PGI User Forum
 SearchSearch   MemberlistMemberlist     RegisterRegister   ProfileProfile    Log inLog in 

CUDA-x86.

GMEM loads: caching vs. non-caching

 
Post new topic   Reply to topic    PGI User Forum Forum Index -> Accelerator Programming
View previous topic :: View next topic  
Author Message
xray



Joined: 21 Jan 2010
Posts: 85

PostPosted: Wed Mar 06, 2013 3:18 am    Post subject: GMEM loads: caching vs. non-caching Reply with quote

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 "-Xptxas -dlcm=cg".
With PGI's OpenACC, I assume we also have caching loads be default. Right? Is there any chance to use non-caching loads with OpenACC (compiler flag, environment variable,...)?
Sandra
Back to top
View user's profile
mkcolg



Joined: 30 Jun 2004
Posts: 6129
Location: The Portland Group Inc.

PostPosted: Fri Mar 08, 2013 3:40 pm    Post subject: Reply with quote

Hi Sandra,

We do have an experimental flag (-Mx,180,8) that will disable the L1 cache. You are welcome to give it a try. The caveat being that since it's not been exposed at the user level, it is subject to change.

- Mat
Back to top
View user's profile
xray



Joined: 21 Jan 2010
Posts: 85

PostPosted: Sun Mar 10, 2013 4:02 am    Post subject: Reply with quote

Thanks Mat! I will give it a try and will report my results.
Back to top
View user's profile
istvanreguly



Joined: 04 Apr 2013
Posts: 3

PostPosted: Mon Feb 10, 2014 2:44 pm    Post subject: Reply with quote

Hi,

Apologies for resurrecting this thread - since in the K40 we can once again use caching loads and dlcm=ca, I was wondering how I could enable this in the CUDA Fortran compiler - could you help me with that please?

Thank you,
Istvan
Back to top
View user's profile
mkcolg



Joined: 30 Jun 2004
Posts: 6129
Location: The Portland Group Inc.

PostPosted: Mon Feb 10, 2014 4:45 pm    Post subject: Reply with quote

Hi Istvan,

We added this as the flag "-ta=tesla:noL1".

- Mat
Back to top
View user's profile
Display posts from previous:   
Post new topic   Reply to topic    PGI User Forum Forum Index -> Accelerator Programming All times are GMT - 7 Hours
Page 1 of 1

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by phpBB © phpBB Group