Skip to content

Conversation

@sunyuechi
Copy link
Contributor

@sunyuechi sunyuechi commented Apr 6, 2025

banana_f3:
    rvv:
        gf_vect_mul_warm: runtime =    3062541 usecs, bandwidth 1889 MB in 3.0625 sec = 616.84 MB/s
        gf_vect_dot_prod_warm: runtime =    3062964 usecs, bandwidth 490 MB in 3.0630 sec = 160.25 MB/s
        erasure_code_encode_warm: runtime =    3065696 usecs, bandwidth 108 MB in 3.0657 sec = 35.37 MB/s
        erasure_code_decode_warm: runtime =    3001213 usecs, bandwidth 136 MB in 3.0012 sec = 45.47 MB/s
    c:
        gf_vect_mul_warm: runtime =    3062014 usecs, bandwidth 285 MB in 3.0620 sec = 93.29 MB/s
        gf_vect_dot_prod_warm: runtime =    3000581 usecs, bandwidth 173 MB in 3.0006 sec = 57.69 MB/s
        erasure_code_encode_warm: runtime =    3002512 usecs, bandwidth 52 MB in 3.0025 sec = 17.34 MB/s
        erasure_code_decode_warm: runtime =    3065235 usecs, bandwidth 57 MB in 3.0652 sec = 18.69 MB/s

@sunyuechi sunyuechi force-pushed the ec branch 2 times, most recently from 3c1f117 to 189e2c5 Compare April 23, 2025 21:20
@sunyuechi
Copy link
Contributor Author

Due to the master branch update, xx_multibinary_riscv64_dispatcher.c has also been updated.

@pablodelara pablodelara reopened this Apr 24, 2025
@pablodelara
Copy link
Contributor

@sunyuechi could you rebase this PR, so we trigger the latest CI? Thanks!

@sunyuechi
Copy link
Contributor Author

Okay, rebased.

@pablodelara
Copy link
Contributor

Looks like there is some undefined reference error shown in the tests. Can you check?

@sunyuechi
Copy link
Contributor Author

Okay, fixed.

@sunyuechi
Copy link
Contributor Author

It looks like the error came from github-act-runner, not isa-l. It has now stopped running. Could you send the token again so I can restart it and try?

@sunyuechi
Copy link
Contributor Author

sunyuechi commented Apr 27, 2025

The RISC-V tests here passed, but the machine crashed when it was idle, and the cause is currently unclear.

Since sending tokens frequently is troublesome, I would like to first run the tests on my fork for a few days. If everything goes well, I will request a new token.

Hmm... the tests are running normally again. It seems I misunderstood earlier — in this case, there's no need to resend the token, so there's no issue.

Signed-off-by: sunyuechi <sunyuechi@iscas.ac.cn>
@sunyuechi sunyuechi changed the title erasure_code: R-V V gf_vect_mul erasure_code: R-V V Apr 27, 2025
banana_f3:
    rvv: gf_vect_mul_warm: runtime =    3062541 usecs, bandwidth 1889 MB in 3.0625 sec = 616.84 MB/s
    c:   gf_vect_mul_warm: runtime =    3062014 usecs, bandwidth 285 MB in 3.0620 sec = 93.29 MB/s

Signed-off-by: sunyuechi <sunyuechi@iscas.ac.cn>
Signed-off-by: sunyuechi <sunyuechi@iscas.ac.cn>
banana_f3:
    rvv: gf_vect_dot_prod_warm: runtime =    3062964 usecs, bandwidth 490 MB in 3.0630 sec = 160.25 MB/s
    c:   gf_vect_dot_prod_warm: runtime =    3000581 usecs, bandwidth 173 MB in 3.0006 sec = 57.69 MB/s

Signed-off-by: sunyuechi <sunyuechi@iscas.ac.cn>
banana_f3:
    rvv:
        erasure_code_encode_warm: runtime =    3065696 usecs, bandwidth 108 MB in 3.0657 sec = 35.37 MB/s
        erasure_code_decode_warm: runtime =    3001213 usecs, bandwidth 136 MB in 3.0012 sec = 45.47 MB/s
    c:
        erasure_code_encode_warm: runtime =    3002512 usecs, bandwidth 52 MB in 3.0025 sec = 17.34 MB/s
        erasure_code_decode_warm: runtime =    3065235 usecs, bandwidth 57 MB in 3.0652 sec = 18.69 MB/s

Signed-off-by: sunyuechi <sunyuechi@iscas.ac.cn>
@pablodelara
Copy link
Contributor

This PR is merged, thanks!

@pablodelara pablodelara closed this May 2, 2025
@sunyuechi sunyuechi deleted the ec branch September 12, 2025 06:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants