| Author |
Message |
 Topic: OpenAcc on CPUs |
xray
Replies: 5
Views: 744
|
 Forum: Accelerator Programming Posted: Tue Apr 02, 2013 3:08 am Subject: OpenAcc on CPUs |
| If there is the possibility to get beta access or the like, it would be great. |
| Topic: OpenAcc on CPUs |
xray
Replies: 5
Views: 744
|
Forum: Accelerator Programming Posted: Thu Mar 28, 2013 5:38 am Subject: OpenAcc on CPUs |
Hi Mat,
Is there a roadmap when the PGI compilers will support Intel's Xeon Phi? I am interested whether we will have it before our next programming workshop in May.
And when will it support AMD GPU ... |
| Topic: GMEM loads: caching vs. non-caching |
xray
Replies: 2
Views: 299
|
Forum: Accelerator Programming Posted: Sun Mar 10, 2013 4:02 am Subject: GMEM loads: caching vs. non-caching |
| Thanks Mat! I will give it a try and will report my results. |
| Topic: GMEM loads: caching vs. non-caching |
xray
Replies: 2
Views: 299
|
Forum: Accelerator Programming Posted: Wed Mar 06, 2013 3:18 am Subject: GMEM loads: caching vs. non-caching |
Hi,
on Fermi GPUs, the default global memory access pattern are caching loads (i.e. a granularity of 128-bytes). With CUDA, you may change it to non-caching loads by compiling with nvcc and "-Xp ... |
| Topic: Overlapping kernel and data execution |
xray
Replies: 2
Views: 447
|
Forum: Accelerator Programming Posted: Tue Mar 05, 2013 3:08 am Subject: Overlapping kernel and data execution |
| Any news on the issue (for Nvidia GPUs)? |
| |
Search
Memberlist
Register
Profile
Log in