Revert "[PGO][GlobalValue][LTO]In GlobalValues::getGlobalIdentifier, use semicolon as delimiter for local-linkage varibles." (#75835)
Reverts llvm/llvm-project#74008 The compiler-rt test failed due to `llvm-dis` not found (https://lab.llvm.org/buildbot/#/builders/127/builds/59884) Will revert and investigate how to require the proper dependency.
This commit is contained in:
Mingming Liu
GitHub
parent
3768039913
commit
3aa5d71127
@ -1,115 +0,0 @@
|
||||
// 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(); }
|
||||
@ -41,10 +41,6 @@ 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.
|
||||
|
||||
@ -171,8 +171,6 @@ 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.
|
||||
@ -198,22 +196,20 @@ 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 IRPGO function name
|
||||
/// (returned by \c getIRPGOFuncName) for LLVM IR instrumentation and PGO
|
||||
/// function name (returned by \c getPGOFuncName) for front-end instrumentation.
|
||||
/// name in PGO instrumentation. \c FuncName is the name of the function
|
||||
/// returned by the \c getPGOFuncName call.
|
||||
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 IRPGO function name (returned by
|
||||
/// \c getIRPGOFuncName) for LLVM IR instrumentation and PGO function name
|
||||
/// (returned by \c getPGOFuncName) for front-end instrumentation.
|
||||
/// instrumentation. \c FuncName is the name of the function returned
|
||||
/// by \c getPGOFuncName call.
|
||||
GlobalVariable *createPGOFuncNameVar(Function &F, StringRef PGOFuncName);
|
||||
|
||||
/// Create and return the global variable for function name used 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.
|
||||
/// 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.
|
||||
GlobalVariable *createPGOFuncNameVar(Module &M,
|
||||
GlobalValue::LinkageTypes Linkage,
|
||||
StringRef PGOFuncName);
|
||||
@ -421,11 +417,11 @@ uint64_t ComputeHash(StringRef K);
|
||||
|
||||
} // end namespace IndexedInstrProf
|
||||
|
||||
/// A symbol table used for function [IR]PGO name look-up with keys
|
||||
/// A symbol table used for function PGO name look-up with keys
|
||||
/// (such as pointers, md5hash values) to the function. A function's
|
||||
/// [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.
|
||||
/// 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.
|
||||
class InstrProfSymtab {
|
||||
public:
|
||||
using AddrHashMap = std::vector<std::pair<uint64_t, uint64_t>>;
|
||||
|
||||
@ -144,27 +144,25 @@ 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 GlobalName;
|
||||
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())
|
||||
GlobalName += "<unknown>";
|
||||
NewName = NewName.insert(0, "<unknown>:");
|
||||
else
|
||||
GlobalName += FileName;
|
||||
|
||||
GlobalName += kGlobalIdentifierDelimiter;
|
||||
NewName = NewName.insert(0, FileName.str() + ":");
|
||||
}
|
||||
GlobalName += Name;
|
||||
return GlobalName;
|
||||
return NewName;
|
||||
}
|
||||
|
||||
std::string GlobalValue::getGlobalIdentifier() const {
|
||||
|
||||
@ -246,27 +246,11 @@ std::string InstrProfError::message() const {
|
||||
|
||||
char InstrProfError::ID = 0;
|
||||
|
||||
std::string getPGOFuncName(StringRef Name, GlobalValue::LinkageTypes Linkage,
|
||||
std::string getPGOFuncName(StringRef RawFuncName,
|
||||
GlobalValue::LinkageTypes Linkage,
|
||||
StringRef FileName,
|
||||
uint64_t Version LLVM_ATTRIBUTE_UNUSED) {
|
||||
// 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;
|
||||
return GlobalValue::getGlobalIdentifier(RawFuncName, Linkage, FileName);
|
||||
}
|
||||
|
||||
// Strip NumPrefix level of directory name from PathNameStr. If the number of
|
||||
@ -316,10 +300,12 @@ getIRPGONameForGlobalObject(const GlobalObject &GO,
|
||||
GlobalValue::LinkageTypes Linkage,
|
||||
StringRef FileName) {
|
||||
SmallString<64> Name;
|
||||
// FIXME: Mangler's handling is kept outside of `getGlobalIdentifier` for now.
|
||||
// For more details please check issue #74565.
|
||||
if (llvm::GlobalValue::isLocalLinkage(Linkage)) {
|
||||
Name.append(FileName.empty() ? "<unknown>" : FileName);
|
||||
Name.append(";");
|
||||
}
|
||||
Mangler().getNameWithPrefix(Name, &GO, /*CannotUsePrivateLabel=*/true);
|
||||
return GlobalValue::getGlobalIdentifier(Name, Linkage, FileName);
|
||||
return Name.str().str();
|
||||
}
|
||||
|
||||
static std::optional<std::string> lookupPGONameFromMetadata(MDNode *MD) {
|
||||
@ -366,9 +352,6 @@ 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
|
||||
@ -401,9 +384,8 @@ getParsedIRPGOFuncName(StringRef IRPGOFuncName) {
|
||||
StringRef getFuncNameWithoutPrefix(StringRef PGOFuncName, StringRef FileName) {
|
||||
if (FileName.empty())
|
||||
return PGOFuncName;
|
||||
// Drop the file name including ':' or ';'. See getIRPGONameForGlobalObject as
|
||||
// well.
|
||||
if (PGOFuncName.startswith(FileName))
|
||||
// Drop the file name including ':'. See also getPGOFuncName.
|
||||
if (PGOFuncName.starts_with(FileName))
|
||||
PGOFuncName = PGOFuncName.drop_front(FileName.size() + 1);
|
||||
return PGOFuncName;
|
||||
}
|
||||
|
||||
@ -1008,14 +1008,13 @@ public:
|
||||
|
||||
/// Extract the original function name from a PGO function name.
|
||||
static StringRef extractName(StringRef Name) {
|
||||
// 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.
|
||||
// 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.
|
||||
std::pair<StringRef, StringRef> Parts = {StringRef(), Name};
|
||||
while (true) {
|
||||
Parts = Parts.second.split(kGlobalIdentifierDelimiter);
|
||||
if (Parts.first.startswith("_Z"))
|
||||
Parts = Parts.second.split(':');
|
||||
if (Parts.first.starts_with("_Z"))
|
||||
return Parts.first;
|
||||
if (Parts.second.empty())
|
||||
return Name;
|
||||
|
||||
@ -6,13 +6,13 @@
|
||||
; COMBINED: <GLOBALVAL_SUMMARY_BLOCK
|
||||
; COMBINED-NEXT: <VERSION
|
||||
; COMBINED-NEXT: <FLAGS
|
||||
; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=686735765308251824/>
|
||||
; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=4507502870619175775/>
|
||||
; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=-8118561185538785069/>
|
||||
; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=4947176790635855146/>
|
||||
; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=-6591587165810580810/>
|
||||
; COMBINED-NEXT: <VALUE_GUID {{.*}} op1=-4377693495213223786/>
|
||||
; COMBINED-DAG: <COMBINED_PROFILE{{ }}
|
||||
; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=-2012135647395072713/>
|
||||
; COMBINED-DAG: <COMBINED_GLOBALVAR_INIT_REFS
|
||||
; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=6699318081062747564/>
|
||||
; COMBINED-DAG: <COMBINED_GLOBALVAR_INIT_REFS
|
||||
; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=-2012135647395072713/>
|
||||
; COMBINED-DAG: <COMBINED_ALIAS
|
||||
; COMBINED-DAG: <COMBINED_ORIGINAL_NAME op0=-4170563161550796836/>
|
||||
; COMBINED-NEXT: </GLOBALVAL_SUMMARY_BLOCK>
|
||||
|
||||
@ -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: 11481133863268513686 (_Z3barv) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 9832687305761716512 (_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: 1807954217441101578 (_Z3bazv) Clones: 0 StackIds: 3 (clone 0)
|
||||
; DUMP: Callee: 5878270615442837395 (_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: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 0 (clone 0)
|
||||
; DUMP: Callee: 6731117468105397038 (_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: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 1 (clone 0)
|
||||
; DUMP: Callee: 6731117468105397038 (_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: 11481133863268513686 (_Z3barv) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 9832687305761716512 (_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: 1807954217441101578 (_Z3bazv) Clones: 0 StackIds: 3 (clone 0)
|
||||
; DUMP: Callee: 5878270615442837395 (_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: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 0 (clone 0)
|
||||
; DUMP: Callee: 6731117468105397038 (_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: 8107868197919466657 (_Z3foov) Clones: 0 StackIds: 1 (clone 0)
|
||||
; DUMP: Callee: 6731117468105397038 (_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: 1807954217441101578 (_Z3bazv) Clones: 0 StackIds: 3 (clone 0)
|
||||
; DUMP: Callee: 5878270615442837395 (_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: 11481133863268513686 (_Z3barv) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 9832687305761716512 (_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: 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: ^[[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: ^[[MAIN:[0-9]+]] = gv: (guid: 15822663052811949562, {{.*}} callsites: ((callee: ^[[FOO]], clones: (0), {{.*}} (callee: ^[[FOO]], clones: (1)
|
||||
|
||||
@ -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: ^[[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)
|
||||
; 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)
|
||||
|
||||
@ -176,7 +176,7 @@ attributes #0 = { noinline optnone }
|
||||
; DUMP: Clones: [[ENEW1CLONE:0x[a-z0-9]+]]
|
||||
|
||||
; DUMP: Node [[D:0x[a-z0-9]+]]
|
||||
; DUMP: Callee: 16147627620923572899 (_Z1EPPcS0_) Clones: 0 StackIds: 0 (clone 0)
|
||||
; DUMP: Callee: 10758063066234039248 (_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: 16147627620923572899 (_Z1EPPcS0_) Clones: 0 StackIds: 1 (clone 0)
|
||||
; DUMP: Callee: 10758063066234039248 (_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: 16147627620923572899 (_Z1EPPcS0_) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 10758063066234039248 (_Z1EPPcS0_) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: AllocTypes: NotCold
|
||||
; DUMP: ContextIds: 3 4
|
||||
; DUMP: CalleeEdges:
|
||||
|
||||
@ -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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 6 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 4 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 5 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 0 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 7 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 3 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 1 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 6 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 4 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 5 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 0 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 7 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 2040285415115148168 (_Z3barP1A) Clones: 0 StackIds: 3 (clone 0)
|
||||
; DUMP: Callee: 4095956691517954349 (_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: 15844184524768596045 (_Z3foov) Clones: 0 StackIds: 1 (clone 0)
|
||||
; DUMP: Callee: 12914368124089294956 (_Z3foov) Clones: 0 StackIds: 1 (clone 0)
|
||||
; DUMP: AllocTypes: Cold
|
||||
; DUMP: ContextIds: 6
|
||||
; DUMP: CalleeEdges:
|
||||
|
||||
@ -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: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 2229562716906371625 (_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: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 3 (clone 0)
|
||||
; DUMP: Callee: 2229562716906371625 (_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: 10349908617508457487 (_Z3barv) Clones: 0 StackIds: 0, 1 (clone 0)
|
||||
; DUMP: Callee: 16064618363798697104 (_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: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 2 (clone 0)
|
||||
; DUMP: Callee: 2229562716906371625 (_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: 644169328058379925 (_Z3foov) Clones: 0 StackIds: 3 (clone 0)
|
||||
; DUMP: Callee: 2229562716906371625 (_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: 10349908617508457487 (_Z3barv) Clones: 0 StackIds: 0, 1 (clone 0)
|
||||
; DUMP: Callee: 16064618363798697104 (_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: 10349908617508457487 (_Z3barv) Clones: 0 StackIds: 0, 1 (clone 0)
|
||||
; DUMP: Callee: 16064618363798697104 (_Z3barv) Clones: 0 StackIds: 0, 1 (clone 0)
|
||||
; DUMP: AllocTypes: Cold
|
||||
; DUMP: ContextIds: 4
|
||||
; DUMP: CalleeEdges:
|
||||
|
||||
@ -0,0 +1,16 @@
|
||||
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"}
|
||||
Binary file not shown.
@ -1,62 +0,0 @@
|
||||
#!/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
|
||||
@ -1,84 +1,39 @@
|
||||
; 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.
|
||||
; 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 storesd compressed function names, so profile reader should
|
||||
; be built with zlib support to decompress them.
|
||||
; REQUIRES: zlib
|
||||
; 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
|
||||
|
||||
; RUN: rm -rf %t && split-file %s %t && cd %t
|
||||
; 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
|
||||
|
||||
; 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
|
||||
|
||||
; 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"}
|
||||
|
||||
; 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 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"
|
||||
|
||||
define i32 @main() {
|
||||
call void @_Z11global_funcv()
|
||||
@foo = external local_unnamed_addr global ptr, align 8
|
||||
@bar = external local_unnamed_addr global ptr, align 8
|
||||
|
||||
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
|
||||
ret i32 0
|
||||
}
|
||||
|
||||
declare void @_Z11global_funcv()
|
||||
!1 = !{!"VP", i32 0, i64 1, i64 -6289574019528802036, i64 1}
|
||||
!2 = !{!"VP", i32 0, i64 1, i64 591260329866125152, i64 1}
|
||||
|
||||
;--- 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
|
||||
}
|
||||
; 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"
|
||||
|
||||
@ -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());
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user