1) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 17972)
Posted 5006 days ago by chumbucket843
i guess you could say that. local data share on rv770 was too restricted to meet opencl requirements.
2) Message boards : Graphics cards (GPUs) : GPUGRID and Fermi (Message 17722)
Posted 5023 days ago by chumbucket843
CUDA 3.1 is out.
http://developer.nvidia.com/object/cuda_3_1_downloads.html
3) Message boards : Graphics cards (GPUs) : GPUGRID and Fermi (Message 17449)
Posted 5052 days ago by chumbucket843
Any other recommendations?


Well.. yes. Better don't increase the voltage ;)
It reduces chip longevity and drives power consumption up. On a chip like Fermi it's also a considerable factor that increased temperature (due to voltage increase) increases the leakage quite a bit, so your card becomes less power efficient (=higher electricity cost). I'd rather try to improve cooling & temperatures. That would also give you an increased frequency headroom. Probably not as much as voltage increases, but without the negative side effects.

MrS

OCing is not as detrimental as your make it sound. modern processes are designed to handle very high and very low temperatures. a major consideration when designing a chip is robustness. in fact it is so important that they are overly conservative with clocks and volts, especially with server/professional chips. that's free performance for us. 400 series is great for OCing too, partially from architecture and partially from high leakage.
4) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 17146)
Posted 5063 days ago by chumbucket843
just out of curiosity have you tested your openCL code on a CPU yet? AMD's opencl cpu compiler should be more mature and less buggy than their gpu compiler. it would also be a nice performance reference.
5) Message boards : Graphics cards (GPUs) : Fermi released (Message 16228)
Posted 5102 days ago by chumbucket843
im no expert on molecular dynamics but it runs well on stream processors. the gtx480 should be excellent because it has a cache that can act as a bandwidth cushion when you have overlapping gathers. fermi also has the ability to put register spills into cache. this can help performance A LOT. if you are spilling registers your performance is terrible. (i.e. 5870 performing as fast as a 8800GT). the new arch makes it easier to write compilers due to unified address space. this all translates to great performance.
6) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 14419)
Posted 5174 days ago by chumbucket843
openMM, aka gpu3, uses opencl but F@H is running into similar problems as gpugrid. two of their kernels wouldnt compile.
7) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 14194)
Posted 5188 days ago by chumbucket843
there is currently no beta work for ATi cards. if you read the whole thread from the start you can see that the ATi client is currently getting ready for beta testing.
8) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 14155)
Posted 5194 days ago by chumbucket843
could you give us an idea of the performance from these new clients? specifically performance of 5870. or is it too early to tell?
9) Message boards : Graphics cards (GPUs) : Application for CUDA2.3 for windows (Message 13741)
Posted 5232 days ago by chumbucket843
started about 4 hours ago. it crashes my computer randomly and i reached my daily quota. i am using drivers 195.62, win7 64 bit, gtx 260 192.
10) Message boards : Graphics cards (GPUs) : GPUGRID and ATI (Message 13692)
Posted 5238 days ago by chumbucket843
graphics dont really need cache so ATi can get away with out having it working for now. GPGPU is a very different story. btw, its not technically a cache. its called local data share. as of now only brook and IL have support for LDS. its the exact same reason folding@home is so slow on ATi cards. to give you an idea of how fast LDS is vram is 115GB/s and LDS is 1.9TB/s on a 4870, a lot of apps need that bandwidth which is almost 20x faster than main memory access.

Is it slow because it uses system RAM or just does not have any GPU Cache RAM???

the cache is there but it will take a driver update to get it working so for now its vram.


Next 10
//