See attachment.
a comment: to run with the btl mx i need to use --mca btl mx,sm,self -mca mtl ^mx or i get a mx_open_endpoint failure due to myrinet busy (I have already increase the number of endpoints to 16 )
On Wed, May 6, 2009 at 7:31 PM, Scott Atchley
<atchley@myri.com> wrote:
On May 4, 2009, at 10:54 AM, Ricardo Fernández-Perea wrote:
I finally have opportunity to run the imb-3.2 benchmark over myrinet I am running in a cluster of 16 node Xservers connected with myrinet 15 of them are 8core ones and the last one is a 4 cores one. Having a limit of 124 process
I have run the test with the bynode option so from the 2 to the 16 process test is always running 1 process by node.
the following test pingpong, pingping, sendrecv, exchange presents a strong drop in performance with the 64k packet size.
any idea where I should look for the cause.
Ricardo
I believe that the pingpong results show the drop that you are experiencing. There is a drop at 64 KB and 128 KB and it returns to the same level at 128 KB.
What you are seeing in the pingpong results is the change over from eager to rendezvous within MX. Up to 32 KB, we use an eager protocol (send the data even if there is not a posted receive). After 32 KB, we switch to a rendezvous protocol.
I do not believe that this limit can be changed. Have you tried the same application when using the MX BTL?