FAQ
1. I noticed it while testing xxhash-go package, all the c files are
included in the repo.
For some reason the linux is performing 2 times faster than the windows
build, the only difference is that linux is running with gcc 4.7.2 and
windows with 4.7.0.
maybe its the reason but I would like to somebody to test it if he can.

go version devel +7778f3df0d19 Sun Mar 10 12:50:44 2013 -0400 linux/amd64
2. go test bitbucket.org/StephaneBunel/xxhash-go -bench=".*"
3.
4. ...
5. Benchmark_xxhash32 50000000 57.4 ns/op
6. Benchmark_CRC32IEEE 10000000 162 ns/op
7. Benchmark_Adler32 50000000 48.7 ns/op
8. Benchmark_Fnv32 20000000 128 ns/op
9. Benchmark_MurmurHash3Hash32 1000000 1953 ns/op
10.
11. go version devel +7778f3df0d19 Sun Mar 10 12:50:44 2013 -0400
windows/amd64
12. go test bitbucket.org/StephaneBunel/xxhash-go -bench=".*"
13.
14. ...
15. Benchmark_xxhash32 20000000 110 ns/op
16. Benchmark_CRC32IEEE 10000000 161 ns/op
17. Benchmark_Adler32 50000000 54.1 ns/op
18. Benchmark_Fnv32 20000000 130 ns/op
19. Benchmark_MurmurHash3Hash32 1000000 1954 ns/op

pprof results (I used 1.0.3 because for some reason I couldn't get
samples with go tip, the results are the same in 1.0.3 386).
the results are not that good though:

linux 1.0.3 386
718 29.2% 29.2% 718 29.2% XXH32
617 25.1% 54.3% 617 25.1% runtime.xadd
305 12.4% 66.7% 716 29.1% runtime.entersyscall
245 10.0% 76.7% 1449 58.9% runtime.cgocall
135 5.5% 82.1% 434 17.6% runtime.exitsyscall
100 4.1% 86.2% 106 4.3% runtime.asmcgocall
78 3.2% 89.4% 1561 63.5%
bitbucket.org/StephaneBunel/xxhash-go_test.Benchmark_xxhash32
65 2.6% 92.0% 1512 61.5%
bitbucket.org/StephaneBunel/xxhash-go.Checksum32
50 2.0% 94.1% 1461 59.4%
bitbucket.org/StephaneBunel/xxhash-go._Cfunc_XXH32
50 2.0% 96.1% 50 2.0% runtime.setprof

windows 1.0.3 386
431 34.9% 34.9% 927 75.0% runtime.cgocall
317 25.6% 60.5% 382 30.9% runtime.entersyscall
107 8.7% 69.2% 974 78.8%
bitbucket.org/StephaneBunel/xxhash-go.Checksum32
103 8.3% 77.5% 1031 83.4%
bitbucket.org/StephaneBunel/xxhash-go_test.Benchmark_xxhash32
98 7.9% 85.4% 953 77.1%
bitbucket.org/StephaneBunel/xxhash-go._Cfunc_XXH32
56 4.5% 90.0% 56 4.5% runtime.gosave
48 3.9% 93.9% 75 6.1% runtime.exitsyscall
40 3.2% 97.1% 40 3.2% unlockm
36 2.9% 100.0% 36 2.9% runtime.setprof
0 0.0% 100.0% 1031 83.4%
bitbucket.org/StephaneBunel/xxhash-go_test.Test_Reset


--
You received this message because you are subscribed to the Google Groups "golang-nuts" group.
To unsubscribe from this group and stop receiving emails from it, send an email to golang-nuts+unsubscribe@googlegroups.com.
For more options, visit https://groups.google.com/groups/opt_out.

Search Discussions

  • Vova Niki at Mar 10, 2013 at 8:40 pm
    I'm talking about Benchmark_xxhash32 function.
    On Sunday, March 10, 2013 10:38:09 PM UTC+2, Vova Niki wrote:


    1. I noticed it while testing xxhash-go package, all the c files are
    included in the repo.
    For some reason the linux is performing 2 times faster than the
    windows build, the only difference is that linux is running with gcc 4.7.2
    and windows with 4.7.0.
    maybe its the reason but I would like to somebody to test it if he can.

    go version devel +7778f3df0d19 Sun Mar 10 12:50:44 2013 -0400
    linux/amd64
    2. go test bitbucket.org/StephaneBunel/xxhash-go -bench=".*"
    3.
    4. ...
    5. Benchmark_xxhash32 50000000 57.4 ns/op
    6. Benchmark_CRC32IEEE 10000000 162 ns/op
    7. Benchmark_Adler32 50000000 48.7 ns/op
    8. Benchmark_Fnv32 20000000 128 ns/op
    9. Benchmark_MurmurHash3Hash32 1000000 1953 ns/op
    10.
    11. go version devel +7778f3df0d19 Sun Mar 10 12:50:44 2013 -0400
    windows/amd64
    12. go test bitbucket.org/StephaneBunel/xxhash-go -bench=".*"
    13.
    14. ...
    15. Benchmark_xxhash32 20000000 110 ns/op
    16. Benchmark_CRC32IEEE 10000000 161 ns/op
    17. Benchmark_Adler32 50000000 54.1 ns/op
    18. Benchmark_Fnv32 20000000 130 ns/op
    19. Benchmark_MurmurHash3Hash32 1000000 1954 ns/op

    pprof results (I used 1.0.3 because for some reason I couldn't get
    samples with go tip, the results are the same in 1.0.3 386).
    the results are not that good though:

    linux 1.0.3 386
    718 29.2% 29.2% 718 29.2% XXH32
    617 25.1% 54.3% 617 25.1% runtime.xadd
    305 12.4% 66.7% 716 29.1% runtime.entersyscall
    245 10.0% 76.7% 1449 58.9% runtime.cgocall
    135 5.5% 82.1% 434 17.6% runtime.exitsyscall
    100 4.1% 86.2% 106 4.3% runtime.asmcgocall
    78 3.2% 89.4% 1561 63.5%
    bitbucket.org/StephaneBunel/xxhash-go_test.Benchmark_xxhash32
    65 2.6% 92.0% 1512 61.5%
    bitbucket.org/StephaneBunel/xxhash-go.Checksum32
    50 2.0% 94.1% 1461 59.4%
    bitbucket.org/StephaneBunel/xxhash-go._Cfunc_XXH32
    50 2.0% 96.1% 50 2.0% runtime.setprof

    windows 1.0.3 386
    431 34.9% 34.9% 927 75.0% runtime.cgocall
    317 25.6% 60.5% 382 30.9% runtime.entersyscall
    107 8.7% 69.2% 974 78.8%
    bitbucket.org/StephaneBunel/xxhash-go.Checksum32
    103 8.3% 77.5% 1031 83.4%
    bitbucket.org/StephaneBunel/xxhash-go_test.Benchmark_xxhash32
    98 7.9% 85.4% 953 77.1%
    bitbucket.org/StephaneBunel/xxhash-go._Cfunc_XXH32
    56 4.5% 90.0% 56 4.5% runtime.gosave
    48 3.9% 93.9% 75 6.1% runtime.exitsyscall
    40 3.2% 97.1% 40 3.2% unlockm
    36 2.9% 100.0% 36 2.9% runtime.setprof
    0 0.0% 100.0% 1031 83.4%
    bitbucket.org/StephaneBunel/xxhash-go_test.Test_Reset
    --
    You received this message because you are subscribed to the Google Groups "golang-nuts" group.
    To unsubscribe from this group and stop receiving emails from it, send an email to golang-nuts+unsubscribe@googlegroups.com.
    For more options, visit https://groups.google.com/groups/opt_out.
  • peterGo at Mar 11, 2013 at 12:27 am
    http://bitbucket.org/StephaneBunel/xxhash-go

    i5-2435M @ 2.40GHz x 4

    go version devel +969045163653 Sun Mar 10 18:19:53 2013 -0400 linux/amd64

    gcc (Ubuntu/Linaro 4.7.2-2ubuntu1) 4.7.2

    Benchmark_xxhash32 10000000 282 ns/op
    Benchmark_goxxhash32 10000000 285 ns/op
    Benchmark_CRC32IEEE 2000000 796 ns/op
    Benchmark_Adler32 10000000 246 ns/op
    Benchmark_Fnv32 5000000 590 ns/op
    Benchmark_MurmurHash3Hash32 200000 9891 ns/op

    go version devel +969045163653 Sun Mar 10 18:19:53 2013 -0400 windows/amd64

    gcc (tdm64-1) 4.7.1

    Benchmark_xxhash32 5000000 505 ns/op
    Benchmark_goxxhash32 10000000 288 ns/op
    Benchmark_CRC32IEEE 2000000 800 ns/op
    Benchmark_Adler32 10000000 257 ns/op
    Benchmark_Fnv32 5000000 590 ns/op
    Benchmark_MurmurHash3Hash32 200000 10060 ns/op

    Peter
    On Sunday, March 10, 2013 4:38:09 PM UTC-4, Vova Niki wrote:


    1. I noticed it while testing xxhash-go package, all the c files are
    included in the repo.
    For some reason the linux is performing 2 times faster than the
    windows build, the only difference is that linux is running with gcc 4.7.2
    and windows with 4.7.0.
    maybe its the reason but I would like to somebody to test it if he can.

    go version devel +7778f3df0d19 Sun Mar 10 12:50:44 2013 -0400
    linux/amd64
    2. go test bitbucket.org/StephaneBunel/xxhash-go -bench=".*"
    3.
    4. ...
    5. Benchmark_xxhash32 50000000 57.4 ns/op
    6. Benchmark_CRC32IEEE 10000000 162 ns/op
    7. Benchmark_Adler32 50000000 48.7 ns/op
    8. Benchmark_Fnv32 20000000 128 ns/op
    9. Benchmark_MurmurHash3Hash32 1000000 1953 ns/op
    10.
    11. go version devel +7778f3df0d19 Sun Mar 10 12:50:44 2013 -0400
    windows/amd64
    12. go test bitbucket.org/StephaneBunel/xxhash-go -bench=".*"
    13.
    14. ...
    15. Benchmark_xxhash32 20000000 110 ns/op
    16. Benchmark_CRC32IEEE 10000000 161 ns/op
    17. Benchmark_Adler32 50000000 54.1 ns/op
    18. Benchmark_Fnv32 20000000 130 ns/op
    19. Benchmark_MurmurHash3Hash32 1000000 1954 ns/op

    pprof results (I used 1.0.3 because for some reason I couldn't get
    samples with go tip, the results are the same in 1.0.3 386).
    the results are not that good though:

    linux 1.0.3 386
    718 29.2% 29.2% 718 29.2% XXH32
    617 25.1% 54.3% 617 25.1% runtime.xadd
    305 12.4% 66.7% 716 29.1% runtime.entersyscall
    245 10.0% 76.7% 1449 58.9% runtime.cgocall
    135 5.5% 82.1% 434 17.6% runtime.exitsyscall
    100 4.1% 86.2% 106 4.3% runtime.asmcgocall
    78 3.2% 89.4% 1561 63.5%
    bitbucket.org/StephaneBunel/xxhash-go_test.Benchmark_xxhash32
    65 2.6% 92.0% 1512 61.5%
    bitbucket.org/StephaneBunel/xxhash-go.Checksum32
    50 2.0% 94.1% 1461 59.4%
    bitbucket.org/StephaneBunel/xxhash-go._Cfunc_XXH32
    50 2.0% 96.1% 50 2.0% runtime.setprof

    windows 1.0.3 386
    431 34.9% 34.9% 927 75.0% runtime.cgocall
    317 25.6% 60.5% 382 30.9% runtime.entersyscall
    107 8.7% 69.2% 974 78.8%
    bitbucket.org/StephaneBunel/xxhash-go.Checksum32
    103 8.3% 77.5% 1031 83.4%
    bitbucket.org/StephaneBunel/xxhash-go_test.Benchmark_xxhash32
    98 7.9% 85.4% 953 77.1%
    bitbucket.org/StephaneBunel/xxhash-go._Cfunc_XXH32
    56 4.5% 90.0% 56 4.5% runtime.gosave
    48 3.9% 93.9% 75 6.1% runtime.exitsyscall
    40 3.2% 97.1% 40 3.2% unlockm
    36 2.9% 100.0% 36 2.9% runtime.setprof
    0 0.0% 100.0% 1031 83.4%
    bitbucket.org/StephaneBunel/xxhash-go_test.Test_Reset
    --
    You received this message because you are subscribed to the Google Groups "golang-nuts" group.
    To unsubscribe from this group and stop receiving emails from it, send an email to golang-nuts+unsubscribe@googlegroups.com.
    For more options, visit https://groups.google.com/groups/opt_out.

Related Discussions

Discussion Navigation
viewthread | post
Discussion Overview
groupgolang-nuts @
categoriesgo
postedMar 10, '13 at 8:38p
activeMar 11, '13 at 12:27a
posts3
users2
websitegolang.org

2 users in discussion

Vova Niki: 2 posts peterGo: 1 post

People

Translate

site design / logo © 2022 Grokbase