René's URL Explorer Experiment


Title: Use `find_char`/`memchr` to improve performance of `str.split` · Issue #145797 · python/cpython · GitHub

Open Graph Title: Use `find_char`/`memchr` to improve performance of `str.split` · Issue #145797 · python/cpython

X Title: Use `find_char`/`memchr` to improve performance of `str.split` · Issue #145797 · python/cpython

Description: Description I propose to use memchr (link) (and memrchr) to speed up str.split (and str.resplit). Currently, str.split (and str.rsplit) use a basic loop to iterate through the string to find delimiters. Using memchr and memrchr can provi...

Open Graph Description: Description I propose to use memchr (link) (and memrchr) to speed up str.split (and str.resplit). Currently, str.split (and str.rsplit) use a basic loop to iterate through the string to find delimi...

X Description: Description I propose to use memchr (link) (and memrchr) to speed up str.split (and str.resplit). Currently, str.split (and str.rsplit) use a basic loop to iterate through the string to find delimi...

Opengraph URL: https://github.com/python/cpython/issues/145797

X: @github

direct link

Domain: github.com


Hey, it has json ld scripts:
{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"Use `find_char`/`memchr` to improve performance of `str.split`","articleBody":"## Description\n\nI propose to use `memchr` ([link](https://en.cppreference.com/w/c/string/byte/memchr.html)) (and `memrchr`) to speed up `str.split` (and `str.resplit`).\n\nCurrently, `str.split` (and `str.rsplit`) use a basic loop to iterate through the string to find delimiters.  \nUsing `memchr` and `memrchr` can provide a significant performance boost as they are typically heavily optimised / implemented using SIMD instructions.\n\nNote that no complicated change is needed to make this happen, as both functions exist within `STRINGLIB` (`find_char` and `rfind_char`).\n\nInterestingly, there is a comment today in the code stating that using `memchr` does not provide any meaningful improvements, but benchmarks seem to disagree. I suspect that this is because this code was written ~16y ago (f2c5484f9ee9c964454b2d4a176170042e3beea5) and `memchr` implementations (and, potentially, hardware) have evolved and started to difference since then.\n\n## Proposed change\n\nI have a [branch in my fork](https://github.com/python/cpython/compare/main...KowalskiThomas:cpython:kowalski/use-memchr-for-str-split) that implements this change and that I can open if we want to go forward with that.\n\nThe long story short code-wise is that the existing `for` loop iterating on characters would be replaced with a call to `STRINGLIB(find_char)`.\n\n## Benchmarks\n\nI made this `pyperf` benchmarking script which should show whether the proposed change helps. (I don't think there's a `pyperformance` benchmark for that.)\n\n```py\nimport pyperf\n\nSIZES = [100, 1_000, 10_000, 100_000, 1_000_000]\nSEGMENT_LENGTHS = [2, 10, 50, 250, 500, 1000, 10_000, 25_000, 100_000, 250_000, 500_000, 999_999]\n\nCHAR_SETS = {\n    \"ascii\": (\"a\", \" \"),\n    \"latin\": (\"é\", \" \"),\n    # we have two CJK cases because find_char has a different implementation for\n    # (sep & 0xff == 0) and (sep & 0xff != 0)\n    \"cjk\": (\"\\u4e16\", \"\\u3000\"),  # CJK ideograph + ideographic space (sep & 0xff == 0)\n    \"cjk_nz\": (\"\\u4e16\", \"\\u3001\"),  # CJK ideograph + ideographic comma (sep & 0xff != 0)\n    \"emoji\": (\"\\U0001f600\", \" \"),\n}\n\n\ndef make_string(char: str, sep: str, size: int, seg_len: int) -> str:\n    segment = char * seg_len + sep\n    repeats = max(1, size // len(segment))\n    return (segment * repeats)[:size]\n\n\ndef bench_split_sep(s: str, sep: str):\n    s.split(sep)\n\n\ndef add_benchmarks(runner: pyperf.Runner):\n    for charset_name, (char, sep) in CHAR_SETS.items():\n        for size in SIZES:\n            for seg_len in SEGMENT_LENGTHS:\n                if seg_len > size:\n                    continue\n\n                s = make_string(char, sep, size, seg_len)\n                name = f\"split_{charset_name}_size{size}_seg{seg_len}\"\n                runner.bench_func(name, bench_split_sep, s, sep)\n\n\nrunner = pyperf.Runner()\nadd_benchmarks(runner)\n```\n\nI ran the benchmarks on two computers (running macOS and Linux), with `--enable-optimizations --enable-lto`.  I don't have a Windows machine around, let alone with a C compiler available, but if needed I may be able to find one.  \nOptimisation flags actually are important in that case. I initially ran benchmarks on a build without LTO and it led to slightly worse results in certain cases (probably due to the `find_char` function not being inlined, although I don't have proof).\n\nOverall, what the benchmarks show is that:\n- There is a performance gain (and a significant one)\n- The performance gains grow with the size of segments (which makes sense, given that what we optimise here is how fast we find the next delimiter)\n  - At lower segment sizes, the performance gain is near zero\n  - At higher segment sizes, the performance gain can be up to 90%\n- Performance gains are much lower (or even inexistent) when the delimiter (searched character) is \"not well supported\"\n  - Splits on ASCII show significant improvements\n  - Same goes for Latin\n  - CJK shows or doesn't show an improvement depending on the delimiter (due to [this](https://github.com/python/cpython/blob/cf7c67b7c6b96527dfb0da2d6305923a92e3d766/Objects/stringlib/fastsearch.h#L63-L69)), in the \"happy case\" the improvement is comparable to ASCII/Latin\n  - Emoji delimiters show no improvement\n- One caveat to all that is that the absolute numbers are already not exactly huge today. However, when splitting many strings in a loop, they could quickly add up.\n\nThe raw results are attached here.\n\n\u003cdetails>\n\n**Note** The _Change_ column is how much time the optimised version takes compared to the baseline, so less is better.\n\n**Linux**\n\n```\nBenchmark                           Optimised           Baseline            Change\n----------------------------------------------------------------------------------\nsplit_ascii_size100_seg2            1.22 us +- 0.02 us  1.35 us +- 0.03 us  -9.6%\nsplit_ascii_size100_seg10           421 ns +- 6 ns      497 ns +- 4 ns      -15.3%\nsplit_ascii_size100_seg50           212 ns +- 1 ns      242 ns +- 12 ns     -12.4%\n\nsplit_ascii_size1000_seg2           11.1 us +- 0.2 us   12.3 us +- 0.2 us   -9.8%\nsplit_ascii_size1000_seg10          3.30 us +- 0.05 us  4.08 us +- 0.05 us  -19.1%\nsplit_ascii_size1000_seg50          768 ns +- 9 ns      1.22 us +- 0.03 us  -37.0%\nsplit_ascii_size1000_seg250         289 ns +- 5 ns      611 ns +- 8 ns      -52.7%\nsplit_ascii_size1000_seg500         245 ns +- 9 ns      429 ns +- 3 ns      -42.9%\nsplit_ascii_size1000_seg1000        191 ns +- 5 ns      529 ns +- 17 ns     -63.9%\n\nsplit_ascii_size10000_seg2          105 us +- 4 us      116 us +- 3 us      -9.5%\nsplit_ascii_size10000_seg10         28.4 us +- 0.4 us   36.8 us +- 0.3 us   -22.8%\nsplit_ascii_size10000_seg50         7.05 us +- 0.09 us  11.7 us +- 0.1 us   -39.7%\nsplit_ascii_size10000_seg250        1.74 us +- 0.05 us  5.95 us +- 0.20 us  -70.8%\nsplit_ascii_size10000_seg500        1.84 us +- 0.06 us  5.61 us +- 0.08 us  -67.2%\nsplit_ascii_size10000_seg1000       1.27 us +- 0.01 us  4.43 us +- 0.04 us  -71.3%\nsplit_ascii_size10000_seg10000      255 ns +- 4 ns      3.52 us +- 0.02 us  -92.8%\n\nsplit_ascii_size100000_seg2         1.54 ms +- 0.03 ms  1.65 ms +- 0.03 ms  -6.7%\nsplit_ascii_size100000_seg10        290 us +- 21 us     361 us +- 4 us      -19.7%\nsplit_ascii_size100000_seg50        65.8 us +- 1.1 us   110 us +- 1 us      -40.2%\nsplit_ascii_size100000_seg250       18.0 us +- 0.2 us   57.7 us +- 1.8 us   -68.8%\nsplit_ascii_size100000_seg500       19.3 us +- 0.3 us   56.4 us +- 0.7 us   -65.8%\nsplit_ascii_size100000_seg1000      12.7 us +- 0.4 us   47.3 us +- 0.3 us   -73.2%\nsplit_ascii_size100000_seg10000     4.26 us +- 0.24 us  33.6 us +- 1.0 us   -87.3%\nsplit_ascii_size100000_seg25000     3.51 us +- 0.18 us  28.2 us +- 1.2 us   -87.6%\nsplit_ascii_size100000_seg100000    1.35 us +- 0.02 us  33.2 us +- 0.9 us   -95.9%\n\nsplit_ascii_size1000000_seg2        18.8 ms +- 0.5 ms   20.7 ms +- 0.7 ms   -9.2%\nsplit_ascii_size1000000_seg10       5.40 ms +- 0.08 ms  6.12 ms +- 0.06 ms  -11.8%\nsplit_ascii_size1000000_seg50       1.19 ms +- 0.04 ms  1.59 ms +- 0.01 ms  -25.2%\nsplit_ascii_size1000000_seg250      677 us +- 10 us     1.07 ms +- 0.01 ms  -36.7%\nsplit_ascii_size1000000_seg500      200 us +- 2 us      554 us +- 2 us      -63.9%\nsplit_ascii_size1000000_seg1000     143 us +- 2 us      459 us +- 9 us      -68.8%\nsplit_ascii_size1000000_seg10000    71.9 us +- 2.6 us   375 us +- 10 us     -80.8%\nsplit_ascii_size1000000_seg25000    77.2 us +- 2.2 us   369 us +- 4 us      -79.1%\nsplit_ascii_size1000000_seg100000   61.6 us +- 1.6 us   346 us +- 13 us     -82.2%\nsplit_ascii_size1000000_seg250000   45.0 us +- 1.0 us   284 us +- 5 us      -84.2%\nsplit_ascii_size1000000_seg500000   27.5 us +- 0.8 us   189 us +- 5 us      -85.4%\nsplit_ascii_size1000000_seg999999   73.7 us +- 3.4 us   387 us +- 2 us      -81.0%\n\nsplit_latin_size100_seg2            1.53 us +- 0.07 us  1.62 us +- 0.01 us  -5.6%\nsplit_latin_size100_seg10           499 ns +- 13 ns     570 ns +- 12 ns     -12.5%\nsplit_latin_size100_seg50           217 ns +- 3 ns      255 ns +- 4 ns      -14.9%\n\nsplit_latin_size1000_seg2           14.4 us +- 0.2 us   15.2 us +- 0.2 us   -5.3%\nsplit_latin_size1000_seg10          4.13 us +- 0.11 us  4.81 us +- 0.10 us  -14.1%\nsplit_latin_size1000_seg50          940 ns +- 12 ns     1.62 us +- 0.10 us  -42.0%\nsplit_latin_size1000_seg250         307 ns +- 2 ns      835 ns +- 12 ns     -63.2%\nsplit_latin_size1000_seg500         247 ns +- 1 ns      584 ns +- 12 ns     -57.7%\nsplit_latin_size1000_seg1000        190 ns +- 4 ns      844 ns +- 7 ns      -77.5%\n\nsplit_latin_size10000_seg2          138 us +- 3 us      145 us +- 4 us      -4.8%\nsplit_latin_size10000_seg10         37.6 us +- 0.7 us   44.0 us +- 0.5 us   -14.5%\nsplit_latin_size10000_seg50         9.51 us +- 0.59 us  15.4 us +- 0.5 us   -38.2%\nsplit_latin_size10000_seg250        2.07 us +- 0.07 us  8.76 us +- 0.11 us  -76.4%\nsplit_latin_size10000_seg500        1.92 us +- 0.02 us  8.46 us +- 0.13 us  -77.3%\nsplit_latin_size10000_seg1000       1.38 us +- 0.03 us  7.30 us +- 0.10 us  -81.1%\nsplit_latin_size10000_seg10000      255 ns +- 2 ns      6.90 us +- 0.32 us  -96.3%\n\nsplit_latin_size100000_seg2         2.26 ms +- 0.21 ms  2.26 ms +- 0.27 ms  ~same\nsplit_latin_size100000_seg10        371 us +- 5 us      435 us +- 11 us     -14.7%\nsplit_latin_size100000_seg50        86.8 us +- 1.2 us   146 us +- 5 us      -40.5%\nsplit_latin_size100000_seg250       20.9 us +- 0.4 us   87.0 us +- 0.7 us   -76.0%\nsplit_latin_size100000_seg500       21.4 us +- 0.6 us   87.5 us +- 1.0 us   -75.5%\nsplit_latin_size100000_seg1000      13.7 us +- 0.5 us   78.8 us +- 0.4 us   -82.6%\nsplit_latin_size100000_seg10000     4.27 us +- 0.19 us  63.0 us +- 1.1 us   -93.2%\nsplit_latin_size100000_seg25000     3.60 us +- 0.23 us  52.6 us +- 0.9 us   -93.2%\nsplit_latin_size100000_seg100000    1.34 us +- 0.01 us  66.3 us +- 2.6 us   -98.0%\n\nsplit_latin_size1000000_seg2        26.0 ms +- 0.8 ms   26.5 ms +- 0.7 ms   -1.9%\nsplit_latin_size1000000_seg10       7.18 ms +- 0.23 ms  8.05 ms +- 0.62 ms  -10.8%\nsplit_latin_size1000000_seg50       1.88 ms +- 0.01 ms  2.47 ms +- 0.09 ms  -23.9%\nsplit_latin_size1000000_seg250      709 us +- 8 us      1.37 ms +- 0.01 ms  -48.2%\nsplit_latin_size1000000_seg500      217 us +- 5 us      869 us +- 11 us     -75.0%\nsplit_latin_size1000000_seg1000     149 us +- 2 us      781 us +- 5 us      -80.9%\nsplit_latin_size1000000_seg10000    74.9 us +- 3.7 us   700 us +- 7 us      -89.3%\nsplit_latin_size1000000_seg25000    76.7 us +- 2.4 us   690 us +- 3 us      -88.9%\nsplit_latin_size1000000_seg100000   62.1 us +- 2.2 us   639 us +- 14 us     -90.3%\nsplit_latin_size1000000_seg250000   45.3 us +- 1.3 us   529 us +- 3 us      -91.4%\nsplit_latin_size1000000_seg500000   27.5 us +- 0.9 us   357 us +- 11 us     -92.3%\nsplit_latin_size1000000_seg999999   74.8 us +- 3.2 us   757 us +- 56 us     -90.1%\n\nsplit_cjk_size100_seg2              1.46 us +- 0.02 us  1.54 us +- 0.04 us  -5.2%\nsplit_cjk_size100_seg10             519 ns +- 5 ns      605 ns +- 4 ns      -14.2%\nsplit_cjk_size100_seg50             248 ns +- 4 ns      278 ns +- 1 ns      -10.8%\n\nsplit_cjk_size1000_seg2             13.8 us +- 0.5 us   14.2 us +- 0.1 us   -2.8%\nsplit_cjk_size1000_seg10            4.53 us +- 0.26 us  5.03 us +- 0.12 us  -9.9%\nsplit_cjk_size1000_seg50            1.52 us +- 0.04 us  1.99 us +- 0.05 us  -23.6%\nsplit_cjk_size1000_seg250           880 ns +- 19 ns     1.17 us +- 0.03 us  -24.8%\nsplit_cjk_size1000_seg500           630 ns +- 5 ns      807 ns +- 9 ns      -21.9%\nsplit_cjk_size1000_seg1000          842 ns +- 18 ns     1.18 us +- 0.01 us  -28.6%\n\nsplit_cjk_size10000_seg2            130 us +- 1 us      136 us +- 8 us      -4.4%\nsplit_cjk_size10000_seg10           41.5 us +- 0.3 us   46.1 us +- 1.5 us   -10.0%\nsplit_cjk_size10000_seg50           14.6 us +- 0.5 us   19.4 us +- 0.6 us   -24.7%\nsplit_cjk_size10000_seg250          10.6 us +- 0.2 us   14.1 us +- 0.1 us   -24.8%\nsplit_cjk_size10000_seg500          9.07 us +- 0.06 us  12.3 us +- 0.1 us   -26.3%\nsplit_cjk_size10000_seg1000         7.44 us +- 0.15 us  10.5 us +- 0.2 us   -29.1%\nsplit_cjk_size10000_seg10000        6.80 us +- 0.12 us  10.1 us +- 0.0 us   -32.7%\n\nsplit_cjk_size100000_seg2           2.18 ms +- 0.18 ms  2.21 ms +- 0.20 ms  -1.4%\nsplit_cjk_size100000_seg10          410 us +- 17 us     443 us +- 4 us      -7.4%\nsplit_cjk_size100000_seg50          138 us +- 4 us      188 us +- 12 us     -26.6%\nsplit_cjk_size100000_seg250         105 us +- 1 us      145 us +- 6 us      -27.6%\nsplit_cjk_size100000_seg500         92.8 us +- 0.7 us   127 us +- 1 us      -26.9%\nsplit_cjk_size100000_seg1000        80.5 us +- 1.7 us   113 us +- 1 us      -28.8%\nsplit_cjk_size100000_seg10000       66.5 us +- 0.3 us   96.1 us +- 0.6 us   -30.8%\nsplit_cjk_size100000_seg25000       55.8 us +- 1.1 us   80.6 us +- 1.6 us   -30.8%\nsplit_cjk_size100000_seg100000      65.7 us +- 0.4 us   98.4 us +- 0.5 us   -33.2%\n\nsplit_cjk_size1000000_seg2          25.7 ms +- 1.8 ms   25.3 ms +- 0.9 ms   +1.6%\nsplit_cjk_size1000000_seg10         7.40 ms +- 0.30 ms  7.86 ms +- 0.31 ms  -5.9%\nsplit_cjk_size1000000_seg50         2.76 ms +- 0.25 ms  3.17 ms +- 0.22 ms  -12.9%\nsplit_cjk_size1000000_seg250        1.05 ms +- 0.01 ms  1.42 ms +- 0.06 ms  -26.1%\nsplit_cjk_size1000000_seg500        949 us +- 7 us      1.32 ms +- 0.07 ms  -28.1%\nsplit_cjk_size1000000_seg1000       804 us +- 14 us     1.13 ms +- 0.01 ms  -28.8%\nsplit_cjk_size1000000_seg10000      748 us +- 15 us     1.07 ms +- 0.01 ms  -30.1%\nsplit_cjk_size1000000_seg25000      741 us +- 4 us      1.06 ms +- 0.00 ms  -30.1%\nsplit_cjk_size1000000_seg100000     682 us +- 7 us      976 us +- 3 us      -30.1%\nsplit_cjk_size1000000_seg250000     572 us +- 22 us     812 us +- 4 us      -29.6%\nsplit_cjk_size1000000_seg500000     390 us +- 21 us     550 us +- 3 us      -29.1%\nsplit_cjk_size1000000_seg999999     815 us +- 4 us      1.14 ms +- 0.01 ms  -28.5%\n\nsplit_cjk_nz_size100_seg2           1.49 us +- 0.02 us  1.54 us +- 0.04 us  -3.2%\nsplit_cjk_nz_size100_seg10          499 ns +- 8 ns      609 ns +- 11 ns     -18.1%\nsplit_cjk_nz_size100_seg50          223 ns +- 5 ns      282 ns +- 10 ns     -20.9%\n\nsplit_cjk_nz_size1000_seg2          14.0 us +- 0.1 us   14.3 us +- 0.3 us   -2.1%\nsplit_cjk_nz_size1000_seg10         3.95 us +- 0.05 us  5.01 us +- 0.04 us  -21.2%\nsplit_cjk_nz_size1000_seg50         951 ns +- 17 ns     1.98 us +- 0.08 us  -52.0%\nsplit_cjk_nz_size1000_seg250        376 ns +- 10 ns     1.16 us +- 0.01 us  -67.6%\nsplit_cjk_nz_size1000_seg500        312 ns +- 11 ns     814 ns +- 33 ns     -61.7%\nsplit_cjk_nz_size1000_seg1000       203 ns +- 12 ns     1.18 us +- 0.03 us  -82.8%\n\nsplit_cjk_nz_size10000_seg2         132 us +- 3 us      134 us +- 1 us      -1.5%\nsplit_cjk_nz_size10000_seg10        36.0 us +- 1.2 us   45.4 us +- 0.5 us   -20.7%\nsplit_cjk_nz_size10000_seg50        9.05 us +- 0.07 us  19.2 us +- 0.4 us   -52.9%\nsplit_cjk_nz_size10000_seg250       3.93 us +- 0.03 us  14.6 us +- 1.1 us   -73.1%\nsplit_cjk_nz_size10000_seg500       2.70 us +- 0.02 us  12.3 us +- 0.1 us   -78.0%\nsplit_cjk_nz_size10000_seg1000      1.65 us +- 0.02 us  10.4 us +- 0.1 us   -84.1%\nsplit_cjk_nz_size10000_seg10000     344 ns +- 5 ns      10.1 us +- 0.1 us   -96.6%\n\nsplit_cjk_nz_size100000_seg2        2.18 ms +- 0.20 ms  2.18 ms +- 0.21 ms  ~same\nsplit_cjk_nz_size100000_seg10       347 us +- 5 us      444 us +- 14 us     -21.8%\nsplit_cjk_nz_size100000_seg50       87.6 us +- 5.6 us   186 us +- 8 us      -52.9%\nsplit_cjk_nz_size100000_seg250      41.0 us +- 1.0 us   141 us +- 1 us      -70.9%\nsplit_cjk_nz_size100000_seg500      29.0 us +- 0.8 us   127 us +- 3 us      -77.2%\nsplit_cjk_nz_size100000_seg1000     17.7 us +- 0.3 us   113 us +- 1 us      -84.3%\nsplit_cjk_nz_size100000_seg10000    8.53 us +- 0.52 us  99.7 us +- 5.7 us   -91.4%\nsplit_cjk_nz_size100000_seg25000    7.04 us +- 0.46 us  80.5 us +- 1.3 us   -91.3%\nsplit_cjk_nz_size100000_seg100000   2.50 us +- 0.05 us  98.4 us +- 0.3 us   -97.5%\n\nsplit_cjk_nz_size1000000_seg2       25.1 ms +- 0.9 ms   25.5 ms +- 0.6 ms   -1.6%\nsplit_cjk_nz_size1000000_seg10      7.01 ms +- 0.17 ms  7.82 ms +- 0.21 ms  -10.4%\nsplit_cjk_nz_size1000000_seg50      2.26 ms +- 0.16 ms  3.24 ms +- 0.16 ms  -30.2%\nsplit_cjk_nz_size1000000_seg250     440 us +- 27 us     1.41 ms +- 0.02 ms  -68.8%\nsplit_cjk_nz_size1000000_seg500     353 us +- 10 us     1.29 ms +- 0.01 ms  -72.6%\nsplit_cjk_nz_size1000000_seg1000    235 us +- 5 us      1.13 ms +- 0.01 ms  -79.2%\nsplit_cjk_nz_size1000000_seg10000   193 us +- 3 us      1.07 ms +- 0.00 ms  -82.0%\nsplit_cjk_nz_size1000000_seg25000   197 us +- 3 us      1.07 ms +- 0.01 ms  -81.6%\nsplit_cjk_nz_size1000000_seg100000  162 us +- 3 us      979 us +- 8 us      -83.5%\nsplit_cjk_nz_size1000000_seg250000  122 us +- 3 us      813 us +- 4 us      -85.0%\nsplit_cjk_nz_size1000000_seg500000  72.9 us +- 2.8 us   552 us +- 6 us      -86.8%\nsplit_cjk_nz_size1000000_seg999999  234 us +- 9 us      1.14 ms +- 0.00 ms  -79.5%\n\nsplit_emoji_size100_seg2            1.69 us +- 0.06 us  1.83 us +- 0.02 us  -7.7%\nsplit_emoji_size100_seg10           615 ns +- 38 ns     674 ns +- 8 ns      -8.8%\nsplit_emoji_size100_seg50           249 ns +- 9 ns      300 ns +- 5 ns      -17.0%\n\nsplit_emoji_size1000_seg2           15.6 us +- 0.7 us   17.1 us +- 0.5 us   -8.8%\nsplit_emoji_size1000_seg10          4.92 us +- 0.12 us  5.67 us +- 0.10 us  -13.2%\nsplit_emoji_size1000_seg50          1.22 us +- 0.01 us  2.10 us +- 0.09 us  -41.9%\nsplit_emoji_size1000_seg250         620 ns +- 11 ns     1.39 us +- 0.04 us  -55.4%\nsplit_emoji_size1000_seg500         331 ns +- 7 ns      816 ns +- 5 ns      -59.4%\nsplit_emoji_size1000_seg1000        231 ns +- 2 ns      1.19 us +- 0.00 us  -80.6%\n\nsplit_emoji_size10000_seg2          148 us +- 3 us      164 us +- 1 us      -9.8%\nsplit_emoji_size10000_seg10         45.9 us +- 0.5 us   52.1 us +- 0.3 us   -11.9%\nsplit_emoji_size10000_seg50         11.9 us +- 0.1 us   20.2 us +- 0.2 us   -41.1%\nsplit_emoji_size10000_seg250        5.82 us +- 0.15 us  15.7 us +- 0.1 us   -62.9%\nsplit_emoji_size10000_seg500        3.45 us +- 0.05 us  12.7 us +- 0.1 us   -72.8%\nsplit_emoji_size10000_seg1000       2.21 us +- 0.03 us  10.7 us +- 0.1 us   -79.3%\nsplit_emoji_size10000_seg10000      669 ns +- 12 ns     10.6 us +- 0.8 us   -93.7%\n\nsplit_emoji_size100000_seg2         2.53 ms +- 0.02 ms  2.62 ms +- 0.12 ms  -3.4%\nsplit_emoji_size100000_seg10        457 us +- 4 us      514 us +- 6 us      -11.1%\nsplit_emoji_size100000_seg50        115 us +- 1 us      194 us +- 1 us      -40.7%\nsplit_emoji_size100000_seg250       64.5 us +- 1.8 us   159 us +- 3 us      -59.4%\nsplit_emoji_size100000_seg500       35.4 us +- 1.2 us   128 us +- 0 us      -72.3%\nsplit_emoji_size100000_seg1000      26.7 us +- 1.2 us   118 us +- 1 us      -77.4%\nsplit_emoji_size100000_seg10000     19.1 us +- 1.0 us   105 us +- 2 us      -81.8%\nsplit_emoji_size100000_seg25000     15.0 us +- 1.1 us   87.3 us +- 1.4 us   -82.8%\nsplit_emoji_size100000_seg100000    4.63 us +- 0.04 us  98.8 us +- 2.1 us   -95.3%\n\nsplit_emoji_size1000000_seg2        31.4 ms +- 0.7 ms   32.7 ms +- 0.8 ms   -4.0%\nsplit_emoji_size1000000_seg10       9.30 ms +- 0.18 ms  10.1 ms +- 0.4 ms   -7.9%\nsplit_emoji_size1000000_seg50       3.68 ms +- 0.09 ms  4.47 ms +- 0.04 ms  -17.7%\nsplit_emoji_size1000000_seg250      748 us +- 12 us     1.62 ms +- 0.03 ms  -53.8%\nsplit_emoji_size1000000_seg500      546 us +- 11 us     1.36 ms +- 0.01 ms  -59.9%\nsplit_emoji_size1000000_seg1000     412 us +- 6 us      1.22 ms +- 0.01 ms  -66.2%\nsplit_emoji_size1000000_seg10000    429 us +- 4 us      1.19 ms +- 0.01 ms  -63.9%\nsplit_emoji_size1000000_seg25000    382 us +- 19 us     1.17 ms +- 0.01 ms  -67.4%\nsplit_emoji_size1000000_seg100000   338 us +- 4 us      1.07 ms +- 0.01 ms  -68.4%\nsplit_emoji_size1000000_seg250000   314 us +- 4 us      924 us +- 6 us      -66.0%\nsplit_emoji_size1000000_seg500000   237 us +- 2 us      652 us +- 6 us      -63.7%\nsplit_emoji_size1000000_seg999999   869 us +- 6 us      1.77 ms +- 0.14 ms  -50.9%\n```\n\n**macOS**\n\n```\nBenchmark                           Optimised           Baseline            Change\n----------------------------------------------------------------------------------\nsplit_ascii_size100_seg2            435 ns +- 28 ns     403 ns +- 10 ns     +7.9%\nsplit_ascii_size100_seg10           145 ns +- 3 ns      150 ns +- 8 ns      -3.3%\nsplit_ascii_size100_seg50           59.8 ns +- 3.5 ns   70.2 ns +- 0.5 ns   -14.8%\n\nsplit_ascii_size1000_seg2           4.50 us +- 0.15 us  3.86 us +- 0.05 us  +16.6%\nsplit_ascii_size1000_seg10          1.15 us +- 0.01 us  1.35 us +- 0.02 us  -14.8%\nsplit_ascii_size1000_seg50          291 ns +- 6 ns      573 ns +- 34 ns     -49.2%\nsplit_ascii_size1000_seg250         92.6 ns +- 0.6 ns   321 ns +- 10 ns     -71.2%\nsplit_ascii_size1000_seg500         94.3 ns +- 1.5 ns   233 ns +- 5 ns      -59.5%\nsplit_ascii_size1000_seg1000        64.4 ns +- 0.6 ns   316 ns +- 3 ns      -79.6%\n\nsplit_ascii_size10000_seg2          45.6 us +- 0.3 us   37.0 us +- 0.8 us   +23.2%\nsplit_ascii_size10000_seg10         11.4 us +- 0.1 us   12.1 us +- 0.2 us   -5.8%\nsplit_ascii_size10000_seg50         2.86 us +- 0.03 us  5.79 us +- 0.12 us  -50.6%\nsplit_ascii_size10000_seg250        684 ns +- 9 ns      3.61 us +- 0.05 us  -81.1%\nsplit_ascii_size10000_seg500        846 ns +- 16 ns     3.44 us +- 0.30 us  -75.4%\nsplit_ascii_size10000_seg1000       539 ns +- 11 ns     2.80 us +- 0.02 us  -80.8%\nsplit_ascii_size10000_seg10000      231 ns +- 2 ns      2.63 us +- 0.02 us  -91.2%\n\nsplit_ascii_size100000_seg2         495 us +- 5 us      413 us +- 6 us      +19.9%\nsplit_ascii_size100000_seg10        115 us +- 3 us      129 us +- 1 us      -10.9%\nsplit_ascii_size100000_seg50        27.8 us +- 0.3 us   54.6 us +- 1.5 us   -49.1%\nsplit_ascii_size100000_seg250       8.16 us +- 0.07 us  37.4 us +- 0.8 us   -78.2%\nsplit_ascii_size100000_seg500       10.9 us +- 0.2 us   37.3 us +- 0.9 us   -70.8%\nsplit_ascii_size100000_seg1000      7.30 us +- 0.18 us  32.2 us +- 0.1 us   -77.3%\nsplit_ascii_size100000_seg10000     2.99 us +- 0.04 us  24.8 us +- 0.4 us   -87.9%\nsplit_ascii_size100000_seg25000     2.14 us +- 0.02 us  20.3 us +- 0.1 us   -89.5%\nsplit_ascii_size100000_seg100000    1.69 us +- 0.01 us  25.8 us +- 0.2 us   -93.4%\n\nsplit_ascii_size1000000_seg2        5.26 ms +- 0.19 ms  4.47 ms +- 0.05 ms  +17.7%\nsplit_ascii_size1000000_seg10       1.43 ms +- 0.01 ms  1.56 ms +- 0.06 ms  -8.3%\nsplit_ascii_size1000000_seg50       329 us +- 3 us      628 us +- 14 us     -47.6%\nsplit_ascii_size1000000_seg250      77.4 us +- 0.5 us   373 us +- 6 us      -79.2%\nsplit_ascii_size1000000_seg500      108 us +- 1 us      380 us +- 7 us      -71.6%\nsplit_ascii_size1000000_seg1000     79.8 us +- 0.7 us   337 us +- 5 us      -76.3%\nsplit_ascii_size1000000_seg10000    34.3 us +- 0.3 us   274 us +- 2 us      -87.5%\nsplit_ascii_size1000000_seg25000    27.6 us +- 0.3 us   264 us +- 1 us      -89.5%\nsplit_ascii_size1000000_seg100000   28.6 us +- 0.3 us   248 us +- 2 us      -88.5%\nsplit_ascii_size1000000_seg250000   24.0 us +- 0.3 us   206 us +- 2 us      -88.3%\nsplit_ascii_size1000000_seg500000   15.3 us +- 0.2 us   136 us +- 3 us      -88.8%\nsplit_ascii_size1000000_seg999999   29.8 us +- 0.5 us   271 us +- 2 us      -89.0%\n\nsplit_latin_size100_seg2            484 ns +- 6 ns      444 ns +- 8 ns      +9.0%\nsplit_latin_size100_seg10           155 ns +- 6 ns      159 ns +- 2 ns      -2.5%\nsplit_latin_size100_seg50           60.1 ns +- 0.6 ns   70.6 ns +- 1.4 ns   -14.9%\n\nsplit_latin_size1000_seg2           5.09 us +- 0.06 us  4.58 us +- 0.13 us  +11.1%\nsplit_latin_size1000_seg10          1.42 us +- 0.01 us  1.49 us +- 0.01 us  -4.7%\nsplit_latin_size1000_seg50          336 ns +- 6 ns      573 ns +- 13 ns     -41.4%\nsplit_latin_size1000_seg250         102 ns +- 1 ns      336 ns +- 7 ns      -69.6%\nsplit_latin_size1000_seg500         95.3 ns +- 1.2 ns   232 ns +- 3 ns      -58.9%\nsplit_latin_size1000_seg1000        66.0 ns +- 0.7 ns   327 ns +- 2 ns      -79.8%\n\nsplit_latin_size10000_seg2          51.2 us +- 0.4 us   47.4 us +- 0.5 us   +8.0%\nsplit_latin_size10000_seg10         13.8 us +- 0.6 us   14.3 us +- 0.5 us   -3.5%\nsplit_latin_size10000_seg50         3.54 us +- 0.06 us  5.94 us +- 0.07 us  -40.4%\nsplit_latin_size10000_seg250        844 ns +- 10 ns     3.80 us +- 0.03 us  -77.8%\nsplit_latin_size10000_seg500        919 ns +- 10 ns     3.50 us +- 0.02 us  -73.7%\nsplit_latin_size10000_seg1000       565 ns +- 9 ns      2.88 us +- 0.03 us  -80.4%\nsplit_latin_size10000_seg10000      234 ns +- 8 ns      2.79 us +- 0.04 us  -91.6%\n\nsplit_latin_size100000_seg2         574 us +- 5 us      541 us +- 5 us      +6.1%\nsplit_latin_size100000_seg10        136 us +- 1 us      145 us +- 1 us      -6.2%\nsplit_latin_size100000_seg50        35.3 us +- 0.3 us   59.9 us +- 1.9 us   -41.1%\nsplit_latin_size100000_seg250       9.38 us +- 0.19 us  39.1 us +- 0.2 us   -76.0%\nsplit_latin_size100000_seg500       11.7 us +- 0.1 us   38.5 us +- 0.2 us   -69.6%\nsplit_latin_size100000_seg1000      7.48 us +- 0.04 us  32.9 us +- 0.2 us   -77.3%\nsplit_latin_size100000_seg10000     3.01 us +- 0.03 us  25.3 us +- 0.1 us   -88.1%\nsplit_latin_size100000_seg25000     2.15 us +- 0.02 us  20.8 us +- 0.4 us   -89.7%\nsplit_latin_size100000_seg100000    1.69 us +- 0.01 us  27.5 us +- 0.4 us   -93.9%\n\nsplit_latin_size1000000_seg2        6.49 ms +- 0.07 ms  5.99 ms +- 0.07 ms  +8.3%\nsplit_latin_size1000000_seg10       1.75 ms +- 0.02 ms  1.85 ms +- 0.02 ms  -5.4%\nsplit_latin_size1000000_seg50       413 us +- 3 us      666 us +- 20 us     -38.0%\nsplit_latin_size1000000_seg250      90.0 us +- 2.0 us   390 us +- 9 us      -76.9%\nsplit_latin_size1000000_seg500      118 us +- 1 us      390 us +- 2 us      -69.7%\nsplit_latin_size1000000_seg1000     83.5 us +- 0.6 us   343 us +- 6 us      -75.7%\nsplit_latin_size1000000_seg10000    34.7 us +- 0.3 us   281 us +- 2 us      -87.7%\nsplit_latin_size1000000_seg25000    27.8 us +- 0.2 us   270 us +- 2 us      -89.7%\nsplit_latin_size1000000_seg100000   28.8 us +- 0.3 us   251 us +- 2 us      -88.5%\nsplit_latin_size1000000_seg250000   24.0 us +- 0.3 us   211 us +- 1 us      -88.6%\nsplit_latin_size1000000_seg500000   15.3 us +- 0.3 us   141 us +- 6 us      -89.1%\nsplit_latin_size1000000_seg999999   29.7 us +- 0.4 us   279 us +- 2 us      -89.4%\n\nsplit_cjk_size100_seg2              577 ns +- 15 ns     549 ns +- 14 ns     +5.1%\nsplit_cjk_size100_seg10             212 ns +- 3 ns      195 ns +- 3 ns      +8.7%\nsplit_cjk_size100_seg50             74.5 ns +- 0.4 ns   73.5 ns +- 2.7 ns   +1.4%\n\nsplit_cjk_size1000_seg2             5.62 us +- 0.17 us  5.29 us +- 0.07 us  +6.2%\nsplit_cjk_size1000_seg10            1.87 us +- 0.06 us  1.81 us +- 0.05 us  +3.3%\nsplit_cjk_size1000_seg50            590 ns +- 6 ns      592 ns +- 11 ns     ~same\nsplit_cjk_size1000_seg250           429 ns +- 13 ns     413 ns +- 10 ns     +3.9%\nsplit_cjk_size1000_seg500           249 ns +- 4 ns      260 ns +- 4 ns      -4.2%\nsplit_cjk_size1000_seg1000          322 ns +- 9 ns      330 ns +- 2 ns      -2.4%\n\nsplit_cjk_size10000_seg2            54.0 us +- 0.5 us   51.6 us +- 0.6 us   +4.7%\nsplit_cjk_size10000_seg10           17.5 us +- 0.2 us   16.7 us +- 0.2 us   +4.8%\nsplit_cjk_size10000_seg50           6.03 us +- 0.06 us  6.07 us +- 0.10 us  ~same\nsplit_cjk_size10000_seg250          4.77 us +- 0.10 us  4.86 us +- 0.04 us  -1.9%\nsplit_cjk_size10000_seg500          3.65 us +- 0.03 us  3.73 us +- 0.04 us  -2.1%\nsplit_cjk_size10000_seg1000         3.00 us +- 0.02 us  3.06 us +- 0.03 us  -2.0%\nsplit_cjk_size10000_seg10000        2.63 us +- 0.02 us  2.80 us +- 0.07 us  -6.1%\n\nsplit_cjk_size100000_seg2           587 us +- 17 us     568 us +- 7 us      +3.3%\nsplit_cjk_size100000_seg10          178 us +- 3 us      168 us +- 3 us      +6.0%\nsplit_cjk_size100000_seg50          59.2 us +- 0.6 us   59.3 us +- 0.6 us   ~same\nsplit_cjk_size100000_seg250         51.8 us +- 0.4 us   52.7 us +- 1.2 us   -1.7%\nsplit_cjk_size100000_seg500         41.4 us +- 0.4 us   41.9 us +- 0.3 us   -1.2%\nsplit_cjk_size100000_seg1000        36.5 us +- 0.9 us   37.0 us +- 0.2 us   -1.4%\nsplit_cjk_size100000_seg10000       25.7 us +- 0.2 us   26.2 us +- 0.2 us   -1.9%\nsplit_cjk_size100000_seg25000       22.6 us +- 0.2 us   23.1 us +- 0.4 us   -2.2%\nsplit_cjk_size100000_seg100000      25.8 us +- 0.1 us   27.8 us +- 0.5 us   -7.2%\n\nsplit_cjk_size1000000_seg2          6.57 ms +- 0.10 ms  6.38 ms +- 0.11 ms  +3.0%\nsplit_cjk_size1000000_seg10         2.18 ms +- 0.04 ms  2.11 ms +- 0.05 ms  +3.3%\nsplit_cjk_size1000000_seg50         708 us +- 6 us      711 us +- 10 us     ~same\nsplit_cjk_size1000000_seg250        514 us +- 10 us     520 us +- 2 us      -1.2%\nsplit_cjk_size1000000_seg500        414 us +- 2 us      420 us +- 3 us      -1.4%\nsplit_cjk_size1000000_seg1000       374 us +- 5 us      381 us +- 4 us      -1.8%\nsplit_cjk_size1000000_seg10000      285 us +- 2 us      290 us +- 2 us      -1.7%\nsplit_cjk_size1000000_seg25000      294 us +- 2 us      302 us +- 8 us      -2.6%\nsplit_cjk_size1000000_seg100000     262 us +- 2 us      268 us +- 2 us      -2.2%\nsplit_cjk_size1000000_seg250000     216 us +- 8 us      220 us +- 1 us      -1.8%\nsplit_cjk_size1000000_seg500000     143 us +- 1 us      145 us +- 1 us      -1.4%\nsplit_cjk_size1000000_seg999999     284 us +- 2 us      289 us +- 2 us      -1.7%\n\nsplit_cjk_nz_size100_seg2           597 ns +- 7 ns      552 ns +- 12 ns     +8.2%\nsplit_cjk_nz_size100_seg10          197 ns +- 3 ns      196 ns +- 3 ns      ~same\nsplit_cjk_nz_size100_seg50          64.8 ns +- 1.8 ns   88.6 ns +- 17.2 ns  -26.9%\n\nsplit_cjk_nz_size1000_seg2          6.41 us +- 0.08 us  5.34 us +- 0.12 us  +20.0%\nsplit_cjk_nz_size1000_seg10         1.86 us +- 0.02 us  1.80 us +- 0.03 us  +3.3%\nsplit_cjk_nz_size1000_seg50         397 ns +- 4 ns      593 ns +- 7 ns      -33.1%\nsplit_cjk_nz_size1000_seg250        212 ns +- 9 ns      413 ns +- 11 ns     -48.7%\nsplit_cjk_nz_size1000_seg500        107 ns +- 1 ns      260 ns +- 2 ns      -58.8%\nsplit_cjk_nz_size1000_seg1000       94.0 ns +- 0.9 ns   329 ns +- 2 ns      -71.4%\n\nsplit_cjk_nz_size10000_seg2         63.9 us +- 0.7 us   51.8 us +- 0.7 us   +23.4%\nsplit_cjk_nz_size10000_seg10        18.0 us +- 0.3 us   16.7 us +- 0.3 us   +7.8%\nsplit_cjk_nz_size10000_seg50        4.15 us +- 0.08 us  6.04 us +- 0.05 us  -31.3%\nsplit_cjk_nz_size10000_seg250       2.08 us +- 0.03 us  4.84 us +- 0.03 us  -57.0%\nsplit_cjk_nz_size10000_seg500       1.32 us +- 0.03 us  3.72 us +- 0.02 us  -64.5%\nsplit_cjk_nz_size10000_seg1000      922 ns +- 9 ns      3.07 us +- 0.02 us  -70.0%\nsplit_cjk_nz_size10000_seg10000     393 ns +- 3 ns      2.80 us +- 0.02 us  -86.0%\n\nsplit_cjk_nz_size100000_seg2        697 us +- 19 us     567 us +- 14 us     +22.9%\nsplit_cjk_nz_size100000_seg10       178 us +- 2 us      168 us +- 2 us      +6.0%\nsplit_cjk_nz_size100000_seg50       40.6 us +- 0.4 us   59.2 us +- 0.7 us   -31.4%\nsplit_cjk_nz_size100000_seg250      25.2 us +- 0.2 us   52.6 us +- 0.3 us   -52.1%\nsplit_cjk_nz_size100000_seg500      16.9 us +- 0.1 us   42.0 us +- 0.9 us   -59.8%\nsplit_cjk_nz_size100000_seg1000     13.5 us +- 0.2 us   37.0 us +- 0.2 us   -63.5%\nsplit_cjk_nz_size100000_seg10000    5.35 us +- 0.06 us  26.1 us +- 0.2 us   -79.5%\nsplit_cjk_nz_size100000_seg25000    5.75 us +- 0.07 us  23.1 us +- 0.2 us   -75.1%\nsplit_cjk_nz_size100000_seg100000   3.39 us +- 0.08 us  27.6 us +- 0.4 us   -87.7%\n\nsplit_cjk_nz_size1000000_seg2       7.77 ms +- 0.18 ms  6.43 ms +- 0.14 ms  +20.8%\nsplit_cjk_nz_size1000000_seg10      2.18 ms +- 0.03 ms  2.13 ms +- 0.06 ms  +2.3%\nsplit_cjk_nz_size1000000_seg50      527 us +- 5 us      711 us +- 7 us      -25.9%\nsplit_cjk_nz_size1000000_seg250     244 us +- 2 us      521 us +- 2 us      -53.2%\nsplit_cjk_nz_size1000000_seg500     167 us +- 1 us      420 us +- 2 us      -60.2%\nsplit_cjk_nz_size1000000_seg1000    141 us +- 2 us      381 us +- 3 us      -63.0%\nsplit_cjk_nz_size1000000_seg10000   61.0 us +- 0.6 us   290 us +- 2 us      -79.0%\nsplit_cjk_nz_size1000000_seg25000   74.2 us +- 0.6 us   301 us +- 2 us      -75.3%\nsplit_cjk_nz_size1000000_seg100000  59.0 us +- 1.2 us   268 us +- 2 us      -78.0%\nsplit_cjk_nz_size1000000_seg250000  46.0 us +- 0.5 us   218 us +- 1 us      -78.9%\nsplit_cjk_nz_size1000000_seg500000  29.8 us +- 0.3 us   146 us +- 1 us      -79.6%\nsplit_cjk_nz_size1000000_seg999999  58.8 us +- 0.4 us   289 us +- 2 us      -79.7%\n\nsplit_emoji_size100_seg2            591 ns +- 13 ns     560 ns +- 6 ns      +5.5%\nsplit_emoji_size100_seg10           224 ns +- 3 ns      211 ns +- 6 ns      +6.2%\nsplit_emoji_size100_seg50           83.5 ns +- 1.1 ns   80.3 ns +- 1.3 ns   +4.0%\n\nsplit_emoji_size1000_seg2           5.98 us +- 0.11 us  5.49 us +- 0.06 us  +8.9%\nsplit_emoji_size1000_seg10          2.02 us +- 0.04 us  1.93 us +- 0.02 us  +4.7%\nsplit_emoji_size1000_seg50          649 ns +- 5 ns      647 ns +- 7 ns      ~same\nsplit_emoji_size1000_seg250         423 ns +- 3 ns      422 ns +- 3 ns      ~same\nsplit_emoji_size1000_seg500         260 ns +- 2 ns      269 ns +- 2 ns      -3.3%\nsplit_emoji_size1000_seg1000        328 ns +- 12 ns     333 ns +- 2 ns      -1.5%\n\nsplit_emoji_size10000_seg2          58.6 us +- 0.8 us   54.8 us +- 0.5 us   +6.9%\nsplit_emoji_size10000_seg10         19.4 us +- 0.2 us   18.7 us +- 0.4 us   +3.7%\nsplit_emoji_size10000_seg50         6.61 us +- 0.10 us  6.60 us +- 0.08 us  ~same\nsplit_emoji_size10000_seg250        5.00 us +- 0.05 us  5.05 us +- 0.03 us  ~same\nsplit_emoji_size10000_seg500        3.94 us +- 0.03 us  4.02 us +- 0.02 us  -2.0%\nsplit_emoji_size10000_seg1000       3.28 us +- 0.03 us  3.31 us +- 0.03 us  ~same\nsplit_emoji_size10000_seg10000      2.64 us +- 0.01 us  2.79 us +- 0.03 us  -5.4%\n\nsplit_emoji_size100000_seg2         689 us +- 6 us      642 us +- 5 us      +7.3%\nsplit_emoji_size100000_seg10        194 us +- 6 us      183 us +- 2 us      +6.0%\nsplit_emoji_size100000_seg50        64.4 us +- 0.8 us   63.8 us +- 0.5 us   ~same\nsplit_emoji_size100000_seg250       57.2 us +- 0.3 us   58.0 us +- 0.3 us   -1.4%\nsplit_emoji_size100000_seg500       49.3 us +- 0.2 us   49.9 us +- 0.4 us   -1.2%\nsplit_emoji_size100000_seg1000      41.7 us +- 0.9 us   42.0 us +- 0.5 us   ~same\nsplit_emoji_size100000_seg10000     31.9 us +- 0.2 us   32.5 us +- 0.3 us   -1.8%\nsplit_emoji_size100000_seg25000     24.1 us +- 0.2 us   24.9 us +- 0.8 us   -3.2%\nsplit_emoji_size100000_seg100000    25.7 us +- 0.1 us   27.7 us +- 0.4 us   -7.2%\n\nsplit_emoji_size1000000_seg2        7.40 ms +- 0.42 ms  7.18 ms +- 0.27 ms  +3.1%\nsplit_emoji_size1000000_seg10       2.51 ms +- 0.07 ms  2.40 ms +- 0.03 ms  +4.6%\nsplit_emoji_size1000000_seg50       916 us +- 16 us     929 us +- 36 us     -1.4%\nsplit_emoji_size1000000_seg250      566 us +- 4 us      576 us +- 4 us      -1.7%\nsplit_emoji_size1000000_seg500      495 us +- 2 us      500 us +- 4 us      ~same\nsplit_emoji_size1000000_seg1000     427 us +- 10 us     427 us +- 3 us      ~same\nsplit_emoji_size1000000_seg10000    353 us +- 4 us      362 us +- 14 us     -2.5%\nsplit_emoji_size1000000_seg25000    315 us +- 2 us      319 us +- 3 us      -1.3%\nsplit_emoji_size1000000_seg100000   287 us +- 2 us      292 us +- 2 us      -1.7%\nsplit_emoji_size1000000_seg250000   237 us +- 13 us     239 us +- 2 us      ~same\nsplit_emoji_size1000000_seg500000   155 us +- 1 us      158 us +- 1 us      -1.9%\nsplit_emoji_size1000000_seg999999   309 us +- 2 us      315 us +- 2 us      -1.9%\n```\n\n\u003c/details>\n\nI have also ensured the tests pass with my changes.\n\n```console\n$ ./python.exe -m unittest Lib/test/test_str.py -v -k split \ntest_additional_rsplit (Lib.test.test_str.StrTest.test_additional_rsplit) ... ok\ntest_additional_split (Lib.test.test_str.StrTest.test_additional_split) ... ok\ntest_rsplit (Lib.test.test_str.StrTest.test_rsplit) ... ok\ntest_split (Lib.test.test_str.StrTest.test_split) ... ok\ntest_splitlines (Lib.test.test_str.StrTest.test_splitlines) ... ok\ntest_formatter_field_name_split (Lib.test.test_str.StringModuleTest.test_formatter_field_name_split) ... ok\n\n----------------------------------------------------------------------\nRan 6 tests in 0.001s\n\nOK\n```\n\nI haven't (yet) made benchmarks for the `rsplit` case, but if that'd be useful, I can also make some (I just wanted to probe for interest / validity first). ","author":{"url":"https://github.com/KowalskiThomas","@type":"Person","name":"KowalskiThomas"},"datePublished":"2026-03-11T09:31:36Z","url":"https://github.com/python/cpython/issues/145797"}

react-profiling0
react-import-mapreact,react-dom,react-dom/client,react-dom/profiling,react-is,react/compiler-runtime,react/jsx-dev-runtime,react/jsx-runtime,scheduler@b8488ee2c322
route-pattern/_view_fragments/issues/show/:user_id/:repository/:id/issue_layout(.:format)
route-controllervoltron_issues_fragments
route-actionissue_layout
fetch-noncev2:2fd53192-a6ce-4e5b-bcd6-33b1b7a77647
current-catalog-service-hash81bb79d38c15960b92d99bca9288a9108c7a47b18f2423d0f6438c5b7bcd2114
request-idBEEC:AFBD9:17AFFBD:1F3B5AC:6B020984
html-safe-nonce30763202c4c85d470ec9b73c0d672463bb9db102a2d8332bb162e2d76dfa9a39
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJCRUVDOkFGQkQ5OjE3QUZGQkQ6MUYzQjVBQzo2QjAyMDk4NCIsInZpc2l0b3JfaWQiOiI1MTQ5MzAwMjAyMDgzMDYwMTAwIiwicmVnaW9uX2VkZ2UiOiJpYWQiLCJyZWdpb25fcmVuZGVyIjoiaWFkIn0=
visitor-hmac0b5c4e35cc0ed70c86e167ea2f7e93179c175ad60ae91266e86b339748111f66
hovercard-subject-tagissue:4057024326
github-keyboard-shortcutsrepository,issues,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location///voltron/issues_fragments/issue_layout
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/_view_fragments/issues/show/python/cpython/145797/issue_layout
twitter:imagehttps://opengraph.githubassets.com/a3304615379be1721d3dc16ec903493334a1229b84d7694347f1ce6add6dadde/python/cpython/issues/145797
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/a3304615379be1721d3dc16ec903493334a1229b84d7694347f1ce6add6dadde/python/cpython/issues/145797
og:image:altDescription I propose to use memchr (link) (and memrchr) to speed up str.split (and str.resplit). Currently, str.split (and str.rsplit) use a basic loop to iterate through the string to find delimi...
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
og:author:usernameKowalskiThomas
hostnamegithub.com
expected-hostnamegithub.com
None87e774ee7c6b3bee0490394e4d3e57ec9dbc956f74b87ea685dc8996c1676456
turbo-cache-controlno-preview
go-importgithub.com/python/cpython git https://github.com/python/cpython.git
octolytics-dimension-user_id1525981
octolytics-dimension-user_loginpython
octolytics-dimension-repository_id81598961
octolytics-dimension-repository_nwopython/cpython
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id81598961
octolytics-dimension-repository_network_root_nwopython/cpython
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release423dbb54c5e7bfecc838eb387c1435eb3d0e760d
ui-targetfull
theme-color#1e2327
color-schemelight dark
react-app-nameissues

Links:

Skip to contenthttps://github.com/python/cpython/issues/145797#start-of-content
https://github.com/
Sign inhttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fpython%2Fcpython%2Fissues%2F145797
GitHubRepository hosting, code review, and collaborationhttps://github.com/platform
CopilotAI coding agent for tasks, projects, and automated workhttps://github.com/features/copilot
ActionsCI/CD and automationhttps://github.com/features/actions
Code QualityQuality analysis, fixes, and enforcementhttps://github.com/features/code-quality
CodespacesCloud development environmentshttps://github.com/features/codespaces
Code SecurityVulnerability detection and remediationhttps://github.com/security/advanced-security/code-security
Secret ProtectionSecret scanning and leak preventionhttps://github.com/security/advanced-security/secret-protection
All Featureshttps://github.com/features
Documentationhttps://docs.github.com/en
Traininghttps://learn.github.com/skills
Certificationshttps://learn.github.com/credentials
Build with Copilothttps://github.com/features/ai
Customize Copilothttps://docs.github.com/en/copilot/how-tos/copilot-on-github/customize-copilot/customize-copilot-overview
Integrationshttps://github.com/marketplace
Trending reposhttps://github.com/trending
GitHub Sponsorshttps://github.com/open-source/sponsors
Developer articleshttps://github.com/resources/articles
ChangelogYour source for the latest features, improvements, and fixes across GitHub products, all in one place.https://github.blog/changelog/
Enterpriseshttps://github.com/enterprise
Teamhttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
See all industrieshttps://github.com/solutions/industry
Why GitHubhttps://github.com/why-github
Customer Storieshttps://github.com/customer-stories
Business insightshttps://github.com/solutions/executive-insights
Trust Centerhttps://github.com/trust-center
GitHub Advanced SecurityEnterprise-grade code securityhttps://github.com/security/advanced-security
Copilot for businessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/enterprise/premium-support
Documentationhttps://docs.github.com/en
Resource centerhttps://github.com/resources
Bloghttps://github.blog/
Events & webinarshttps://github.com/resources/events
Community Forumhttps://github.com/orgs/community/discussions
Customer Storieshttps://github.com/customer-stories
Integrationshttps://github.com/marketplace
Customer supporthttps://help.github.com/
Traininghttps://learn.github.com/skills
GitHub Statushttps://www.githubstatus.com/
Abouthttps://github.com/about
Partnershttps://github.com/partners
Changeloghttps://github.blog/changelog/
GitHub UniverseThe event for developers, by developers — talks, workshops, and what’s next for GitHub.https://githubuniverse.com/
Pricinghttps://github.com/pricing
Sign inhttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fpython%2Fcpython%2Fissues%2F145797
Sign uphttps://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E%2Fvoltron%2Fissues_fragments%2Fissue_layout&source=header-repo&source_repo=python%2Fcpython
Reloadhttps://github.com/python/cpython/issues/145797
Reloadhttps://github.com/python/cpython/issues/145797
Reloadhttps://github.com/python/cpython/issues/145797
pythonhttps://github.com/python
cpythonhttps://github.com/python/cpython
Codehttps://github.com/python/cpython
Issues5k+ (5k+)https://github.com/python/cpython/issues
Pull requests2.4k (2.4k)https://github.com/python/cpython/pulls
Actionshttps://github.com/python/cpython/actions
Projectshttps://github.com/python/cpython/projects
Security and qualityhttps://github.com/python/cpython/security
Insightshttps://github.com/python/cpython/insights
https://github.com/python/cpython
New issuehttps://github.com/login?return_to=https://github.com/python/cpython/issues/145797
New issuehttps://github.com/login?return_to=https://github.com/python/cpython/issues/145797
Use find_char/memchr to improve performance of str.splithttps://github.com/python/cpython/issues/145797#top
interpreter-core(Objects, Python, Grammar, and Parser dirs)https://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22interpreter-core%22
performancePerformance or resource usagehttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22performance%22
type-featureA feature request or enhancementhttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22type-feature%22
https://github.com/KowalskiThomas
KowalskiThomashttps://github.com/KowalskiThomas
on Mar 11, 2026https://github.com/python/cpython/issues/145797#issue-4057024326
linkhttps://en.cppreference.com/w/c/string/byte/memchr.html
f2c5484https://github.com/python/cpython/commit/f2c5484f9ee9c964454b2d4a176170042e3beea5
branch in my forkhttps://github.com/python/cpython/compare/main...KowalskiThomas:cpython:kowalski/use-memchr-for-str-split
thishttps://github.com/python/cpython/blob/cf7c67b7c6b96527dfb0da2d6305923a92e3d766/Objects/stringlib/fastsearch.h#L63-L69
sergey-miryanovhttps://github.com/sergey-miryanov
type-featureA feature request or enhancementhttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22type-feature%22
performancePerformance or resource usagehttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22performance%22
extension-modulesC modules in the Modules dirhttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22extension-modules%22
interpreter-core(Objects, Python, Grammar, and Parser dirs)https://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22interpreter-core%22
extension-modulesC modules in the Modules dirhttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22extension-modules%22
on Mar 11, 2026https://github.com/python/cpython/issues/145797#event-23464403115
https://github.com/serhiy-storchaka
serhiy-storchakahttps://github.com/serhiy-storchaka
on Mar 12, 2026https://github.com/python/cpython/issues/145797#issuecomment-4045743297
https://github.com/vstinner
vstinnerhttps://github.com/vstinner
on Mar 13, 2026https://github.com/python/cpython/issues/145797#issuecomment-4054938386
https://github.com/KowalskiThomas
KowalskiThomashttps://github.com/KowalskiThomas
on Mar 13, 2026https://github.com/python/cpython/issues/145797#issuecomment-4055705832
https://github.com/khalidsaidi
khalidsaidihttps://github.com/khalidsaidi
on Mar 14, 2026https://github.com/python/cpython/issues/145797#issuecomment-4060967207
https://github.com/picnixz
picnixzhttps://github.com/picnixz
on Mar 14, 2026https://github.com/python/cpython/issues/145797#issuecomment-4060975190
@khalidsaidihttps://github.com/khalidsaidi
https://github.com/vstinner
vstinnerhttps://github.com/vstinner
on Mar 25, 2026https://github.com/python/cpython/issues/145797#issuecomment-4128306870
https://github.com/KowalskiThomas
KowalskiThomashttps://github.com/KowalskiThomas
on Apr 3, 2026https://github.com/python/cpython/issues/145797#issuecomment-4182089853
https://github.com/Siyet
Siyethttps://github.com/Siyet
on Apr 12, 2026https://github.com/python/cpython/issues/145797#issuecomment-4231059743
KowalskiThomas:kowalski/use-memchr-for-str-splithttps://github.com/python/cpython/compare/main...KowalskiThomas:cpython:kowalski/use-memchr-for-str-split
gh-57343https://github.com/python/cpython/issues/57343
gh-69009https://github.com/python/cpython/issues/69009
gh-93033https://github.com/python/cpython/issues/93033
@serhiy-storchakahttps://github.com/serhiy-storchaka
@KowalskiThomashttps://github.com/KowalskiThomas
https://github.com/picnixz
picnixzhttps://github.com/picnixz
on Apr 12, 2026https://github.com/python/cpython/issues/145797#issuecomment-4231176836
@Siyethttps://github.com/Siyet
https://github.com/Siyet
Siyethttps://github.com/Siyet
on Apr 12, 2026https://github.com/python/cpython/issues/145797#issuecomment-4231437257
https://github.com/haampie
haampiehttps://github.com/haampie
on Apr 27, 2026https://github.com/python/cpython/issues/145797#issuecomment-4325405380
Sign up for freehttps://github.com/signup?return_to=https://github.com/python/cpython/issues/145797
Sign in to commenthttps://github.com/login?return_to=https://github.com/python/cpython/issues/145797
interpreter-core(Objects, Python, Grammar, and Parser dirs)https://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22interpreter-core%22
performancePerformance or resource usagehttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22performance%22
type-featureA feature request or enhancementhttps://github.com/python/cpython/issues?q=state%3Aopen%20label%3A%22type-feature%22
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width


URLs of crawlers that visited me.