11) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 13565)
Posted 5278 days ago by chumbucket843
FFT will not be a problem at first.
We have implemented an alternative algorithm which will be fine to run several types of WUs and we still have Nvidia for the WUs which require FFT.

gdf

how much work in the WU's is fft's? they run quite fast from what i have seen on ATi cards, like video transcoding. it almost seems like their architecture is designed for signal processing rather than graphics. i saw an AMD slideshow that had an optimized fft running at 300 GFLOPs on a 4870. thats with LDS too.
12) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 13434)
Posted 5283 days ago by chumbucket843
no, only 4000 series and up will run opencl. nvidia 8 series and higher will too.
13) Message boards : Graphics cards (GPUs) : Nvidia GT300 (Message 13259)
Posted 5301 days ago by chumbucket843
There is a fundamental flaw with NVidia. They sell GPU’s that are excellent for gamers and for crunchers, but they are expensive due to research and design of cutting edge technology. Partially as a result of this, they don’t sell well against Intel in the low end market – where most of the sales occur. Unfortunately for NVidia Intel have proprietary rights on chip design and can therefore hold NVidia to random – and have been doing so for some time! With a year of financial instability it is little wonder that the manufactures of a panicle technological design are struggling. When you are faced with competitors that are capable of flexing considerable muscle (buy our GPUs or you wont get our CPU’s) and governments who are scared to help NVidia, you are in a difficult position!
It is likely that in Europe Intel could be fined for their present actions, but by the time that happens there might be two CPU manufacturers and the same two GPU manufacturers.
By most accounts the G200 range was difficult and expensive to manufacture so it would be an unnecessary financial burden on the company to try to keep these production lines running. Now is not the time to produce a card that will not sell at a profit! It seems sensible that they are cutting manufacturing back now, several months before the release of the G300 based GPU’s. I expect the new G300 line will require the full attention of NVidia – it could make or break the company. To keep manufacturing lots of pointless old lines of technologies, as Intel do with their CPU’s, would definitely spell the end for NVidia.

thats a little out there to think a company will fail from one generation. AMD is still with us. 5870 is not 2x faster. it is bottlenecked by bandwidth specifically L1 cache. on milky way the card gets 2tflops which is a perfect match for the 2TB/s of bandwidth.nvidias l1 bandwidth on fermi should be 3TB/s so the card will be very fast. something that should be noted about ati's architecture is that it was designed for dx10, not gpgpu. not all applications can take full advantage of vliw or vectors. nvidia has spent very little r&d lately. gt200 and g92 were very small tweaks. fermi is the same basic architecture with more programmablity and cache. how gpugrid performs with ati is a mystery. its going to come down to bandwidth and ilp.
14) Message boards : Graphics cards (GPUs) : Nvidia GT300 (Message 13014)
Posted 5319 days ago by chumbucket843
the best article is from realworldtech.com. its a good read. they know what they are talking about.will gpugrid take advamtage of the double precision capabilities? does scientific computing cache well? ie data locality.
15) Message boards : Graphics cards (GPUs) : Any plans for ATI Support. (Message 12997)
Posted 5321 days ago by chumbucket843
i was reading a whitepaper from folding at home and it said that ATi's kernels cant scatter memory accesses between memory accesses between kernels and this leads to scaling of N^2/2 compared to nvidia with N^2. N being the number of molecules of course. they probably wont match nvidia's performance until they fix this.
16) Message boards : Graphics cards (GPUs) : NVidia GPU Card comparisons in GFLOPS peak (Message 12642)
Posted 5331 days ago by chumbucket843
is ACEMD bandwidth bound? it seems like it should be getting closer to peak flops or does gpugrid use double precision? if so these numbers are impressive.
17) Message boards : Graphics cards (GPUs) : Whats wrong with GPU Grid and Nvidia Drivers 190.x on the GTX 260 with 192 SP´s ? (Message 12465)
Posted 5342 days ago by chumbucket843
i have the same problem. vista 64 sp1 and 190.XX. its probably something with cuda if it is bugging out on one card.
18) Message boards : Graphics cards (GPUs) : LOOKING for buggy/crashing GTX216 (Message 12169)
Posted 5357 days ago by chumbucket843
Do you have it under Linux?
gdf

yeah i have dual boot but i dont use linux much. what info do i need to PM you?
19) Message boards : Graphics cards (GPUs) : LOOKING for buggy/crashing GTX216 (Message 12138)
Posted 5358 days ago by chumbucket843
i have a 192 that fails every packet(not currently running on the grid until this is fixed).do you think this card would also be affected by FFT's?
20) Message boards : Number crunching : G300 possible numbers (Message 11682)
Posted 5379 days ago by chumbucket843
nvidia probably has more than one development team and its time for a new arch. especially with ati and larrabee not too far behind.


Previous 10 | Next 10
//