You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2020/02/17 06:20:35 UTC
[GitHub] [spark] yma11 commented on issue #27546: [SPARK-30773][ML]Support
NativeBlas for level-1 routines
yma11 commented on issue #27546: [SPARK-30773][ML]Support NativeBlas for level-1 routines
URL: https://github.com/apache/spark/pull/27546#issuecomment-586835613
Hi @srowen and @mengxr ,
With MKL_NUM_THREADS/OPENBLAS_NUM_THREADS set 1, I have tested 10-element, 100-element, 1000-element vectors. Within 10-element vector, nativeBLAS has big gap compared with java implementation, which is quite easy to understand. But when elements number increases from 10 to 100, the performance gap drops dramatically and when the vectors have 1000 elements, nativeBLAS has quite big advantage against f2jBLAS in some dense vector operations. Please see details in the attached excel.
[Level1-routines-perf - part-2.xlsx](https://github.com/apache/spark/files/4212090/Level1-routines-perf.-.part-2.xlsx)
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org