[llvm-branch-commits] [llvm] [BOLT] Match functions with name similarity (PR #95884)
Shaw Young via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Wed Jul 3 11:35:09 PDT 2024
https://github.com/shawbyoung updated https://github.com/llvm/llvm-project/pull/95884
>From 34652b2eebc62218c50a23509ce99937385c30e6 Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Thu, 20 Jun 2024 23:42:00 -0700
Subject: [PATCH 1/8] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 73 ++++++++++++++++++++------
1 file changed, 56 insertions(+), 17 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index 66cabc236f4b2..c9f6d88f0b13a 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -424,36 +424,75 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
// Uses name similarity to match functions that were not matched by name.
uint64_t MatchedWithDemangledName = 0;
- if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
-
- std::unordered_map<std::string, BinaryFunction *> NameToBinaryFunction;
- NameToBinaryFunction.reserve(BC.getBinaryFunctions().size());
- for (auto &[_, BF] : BC.getBinaryFunctions()) {
+ if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
+ auto DemangleName = [&](const char* String) {
int Status = 0;
- char *DemangledName = abi::__cxa_demangle(BF.getOneName().str().c_str(),
+ char *DemangledName = abi::__cxa_demangle(String,
nullptr, nullptr, &Status);
- if (Status == 0)
- NameToBinaryFunction[std::string(DemangledName)] = &BF;
+ return Status == 0 ? new std::string(DemangledName) : nullptr;
+ };
+
+ auto DeriveNameSpace = [&](std::string DemangledName) {
+ size_t LParen = std::string(DemangledName).find("(");
+ std::string FunctionName = std::string(DemangledName).substr(0, LParen);
+ size_t ScopeResolutionOperator = std::string(FunctionName).rfind("::");
+ return ScopeResolutionOperator == std::string::npos ? std::string("") : std::string(DemangledName).substr(0, ScopeResolutionOperator);
+ };
+
+ std::unordered_map<std::string, std::vector<BinaryFunction *>> NamespaceToBFs;
+ NamespaceToBFs.reserve(BC.getBinaryFunctions().size());
+
+ for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
+ std::string* DemangledName = DemangleName(BF->getOneName().str().c_str());
+ if (!DemangledName)
+ continue;
+ std::string Namespace = DeriveNameSpace(*DemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
+ NamespaceToBFs[Namespace] = {BF};
+ else
+ It->second.push_back(BF);
}
for (auto YamlBF : YamlBP.Functions) {
if (YamlBF.Used)
continue;
- int Status = 0;
- char *DemangledName =
- abi::__cxa_demangle(YamlBF.Name.c_str(), nullptr, nullptr, &Status);
- if (Status != 0)
+ std::string* YamlBFDemangledName = DemangleName(YamlBF.Name.c_str());
+ if (!YamlBFDemangledName)
continue;
- auto It = NameToBinaryFunction.find(DemangledName);
- if (It == NameToBinaryFunction.end())
+ std::string Namespace = DeriveNameSpace(*YamlBFDemangledName);
+ auto It = NamespaceToBFs.find(Namespace);
+ if (It == NamespaceToBFs.end())
continue;
- BinaryFunction *BF = It->second;
- matchProfileToFunction(YamlBF, *BF);
- ++MatchedWithDemangledName;
+ std::vector<BinaryFunction *> BFs = It->second;
+
+ unsigned MinEditDistance = UINT_MAX;
+ BinaryFunction *ClosestNameBF = nullptr;
+
+ for (BinaryFunction *BF : BFs) {
+ if (ProfiledFunctions.count(BF))
+ continue;
+ std::string *BFDemangledName = DemangleName(BF->getOneName().str().c_str());
+ if (!BFDemangledName)
+ continue;
+ unsigned BFEditDistance = StringRef(*BFDemangledName).edit_distance(*YamlBFDemangledName);
+ if (BFEditDistance < MinEditDistance) {
+ MinEditDistance = BFEditDistance;
+ ClosestNameBF = BF;
+ }
+ }
+
+ if (ClosestNameBF &&
+ MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
+ matchProfileToFunction(YamlBF, *ClosestNameBF);
+ ++MatchedWithDemangledName;
+ }
}
}
+ outs() << MatchedWithDemangledName << ": functions matched by name similarity\n";
+
for (yaml::bolt::BinaryFunctionProfile &YamlBF : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 2d23bbd6b9ce4f0786ae8ceb39b1b008b4ca9c4d Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Thu, 20 Jun 2024 23:45:27 -0700
Subject: [PATCH 2/8] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 2 --
1 file changed, 2 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index c9f6d88f0b13a..cf4a5393df8f4 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -491,8 +491,6 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
}
}
- outs() << MatchedWithDemangledName << ": functions matched by name similarity\n";
-
for (yaml::bolt::BinaryFunctionProfile &YamlBF : YamlBP.Functions)
if (!YamlBF.Used && opts::Verbosity >= 1)
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
>From 9e6bb260197ca22219887c9158d1d19529301064 Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Fri, 21 Jun 2024 11:14:15 -0700
Subject: [PATCH 3/8] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 50 +++++++++++++-------------
1 file changed, 24 insertions(+), 26 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index cf4a5393df8f4..6aef9ea566858 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -11,13 +11,13 @@
#include "bolt/Core/BinaryFunction.h"
#include "bolt/Passes/MCF.h"
#include "bolt/Profile/ProfileYAMLMapping.h"
+#include "bolt/Utils/NameResolver.h"
#include "bolt/Utils/Utils.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/edit_distance.h"
+#include "llvm/Demangle/Demangle.h"
#include "llvm/Support/CommandLine.h"
-#include <cxxabi.h>
-
using namespace llvm;
namespace opts {
@@ -426,43 +426,40 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
uint64_t MatchedWithDemangledName = 0;
if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
- auto DemangleName = [&](const char* String) {
- int Status = 0;
- char *DemangledName = abi::__cxa_demangle(String,
- nullptr, nullptr, &Status);
- return Status == 0 ? new std::string(DemangledName) : nullptr;
+ auto DemangleName = [&](std::string &FunctionName) {
+ StringRef RestoredName = NameResolver::restore(FunctionName);
+ return demangle(RestoredName);
};
+ ItaniumPartialDemangler ItaniumPartialDemangler;
auto DeriveNameSpace = [&](std::string DemangledName) {
- size_t LParen = std::string(DemangledName).find("(");
- std::string FunctionName = std::string(DemangledName).substr(0, LParen);
- size_t ScopeResolutionOperator = std::string(FunctionName).rfind("::");
- return ScopeResolutionOperator == std::string::npos ? std::string("") : std::string(DemangledName).substr(0, ScopeResolutionOperator);
+ std::vector<char> Buffer(DemangledName.begin(), DemangledName.end());
+ size_t BufferSize = Buffer.size();
+ char *NameSpace = ItaniumPartialDemangler.getFunctionDeclContextName(
+ &Buffer[0], &BufferSize);
+ return NameSpace ? std::string(NameSpace) : std::string("");
};
- std::unordered_map<std::string, std::vector<BinaryFunction *>> NamespaceToBFs;
+ std::unordered_map<std::string, std::vector<BinaryFunction *>>
+ NamespaceToBFs;
+
NamespaceToBFs.reserve(BC.getBinaryFunctions().size());
for (BinaryFunction *BF : BC.getAllBinaryFunctions()) {
- std::string* DemangledName = DemangleName(BF->getOneName().str().c_str());
- if (!DemangledName)
- continue;
- std::string Namespace = DeriveNameSpace(*DemangledName);
+ std::string DemangledName = BF->getDemangledName();
+ std::string Namespace = DeriveNameSpace(DemangledName);
auto It = NamespaceToBFs.find(Namespace);
if (It == NamespaceToBFs.end())
NamespaceToBFs[Namespace] = {BF};
else
It->second.push_back(BF);
}
-
for (auto YamlBF : YamlBP.Functions) {
if (YamlBF.Used)
continue;
- std::string* YamlBFDemangledName = DemangleName(YamlBF.Name.c_str());
- if (!YamlBFDemangledName)
- continue;
- std::string Namespace = DeriveNameSpace(*YamlBFDemangledName);
- auto It = NamespaceToBFs.find(Namespace);
+ std::string YamlBFDemangledName = DemangleName(YamlBF.Name);
+ std::string YamlBFNamespace = DeriveNameSpace(YamlBFDemangledName);
+ auto It = NamespaceToBFs.find(YamlBFNamespace);
if (It == NamespaceToBFs.end())
continue;
std::vector<BinaryFunction *> BFs = It->second;
@@ -473,10 +470,11 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
for (BinaryFunction *BF : BFs) {
if (ProfiledFunctions.count(BF))
continue;
- std::string *BFDemangledName = DemangleName(BF->getOneName().str().c_str());
- if (!BFDemangledName)
+ if (BF->size() != YamlBF.NumBasicBlocks)
continue;
- unsigned BFEditDistance = StringRef(*BFDemangledName).edit_distance(*YamlBFDemangledName);
+ std::string BFDemangledName = BF->getDemangledName();
+ unsigned BFEditDistance =
+ StringRef(BFDemangledName).edit_distance(YamlBFDemangledName);
if (BFEditDistance < MinEditDistance) {
MinEditDistance = BFEditDistance;
ClosestNameBF = BF;
@@ -484,7 +482,7 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
}
if (ClosestNameBF &&
- MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
+ MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
matchProfileToFunction(YamlBF, *ClosestNameBF);
++MatchedWithDemangledName;
}
>From 669afca2beb4b1f70cd3f8aabeaf8e227161751b Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Fri, 21 Jun 2024 14:13:13 -0700
Subject: [PATCH 4/8] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 1 -
1 file changed, 1 deletion(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index 82139af2bd34a..0cf12c9765959 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -426,7 +426,6 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
uint64_t MatchedWithDemangledName = 0;
if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
- outs() << "starting name similarity matching\n";
auto DemangleName = [&](std::string &FunctionName) {
StringRef RestoredName = NameResolver::restore(FunctionName);
return demangle(RestoredName);
>From 9c021f883374e82012d6aa7228c2d99bd368e7d8 Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Fri, 21 Jun 2024 14:17:22 -0700
Subject: [PATCH 5/8] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index 0cf12c9765959..c0a17a475bae0 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -423,7 +423,7 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
matchProfileToFunction(YamlBF, *BF);
// Uses name similarity to match functions that were not matched by name.
- uint64_t MatchedWithDemangledName = 0;
+ uint64_t MatchedWithNameSimilarity = 0;
if (opts::NameSimilarityFunctionMatchingThreshold > 0) {
auto DemangleName = [&](std::string &FunctionName) {
@@ -490,7 +490,7 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
if (ClosestNameBF &&
MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
matchProfileToFunction(YamlBF, *ClosestNameBF);
- ++MatchedWithDemangledName;
+ ++MatchedWithNameSimilarity;
}
}
}
@@ -500,6 +500,11 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
errs() << "BOLT-WARNING: profile ignored for function " << YamlBF.Name
<< '\n';
+ if (opts::Verbosity >= 2) {
+ outs() << "BOLT-INFO: matched " << MatchedWithNameSimilarity
+ << " functions with similar names\n";
+ }
+
// Set for parseFunctionProfile().
NormalizeByInsnCount = usesEvent("cycles") || usesEvent("instructions");
NormalizeByCalls = usesEvent("branches");
>From 9fc1899e6f84a6c133e941e69f112717d15eefad Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Fri, 21 Jun 2024 15:11:05 -0700
Subject: [PATCH 6/8] spr amend
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 1 -
1 file changed, 1 deletion(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index c0a17a475bae0..60899ead52f85 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -486,7 +486,6 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
}
}
-
if (ClosestNameBF &&
MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
matchProfileToFunction(YamlBF, *ClosestNameBF);
>From d687bc035e5f279a8af526381a8af7acb2fc67bf Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Mon, 24 Jun 2024 16:33:14 -0700
Subject: [PATCH 7/8] Added test
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 3 +-
.../name-similarity-function-matching.test | 64 +++++++++++++++++++
2 files changed, 65 insertions(+), 2 deletions(-)
create mode 100644 bolt/test/X86/name-similarity-function-matching.test
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index 60899ead52f85..cbbb0f96f358b 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -458,7 +458,6 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
It->second.push_back(BF);
}
- size_t I = 0; size_t N = YamlBP.Functions.size();
for (auto YamlBF : YamlBP.Functions) {
if (YamlBF.Used)
continue;
@@ -487,7 +486,7 @@ Error YAMLProfileReader::readProfile(BinaryContext &BC) {
}
if (ClosestNameBF &&
- MinEditDistance < opts::NameSimilarityFunctionMatchingThreshold) {
+ MinEditDistance <= opts::NameSimilarityFunctionMatchingThreshold) {
matchProfileToFunction(YamlBF, *ClosestNameBF);
++MatchedWithNameSimilarity;
}
diff --git a/bolt/test/X86/name-similarity-function-matching.test b/bolt/test/X86/name-similarity-function-matching.test
new file mode 100644
index 0000000000000..1480a2165c389
--- /dev/null
+++ b/bolt/test/X86/name-similarity-function-matching.test
@@ -0,0 +1,64 @@
+## Tests function matching in YAMLProfileReader by name similarity.
+
+# REQUIRES: system-linux
+# RUN: split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %t/main.s -o %t.o
+# RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib
+# RUN: llvm-bolt %t.exe -o %t.out --data %t/yaml -v=2 \
+# RUN: --print-cfg --name-similarity-function-matching-threshold=1 2>&1 --funcs=main --profile-ignore-hash=0 | FileCheck %s
+
+# CHECK: BOLT-INFO: matched 1 functions with similar names
+
+#--- main.s
+.globl main
+.type main, @function
+main:
+ .cfi_startproc
+.LBB00:
+ pushq %rbp
+ movq %rsp, %rbp
+ subq $16, %rsp
+ testq %rax, %rax
+ js .LBB03
+.LBB01:
+ jne .LBB04
+.LBB02:
+ nop
+.LBB03:
+ xorl %eax, %eax
+ addq $16, %rsp
+ popq %rbp
+ retq
+.LBB04:
+ xorl %eax, %eax
+ addq $16, %rsp
+ popq %rbp
+ retq
+## For relocations against .text
+.LBB05:
+ call exit
+ .cfi_endproc
+ .size main, .-main
+
+#--- yaml
+---
+header:
+ profile-version: 1
+ binary-name: 'hashing-based-function-matching.s.tmp.exe'
+ binary-build-id: '<unknown>'
+ profile-flags: [ lbr ]
+ profile-origin: branch profile reader
+ profile-events: ''
+ dfs-order: false
+ hash-func: xxh3
+functions:
+ - name: main2
+ fid: 0
+ hash: 0x0000000000000001
+ exec: 1
+ nblocks: 6
+ blocks:
+ - bid: 1
+ insns: 1
+ succ: [ { bid: 3, cnt: 1} ]
+...
>From 60047ab888b944b4b7d9fde7176e18ff4886d163 Mon Sep 17 00:00:00 2001
From: shawbyoung <shawbyoung at gmail.com>
Date: Wed, 3 Jul 2024 09:58:00 -0700
Subject: [PATCH 8/8] Changing buffer initialization in DeriveNamespace
Created using spr 1.3.4
---
bolt/lib/Profile/YAMLProfileReader.cpp | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/bolt/lib/Profile/YAMLProfileReader.cpp b/bolt/lib/Profile/YAMLProfileReader.cpp
index 4c3dacd781da9..63222147bedd6 100644
--- a/bolt/lib/Profile/YAMLProfileReader.cpp
+++ b/bolt/lib/Profile/YAMLProfileReader.cpp
@@ -371,7 +371,7 @@ uint64_t YAMLProfileReader::matchWithNameSimilarity(BinaryContext &BC) {
if (Demangler.partialDemangle(DemangledName.c_str()))
return std::string("");
std::vector<char> Buffer(DemangledName.begin(), DemangledName.end());
- size_t BufferSize = Buffer.size();
+ size_t BufferSize;
char *NameSpace =
Demangler.getFunctionDeclContextName(&Buffer[0], &BufferSize);
return std::string(NameSpace, BufferSize);
More information about the llvm-branch-commits
mailing list