a/llvm/include/llvm/ProfileData/InstrProf.h
b/llvm/include/llvm/ProfileData/InstrProf.h
index 288dc71d756aee..36be2e7d869e7b 100644
--- a/llvm/include/llvm/ProfileData/InstrProf.h
+++ b/llvm/include/llvm/ProfileData/InstrProf.h
@@ -171,6 +171,8 @@ inline StringRef getInstrProfCounterBiasVarName() {
/// Return the marker used to separate PGO names during serialization.
inline StringRef getInstrProfNameSeparator() { return "\01"; }
+/// Please use getIRPGOFuncName for LLVM IR instrumentation. This function is
+/// for front-end (Clang, etc) instrumentation.
/// Return the modified name for function \c F suitable to be
/// used the key for profile lookup. Variable \c InLTO indicates if this
/// is called in LTO optimization passes.
@@ -196,20 +198,22 @@ std::string getIRPGOFuncName(const Function &F, bool
InLTO = false);
std::pair<StringRef, StringRef> getParsedIRPGOFuncName(StringRef
IRPGOFuncName);
/// Return the name of the global variable used to store a function
-/// name in PGO instrumentation. \c FuncName is the name of the function
-/// returned by the \c getPGOFuncName call.
+/// name in PGO instrumentation. \c FuncName is the IRPGO function name
+/// (returned by \c getIRPGOFuncName) for LLVM IR instrumentation and PGO
+/// function name (returned by \c getPGOFuncName) for front-end
instrumentation.
std::string getPGOFuncNameVarName(StringRef FuncName,
GlobalValue::LinkageTypes Linkage);
/// Create and return the global variable for function name used in PGO
-/// instrumentation. \c FuncName is the name of the function returned
-/// by \c getPGOFuncName call.
+/// instrumentation. \c FuncName is the IRPGO function name (returned by
+/// \c getIRPGOFuncName) for LLVM IR instrumentation and PGO function name
+/// (returned by \c getPGOFuncName) for front-end instrumentation.
GlobalVariable *createPGOFuncNameVar(Function &F, StringRef PGOFuncName);
/// Create and return the global variable for function name used in PGO
-/// instrumentation. /// \c FuncName is the name of the function
-/// returned by \c getPGOFuncName call, \c M is the owning module,
-/// and \c Linkage is the linkage of the instrumented function.
+/// instrumentation. \c FuncName is the IRPGO function name (returned by
+/// \c getIRPGOFuncName) for LLVM IR instrumentation and PGO function name
+/// (returned by \c getPGOFuncName) for front-end instrumentation.
GlobalVariable *createPGOFuncNameVar(Module &M,
GlobalValue::LinkageTypes Linkage,
StringRef PGOFuncName);
@@ -417,11 +421,11 @@ uint64_t ComputeHash(StringRef K);
} // end namespace IndexedInstrProf
-/// A symbol table used for function PGO name look-up with keys
+/// A symbol table used for function [IR]PGO name look-up with keys
/// (such as pointers, md5hash values) to the function. A function's
-/// PGO name or name's md5hash are used in retrieving the profile
-/// data of the function. See \c getPGOFuncName() method for details
-/// on how PGO name is formed.
+/// [IR]PGO name or name's md5hash are used in retrieving the profile
+/// data of the function. See \c getIRPGOFuncName() and \c getPGOFuncName
+/// methods for details how [IR]PGO name is formed.
class InstrProfSymtab {
public:
using AddrHashMap = std::vector<std::pair<uint64_t, uint64_t>>;
diff --git a/llvm/lib/IR/Globals.cpp b/llvm/lib/IR/Globals.cpp
index 51bdbeb0abf2c4..239acd2181e854 100644
--- a/llvm/lib/IR/Globals.cpp
+++ b/llvm/lib/IR/Globals.cpp
@@ -144,25 +144,27 @@ void GlobalObject::copyAttributesFrom(const GlobalObject
*Src) {
std::string GlobalValue::getGlobalIdentifier(StringRef Name,
GlobalValue::LinkageTypes Linkage,
StringRef FileName) {
-
// Value names may be prefixed with a binary '1' to indicate
// that the backend should not modify the symbols due to any platform
// naming convention. Do not include that '1' in the PGO profile name.
if (Name[0] == '\1')
Name = Name.substr(1);
- std::string NewName = std::string(Name);
+ std::string GlobalName;
if (llvm::GlobalValue::isLocalLinkage(Linkage)) {
// For local symbols, prepend the main file name to distinguish them.
// Do not include the full path in the file name since there's no guarantee
// that it will stay the same, e.g., if the files are checked out from
// version control in different locations.
if (FileName.empty())
- NewName = NewName.insert(0, "<unknown>:");
+ GlobalName += "<unknown>";
else
- NewName = NewName.insert(0, FileName.str() + ":");
+ GlobalName += FileName;
+
+ GlobalName += kGlobalIdentifierDelimiter;
}
- return NewName;
+ GlobalName += Name;
+ return GlobalName;
}
std::string GlobalValue::getGlobalIdentifier() const {
diff --git a/llvm/lib/ProfileData/InstrProf.cpp
b/llvm/lib/ProfileData/InstrProf.cpp
index 649d814cfd9de0..134a400e639c4b 100644
--- a/llvm/lib/ProfileData/InstrProf.cpp
+++ b/llvm/lib/ProfileData/InstrProf.cpp
@@ -246,11 +246,27 @@ std::string InstrProfError::message() const {
char InstrProfError::ID = 0;
-std::string getPGOFuncName(StringRef RawFuncName,
- GlobalValue::LinkageTypes Linkage,
+std::string getPGOFuncName(StringRef Name, GlobalValue::LinkageTypes Linkage,
StringRef FileName,
uint64_t Version LLVM_ATTRIBUTE_UNUSED) {
- return GlobalValue::getGlobalIdentifier(RawFuncName, Linkage, FileName);
+ // Value names may be prefixed with a binary '1' to indicate
+ // that the backend should not modify the symbols due to any platform
+ // naming convention. Do not include that '1' in the PGO profile name.
+ if (Name[0] == '\1')
+ Name = Name.substr(1);
+
+ std::string NewName = std::string(Name);
+ if (llvm::GlobalValue::isLocalLinkage(Linkage)) {
+ // For local symbols, prepend the main file name to distinguish them.
+ // Do not include the full path in the file name since there's no guarantee
+ // that it will stay the same, e.g., if the files are checked out from
+ // version control in different locations.
+ if (FileName.empty())
+ NewName = NewName.insert(0, "<unknown>:");
+ else
+ NewName = NewName.insert(0, FileName.str() + ":");
+ }
+ return NewName;
}
// Strip NumPrefix level of directory name from PathNameStr. If the number of
@@ -300,12 +316,10 @@ getIRPGONameForGlobalObject(const GlobalObject &GO,
GlobalValue::LinkageTypes Linkage,
StringRef FileName) {
SmallString<64> Name;
- if (llvm::GlobalValue::isLocalLinkage(Linkage)) {
- Name.append(FileName.empty() ? "<unknown>" : FileName);
- Name.append(";");
- }
+ // FIXME: Mangler's handling is kept outside of `getGlobalIdentifier` for
now.
+ // For more details please check issue #74565.
Mangler().getNameWithPrefix(Name, &GO, /*CannotUsePrivateLabel=*/true);
- return Name.str().str();
+ return GlobalValue::getGlobalIdentifier(Name, Linkage, FileName);
}
static std::optional<std::string> lookupPGONameFromMetadata(MDNode *MD) {
@@ -352,6 +366,9 @@ std::string getIRPGOFuncName(const Function &F, bool InLTO)
{
return getIRPGOObjectName(F, InLTO, getPGOFuncNameMetadata(F));
}
+// Please use getIRPGOFuncName for LLVM IR instrumentation. This function is
+// for front-end (Clang, etc) instrumentation.
+// The implementation is kept for profile matching from older profiles.
// This is similar to `getIRPGOFuncName` except that this function calls
// 'getPGOFuncName' to get a name and `getIRPGOFuncName` calls
// 'getIRPGONameForGlobalObject'. See the difference between two callees in the
@@ -384,7 +401,8 @@ getParsedIRPGOFuncName(StringRef IRPGOFuncName) {
StringRef getFuncNameWithoutPrefix(StringRef PGOFuncName, StringRef FileName) {
if (FileName.empty())
return PGOFuncName;
- // Drop the file name including ':'. See also getPGOFuncName.
+ // Drop the file name including ':' or ';'. See getIRPGONameForGlobalObject
as
+ // well.
if (PGOFuncName.starts_with(FileName))
PGOFuncName = PGOFuncName.drop_front(FileName.size() + 1);
return PGOFuncName;
diff --git a/llvm/lib/ProfileData/InstrProfReader.cpp
b/llvm/lib/ProfileData/InstrProfReader.cpp
index 068922d421f8b9..8f62df79d5b7e8 100644
--- a/llvm/lib/ProfileData/InstrProfReader.cpp
+++ b/llvm/lib/ProfileData/InstrProfReader.cpp
@@ -1008,12 +1008,13 @@ class llvm::InstrProfReaderItaniumRemapper
/// Extract the original function name from a PGO function name.
static StringRef extractName(StringRef Name) {
- // We can have multiple :-separated pieces; there can be pieces both
- // before and after the mangled name. Find the first part that starts
- // with '_Z'; we'll assume that's the mangled name we want.
+ // We can have multiple pieces separated by kGlobalIdentifierDelimiter (
+ // semicolon now and colon in older profiles); there can be pieces both
+ // before and after the mangled name. Find the first part that starts with
+ // '_Z'; we'll assume that's the mangled name we want.
std::pair<StringRef, StringRef> Parts = {StringRef(), Name};
while (true) {
- Parts = Parts.second.split(':');
+ Parts = Parts.second.split(kGlobalIdentifierDelimiter);
if (Parts.first.starts_with("_Z"))
return Parts.first;
if (Parts.second.empty())
diff --git a/llvm/test/Bitcode/thinlto-function-summary-originalnames.ll
b/llvm/test/Bitcode/thinlto-function-summary-originalnames.ll
index 7cc9654c8c7b12..0139f00b4aa3f4 100644
--- a/llvm/test/Bitcode/thinlto-function-summary-originalnames.ll
+++ b/llvm/test/Bitcode/thinlto-function-summary-originalnames.ll
@@ -6,13 +6,13 @@
; COMBINED: <GLOBALVAL_SUMMARY_BLOCK
; COMBINED-NEXT: <VERSION
; COMBINED-NEXT: <FLAGS
-; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=4947176790635855146/>
-; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=-6591587165810580810/>
-; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=-4377693495213223786/>
+; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=686735765308251824/>
+; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=4507502870619175775/>
+; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=-8118561185538785069/>
; COMBINED-DAG: <COMBINED_PROFILE{{ }}
-; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=6699318081062747564/>
-; COMBINED-DAG: <COMBINED_GLOBALVAR_INIT_REFS
; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=-2012135647395072713/>
+; COMBINED-DAG: <COMBINED_GLOBALVAR_INIT_REFS
+; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=6699318081062747564/>
; COMBINED-DAG: <COMBINED_ALIAS
; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=-4170563161550796836/>
; COMBINED-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
diff --git a/llvm/test/ThinLTO/X86/memprof-basic.ll
b/llvm/test/ThinLTO/X86/memprof-basic.ll
index 0d466830ba57d6..54e01e5fcdf955 100644
--- a/llvm/test/ThinLTO/X86/memprof-basic.ll
+++ b/llvm/test/ThinLTO/X86/memprof-basic.ll
@@ -148,7 +148,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[BAR]] to Caller: [[BAZ:0x[a-z0-9]+]]
AllocTypes: NotColdCold ContextIds: 1 2
; DUMP: Node [[BAZ]]
-; DUMP: Callee: 9832687305761716512 (_Z3barv) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 11481133863268513686 (_Z3barv) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 1 2
; DUMP: CalleeEdges:
@@ -157,7 +157,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[BAZ]] to Caller: [[FOO:0x[a-z0-9]+]]
AllocTypes: NotColdCold ContextIds: 1 2
; DUMP: Node [[FOO]]
-; DUMP: Callee: 5878270615442837395 (_Z3bazv) Clones: 0 StackIds: 3
(clone 0)
+; DUMP: Callee: 1807954217441101578 (_Z3bazv) Clones: 0 StackIds: 3
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 1 2
; DUMP: CalleeEdges:
@@ -167,7 +167,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[FOO]] to Caller:
[[MAIN2:0x[a-z0-9]+]] AllocTypes: Cold ContextIds: 2
; DUMP: Node [[MAIN1]]
-; DUMP: Callee: 6731117468105397038 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
+; DUMP: Callee: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1
; DUMP: CalleeEdges:
@@ -175,7 +175,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN2]]
-; DUMP: Callee: 6731117468105397038 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
+; DUMP: Callee: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2
; DUMP: CalleeEdges:
@@ -197,7 +197,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clones: [[BAR2:0x[a-z0-9]+]]
; DUMP: Node [[BAZ]]
-; DUMP: Callee: 9832687305761716512 (_Z3barv) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 11481133863268513686 (_Z3barv) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1
; DUMP: CalleeEdges:
@@ -207,7 +207,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clones: [[BAZ2:0x[a-z0-9]+]]
; DUMP: Node [[FOO]]
-; DUMP: Callee: 5878270615442837395 (_Z3bazv) Clones: 0 StackIds: 3
(clone 0)
+; DUMP: Callee: 1807954217441101578 (_Z3bazv) Clones: 0 StackIds: 3
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1
; DUMP: CalleeEdges:
@@ -217,7 +217,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clones: [[FOO2:0x[a-z0-9]+]]
; DUMP: Node [[MAIN1]]
-; DUMP: Callee: 6731117468105397038 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
+; DUMP: Callee: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1
; DUMP: CalleeEdges:
@@ -225,7 +225,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN2]]
-; DUMP: Callee: 6731117468105397038 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
+; DUMP: Callee: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2
; DUMP: CalleeEdges:
@@ -233,7 +233,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[FOO2]]
-; DUMP: Callee: 5878270615442837395 (_Z3bazv) Clones: 0 StackIds: 3
(clone 0)
+; DUMP: Callee: 1807954217441101578 (_Z3bazv) Clones: 0 StackIds: 3
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2
; DUMP: CalleeEdges:
@@ -243,7 +243,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clone of [[FOO]]
; DUMP: Node [[BAZ2]]
-; DUMP: Callee: 9832687305761716512 (_Z3barv) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 11481133863268513686 (_Z3barv) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2
; DUMP: CalleeEdges:
@@ -344,7 +344,7 @@ attributes #0 = { noinline optnone }
; DOTCLONED: }
-; DISTRIB: ^[[BAZ:[0-9]+]] = gv: (guid: 5878270615442837395, {{.*}} callsites:
((callee: ^[[BAR:[0-9]+]], clones: (0, 1)
-; DISTRIB: ^[[FOO:[0-9]+]] = gv: (guid: 6731117468105397038, {{.*}} callsites:
((callee: ^[[BAZ]], clones: (0, 1)
-; DISTRIB: ^[[BAR]] = gv: (guid: 9832687305761716512, {{.*}} allocs:
((versions: (notcold, cold)
+; DISTRIB: ^[[BAZ:[0-9]+]] = gv: (guid: 1807954217441101578, {{.*}} callsites:
((callee: ^[[BAR:[0-9]+]], clones: (0, 1)
+; DISTRIB: ^[[FOO:[0-9]+]] = gv: (guid: 8107868197919466657, {{.*}} callsites:
((callee: ^[[BAZ]], clones: (0, 1)
+; DISTRIB: ^[[BAR]] = gv: (guid: 11481133863268513686, {{.*}} allocs:
((versions: (notcold, cold)
; DISTRIB: ^[[MAIN:[0-9]+]] = gv: (guid: 15822663052811949562, {{.*}}
callsites: ((callee: ^[[FOO]], clones: (0), {{.*}} (callee: ^[[FOO]], clones:
(1)
diff --git a/llvm/test/ThinLTO/X86/memprof-duplicate-context-ids.ll
b/llvm/test/ThinLTO/X86/memprof-duplicate-context-ids.ll
index f7ba0d27dca78a..65d794e9cba87c 100644
--- a/llvm/test/ThinLTO/X86/memprof-duplicate-context-ids.ll
+++ b/llvm/test/ThinLTO/X86/memprof-duplicate-context-ids.ll
@@ -260,8 +260,8 @@ attributes #0 = { noinline optnone}
; STATS-BE: 1 memprof-context-disambiguation - Number of original (not cloned)
allocations with memprof profiles during ThinLTO backend
-; DISTRIB: ^[[C:[0-9]+]] = gv: (guid: 1643923691937891493, {{.*}} callsites:
((callee: ^[[D:[0-9]+]], clones: (1)
-; DISTRIB: ^[[D]] = gv: (guid: 4881081444663423788, {{.*}} allocs: ((versions:
(notcold, cold)
-; DISTRIB: ^[[B:[0-9]+]] = gv: (guid: 14590037969532473829, {{.*}} callsites:
((callee: ^[[D]], clones: (1)
-; DISTRIB: ^[[F:[0-9]+]] = gv: (guid: 17035303613541779335, {{.*}} callsites:
((callee: ^[[D]], clones: (0)
-; DISTRIB: ^[[E:[0-9]+]] = gv: (guid: 17820708772846654376, {{.*}} callsites:
((callee: ^[[D]], clones: (1)
+; DISTRIB: ^[[E:[0-9]+]] = gv: (guid: 331966645857188136, {{.*}} callsites:
((callee: ^[[D:[0-9]+]], clones: (1)
+; DISTRIB: ^[[D]] = gv: (guid: 11079124245221721799, {{.*}} allocs:
((versions: (notcold, cold)
+; DISTRIB: ^[[F:[0-9]+]] = gv: (guid: 11254287701717398916, {{.*}} callsites:
((callee: ^[[D]], clones: (0)
+; DISTRIB: ^[[B:[0-9]+]] = gv: (guid: 13579056193435805313, {{.*}} callsites:
((callee: ^[[D]], clones: (1)
+; DISTRIB: ^[[C:[0-9]+]] = gv: (guid: 15101436305866936160, {{.*}} callsites:
((callee: ^[[D:[0-9]+]], clones: (1)
diff --git a/llvm/test/ThinLTO/X86/memprof-funcassigncloning.ll
b/llvm/test/ThinLTO/X86/memprof-funcassigncloning.ll
index 9a72ae43b2f1e4..f1a494d077fefc 100644
--- a/llvm/test/ThinLTO/X86/memprof-funcassigncloning.ll
+++ b/llvm/test/ThinLTO/X86/memprof-funcassigncloning.ll
@@ -176,7 +176,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clones: [[ENEW1CLONE:0x[a-z0-9]+]]
; DUMP: Node [[D:0x[a-z0-9]+]]
-; DUMP: Callee: 10758063066234039248 (_Z1EPPcS0_) Clones: 0 StackIds: 0
(clone 0)
+; DUMP: Callee: 16147627620923572899 (_Z1EPPcS0_) Clones: 0 StackIds: 0
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 1 6
; DUMP: CalleeEdges:
@@ -185,7 +185,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[C]]
-; DUMP: Callee: 10758063066234039248 (_Z1EPPcS0_) Clones: 0 StackIds: 1
(clone 0)
+; DUMP: Callee: 16147627620923572899 (_Z1EPPcS0_) Clones: 0 StackIds: 1
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 2 5
; DUMP: CalleeEdges:
@@ -194,7 +194,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[B]]
-; DUMP: Callee: 10758063066234039248 (_Z1EPPcS0_) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 16147627620923572899 (_Z1EPPcS0_) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 3 4
; DUMP: CalleeEdges:
diff --git a/llvm/test/ThinLTO/X86/memprof-indirectcall.ll
b/llvm/test/ThinLTO/X86/memprof-indirectcall.ll
index 76273959f4f4ac..07a52f441ca278 100644
--- a/llvm/test/ThinLTO/X86/memprof-indirectcall.ll
+++ b/llvm/test/ThinLTO/X86/memprof-indirectcall.ll
@@ -202,7 +202,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[FOO]] to Caller:
[[MAIN2:0x[a-z0-9]+]] AllocTypes: Cold ContextIds: 6
; DUMP: Node [[AX]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 6
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 6
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 1 2
; DUMP: CalleeEdges:
@@ -225,7 +225,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[BAR]] to Caller:
[[MAIN6:0x[a-z0-9]+]] AllocTypes: NotCold ContextIds: 5
; DUMP: Node [[MAIN3]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 4
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 4
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1
; DUMP: CalleeEdges:
@@ -233,7 +233,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN4]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 5
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 5
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2
; DUMP: CalleeEdges:
@@ -241,7 +241,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN1]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 3
; DUMP: CalleeEdges:
@@ -249,7 +249,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[BX]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 7
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 7
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 4 5
; DUMP: CalleeEdges:
@@ -258,7 +258,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[BX]] to Caller: [[BAR]] AllocTypes:
NotColdCold ContextIds: 4 5
; DUMP: Node [[MAIN5]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 4
; DUMP: CalleeEdges:
@@ -266,7 +266,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN6]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 3
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 3
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 5
; DUMP: CalleeEdges:
@@ -274,7 +274,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN2]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 6
; DUMP: CalleeEdges:
@@ -302,7 +302,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clones: [[FOO2:0x[a-z0-9]+]]
; DUMP: Node [[AX]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 6
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 6
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 1 2
; DUMP: CalleeEdges:
@@ -324,7 +324,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[BAR]] to Caller: [[MAIN6]]
AllocTypes: NotCold ContextIds: 5
; DUMP: Node [[MAIN3]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 4
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 4
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1
; DUMP: CalleeEdges:
@@ -332,7 +332,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN4]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 5
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 5
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2
; DUMP: CalleeEdges:
@@ -340,7 +340,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN1]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 0
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 3
; DUMP: CalleeEdges:
@@ -348,7 +348,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[BX]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 7
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 7
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 4 5
; DUMP: CalleeEdges:
@@ -357,7 +357,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[BX]] to Caller: [[BAR]] AllocTypes:
NotColdCold ContextIds: 4 5
; DUMP: Node [[MAIN5]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 4
; DUMP: CalleeEdges:
@@ -365,7 +365,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN6]]
-; DUMP: Callee: 4095956691517954349 (_Z3barP1A) Clones: 0 StackIds: 3
(clone 0)
+; DUMP: Callee: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 3
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 5
; DUMP: CalleeEdges:
@@ -373,7 +373,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN2]]
-; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
+; DUMP: Callee: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 1
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 6
; DUMP: CalleeEdges:
diff --git a/llvm/test/ThinLTO/X86/memprof-inlined.ll
b/llvm/test/ThinLTO/X86/memprof-inlined.ll
index feb9c94344223c..89df345b220423 100644
--- a/llvm/test/ThinLTO/X86/memprof-inlined.ll
+++ b/llvm/test/ThinLTO/X86/memprof-inlined.ll
@@ -170,7 +170,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[FOO2]] to Caller:
[[MAIN2:0x[a-z0-9]+]] AllocTypes: Cold ContextIds: 2
; DUMP: Node [[MAIN1]]
-; DUMP: Callee: 2229562716906371625 (_Z3foov) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1 3
; DUMP: CalleeEdges:
@@ -179,7 +179,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN2]]
-; DUMP: Callee: 2229562716906371625 (_Z3foov) Clones: 0 StackIds: 3
(clone 0)
+; DUMP: Callee: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 3
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2 4
; DUMP: CalleeEdges:
@@ -201,7 +201,7 @@ attributes #0 = { noinline optnone }
;; This is the node synthesized for the call to bar in foo that was created
;; by inlining baz into foo.
; DUMP: Node [[FOO]]
-; DUMP: Callee: 16064618363798697104 (_Z3barv) Clones: 0 StackIds: 0, 1
(clone 0)
+; DUMP: Callee: 10349908617508457487 (_Z3barv) Clones: 0 StackIds: 0, 1
(clone 0)
; DUMP: AllocTypes: NotColdCold
; DUMP: ContextIds: 3 4
; DUMP: CalleeEdges:
@@ -234,7 +234,7 @@ attributes #0 = { noinline optnone }
; DUMP: Edge from Callee [[FOO2]] to Caller: [[MAIN2]]
AllocTypes: Cold ContextIds: 2
; DUMP: Node [[MAIN1]]
-; DUMP: Callee: 2229562716906371625 (_Z3foov) Clones: 0 StackIds: 2
(clone 0)
+; DUMP: Callee: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 2
(clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 1 3
; DUMP: CalleeEdges:
@@ -243,7 +243,7 @@ attributes #0 = { noinline optnone }
; DUMP: CallerEdges:
; DUMP: Node [[MAIN2]]
-; DUMP: Callee: 2229562716906371625 (_Z3foov) Clones: 0 StackIds: 3
(clone 0)
+; DUMP: Callee: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 3
(clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 2 4
; DUMP: CalleeEdges:
@@ -264,7 +264,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clones: [[BAR2:0x[a-z0-9]+]]
; DUMP: Node [[FOO]]
-; DUMP: Callee: 16064618363798697104 (_Z3barv) Clones: 0 StackIds: 0,
1 (clone 0)
+; DUMP: Callee: 10349908617508457487 (_Z3barv) Clones: 0 StackIds: 0,
1 (clone 0)
; DUMP: AllocTypes: NotCold
; DUMP: ContextIds: 3
; DUMP: CalleeEdges:
@@ -274,7 +274,7 @@ attributes #0 = { noinline optnone }
; DUMP: Clones: [[FOO3]]
; DUMP: Node [[FOO3]]
-; DUMP: Callee: 16064618363798697104 (_Z3barv) Clones: 0 StackIds: 0,
1 (clone 0)
+; DUMP: Callee: 10349908617508457487 (_Z3barv) Clones: 0 StackIds: 0,
1 (clone 0)
; DUMP: AllocTypes: Cold
; DUMP: ContextIds: 4
; DUMP: CalleeEdges:
diff --git
a/llvm/test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.ll
b/llvm/test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.ll
deleted file mode 100644
index 7412120bb52cf5..00000000000000
--- a/llvm/test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.ll
+++ /dev/null
@@ -1,16 +0,0 @@
-target datalayout =
"e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
-target triple = "x86_64-unknown-linux-gnu"
-
-source_filename = "thinlto_indirect_call_promotion.c"
-
-define void @a() {
-entry:
- ret void
-}
-
-define internal void @c() !PGOFuncName !1 {
-entry:
- ret void
-}
-
-!1 = !{!"thinlto_indirect_call_promotion.c:c"}
diff --git
a/llvm/test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.profraw
b/llvm/test/Transforms/PGOProfile/Inputs/thinlto_indirect_call_promotion.profraw
new file mode 100644
index
0000000000000000000000000000000000000000..5efda10bb98a941c04b6846db05d3691bc36aac0
GIT binary patch
literal 528
zcmZoHO3N=Q$obF700xW@ih+Rz#(>i3d^BkWXQ;q~{}ABueD@>eRsa8Q&U2Q%6Ux8<
zGg$D|W`(~SCZ7PRdViVAmkXvIW}d)Ih<X?wrVqxCo@t!pb5*AXrhf(0KA5}$0sU81
zHLMa3<=qEq6WVr<y#P(W0aX7ENf)@gnP7$k>0eiSpPQvjy$#d`cE1Ih{ssc}!~BDb
zHZZQZ)!lF8?|0^;r?06_@|lx9m%RP9_4R*h?2?>fc+6c=YT5HA>Z;F<ET8&Jbvh$M
re~rLy7M_Y*r+v?yVP;^FW?Tk#tp$*T*#UAtBa{ORADA30ykUF*Dr$#p
literal 0
HcmV?d00001
diff --git
a/llvm/test/Transforms/PGOProfile/Inputs/update_thinlto_indirect_call_promotion_inputs.sh
b/llvm/test/Transforms/PGOProfile/Inputs/update_thinlto_indirect_call_promotion_inputs.sh
new file mode 100755
index 00000000000000..9676b042a641ca
--- /dev/null
+++
b/llvm/test/Transforms/PGOProfile/Inputs/update_thinlto_indirect_call_promotion_inputs.sh
@@ -0,0 +1,62 @@
+#!/bin/bash
+
+if [ $# -lt 1 ]; then
+ echo "Path to clang required!"
+ echo "Usage: update_thinlto_indirect_call_promotion_inputs.sh
/path/to/updated/clang"
+ exit 1
+else
+ CLANG=$1
+fi
+
+# Remember current directory.
+CURDIR=$PWD
+
+# Allows the script to be invoked from other directories.
+OUTDIR=$(dirname $(realpath -s $0))
+cd $OUTDIR
+
+# Creates trivial header file to expose `global_func`.
+cat > lib.h << EOF
+void global_func();
+EOF
+
+# Creates lib.cc. `global_func` might call one of two indirect callees. One
+# callee has internal linkage and the other has external linkage.
+cat > lib.cc << EOF
+#include "lib.h"
+static void callee0() {}
+void callee1() {}
+typedef void (*FPT)();
+FPT calleeAddrs[] = {callee0, callee1};
+void global_func() {
+ FPT fp = nullptr;
+ fp = calleeAddrs[0];
+ fp();
+ fp = calleeAddrs[1];
+ fp();
+}
+EOF
+
+# Create main.cc. Function `main` calls `global_func`.
+cat > main.cc << EOF
+#include "lib.h"
+int main() {
+ global_func();
+}
+EOF
+
+# Clean up temporary files on exit and return to original directory.
+cleanup() {
+ rm -f $OUTDIR/lib.h
+ rm -f $OUTDIR/lib.cc
+ rm -f $OUTDIR/main.cc
+ rm -f $OUTDIR/lib.h.pch
+ rm -f $OUTDIR/a.out
+ cd $CURDIR
+}
+trap cleanup EXIT
+
+# Generate instrumented binary
+${CLANG} -fuse-ld=lld -O2 -fprofile-generate=. lib.h lib.cc main.cc
+# Create raw profiles
+env LLVM_PROFILE_FILE=thinlto_indirect_call_promotion.profraw ./a.out
diff --git a/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
b/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
index 173296f223e56a..63e2a7a904a1bd 100644
--- a/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
+++ b/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
@@ -1,39 +1,84 @@
-; Do setup work for all below tests: generate bitcode and combined index
-; RUN: opt -module-summary %s -o %t.bc
-; RUN: opt -module-summary %p/Inputs/thinlto_indirect_call_promotion.ll -o
%t2.bc
-; RUN: llvm-lto -thinlto -o %t3 %t.bc %t2.bc
+; The raw profiles (and reduced IR if needed) could be re-generated (e.g., when
+; there is a profile version bump) from script
+; Inputs/update_thinlto_indirect_call_promotion_inputs.sh
+;
+; The script generates raw profiles. This regression test will convert it to
+; indexed profiles. This way the test exercises code path where a profiled
+; callee address in raw profiles is converted to function hash in index
profiles.
-; RUN: opt -passes=function-import -summary-file %t3.thinlto.bc %t.bc -o
%t4.bc -print-imports 2>&1 | FileCheck %s --check-prefix=IMPORTS
-; IMPORTS-DAG: Import a
-; IMPORTS-DAG: Import c
+; The raw profiles storesd compressed function names, so profile reader should
+; be built with zlib support to decompress them.
+; REQUIRES: zlib
-; RUN: opt %t4.bc -icp-lto -passes=pgo-icall-prom -S | FileCheck %s
--check-prefix=ICALL-PROM
-; RUN: opt %t4.bc -icp-lto -passes=pgo-icall-prom -S
-pass-remarks=pgo-icall-prom 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
-; PASS-REMARK: Promote indirect call to a with count 1 out of 1
-; PASS-REMARK: Promote indirect call to c.llvm.0 with count 1 out of 1
+; RUN: rm -rf %t && split-file %s %t && cd %t
-target datalayout =
"e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
-target triple = "x86_64-unknown-linux-gnu"
+; Do setup work for all below tests: convert raw profiles to indexed profiles,
+; run profile-use pass, generate bitcode and combined ThinLTO index.
+; Note `pgo-instr-use` pass runs without `pgo-icall-prom` pass. As a result ICP
+; transformation won't happen at test setup time.
+; RUN: llvm-profdata merge %p/Inputs/thinlto_indirect_call_promotion.profraw
-o icp.profdata
+; RUN: opt -passes=pgo-instr-use -pgo-test-profile-file=icp.profdata
-module-summary main.ll -o main.bc
+; RUN: opt -passes=pgo-instr-use -pgo-test-profile-file=icp.profdata
-module-summary lib.ll -o lib.bc
+; RUN: llvm-lto -thinlto -o summary main.bc lib.bc
-@foo = external local_unnamed_addr global ptr, align 8
-@bar = external local_unnamed_addr global ptr, align 8
+; Test that callee with local linkage has `PGOFuncName` metadata while callee
with external doesn't have it.
+; RUN: llvm-dis lib.bc -o - | FileCheck %s --check-prefix=PGOName
+; PGOName: define void @_Z7callee1v() {{.*}} !prof ![[#]] {
+; PGOName: define internal void @_ZL7callee0v() {{.*}} !prof ![[#]]
!PGOFuncName ![[#MD:]] {
+; The source filename of `lib.ll` is specified as "lib.cc" (i.e., the name does
+; not change with the directory), so match the full name here.
+; PGOName: ![[#MD]] = !{!"lib.cc;_ZL7callee0v"}
-define i32 @main() local_unnamed_addr {
-entry:
- %0 = load ptr, ptr @foo, align 8
-; ICALL-PROM: br i1 %{{[0-9]+}}, label %if.true.direct_targ, label
%if.false.orig_indirect, !prof [[BRANCH_WEIGHT:![0-9]+]]
- tail call void %0(), !prof !1
- %1 = load ptr, ptr @bar, align 8
-; ICALL-PROM: br i1 %{{[0-9]+}}, label %if.true.direct_targ1, label
%if.false.orig_indirect2, !prof [[BRANCH_WEIGHT:![0-9]+]]
- tail call void %1(), !prof !2
+; Tests that both external and internal callees are correctly imported.
+; RUN: opt -passes=function-import -summary-file summary.thinlto.bc main.bc -o
main.import.bc -print-imports 2>&1 | FileCheck %s --check-prefix=IMPORTS
+; IMPORTS: Import _Z7callee1v
+; IMPORTS: Import _ZL7callee0v.llvm.[[#]]
+; IMPORTS: Import _Z11global_funcv
+
+; Tests that ICP transformations happen.
+; Both candidates are ICP'ed, check there is no `!VP` in the IR.
+; RUN: opt main.import.bc -icp-lto -passes=pgo-icall-prom -S | FileCheck %s
--check-prefix=ICALL-PROM --implicit-check-not="!VP"
+; RUN: opt main.import.bc -icp-lto -passes=pgo-icall-prom -S
-pass-remarks=pgo-icall-prom 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
+
+; PASS-REMARK: Promote indirect call to _ZL7callee0v.llvm.[[#]] with count 1
out of 1
+; PASS-REMARK: Promote indirect call to _Z7callee1v with count 1 out of 1
+
+; ICALL-PROM: br i1 %[[#]], label %if.true.direct_targ, label
%if.false.orig_indirect, !prof ![[#BRANCH_WEIGHT1:]]
+; ICALL-PROM: br i1 %[[#]], label %if.true.direct_targ1, label
%if.false.orig_indirect2, !prof ![[#BRANCH_WEIGHT1]]
+
+; ICALL-PROM: ![[#BRANCH_WEIGHT1]] = !{!"branch_weights", i32 1, i32 0}
+
+;--- main.ll
+target datalayout =
"e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @main() {
+ call void @_Z11global_funcv()
ret i32 0
}
-!1 = !{!"VP", i32 0, i64 1, i64 -6289574019528802036, i64 1}
-!2 = !{!"VP", i32 0, i64 1, i64 591260329866125152, i64 1}
+declare void @_Z11global_funcv()
-; Should not have a VP annotation on new indirect call (check before and after
-; branch_weights annotation).
-; ICALL-PROM-NOT: !"VP"
-; ICALL-PROM: [[BRANCH_WEIGHT]] = !{!"branch_weights", i32 1, i32 0}
-; ICALL-PROM-NOT: !"VP"
+;--- lib.ll
+source_filename = "lib.cc"
+target datalayout =
"e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@calleeAddrs = global [2 x ptr] [ptr @_ZL7callee0v, ptr @_Z7callee1v]
+
+define void @_Z7callee1v() {
+ ret void
+}
+
+define internal void @_ZL7callee0v() {
+ ret void
+}
+
+define void @_Z11global_funcv() {
+entry:
+ %0 = load ptr, ptr @calleeAddrs
+ call void %0()
+ %1 = load ptr, ptr getelementptr inbounds ([2 x ptr], ptr @calleeAddrs, i64
0, i64 1)
+ call void %1()
+ ret void
+}
diff --git a/llvm/unittests/ProfileData/InstrProfTest.cpp
b/llvm/unittests/ProfileData/InstrProfTest.cpp
index e6613a90dc7c53..6a71a975fbb12d 100644
--- a/llvm/unittests/ProfileData/InstrProfTest.cpp
+++ b/llvm/unittests/ProfileData/InstrProfTest.cpp
@@ -1379,7 +1379,7 @@ TEST(SymtabTest, instr_prof_symtab_compression_test) {
TEST_P(MaybeSparseInstrProfTest, remapping_test) {
Writer.addRecord({"_Z3fooi", 0x1234, {1, 2, 3, 4}}, Err);
- Writer.addRecord({"file:_Z3barf", 0x567, {5, 6, 7}}, Err);
+ Writer.addRecord({"file;_Z3barf", 0x567, {5, 6, 7}}, Err);
auto Profile = Writer.writeBuffer();
readProfile(std::move(Profile), llvm::MemoryBuffer::getMemBuffer(R"(
type i l
@@ -1397,7 +1397,7 @@ TEST_P(MaybeSparseInstrProfTest, remapping_test) {
EXPECT_EQ(4u, Counts[3]);
}
- for (StringRef BarName : {"file:_Z3barf", "file:_Z4quuxf"}) {
+ for (StringRef BarName : {"file;_Z3barf", "file;_Z4quuxf"}) {
EXPECT_THAT_ERROR(Reader->getFunctionCounts(BarName, 0x567, Counts),
Succeeded());
ASSERT_EQ(3u, Counts.size());
>From cca510e569e9325ec089974e006eb2a8e2d0a2a7 Mon Sep 17 00:00:00 2001
From: mingmingl <mingmi...@google.com>
Date: Mon, 18 Dec 2023 23:03:11 -0800
Subject: [PATCH 2/2] Simplify tests and relax restrictive checks.
---
compiler-rt/test/profile/CMakeLists.txt | 2 +-
...trprof-thinlto-indirect-call-promotion.cpp | 45 +++++++------------
.../thinlto_indirect_call_promotion.ll | 10 ++---
3 files changed, 22 insertions(+), 35 deletions(-)
diff --git a/compiler-rt/test/profile/CMakeLists.txt
b/compiler-rt/test/profile/CMakeLists.txt
index eebe0469efebe0..e7494f520aa23a 100644
--- a/compiler-rt/test/profile/CMakeLists.txt
+++ b/compiler-rt/test/profile/CMakeLists.txt
@@ -6,7 +6,7 @@ set(PROFILE_TESTSUITES)
set(PROFILE_TEST_DEPS ${SANITIZER_COMMON_LIT_TEST_DEPS} compiler-rt-headers)
list(APPEND PROFILE_TEST_DEPS profile)
if(NOT COMPILER_RT_STANDALONE_BUILD)
- list(APPEND PROFILE_TEST_DEPS llvm-cov llvm-dis llvm-lto llvm-profdata opt)
+ list(APPEND PROFILE_TEST_DEPS llvm-cov llvm-lto llvm-profdata opt)
if(NOT APPLE AND COMPILER_RT_HAS_LLD AND "lld" IN_LIST LLVM_ENABLE_PROJECTS)
list(APPEND PROFILE_TEST_DEPS lld)
endif()
diff --git
a/compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
b/compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
index 82ca1cd7d0a564..ed7faada0b8630 100644
--- a/compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
+++ b/compiler-rt/test/profile/instrprof-thinlto-indirect-call-promotion.cpp
@@ -13,6 +13,11 @@
// - Generate ThinLTO summary file with LLVM bitcodes, and run
`function-import` pass.
// - Run `pgo-icall-prom` pass for the IR module which needs to import callees.
+// This test and IR test
llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
+// are complementary to each other; a compiler-rt test has better test coverage
+// on different platforms, and the IR test is less restrictive in terms of
+// running environment and could be executed more widely.
+
// Use lld as linker for more robust test. We need to REQUIRE LLVMgold.so for
// LTO if default linker is GNU ld or gold anyway.
// REQUIRES: lld-available
@@ -40,12 +45,9 @@
// RUN: env LLVM_PROFILE_FILE=main.profraw %run ./main
// RUN: llvm-profdata merge main.profraw -o main.profdata
-// Use profile on lib and get bitcode, test that local function callee0 has
-// expected !PGOFuncName metadata and external function callee1 doesn't have
-// !PGOFuncName metadata. Explicitly skip ICP pass to test ICP happens as
+// Use profile on lib and get bitcode. Explicitly skip ICP pass to test ICP
happens as
// expected in the IR module that imports functions from lib.
// RUN: %clang -mllvm -disable-icp -fprofile-use=main.profdata -flto=thin -O2
-c lib.cpp -o lib.bc
-// RUN: llvm-dis lib.bc -o - | FileCheck %s --check-prefix=PGOName
// Use profile on main and get bitcode.
// RUN: %clang -fprofile-use=main.profdata -flto=thin -O2 -c main.cpp -o
main.bc
@@ -58,35 +60,20 @@
// block with a function-entry-count of one, so they are actually hot functions
// per default profile summary hotness cutoff.
// RUN: opt -passes=function-import -import-instr-limit=100
-import-cold-multiplier=1 -summary-file summary.thinlto.bc main.bc -o
main.import.bc -print-imports 2>&1 | FileCheck %s --check-prefix=IMPORTS
-// Test that '_Z11global_funcv' has indirect calls annotated with value
profiles.
-// RUN: llvm-dis main.import.bc -o - | FileCheck %s --check-prefix=IR
// Test that both candidates are ICP'ed and there is no `!VP` in the IR.
// RUN: opt main.import.bc -icp-lto -passes=pgo-icall-prom -S
-pass-remarks=pgo-icall-prom 2>&1 | FileCheck %s
--check-prefixes=ICP-IR,ICP-REMARK --implicit-check-not="!VP"
-// IMPORTS: main.cpp: Import _Z7callee1v
-// IMPORTS: main.cpp: Import _ZL7callee0v.llvm.[[#]]
-// IMPORTS: main.cpp: Import _Z11global_funcv
-
-// PGOName: define {{(dso_local )?}}void @_Z7callee1v() #[[#]] !prof ![[#]] {
-// PGOName: define internal void @_ZL7callee0v() #[[#]] !prof ![[#]]
!PGOFuncName ![[#MD:]] {
-// PGOName: ![[#MD]] = !{!"{{.*}}lib.cpp;_ZL7callee0v"}
-
-// IR-LABEL: define available_externally {{.*}} void @_Z11global_funcv()
{{.*}} !prof ![[#]] {
-// IR-NEXT: entry:
-// IR-NEXT: %0 = load ptr, ptr @calleeAddrs
-// IR-NEXT: tail call void %0(), !prof ![[#PROF1:]]
-// IR-NEXT: %1 = load ptr, ptr getelementptr inbounds ([2 x ptr], ptr
@calleeAddrs,
-// IR-NEXT: tail call void %1(), !prof ![[#PROF2:]]
-
-// The GUID of indirect callee is the MD5 hash of
`/path/to/lib.cpp;_ZL7callee0v`
-// that depends on the directory. Use [[#]] for its MD5 hash.
-// Use {{.*}} for integer types so the test works on 32-bit and 64-bit systems.
-// IR: ![[#PROF1]] = !{!"VP", i32 0, {{.*}} 1, {{.*}} [[#]], {{.*}} 1}
-// IR: ![[#PROF2]] = !{!"VP", i32 0, {{.*}} 1, {{.*}} -3993653843325621743,
{{.*}} 1}
-
-// ICP-REMARK: Promote indirect call to _ZL7callee0v.llvm.[[#]] with count 1
out of 1
-// ICP-REMARK: Promote indirect call to _Z7callee1v with count 1 out of 1
+// IMPORTS-DAG: main.cpp: Import {{.*}}callee1{{.*}}
+// IMPORTS-DAG: main.cpp: Import {{.*}}callee0{{.*}}llvm.[[#]]
+// IMPORTS-DAG: main.cpp: Import {{.*}}global_func{{.*}}
+
+// PGOName-DAG: define {{.*}}callee1{{.*}} !prof ![[#]] {
+// PGOName-DAG: define internal {{.*}}callee0{{.*}} !prof ![[#]] !PGOFuncName
![[#MD:]] {
+// PGOName-DAG: ![[#MD]] = !{!"{{.*}}lib.cpp;{{.*}}callee0{{.*}}"}
+
+// ICP-REMARK: Promote indirect call to {{.*}}callee0{{.*}}llvm.[[#]] with
count 1 out of 1
+// ICP-REMARK: Promote indirect call to {{.*}}callee1{{.*}} with count 1 out
of 1
// ICP-IR: br i1 %[[#]], label %if.true.direct_targ, label
%if.false.orig_indirect, !prof ![[#BRANCH_WEIGHT1:]]
// ICP-IR: br i1 %[[#]], label %if.true.direct_targ1, label
%if.false.orig_indirect2, !prof ![[#BRANCH_WEIGHT1]]
diff --git a/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
b/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
index 63e2a7a904a1bd..d2f4696ccf41d7 100644
--- a/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
+++ b/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
@@ -23,17 +23,17 @@
; Test that callee with local linkage has `PGOFuncName` metadata while callee
with external doesn't have it.
; RUN: llvm-dis lib.bc -o - | FileCheck %s --check-prefix=PGOName
-; PGOName: define void @_Z7callee1v() {{.*}} !prof ![[#]] {
-; PGOName: define internal void @_ZL7callee0v() {{.*}} !prof ![[#]]
!PGOFuncName ![[#MD:]] {
+; PGOName-DAG: define void @_Z7callee1v() {{.*}} !prof ![[#]] {
+; PGOName-DAG: define internal void @_ZL7callee0v() {{.*}} !prof ![[#]]
!PGOFuncName ![[#MD:]] {
; The source filename of `lib.ll` is specified as "lib.cc" (i.e., the name does
; not change with the directory), so match the full name here.
; PGOName: ![[#MD]] = !{!"lib.cc;_ZL7callee0v"}
; Tests that both external and internal callees are correctly imported.
; RUN: opt -passes=function-import -summary-file summary.thinlto.bc main.bc -o
main.import.bc -print-imports 2>&1 | FileCheck %s --check-prefix=IMPORTS
-; IMPORTS: Import _Z7callee1v
-; IMPORTS: Import _ZL7callee0v.llvm.[[#]]
-; IMPORTS: Import _Z11global_funcv
+; IMPORTS-DAG: Import _Z7callee1v
+; IMPORTS-DAG: Import _ZL7callee0v.llvm.[[#]]
+; IMPORTS-DAG: Import _Z11global_funcv
; Tests that ICP transformations happen.
; Both candidates are ICP'ed, check there is no `!VP` in the IR.
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
