[mpich-discuss] MPICH2 & Large data

The Source thesourcehim at gmail.com
Thu Oct 2 08:52:07 CDT 2008


I understand that. I only suggest a way how to decrease this count 
number. For example you have an array of 2.5 GB size.
Now a little trick:
MPI_Send(array, arraysize/sizeof(int), MPI_INT,......);
Thus you'll send the entire array without data loss or integer overflow 
(just don't forget any remnants if arraysize%sizeof(int) != 0).

Hisham Adel пишет:
> The problem is in the count number not in the data type.
>
> Thanks  a lot
>
>  
>
>
> --- On *Thu, 10/2/08, The Source /<thesourcehim at gmail.com>/* wrote:
>
>     From: The Source <thesourcehim at gmail.com>
>     Subject: Re: [mpich-discuss] MPICH2 & Large data
>     To: mpich-discuss at mcs.anl.gov
>     Date: Thursday, October 2, 2008, 3:08 PM
>
>     Send, using different MPI data types. For example MPI_INT instead
>     of MPI_CHAR, so element number will be 4 time smaller. The other
>     way is to split data to several messages.
>
>     Hisham Adel пишет:
>>
>>     Hi,
>>
>>     I am trying to send large data (2.5GB) using MPICH2. When the
>>     other node is going to receive the data it can not cause in
>>     MPI_RECV (void * buffer, Int count, .......) the count number
>>     will be very large than the integer range.
>>
>>     how can I make it receive large data ?
>>     Is there any solution for this problem ?
>>
>>     Thanks alot
>>
>>     Regards,
>>     Hisham Adel
>>
>>
>
>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20081002/7251c262/attachment.htm>


More information about the mpich-discuss mailing list