Thanks to visit codestin.com
Credit goes to Github.com

Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: gorilla/websocket
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: main
Choose a base ref
...
head repository: RomiChan/websocket
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: master
Choose a head ref
Checking mergeability… Don’t worry, you can still create the pull request.
  • 16 commits
  • 27 files changed
  • 2 contributors

Commits on Jan 12, 2022

  1. mask: speed up for amd64 with sse&avx2 

    for sse benchmark:
name                                old time/op    new time/op    delta
MaskBytes/size-32/align-0/mask-8      11.1ns ± 1%    11.8ns ± 4%   +6.77%  (p=0.008 n=5+5)
MaskBytes/size-32/align-4/mask-8      10.6ns ± 4%    11.3ns ± 0%   +6.39%  (p=0.008 n=5+5)
MaskBytes/size-512/align-0/mask-8     26.4ns ± 1%    21.1ns ± 1%  -19.92%  (p=0.008 n=5+5)
MaskBytes/size-512/align-4/mask-8     26.3ns ± 1%    21.3ns ± 1%  -19.05%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-0/mask-8    42.7ns ± 0%    29.4ns ± 1%  -31.20%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-4/mask-8    44.0ns ± 0%    30.6ns ± 1%  -30.39%  (p=0.008 n=5+5)
MaskBytes/size-4096/align-0/mask-8     142ns ± 1%      79ns ± 1%  -44.45%  (p=0.016 n=4+5)
MaskBytes/size-4096/align-4/mask-8     162ns ± 0%     100ns ± 0%  -37.95%  (p=0.008 n=5+5)

name                                old speed      new speed      delta
MaskBytes/size-32/align-0/mask-8    2.90GB/s ± 1%  2.71GB/s ± 4%   -6.28%  (p=0.008 n=5+5)
MaskBytes/size-32/align-4/mask-8    3.01GB/s ± 4%  2.83GB/s ± 0%   -6.11%  (p=0.008 n=5+5)
MaskBytes/size-512/align-0/mask-8   19.4GB/s ± 1%  24.3GB/s ± 1%  +24.89%  (p=0.008 n=5+5)
MaskBytes/size-512/align-4/mask-8   19.5GB/s ± 1%  24.1GB/s ± 1%  +23.53%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-0/mask-8  24.0GB/s ± 0%  34.9GB/s ± 1%  +45.36%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-4/mask-8  23.3GB/s ± 0%  33.5GB/s ± 1%  +43.67%  (p=0.008 n=5+5)
MaskBytes/size-4096/align-0/mask-8  28.9GB/s ± 1%  51.9GB/s ± 1%  +80.02%  (p=0.016 n=4+5)
MaskBytes/size-4096/align-4/mask-8  25.3GB/s ± 0%  40.8GB/s ± 0%  +61.14%  (p=0.008 n=5+5)

for avx2 benchmark:
name                                old time/op    new time/op    delta
MaskBytes/size-32/align-0/mask-8      11.1ns ± 1%    11.7ns ± 5%    +5.68%  (p=0.008 n=5+5)
MaskBytes/size-32/align-4/mask-8      10.6ns ± 4%    11.3ns ± 0%    +6.60%  (p=0.008 n=5+5)
MaskBytes/size-512/align-0/mask-8     26.4ns ± 1%    18.4ns ± 0%   -30.05%  (p=0.008 n=5+5)
MaskBytes/size-512/align-4/mask-8     26.3ns ± 1%    18.9ns ± 4%   -28.21%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-0/mask-8    42.7ns ± 0%    22.7ns ± 1%   -46.70%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-4/mask-8    44.0ns ± 0%    24.9ns ± 9%   -43.44%  (p=0.008 n=5+5)
MaskBytes/size-4096/align-0/mask-8     142ns ± 1%      53ns ± 2%   -62.86%  (p=0.016 n=4+5)
MaskBytes/size-4096/align-4/mask-8     162ns ± 0%      68ns ± 1%   -57.64%  (p=0.008 n=5+5)

name                                old speed      new speed      delta
MaskBytes/size-32/align-0/mask-8    2.90GB/s ± 1%  2.74GB/s ± 5%    -5.25%  (p=0.008 n=5+5)
MaskBytes/size-32/align-4/mask-8    3.01GB/s ± 4%  2.82GB/s ± 0%    -6.30%  (p=0.008 n=5+5)
MaskBytes/size-512/align-0/mask-8   19.4GB/s ± 1%  27.8GB/s ± 0%   +42.97%  (p=0.008 n=5+5)
MaskBytes/size-512/align-4/mask-8   19.5GB/s ± 1%  27.2GB/s ± 4%   +39.38%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-0/mask-8  24.0GB/s ± 0%  45.0GB/s ± 1%   +87.65%  (p=0.008 n=5+5)
MaskBytes/size-1024/align-4/mask-8  23.3GB/s ± 0%  41.3GB/s ± 9%   +77.15%  (p=0.008 n=5+5)
MaskBytes/size-4096/align-0/mask-8  28.9GB/s ± 1%  77.7GB/s ± 2%  +169.23%  (p=0.016 n=4+5)
MaskBytes/size-4096/align-4/mask-8  25.3GB/s ± 0%  59.8GB/s ± 1%  +136.08%  (p=0.008 n=5+5)
    @wdvxdr1123
    wdvxdr1123 committed Jan 12, 2022
    Configuration menu
    Copy the full SHA
    2fc8487 View commit details
    Browse the repository at this point in the history

  2. style: run asmfmt -w mask_amd64.s

    @wdvxdr1123
    wdvxdr1123 committed Jan 12, 2022
    Configuration menu
    Copy the full SHA
    0fb50fc View commit details
    Browse the repository at this point in the history

  3. mask: impl avx512 masking

    @wdvxdr1123
    wdvxdr1123 committed Jan 12, 2022
    Configuration menu
    Copy the full SHA
    cda681e View commit details
    Browse the repository at this point in the history

Commits on Jan 22, 2022

  1. mask: use arm8 neon speed up mask

    @wdvxdr1123
    wdvxdr1123 committed Jan 22, 2022
    Configuration menu
    Copy the full SHA
    2ec9cbb View commit details
    Browse the repository at this point in the history

Commits on Jan 23, 2022

  1. perf: optimize unaligned mask

    @wdvxdr1123
    wdvxdr1123 committed Jan 23, 2022
    Configuration menu
    Copy the full SHA
    4995d1f View commit details
    Browse the repository at this point in the history

  2. ci: add test ci

    @wdvxdr1123
    wdvxdr1123 committed Jan 23, 2022
    Configuration menu
    Copy the full SHA
    cb552c5 View commit details
    Browse the repository at this point in the history

  3. ci: fix ci

    @wdvxdr1123
    wdvxdr1123 committed Jan 23, 2022
    Configuration menu
    Copy the full SHA
    0134de4 View commit details
    Browse the repository at this point in the history

  4. ci: fix go mod

    @wdvxdr1123
    wdvxdr1123 committed Jan 23, 2022
    Configuration menu
    Copy the full SHA
    adfe507 View commit details
    Browse the repository at this point in the history

  5. fix arm64 mask

    @wdvxdr1123
    wdvxdr1123 committed Jan 23, 2022
    Configuration menu
    Copy the full SHA
    6e64c2a View commit details
    Browse the repository at this point in the history

  6. fix: fix generic mask

    @wdvxdr1123
    wdvxdr1123 committed Jan 23, 2022
    Configuration menu
    Copy the full SHA
    307a86b View commit details
    Browse the repository at this point in the history

Commits on Feb 27, 2022

  1. bump to go1.17

    @wdvxdr1123
    wdvxdr1123 committed Feb 27, 2022
    Configuration menu
    Copy the full SHA
    9b2c616 View commit details
    Browse the repository at this point in the history

Commits on Oct 2, 2025

  1. Merge branch 'main' of https://github.com/gorilla/websocket

    @fumiama
    fumiama committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    bf5b151 View commit details
    Browse the repository at this point in the history

  2. optimize: cache some byte IOs

    @fumiama
    fumiama committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    67e2604 View commit details
    Browse the repository at this point in the history

  3. optimize: use pbuf as write buffer pool

    @fumiama
    fumiama committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    1a88b05 View commit details
    Browse the repository at this point in the history

  4. feat(test): add multiple platforms

    @fumiama
    fumiama committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    0299fcc View commit details
    Browse the repository at this point in the history

  5. chore: make lint happy

    @fumiama
    fumiama committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    d3eb417 View commit details
    Browse the repository at this point in the history
Loading