[libc++] Fold __search_substring into _Traits::find in case the second string has length 1 #160076

philnik777 · 2025-09-22T11:27:27Z

Apple M4:

Benchmark                                                      Baseline    Candidate    Difference    % Difference
-----------------------------------------------------------  ----------  -----------  ------------  --------------
BM_string_literal/1024                                            16.99        16.79         -0.21           -1.21
BM_string_literal/128                                              3.44         3.34         -0.10           -2.88
BM_string_literal/16                                               1.80         1.69         -0.11           -5.93
BM_string_literal/2048                                            38.44        38.38         -0.07           -0.17
BM_string_literal/256                                              5.77         5.65         -0.12           -2.02
BM_string_literal/32                                               2.03         1.92         -0.11           -5.44
BM_string_literal/4096                                            73.92        73.74         -0.18           -0.25
BM_string_literal/512                                              9.49         9.41         -0.08           -0.84
BM_string_literal/64                                               2.59         2.45         -0.14           -5.38
BM_string_literal/8                                                1.79         1.69         -0.11           -5.90
BM_string_literal/8192                                           132.09       131.81         -0.28           -0.21

github-actions · 2025-09-22T11:31:38Z

✅ With the latest revision this PR passed the C/C++ code formatter.

llvmbot · 2025-09-23T10:22:12Z

@llvm/pr-subscribers-libcxx

Author: Nikolas Klauser (philnik777)

Changes

Full diff: https://github.com/llvm/llvm-project/pull/160076.diff

3 Files Affected:

(modified) libcxx/include/__string/char_traits.h (+7)
(modified) libcxx/test/benchmarks/containers/string.bench.cpp (+39)
(modified) libcxx/test/std/strings/basic.string/string.ops/string_find/string_size.pass.cpp (+17)

diff --git a/libcxx/include/__string/char_traits.h b/libcxx/include/__string/char_traits.h
index 86c92477cbfeb..8292750919427 100644
--- a/libcxx/include/__string/char_traits.h
+++ b/libcxx/include/__string/char_traits.h
@@ -369,6 +369,13 @@ _LIBCPP_HIDE_FROM_ABI inline _LIBCPP_CONSTEXPR_SINCE_CXX14 const _CharT* __searc
   if (__len1 < __len2)
     return __last1;
 
+  if (__builtin_constant_p(__len2 == 1) && __len2 == 1) {
+    auto __res = _Traits::find(__first1, __len1, *__first2);
+    if (__res == nullptr)
+      return __last1;
+    return __res;
+  }
+
   // First element of __first2 is loop invariant.
   _CharT __f2 = *__first2;
   while (true) {
diff --git a/libcxx/test/benchmarks/containers/string.bench.cpp b/libcxx/test/benchmarks/containers/string.bench.cpp
index 966775d31a8cf..68f596b1be62a 100644
--- a/libcxx/test/benchmarks/containers/string.bench.cpp
+++ b/libcxx/test/benchmarks/containers/string.bench.cpp
@@ -60,6 +60,45 @@ static void BM_StringFindMatch2(benchmark::State& state) {
 }
 BENCHMARK(BM_StringFindMatch2)->Range(1, MAX_STRING_LEN / 4);
 
+static void BM_string_literal(benchmark::State& state) {
+  std::string s;
+
+  for (int i = 0; i < state.range(0); i++)
+    s += 'a';
+
+  s += 'b';
+
+  benchmark::DoNotOptimize(s.data());
+  benchmark::ClobberMemory();
+  size_t pos;
+
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(pos = s.find("b")); // "b" is a string literal, it should be longer
+    benchmark::ClobberMemory();
+  }
+}
+
+BENCHMARK(BM_string_literal)->RangeMultiplier(2)->Range(8, 8 << 10);
+
+static void BM_char_literal(benchmark::State& state) {
+  std::string s;
+
+  for (int i = 0; i < state.range(0); i++)
+    s += 'a';
+
+  s += 'b';
+
+  benchmark::DoNotOptimize(s.data());
+  benchmark::ClobberMemory();
+  size_t pos;
+
+  for (auto _ : state) {
+    benchmark::DoNotOptimize(pos = s.find('b')); // 'b' is a char literal, it should be faster
+    benchmark::ClobberMemory();
+  }
+}
+BENCHMARK(BM_char_literal)->RangeMultiplier(2)->Range(8, 8 << 10);
+
 static void BM_StringCtorDefault(benchmark::State& state) {
   for (auto _ : state) {
     std::string Default;
diff --git a/libcxx/test/std/strings/basic.string/string.ops/string_find/string_size.pass.cpp b/libcxx/test/std/strings/basic.string/string.ops/string_find/string_size.pass.cpp
index 60ed469ce991b..4aa4a3f339142 100644
--- a/libcxx/test/std/strings/basic.string/string.ops/string_find/string_size.pass.cpp
+++ b/libcxx/test/std/strings/basic.string/string.ops/string_find/string_size.pass.cpp
@@ -43,14 +43,17 @@ TEST_CONSTEXPR_CXX20 void test0() {
   test(S(""), S("abcdeabcde"), 1, S::npos);
   test(S(""), S("abcdeabcdeabcdeabcde"), 1, S::npos);
   test(S("abcde"), S(""), 0, 0);
+  test(S("abcde"), S("a"), 0, 0);
   test(S("abcde"), S("abcde"), 0, 0);
   test(S("abcde"), S("abcdeabcde"), 0, S::npos);
   test(S("abcde"), S("abcdeabcdeabcdeabcde"), 0, S::npos);
   test(S("abcde"), S(""), 1, 1);
+  test(S("abcde"), S("a"), 1, S::npos);
   test(S("abcde"), S("abcde"), 1, S::npos);
   test(S("abcde"), S("abcdeabcde"), 1, S::npos);
   test(S("abcde"), S("abcdeabcdeabcdeabcde"), 1, S::npos);
   test(S("abcde"), S(""), 2, 2);
+  test(S("abcde"), S("a"), 2, S::npos);
   test(S("abcde"), S("abcde"), 2, S::npos);
   test(S("abcde"), S("abcdeabcde"), 2, S::npos);
   test(S("abcde"), S("abcdeabcdeabcdeabcde"), 2, S::npos);
@@ -59,58 +62,72 @@ TEST_CONSTEXPR_CXX20 void test0() {
   test(S("abcde"), S("abcdeabcde"), 4, S::npos);
   test(S("abcde"), S("abcdeabcdeabcdeabcde"), 4, S::npos);
   test(S("abcde"), S(""), 5, 5);
+  test(S("abcde"), S("a"), 5, S::npos);
   test(S("abcde"), S("abcde"), 5, S::npos);
   test(S("abcde"), S("abcdeabcde"), 5, S::npos);
   test(S("abcde"), S("abcdeabcdeabcdeabcde"), 5, S::npos);
   test(S("abcde"), S(""), 6, S::npos);
+  test(S("abcde"), S("a"), 6, S::npos);
   test(S("abcde"), S("abcde"), 6, S::npos);
   test(S("abcde"), S("abcdeabcde"), 6, S::npos);
   test(S("abcde"), S("abcdeabcdeabcdeabcde"), 6, S::npos);
   test(S("abcdeabcde"), S(""), 0, 0);
+  test(S("abcdeabcde"), S("a"), 0, 0);
   test(S("abcdeabcde"), S("abcde"), 0, 0);
   test(S("abcdeabcde"), S("abcdeabcde"), 0, 0);
   test(S("abcdeabcde"), S("abcdeabcdeabcdeabcde"), 0, S::npos);
   test(S("abcdeabcde"), S(""), 1, 1);
+  test(S("abcdeabcde"), S("a"), 1, 5);
   test(S("abcdeabcde"), S("abcde"), 1, 5);
   test(S("abcdeabcde"), S("abcdeabcde"), 1, S::npos);
   test(S("abcdeabcde"), S("abcdeabcdeabcdeabcde"), 1, S::npos);
   test(S("abcdeabcde"), S(""), 5, 5);
+  test(S("abcdeabcde"), S("a"), 5, 5);
   test(S("abcdeabcde"), S("abcde"), 5, 5);
   test(S("abcdeabcde"), S("abcdeabcde"), 5, S::npos);
   test(S("abcdeabcde"), S("abcdeabcdeabcdeabcde"), 5, S::npos);
   test(S("abcdeabcde"), S(""), 9, 9);
+  test(S("abcdeabcde"), S("a"), 9, S::npos);
   test(S("abcdeabcde"), S("abcde"), 9, S::npos);
   test(S("abcdeabcde"), S("abcdeabcde"), 9, S::npos);
   test(S("abcdeabcde"), S("abcdeabcdeabcdeabcde"), 9, S::npos);
   test(S("abcdeabcde"), S(""), 10, 10);
+  test(S("abcdeabcde"), S("a"), 10, S::npos);
   test(S("abcdeabcde"), S("abcde"), 10, S::npos);
   test(S("abcdeabcde"), S("abcdeabcde"), 10, S::npos);
   test(S("abcdeabcde"), S("abcdeabcdeabcdeabcde"), 10, S::npos);
   test(S("abcdeabcde"), S(""), 11, S::npos);
+  test(S("abcdeabcde"), S("a"), 11, S::npos);
   test(S("abcdeabcde"), S("abcde"), 11, S::npos);
   test(S("abcdeabcde"), S("abcdeabcde"), 11, S::npos);
   test(S("abcdeabcde"), S("abcdeabcdeabcdeabcde"), 11, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S(""), 0, 0);
+  test(S("abcdeabcdeabcdeabcde"), S("a"), 0, 0);
   test(S("abcdeabcdeabcdeabcde"), S("abcde"), 0, 0);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcde"), 0, 0);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcdeabcdeabcde"), 0, 0);
   test(S("abcdeabcdeabcdeabcde"), S(""), 1, 1);
+  test(S("abcdeabcdeabcdeabcde"), S("a"), 1, 5);
   test(S("abcdeabcdeabcdeabcde"), S("abcde"), 1, 5);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcde"), 1, 5);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcdeabcdeabcde"), 1, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S(""), 10, 10);
+  test(S("abcdeabcdeabcdeabcde"), S("a"), 10, 10);
   test(S("abcdeabcdeabcdeabcde"), S("abcde"), 10, 10);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcde"), 10, 10);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcdeabcdeabcde"), 10, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S(""), 19, 19);
+  test(S("abcdeabcdeabcdeabcde"), S("a"), 19, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcde"), 19, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcde"), 19, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcdeabcdeabcde"), 19, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S(""), 20, 20);
+  test(S("abcdeabcdeabcdeabcde"), S("a"), 20, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcde"), 20, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcde"), 20, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcdeabcdeabcde"), 20, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S(""), 21, S::npos);
+  test(S("abcdeabcdeabcdeabcde"), S("a"), 21, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcde"), 21, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcde"), 21, S::npos);
   test(S("abcdeabcdeabcdeabcde"), S("abcdeabcdeabcdeabcde"), 21, S::npos);

libcxx/test/benchmarks/containers/string.bench.cpp

libcxx/include/__string/char_traits.h

…d string has length 1

…d string has length 1 (llvm#160076) Apple M4: ``` Benchmark Baseline Candidate Difference % Difference ----------------------------------------------------------- ---------- ----------- ------------ -------------- BM_string_literal/1024 16.99 16.79 -0.21 -1.21 BM_string_literal/128 3.44 3.34 -0.10 -2.88 BM_string_literal/16 1.80 1.69 -0.11 -5.93 BM_string_literal/2048 38.44 38.38 -0.07 -0.17 BM_string_literal/256 5.77 5.65 -0.12 -2.02 BM_string_literal/32 2.03 1.92 -0.11 -5.44 BM_string_literal/4096 73.92 73.74 -0.18 -0.25 BM_string_literal/512 9.49 9.41 -0.08 -0.84 BM_string_literal/64 2.59 2.45 -0.14 -5.38 BM_string_literal/8 1.79 1.69 -0.11 -5.90 BM_string_literal/8192 132.09 131.81 -0.28 -0.21 ```

philnik777 force-pushed the optimize_string_find_single_char branch from dd1885a to f188376 Compare September 22, 2025 13:38

philnik777 marked this pull request as ready for review September 23, 2025 10:21

philnik777 requested a review from a team as a code owner September 23, 2025 10:21

llvmbot added the libc++ libc++ C++ Standard Library. Not GNU libstdc++. Not libc++abi. label Sep 23, 2025

ldionne approved these changes Sep 23, 2025

View reviewed changes

[libc++] Fold __search_substring into _Traits::find in case the secon…

57ff008

…d string has length 1

philnik777 force-pushed the optimize_string_find_single_char branch from f188376 to 57ff008 Compare September 24, 2025 08:45

philnik777 merged commit a769608 into llvm:main Sep 25, 2025
78 checks passed

philnik777 deleted the optimize_string_find_single_char branch September 25, 2025 07:29

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[libc++] Fold __search_substring into _Traits::find in case the second string has length 1 #160076

[libc++] Fold __search_substring into _Traits::find in case the second string has length 1 #160076

Uh oh!

philnik777 commented Sep 22, 2025 •

edited

Loading

Uh oh!

github-actions bot commented Sep 22, 2025 •

edited

Loading

Uh oh!

llvmbot commented Sep 23, 2025

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

[libc++] Fold __search_substring into _Traits::find in case the second string has length 1 #160076

[libc++] Fold __search_substring into _Traits::find in case the second string has length 1 #160076

Uh oh!

Conversation

philnik777 commented Sep 22, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Sep 22, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

llvmbot commented Sep 23, 2025

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

philnik777 commented Sep 22, 2025 •

edited

Loading

github-actions bot commented Sep 22, 2025 •

edited

Loading