Latest drivers (NVidia and ATI)

[Claggy]

What PSU do you have running that host?, I'd expect at least 800 Watt PSU is required,

Claggy

For a 465 + 560ti factory OC'd model, it would have to be at least a very good 850W, or preferably larger IMO.

I agree, Asus's Recommended Power Supply Wattage Calculator says 800W when you put in 2*560Ti's and 900Watts when you put in 2*465's,
while Corsairs PSUfinder says 950Watts when you put in 2*470's, and 750Watts when you put in 2*460's (the closest matches)

Claggy

[arkayn]

With my 560 and 5830, I put a 850 watt PSU in.

[k6xt]

Which application Art ? x41g Cuda 3.2 release ?  How many tasks per card ? What are the temperatures like & did you do a 'Clean Install' with the driver installtion advanced options?

Sorry for the questions, but they'll help narrow down the possibilities.

Offthe top of my head, One possibility could be other wacky drivers in the system, so a check with DPC latency Checker might be in order as an easy pre-check before troubleshooting.

[Edit:]  for reference, her's what my 480 system (main dev machine) looks like at full crunch while browsing with Google Chrome, which took a lot of work to find and force installation of better drivers for chipset & Wifi etc.

Jason

The power supply is a Corsair 750W. I did a clean install of x41g prior to loading the cards based on the post you sent before I bought the 560Ti, thanks again for that.

I did the clean install by first un-installing all Nvidia software plus a reboot. Then started over.

When its running there are two tasks per card, four total. I use MSI Afterburner to control the fans with a more aggressive speed curve. My GPU temps are running in the 60-65 deg C range, near where they run as single GPU's. CPU temps are in the 65 deg C range except for CPU 1 which runs 70 deg C and always has in the 15 months or so since new.

Edit: Right now there's three tasks per GPU running. I set that parm to 0.3.

Thanks, regards
Art

[Jason G]

OK, there's good news & there's bad news.  Sounds mostly good, but no way is a 750 watt PSU enough for both those cards at once,  I have a 480 & a 560ti in separate machines.  The 560ti by itself seems happy with a Corsair AX 750 Gold... The 480 took about 4 months or so by itself to hose a seasonic gold 750.  I'd suggest pulling the 465 for now, before your PSU blows up.  I'm not being silly.

Jason

[k6xt]

OK, there's good news & there's bad news.  Sounds mostly good, but no way is a 750 watt PSU enough for both those cards at once,  I have a 480 & a 560ti in separate machines.  The 560ti by itself seems happy with a Corsair AX 750 Gold... The 480 took about 4 months or so by itself to hose a seasonic gold 750.  I'd suggest pulling the 465 for now, before your PSU blows up.  I'm not being silly.

Jason

I hear ya. Ran to get my VOM. THe PS outlet air didn't feel very hot and it isn't, about 37 deg C. Doesn't seem like its very stressed -- but the point is a good one. I'll get a 1kW in there. My latency picture is not so sweet with that program you suggested, got work to do there.

Thanks ARt

[Jason G]

I hear ya. Ran to get my VOM. THe PS outlet air didn't feel very hot and it isn't, about 37 deg C. Doesn't seem like its very stressed -- but the point is a good one. I'll get a 1kW in there. My latency picture is not so sweet with that program you suggested, got work to do there.

Thanks ARt

Alright, sounds like the right track.  The DPC latency issues are more obscure & related more to newer technologies than traditional concerns....  but my attitude is that a modern system should really handle streaming audio/video no problem even while crunching, or there's something wrong, since my garbage Pentium 2 could manage    It can be tricky to get the drivers to cooperate... but that'll come after stabilising anyway.

[perryjay]

I upgraded to 290.53 two days ago and it is running okay on my machine, Intel E5400 dual with a GTS 450. No downclocking or anything but I have noticed I have been getting quite a few inconclusives though. I seem to be finding a lot more pulses than my wingmen. In this one  http://setiathome.berkeley.edu/workunit.php?wuid=910961253 I found 13 pulses my wingmen didn't find but we all three got credit. Others I have found one or two pulses my wingmen didn't find. I am getting credit but it strikes me as strange.

[Richard Haselgrove]

Report at GPUGrid that the CUDA 4.1 developer toolkit went onto public production release today - downloadable from http://developer.nvidia.com/cuda-downloads

Presumably there'll be consumer-grade drivers to follow, but I can't find anything newer than 290.53 beta yet. WHQL drivers are still 285.58

[Mike]

Cat 12.1 WHQL released.

http://sites.amd.com/us/game/downloads/Pages/radeon_vista-64.aspx

Note 12.1 as well as 12.2 preview are not for 7xxx cards still.

Mike

[Jason G]

Report at GPUGrid that the CUDA 4.1 developer toolkit went onto public production release today - downloadable from http://developer.nvidia.com/cuda-downloads

Presumably there'll be consumer-grade drivers to follow, but I can't find anything newer than 290.53 beta yet. WHQL drivers are still 285.58

4.1 release needs 286.16 or newer. WHQL release will more than likely coincide with Kepler release, which is rumoured to be an early surprise.

Jason

[MarkJ]

Anything useful in cuda 4.1 for us? Does the optimizing compiler make any difference to earlier ones?

[Raistmer]

Anything useful in cuda 4.1 for us? Does the optimizing compiler make any difference to earlier ones?

I saw OpenCL 1.1 support on FERMI (not sure it was added only now though).
OpenCL part of distro became wider, separate best practice guide for OpenCL... need to read for more

[Jason G]

Anything useful in cuda 4.1 for us? Does the optimizing compiler make any difference to earlier ones?

Decent performance gain on Fermis.  Older GPUs are seeing a slowdown over Cuda 3.2, which has been reported & apparently reproduced by nVidia.  I was hoping they'd fix that by release, as it means will probably have to support 2 builds next installer.

Jason

[msattler]

The kitties were rather hoping for another driver release beyond 290.53 to go along with 4.1 too.  Hope they haven't given up on it.

[Jason G]

The kitties were rather hoping for another driver release beyond 290.53 to go along with 4.1 too.  Hope they haven't given up on it.

I did spot leaked GK107 drivers (295 point something) floating around somewhere, which I think are some mobile chip.  experience on the new compiler was pretty good on Fermi's, so I suspect they'll want to iron out any reported issues ( perhaps including ours) before the big release.  Just guessing, maybe they've realised they're  more or less ready software wise and have all the focus on prepping for a solid launch.  They've been pretty quiet about the new architecture, I suppose playing their cards close to their chests.  Plenty of rumours about but nothing solid. Certain notorious anti-nvidia guys are suggesting nVidia might well 'win this round', which I presume referred to gaming performance.  If that's the case though, it implies a few technical things that should apply to Cuda as well...

Jason