]> Cypherpunks repositories - gostls13.git/commit
internal/bytealg: optimize Index/IndexString on loong64
authorlimeidan <limeidan@loongson.cn>
Thu, 7 Aug 2025 03:34:28 +0000 (11:34 +0800)
committerabner chenc <chenguoqi@loongson.cn>
Fri, 8 Aug 2025 03:32:55 +0000 (20:32 -0700)
commitdd3abf6bc5203df3c8a09ff151852fa8b9e7f2f4
treebee6985c31774b360948b09a528c00d1d76720e4
parent73ff6d148038da77dd05b3dca3f0767db000a0f7
internal/bytealg: optimize Index/IndexString on loong64

goos: linux
goarch: loong64
pkg: bytes
cpu: Loongson-3A6000 @ 2500.00MHz
                              | 3a6000.old.txt |           3a6000.new.txt            |
                              |     sec/op     |   sec/op     vs base                |
IndexRune/10                      23.56n ±  1%   20.42n ± 0%  -13.33% (p=0.000 n=10)
IndexRune/32                      29.91n ±  1%   22.46n ± 0%  -24.90% (p=0.000 n=10)
IndexRune/4K                     102.45n ±  2%   72.66n ± 0%  -29.08% (p=0.000 n=10)
IndexRune/4M                     111.96µ ±  1%   52.50µ ± 1%  -53.11% (p=0.000 n=10)
IndexRune/64M                     3.653m ± 30%   3.633m ± 0%        ~ (p=0.143 n=10)
IndexRuneASCII/10                 8.736n ±  2%   7.206n ± 0%  -17.51% (p=0.000 n=10)
IndexRuneASCII/32                10.195n ±  2%   8.008n ± 0%  -21.45% (p=0.000 n=10)
IndexRuneASCII/4K                 70.27n ±  2%   52.84n ± 0%  -24.80% (p=0.000 n=10)
IndexRuneASCII/4M                 98.15µ ±  1%   87.87µ ± 1%  -10.47% (p=0.000 n=10)
IndexRuneASCII/64M                2.028m ±  0%   1.918m ± 2%   -5.41% (p=0.000 n=10)
IndexRuneUnicode/Latin/10         18.80n ±  1%   13.61n ± 0%  -27.59% (p=0.000 n=10)
IndexRuneUnicode/Latin/32         28.09n ±  2%   20.82n ± 0%  -25.88% (p=0.000 n=10)
IndexRuneUnicode/Latin/4K         373.8n ±  1%   357.1n ± 0%   -4.47% (p=0.000 n=10)
IndexRuneUnicode/Latin/4M         395.8µ ±  0%   381.0µ ± 0%   -3.74% (p=0.000 n=10)
IndexRuneUnicode/Latin/64M        8.056m ±  0%   7.614m ± 0%   -5.49% (p=0.000 n=10)
IndexRuneUnicode/Cyrillic/10      23.72n ±  1%   20.42n ± 0%  -13.91% (p=0.000 n=10)
IndexRuneUnicode/Cyrillic/32      30.20n ±  1%   22.42n ± 0%  -25.77% (p=0.000 n=10)
IndexRuneUnicode/Cyrillic/4K      1.134µ ±  1%   1.122µ ± 0%   -1.06% (p=0.000 n=10)
IndexRuneUnicode/Cyrillic/4M      1.160m ±  1%   1.152m ± 0%   -0.72% (p=0.005 n=10)
IndexRuneUnicode/Cyrillic/64M     20.26m ±  1%   19.61m ± 0%   -3.24% (p=0.000 n=10)
IndexRuneUnicode/Han/10           30.11n ±  2%   24.82n ± 0%  -17.57% (p=0.000 n=10)
IndexRuneUnicode/Han/32           36.16n ±  2%   27.20n ± 0%  -24.78% (p=0.000 n=10)
IndexRuneUnicode/Han/4K           548.1n ±  0%   524.8n ± 0%   -4.25% (p=0.000 n=10)
IndexRuneUnicode/Han/4M           706.7µ ±  1%   624.0µ ± 0%  -11.70% (p=0.000 n=10)
IndexRuneUnicode/Han/64M          12.50m ±  1%   10.84m ± 1%  -13.24% (p=0.000 n=10)
Index/10                          42.03n ±  2%   10.01n ± 0%  -76.18% (p=0.000 n=10)
Index/32                         133.15n ±  1%   40.03n ± 0%  -69.94% (p=0.000 n=10)
Index/4K                         11.647µ ±  1%   2.493µ ± 0%  -78.60% (p=0.000 n=10)
Index/4M                         11.536m ±  0%   2.519m ± 0%  -78.16% (p=0.000 n=10)
Index/64M                        184.60m ±  1%   40.42m ± 0%  -78.10% (p=0.000 n=10)
IndexEasy/10                     17.290n ±  2%   9.608n ± 0%  -44.43% (p=0.000 n=10)
IndexEasy/32                      23.71n ±  2%   16.61n ± 0%  -29.95% (p=0.000 n=10)
IndexEasy/4K                      95.64n ±  2%   68.25n ± 0%  -28.64% (p=0.000 n=10)
IndexEasy/4M                     105.04µ ±  1%   91.94µ ± 0%  -12.47% (p=0.000 n=10)
IndexEasy/64M                     4.280m ±  0%   4.264m ± 0%   -0.38% (p=0.002 n=10)
Count/10                          53.09n ±  1%   16.81n ± 0%  -68.33% (p=0.000 n=10)
Count/32                         142.20n ±  2%   46.44n ± 0%  -67.34% (p=0.000 n=10)
Count/4K                         11.428µ ±  1%   2.500µ ± 1%  -78.12% (p=0.000 n=10)
Count/4M                         11.536m ±  1%   2.520m ± 0%  -78.16% (p=0.000 n=10)
Count/64M                        183.80m ±  1%   40.42m ± 0%  -78.01% (p=0.000 n=10)
IndexHard1                       2906.4µ ±  1%   420.4µ ± 0%  -85.54% (p=0.000 n=10)
IndexHard2                       2918.0µ ±  1%   421.1µ ± 1%  -85.57% (p=0.000 n=10)
IndexHard3                       2912.8µ ±  1%   440.2µ ± 0%  -84.89% (p=0.000 n=10)
IndexHard4                       2909.6µ ±  1%   840.4µ ± 0%  -71.12% (p=0.000 n=10)
LastIndexHard1                    2.939m ±  1%   2.621m ± 0%  -10.83% (p=0.000 n=10)
LastIndexHard2                    2.924m ±  1%   2.624m ± 0%  -10.26% (p=0.000 n=10)
LastIndexHard3                    2.936m ±  1%   2.580m ± 1%  -12.12% (p=0.000 n=10)
CountHard1                       2900.4µ ±  1%   420.0µ ± 0%  -85.52% (p=0.000 n=10)
CountHard2                       2915.6µ ±  1%   420.0µ ± 0%  -85.59% (p=0.000 n=10)
CountHard3                       2905.0µ ±  0%   440.0µ ± 0%  -84.85% (p=0.000 n=10)
IndexPeriodic/IndexPeriodic2     181.95µ ±  1%   26.28µ ± 0%  -85.56% (p=0.000 n=10)
IndexPeriodic/IndexPeriodic4     182.59µ ±  1%   26.29µ ± 0%  -85.60% (p=0.000 n=10)
IndexPeriodic/IndexPeriodic8      183.9µ ±  1%   108.2µ ± 0%  -41.14% (p=0.000 n=10)
IndexPeriodic/IndexPeriodic16     58.24µ ±  0%   56.58µ ± 0%   -2.86% (p=0.000 n=10)
IndexPeriodic/IndexPeriodic32     30.82µ ±  0%   29.62µ ± 0%   -3.92% (p=0.000 n=10)
IndexPeriodic/IndexPeriodic64     16.59µ ±  0%   15.00µ ± 0%   -9.62% (p=0.000 n=10)
geomean                           22.69µ         11.59µ       -48.92%

Change-Id: Iacc9e686027f99bb0413b566cfc8ee6cd873d2d9
Reviewed-on: https://go-review.googlesource.com/c/go/+/693878
Reviewed-by: abner chenc <chenguoqi@loongson.cn>
Reviewed-by: Dmitri Shuralyov <dmitshur@google.com>
Reviewed-by: Mark Freeman <markfreeman@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
src/internal/bytealg/index_generic.go
src/internal/bytealg/index_loong64.go [new file with mode: 0644]
src/internal/bytealg/index_loong64.s [new file with mode: 0644]
src/internal/bytealg/index_native.go