PGI User Forum
 SearchSearch   MemberlistMemberlist     RegisterRegister   ProfileProfile    Log inLog in 

CUDA-x86.

Search found 3 matches
PGI User Forum Forum Index
Author Message
  Topic: Using constant memory in Fortran CUDA and with multiple GPUs
MaciejG

Replies: 4
Views: 69
 PostForum: Accelerator Programming   Posted: Thu Jun 06, 2013 9:56 pm   Subject: Using constant memory in Fortran CUDA and with multiple GPUs
I believe there are actually multiple context created hence you need establish Peer-to-peer so you can manage them.
I could do that but that would just let me access constant memory on dev A from ke ...
  Topic: Using constant memory in Fortran CUDA and with multiple GPUs
MaciejG

Replies: 4
Views: 69
 PostForum: Accelerator Programming   Posted: Wed Jun 05, 2013 4:40 pm   Subject: Using constant memory in Fortran CUDA and with multiple GPUs
Hi Mat,

Thanks for your reply.

I'm not sure if GPUDirect is actually relevant to what I am trying to achieve. I understand GPUDirect is required if a kernel running on device 1 is trying to acce ...
  Topic: Using constant memory in Fortran CUDA and with multiple GPUs
MaciejG

Replies: 4
Views: 69
 PostForum: Accelerator Programming   Posted: Tue Jun 04, 2013 4:42 pm   Subject: Using constant memory in Fortran CUDA and with multiple GPUs
Hello,

I'm developing a program in Fortran CUDA and trying to use/access multiple GPUs from a single host thread. The original code (single GPU only) was using global and constant memory and when a ...
 
Page 1 of 1
All times are GMT - 7 Hours
Jump to:  


Powered by phpBB © 2001, 2002 phpBB Group