24小时热门版块排行榜    

CyRhmU.jpeg
查看: 172  |  回复: 0
当前主题已经存档。
【有奖交流】积极回复本帖子,参与交流,就有机会分得作者 hadone 的 2 个金币

hadone

银虫 (小有名气)

[交流] 【求助】关于torque任务CPU调用的问题。

我用torque调用4个节点的cpu。每个核心cpu是这样排列的。
Numbers of Processors:  16
---------------------------
started mpd Number: 4
---------------------------
[0] MPI startup(): shared memory and socket data transfer modes
[1] MPI startup(): shared memory and socket data transfer modes
[2] MPI startup(): shared memory and socket data transfer modes
[0] MPI Startup(): process is pinned to CPU00 on node compute-0-4.local
[2] MPI Startup(): process is pinned to CPU00 on node compute-0-2.local
[1] MPI Startup(): process is pinned to CPU00 on node compute-0-1.local
[3] MPI startup(): shared memory and socket data transfer modes
[4] MPI startup(): shared memory and socket data transfer modes
[3] MPI Startup(): process is pinned to CPU00 on node compute-0-3.local
[4] MPI Startup(): process is pinned to CPU01 on node compute-0-4.local
[5] MPI startup(): shared memory and socket data transfer modes
[5] MPI Startup(): process is pinned to CPU01 on node compute-0-1.local
[7] MPI startup(): shared memory and socket data transfer modes
[6] MPI startup(): shared memory and socket data transfer modes
[6] MPI Startup(): process is pinned to CPU01 on node compute-0-2.local
[7] MPI Startup(): process is pinned to CPU01 on node compute-0-3.local
[9] MPI startup(): shared memory and socket data transfer modes
[8] MPI startup(): shared memory and socket data transfer modes
[8] MPI Startup(): process is pinned to CPU02 on node compute-0-4.local
[10] MPI startup(): shared memory and socket data transfer modes
[9] MPI Startup(): process is pinned to CPU02 on node compute-0-1.local
[10] MPI Startup(): process is pinned to CPU02 on node compute-0-2.local
[12] MPI startup(): shared memory and socket data transfer modes
[11] MPI startup(): shared memory and socket data transfer modes
[11] MPI Startup(): process is pinned to CPU02 on node compute-0-3.local
[12] MPI Startup(): process is pinned to CPU03 on node compute-0-4.local
[14] MPI startup(): shared memory and socket data transfer modes
[13] MPI startup(): shared memory and socket data transfer modes
[13] MPI Startup(): process is pinned to CPU03 on node compute-0-1.local
[14] MPI Startup(): process is pinned to CPU03 on node compute-0-2.local
[15] MPI startup(): shared memory and socket data transfer modes
[15] MPI Startup(): process is pinned to CPU03 on node compute-0-3.local
[0] Rank    Pid     Node name
[0] 0       14839   compute-0-4.local
[0] 1       14817   compute-0-1.local
[0] 2       14645   compute-0-2.local
[0] 3       14832   compute-0-3.local
[0] 4       14836   compute-0-4.local
[0] 5       14818   compute-0-1.local
[0] 6       14646   compute-0-2.local
[0] 7       14833   compute-0-3.local
[0] 8       14837   compute-0-4.local
[0] 9       14819   compute-0-1.local
[0] 10      14647   compute-0-2.local
[0] 11      14834   compute-0-3.local
[0] 12      14838   compute-0-4.local
[0] 13      14820   compute-0-1.local
[0] 14      14648   compute-0-2.local
[0] 15      14835   compute-0-3.local
running on   16 nodes

上面四节点共16个核心。排列方式是,先排一个节点的一个核心,然后排令一个节点的一个核心……

我能不能实现先把某个节点的cpu核心排完了再排另一个节点的cpu核心?

谢谢啦!

[ Last edited by mingdong on 2009-4-15 at 13:52 ]
回复此楼
已阅   回复此楼   关注TA 给TA发消息 送TA红花 TA的回帖
相关版块跳转 我要订阅楼主 hadone 的主题更新
普通表情 高级回复(可上传附件)
信息提示
请填处理意见