What's new
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

Update On GPU3, ATi Version Will Be Delayed

El_Fiendo

Well-known member
Joined
Feb 3, 2009
Messages
577
Location
Edmonton
LCB, if you don't mind I'd like to post links to your posts on TPU. This way, I won't copypasta and then glory hog, so you should get the recognition for the hard work you do on scanning these stories down (good [email protected] journalism sir). If you'd rather me not do this, let me know and I'll refrain from doing so in the future.
 

LCB001

Well-known member
Joined
Feb 19, 2008
Messages
1,732
Location
Aylmer QC.
LCB, if you don't mind I'd like to post links to your posts on TPU. This way, I won't copypasta and then glory hog, so you should get the recognition for the hard work you do on scanning these stories down (good [email protected] journalism sir). If you'd rather me not do this, let me know and I'll refrain from doing so in the future.
Feel free to pass along the info in whatever way you see fit, anything to help a fellow Folder...:canadianwave:
 

chrisk

Folding Captain
Joined
Jul 12, 2008
Messages
7,541
Location
GTA, Ontario
dont edit my words lol.

ati has good hw, coincidentally not supported...somebody mustve pulled a few over the green goblins i think..maybe not?
Some info on nVidia vs. ATI folding here:
[email protected] GPU3 Client to use RV870

Looks like the nVidia hardware gets more work done due to how errors are handled and threads. The paper linked in that post mentions Pande's work in getting ATI folding better (which I don't care to read lol)
 

geokilla

Well-known member
Joined
Aug 11, 2008
Messages
3,757
Location
Toronto
This should end some quarrels. [email protected]

Just an update on my blog post. I want to make it clear that we're seeing problems in both of our ATI and NVIDIA GPU OpenCL implementations for OpenMM. Maybe it's on our side (I'm bet some bugs are on our side), but we suspect there could possibly be some issues with both the NVIDIA and ATI OpenCL implementations (and maybe even Apple's). We are working with everyone closely to either fix our bugs or get our code compliant with the OpenCL implementations.Also, it looks like I should have been more careful in my wording of my previous post. I was referring to the issues above when talking about whether the ATI implementation was "fully functional" and some groups have gotten this out of my intended context. As far as I understand, the ATI OpenCL implementation is fully functional.
Finally, it is important to note that our Brook code is still supported, just not actively developed so [email protected]/OpenMM is concentrating on shifting to OpenCL, so no more active development using Brook.
 

Twitter

Top