[RFC][libc++][format] Implements compile-time caching.

[mordante]

This is a proof-of-concept patch to implement caching in basic_format_string. This is only intended for this Discourse discussion.

The real patch needs to do things cleaner.

lit -a -Doptimization=speed libcxx/test/benchmarks/format/parsing.bench.cpp BEFORE

| ----------------------------------------------------------------------------
| Benchmark                                  Time             CPU   Iterations
| ----------------------------------------------------------------------------
| BM_empty                                6.18 ns         6.17 ns     87897649
| BM_curly_open                           11.2 ns         11.2 ns     62229450
| BM_curly_close                          10.7 ns         10.7 ns     65368952
| BM_pipe                                 12.9 ns         12.9 ns     54477724
| BM_int                                  47.6 ns         47.6 ns     14718165
| BM_int_formatted                        97.4 ns         97.4 ns      6953144
| BM_3_ints                                141 ns          141 ns      4944337
| BM_3_ints_formatted                      283 ns          283 ns      2464184
| BM_prefix_5_and_empty                   16.5 ns         16.5 ns     42569346
| BM_prefix_5_and_curly_open              17.8 ns         17.8 ns     39273542
| BM_prefix_5_and_curly_close             17.8 ns         17.8 ns     39140130
| BM_prefix_5_and_pipe                    19.5 ns         19.5 ns     35803584
| BM_prefix_5_and_int                     51.1 ns         51.0 ns     13436274
| BM_prefix_5_and_int_formatted            102 ns          102 ns      6793303
| BM_prefix_5_and_3_ints                   151 ns          151 ns      4573472
| BM_prefix_5_and_3_ints_formatted         291 ns          291 ns      2351850
| BM_prefix_10_and_empty                  24.9 ns         24.9 ns     28109036
| BM_prefix_10_and_curly_open             27.2 ns         27.2 ns     25713490
| BM_prefix_10_and_curly_close            30.2 ns         30.2 ns     23176332
| BM_prefix_10_and_pipe                   32.7 ns         32.6 ns     21420861
| BM_prefix_10_and_int                    61.6 ns         61.6 ns     11034101
| BM_prefix_10_and_int_formatted           120 ns          120 ns      5610531
| BM_prefix_10_and_3_ints                  156 ns          156 ns      4470738
| BM_prefix_10_and_3_ints_formatted        312 ns          311 ns      2217207
| BM_prefix_20_and_empty                  52.7 ns         52.7 ns     13138425
| BM_prefix_20_and_curly_open             58.8 ns         58.8 ns     11863712
| BM_prefix_20_and_curly_close            56.6 ns         56.6 ns     12407764
| BM_prefix_20_and_pipe                   56.5 ns         56.4 ns     12411003
| BM_prefix_20_and_int                    86.9 ns         86.8 ns      8089463
| BM_prefix_20_and_int_formatted           153 ns          153 ns      4582443
| BM_prefix_20_and_3_ints                  204 ns          204 ns      3354539
| BM_prefix_20_and_3_ints_formatted        349 ns          349 ns      2002457
| BM_prefix_40_and_empty                   116 ns          116 ns      6018618
| BM_prefix_40_and_curly_open              122 ns          122 ns      5655627
| BM_prefix_40_and_curly_close             121 ns          121 ns      5722255
| BM_prefix_40_and_pipe                    120 ns          120 ns      5823239
| BM_prefix_40_and_int                     158 ns          158 ns      4476432
| BM_prefix_40_and_int_formatted           207 ns          207 ns      3306182
| BM_prefix_40_and_3_ints                  255 ns          255 ns      2759277
| BM_prefix_40_and_3_ints_formatted        371 ns          370 ns      1884154

AFTER

| ----------------------------------------------------------------------------
| Benchmark                                  Time             CPU   Iterations
| ----------------------------------------------------------------------------
| BM_empty                                21.6 ns         21.6 ns     32391462
| BM_curly_open                           22.9 ns         22.9 ns     30588441
| BM_curly_close                          22.9 ns         22.9 ns     30592394
| BM_pipe                                 26.0 ns         26.0 ns     26953859
| BM_int                                  60.5 ns         60.5 ns     11577625
| BM_int_formatted                        81.3 ns         81.2 ns      8594596
| BM_3_ints                                156 ns          156 ns      4409940
| BM_3_ints_formatted                      220 ns          220 ns      3187392
| BM_prefix_5_and_empty                   26.0 ns         26.0 ns     26936925
| BM_prefix_5_and_curly_open              26.0 ns         26.0 ns     26965917
| BM_prefix_5_and_curly_close             26.0 ns         26.0 ns     26961356
| BM_prefix_5_and_pipe                    26.0 ns         26.0 ns     26959641
| BM_prefix_5_and_int                     64.1 ns         64.1 ns     10920953
| BM_prefix_5_and_int_formatted           84.4 ns         84.4 ns      8037453
| BM_prefix_5_and_3_ints                   165 ns          165 ns      4217532
| BM_prefix_5_and_3_ints_formatted         247 ns          247 ns      2823553
| BM_prefix_10_and_empty                  26.0 ns         26.0 ns     26949246
| BM_prefix_10_and_curly_open             26.0 ns         26.0 ns     26955524
| BM_prefix_10_and_curly_close            26.0 ns         26.0 ns     26956279
| BM_prefix_10_and_pipe                   26.0 ns         26.0 ns     26947963
| BM_prefix_10_and_int                    59.8 ns         59.8 ns     11674226
| BM_prefix_10_and_int_formatted          87.1 ns         87.0 ns      7814714
| BM_prefix_10_and_3_ints                  165 ns          165 ns      4149378
| BM_prefix_10_and_3_ints_formatted        245 ns          245 ns      2884163
| BM_prefix_20_and_empty                  29.3 ns         29.3 ns     23873593
| BM_prefix_20_and_curly_open             28.5 ns         28.4 ns     24625298
| BM_prefix_20_and_curly_close            27.5 ns         27.5 ns     25438870
| BM_prefix_20_and_pipe                   29.4 ns         29.3 ns     23863557
| BM_prefix_20_and_int                    57.6 ns         57.6 ns     12247413
| BM_prefix_20_and_int_formatted           104 ns          104 ns      6690343
| BM_prefix_20_and_3_ints                  183 ns          183 ns      3828112
| BM_prefix_20_and_3_ints_formatted        244 ns          244 ns      2833578
| BM_prefix_40_and_empty                  37.5 ns         37.5 ns     18650804
| BM_prefix_40_and_curly_open             36.8 ns         36.8 ns     19094990
| BM_prefix_40_and_curly_close            37.1 ns         37.0 ns     18904266
| BM_prefix_40_and_pipe                   36.5 ns         36.5 ns     19147265
| BM_prefix_40_and_int                    81.1 ns         81.0 ns      8611919
| BM_prefix_40_and_int_formatted           102 ns          102 ns      6854642
| BM_prefix_40_and_3_ints                  181 ns          181 ns      3828217
| BM_prefix_40_and_3_ints_formatted        243 ns          243 ns      2814977

[github-actions]

⚠️ C/C++ code formatter, clang-format found issues in your code. ⚠️

You can test this locally with the following command:

git-clang-format --diff dd97324f119af515944b7ec79fe627cfa70d4a2a e02e5bac0bbdd2e62d8cd9d07c2f0e7810b393b9 --extensions cpp,h -- libcxx/test/benchmarks/format/parsing.bench.cpp libcxx/test/std/utilities/format/format.functions/cache.pass.cpp libcxx/include/__format/format_functions.h

View the diff from clang-format here.

diff --git a/libcxx/include/__format/format_functions.h b/libcxx/include/__format/format_functions.h
index 98e2d97718..d092561743 100644
--- a/libcxx/include/__format/format_functions.h
+++ b/libcxx/include/__format/format_functions.h
@@ -725,8 +725,7 @@ private:
         break;
 
       switch (__element.__type) {
-      case __element_type::__formatter_std:
-      {
+      case __element_type::__formatter_std: {
         std::__visit_format_arg(
             [&](auto __arg) {
               if constexpr (same_as<decltype(__arg), monostate>)
diff --git a/libcxx/test/std/utilities/format/format.functions/cache.pass.cpp b/libcxx/test/std/utilities/format/format.functions/cache.pass.cpp
index a1d8ced4ae..bd6e07a726 100644
--- a/libcxx/test/std/utilities/format/format.functions/cache.pass.cpp
+++ b/libcxx/test/std/utilities/format/format.functions/cache.pass.cpp
@@ -8,7 +8,6 @@
 // UNSUPPORTED: c++03, c++11, c++14, c++17
 // UNSUPPORTED: GCC-ALWAYS_INLINE-FIXME
 
-
 // TODO FMT This test should not require std::to_chars(floating-point)
 // XFAIL: availability-fp_to_chars-missing
 
@@ -16,7 +15,6 @@
 
 // <format>
 
-
 // This is a test for the new caching mechanism.
 
 #include <format>
@@ -84,8 +82,8 @@ static void test() {
   check(SV("FULL:0x0042"), SV("{:#06x}"), 0x42);
   check(SV("FULL:0x0042=answer"), SV("{:#06x}={}"), 0x42, SV("answer"));
 
-//  check(SV("FULL:hello world"), SV("{} world"), String<char>{"hello"});
-//  check(SV("FULL:hello world"), SV("{0:} world"), String<char>{"hello"});
+  //  check(SV("FULL:hello world"), SV("{} world"), String<char>{"hello"});
+  //  check(SV("FULL:hello world"), SV("{0:} world"), String<char>{"hello"});
 
   // TODO TEST WITH ARG EATER
 }