From 97dc50882cbc63d7098e95f73f242185c75c226b Mon Sep 17 00:00:00 2001
From: Shaw Young <58664393+shawbyoung@users.noreply.github.com>
Date: Wed, 3 Jul 2024 11:39:18 -0700
Subject: [BOLT] Match functions with name similarity (#95884)

A mapping - from namespace to associated binary functions - is used to
match function profiles to binary based on the
'--name-similarity-function-matching-threshold' flag set edit distance
threshold. The flag is set to 0 (exact name matching) by default as it is
expensive, requiring the processing of all BFs.

Test Plan: Added name-similarity-function-matching.test. On a binary
with 5M functions, rewrite passes took ~520s without the flag and
~2018s with the flag set to 20.
---
 .../X86/name-similarity-function-matching.test     | 63 ++++++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 bolt/test/X86/name-similarity-function-matching.test

(limited to 'bolt/test')

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 0000000..97ef4bf
--- /dev/null
+++ b/bolt/test/X86/name-similarity-function-matching.test
@@ -0,0 +1,63 @@
+## 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 --funcs=main --profile-ignore-hash=0 2>&1 | 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
+  .reloc 0, R_X86_64_NONE
+  .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:         5
+    blocks:
+      - bid:             1
+        insns:           1
+        succ:            [ { bid: 3, cnt: 1} ]
+...
-- 
cgit v1.1