The VIA model of high-performance by simplifying protocol stacks and reducing kernel-copy overheads, can be also used to avoid bottlenecks caused by the communication overheads in Parallel clustering system.
Message (bytes) | VIA-based BSPLib | BSPLib | ||
bsp_get() | bsp_send() | bsp_get() | bsp_send() | |
1k | 387 | 359 | 685 | 762 |
2k | 506 | 476 | 825 | 903 |
4k | 683 | 667 | 1033 | 1082 |
8k | 1055 | 1108 | 1421 | 1377 |
16k | 1776 | 1815 | 2224 | 2129 |
32k | 3245 | 3231 | 3885 | 3716 |
The above table presents a comparison of time delay(us) of VIA-based and UDP/IP based BSPLib. VIA-based BSPLib shows the obvious better performance than the performance of UDP/IP based.
No comments:
Post a Comment