Go Back   Hardware Canucks > HARDWARE CANUCKS COMMUNITY > HardwareCanucks F@H Team

    
Reply
 
LinkBack Thread Tools Display Modes
  #1 (permalink)  
Old April 12, 2011, 08:21 PM
SKYMTL's Avatar
HardwareCanuck Review Editor
 
Join Date: Feb 2007
Location: Montreal
Posts: 11,617
Default F@H Core 16: Taking AMD GPU Folding to the Next Level?

A few weeks ago, Stanford introduced the new Core 16 Project 11293 work units which are specifically tailored towards OpenCL-supporting AMD graphics cards. But do they bring the hoped-for increase in Folding@Home performance or is this yet another step towards disappointment?...

[ Read full article ]

Been working on this one since the new core came out. Hope you enjoy guys. This will be the first of many F@H articles in the coming months.
Reply With Quote
  #2 (permalink)  
Old April 12, 2011, 08:29 PM
chrisk's Avatar
Folding Captain
 
Join Date: Jul 2008
Location: GTA, Ontario
Posts: 7,401

My System Specs

Default

Thanks for this Sky! Will come in handy when some of the AMD folders join up for the Chimp Challenge.

The high CPU usage bothers me a bit. That said, if I recall correctly (I was a rookie folder then), the first nVidia cores used more cpu cycles then too, but that could have been a CUDA issue as well.

Hopefully the cpu cycles come down on those WUs and the GPU folding won't rely on a 'CPU crutch' too much in the future, but at least Stanford is making some progress. The Gromacs team will have to do lots of work on this as well.
__________________
Fold for team #54196
Reply With Quote
  #3 (permalink)  
Old April 12, 2011, 09:09 PM
Banned
F@H
 
Join Date: Aug 2007
Location: mtl
Posts: 12,694
Default

very nice.

but plz explain again why the 5870 beats the 6970 at folding? :)
Reply With Quote
  #4 (permalink)  
Old April 12, 2011, 09:15 PM
SKYMTL's Avatar
HardwareCanuck Review Editor
 
Join Date: Feb 2007
Location: Montreal
Posts: 11,617
Default

Quote:
Originally Posted by _dangtx_ View Post
very nice.

but plz explain again why the 5870 beats the 6970 at folding? :)
It's all about the number of cores initially. The other pieces of the puzzle I am not quite sure about but the way Cypress handles GPGPU instructions is quite different from Cayman. Remember, the VLIW4 architecture of the Cayman series eliminates one Special Function Unit per SIMD (versus the VLIW5 architecture of Cypress) which can in effect have an impact upon certain areas of performance.

That's part of my theory and I won't bore you with the rest.
__________________
Reply With Quote
  #5 (permalink)  
Old April 12, 2011, 09:18 PM
Banned
F@H
 
Join Date: Aug 2007
Location: mtl
Posts: 12,694
Default

basically, depending on the application using the cores, one can be faster than the other and viceversa?
looking at 3d apps you would think the 6970 would leave the ole 5870 way way back
Reply With Quote
  #6 (permalink)  
Old April 12, 2011, 09:22 PM
SKYMTL's Avatar
HardwareCanuck Review Editor
 
Join Date: Feb 2007
Location: Montreal
Posts: 11,617
Default

Quote:
Originally Posted by _dangtx_ View Post
basically, depending on the application using the cores, one can be faster than the other and viceversa?
Of course. AMD needed to make certain trade offs in order to offer a more robust DX11 gaming experience with Cayman. Application is everything but then again, VLIW4 has its own set of optimizations which may not have been built into the beta version of Core 16 so things could very well change.
__________________
Reply With Quote
  #7 (permalink)  
Old April 12, 2011, 09:28 PM
Banned
F@H
 
Join Date: Aug 2007
Location: mtl
Posts: 12,694
Default

interesting. also,whenever you got time, give the on chip gpu a folding and see how it does, unless its not supported yet :)
danke herr sky
Reply With Quote
  #8 (permalink)  
Old April 12, 2011, 10:25 PM
Dead Things's Avatar
Hall Of Fame
F@H
 
Join Date: Oct 2008
Location: Centre of the Universe
Posts: 1,572

My System Specs

Default

Thanks for the write-up SKY! A thorough assessment. If the project maturation for OpenCL units turns out to be anything like that for CUDA, then later, larger projects will likely yield even greater dividends for cards with more stream processors as opposed to those with higher clock frequencies.

Given the resource requirements for AMD-based projects, it behooves Stanford to figure out a way to park the data in VRAM rather than rely on swaps with the system memory. User-added environment variables could partially do this with Brook. I really don't see any reason why Stanford can't do it completely with OpenCL. Certainly, in the current bigadv era, this advancement is too-little-too-late for dedicated folders and should be understood as an improvement for regular users. And regular users don't mess around with environment variables. As you said - a good first step. But there remains much to improve for AMD folders.
__________________
Follow my folding, mining & benching shenanigans @dt_oc!

Think you can overclock? Then show us what you got!
Join the Hardware Canucks Overclocking team today!
Reply With Quote
  #9 (permalink)  
Old April 13, 2011, 11:05 AM
matsta31's Avatar
Hall Of Fame
F@H
 
Join Date: May 2008
Location: Montreal
Posts: 2,204
Default

Interesting read, thanks for this article and the work behing

And wanted to add,

Congrats to HWC reviewers who did receive some loving from PCPER this week this is the second HW review Jeremy Hellstrom has highligted on the main page.

PC Perspective - The #1 Choice for PC Hardware Reviews and Information
__________________

Sold hardware again.....
Currently using WHS hardware....
Reply With Quote
  #10 (permalink)  
Old April 13, 2011, 11:35 AM
SKYMTL's Avatar
HardwareCanuck Review Editor
 
Join Date: Feb 2007
Location: Montreal
Posts: 11,617
Default

Props to PcPer as well for continually bringing up to date news to their front page. They do one hell of a job!
__________________
Reply With Quote
Reply


Thread Tools
Display Modes

Similar Threads
Thread Thread Starter Forum Replies Last Post
folding on 3 core / core free for gpu folding phil3_66666 HardwareCanucks F@H Team 12 January 11, 2010 06:07 PM
GPU client 100% cpu core utilization? hd4200 folding? 0o0 HardwareCanucks F@H Team 18 December 21, 2009 03:53 PM
Dual GPU Folding on one GPU (FahCore_14 only) geokilla HardwareCanucks F@H Team 2 August 8, 2009 05:35 PM
Mid level and low level parts for sale mattlef Buy/Sell & Trade 0 July 21, 2008 12:05 PM