#AMD FIREPRO W4100 BENCHMARK SOFTWARE#
You saying that the point of view must be based on software people use. Good answer mapesdhs, and i agree with almost everything you posted, but yet i think you didn't got what i meant to explain in my replay. Longer a factor even with a lot of GPUs installed, and at the same time one gains from high CPU/RAMĪvailability, assuming the available OS platform is suitable (though such systems are expensive). The oneĮxception to this might be to use a shared memory system such as an SGI UV 2 in which latency is no This regard, GPU acceleration of rendering is more applicable to small scale work with lesser data/RAMĭemands, not for large productions (latency in GPU clusters is a major issue for rendering). A friend at SPI told me oneįrame can involve as much as 500GB of data, which is fed across their renderfarm via a 10GB/sec SAN. True picture of available performance to the user.Ītm I'm running my own tests with a K5000, two 6000s, 4000, 2000 and various gamer cards,ītw, renderfarms are still generally CPU-based, because GPUs have a long way to go before they canĬope with the memory demands of complex scene renders for motion pictures. Results for the relevant NVIDIA cards should be included, otherwise the results are not a (my research has been mainly with AE so far), but if any of them can, then CUDA-based Now for the apps covered here, I don't know which of them (if any) can make use of CUDA You'd try to force them to employ OpenCL, a notion I don't believe for a microsecond. Otherwise, what you're saying is that if you were running AE with a bunch of NVIDIA cards then But where an NVIDIA card can offerĬUDA to a user for an application then that comparison should be included aswell. Sure, run OpenCL tests on both cards, I have no problem with that. Some of them only use OpenCL, in which case What matters are the apps people are running. You must use a tool that both contenders can read. Nobody with an NVIDIA card running After Effects would use OpenCL for GPU acceleration. And for me the only way is openCL because it is open. > But here they put a card against a card. Your preferred scope is narrow to the point of useless in making a proper AMD cards could mean an AMD solution is more favourable, but without the data oneĬannot know for sure. Sufficiently better than the OpenCL performance for running the same task, then cost/power differences Particular app which supports both OpenCL and CUDA if the CUDA performance from such a card is not Rather, atm, there is a glaring lack of real data about how well the same NVIDIA card can run a Your phrasing suggests I would like to see a test that artifically makes the NVIDIA card look better, which is Since uses vary, an array of comparisons can be useful. Some might say the comparison should be based on a fixedĬost basis, others on power consumption or TCO, others on the number of cards, others might say 1 vs. They do offer excellent scalability, in theory up to as many as 56 GPUs per system usingĨ-way splitters on a 7-slot mbd such as an Asrock X79 Extreme11 or relevant server board.ĭifferent people would have varying opinions. the guyĪt the top of the Arion table is using seven Titans, but PCIe splitters are expensive, though You'd need to use a PCIe splitter to do that.
> Then put a box with 8 k6000(8 is the total of cards that the "Nvidia maximum" alow). You must use a tool that both contenders can read.Īnd yes NVidia dont give a shit to openCL, and i understand why, but i dont think it's wise. You cant benchmark over a proprietary maner.
Also dont forget that he have to deal with the price(8 $5K($40,000) against 4 $4K($16,000)) maybe he find that the cheaper solution isn't the faster one but maybe faster enough.īut here they put a card against a card. Then put a box with 8 k6000(8 is the total of cards that the "Nvidia maximum" alow) against 4 w9100(4 is the total of cards that amd said that should put in one system).ĭo you think it is fair? From the point of view of a renderfarm owner perhaps, because he dont look at a card but at a solution. Issue for such markets (sha7bot is spot on in that regard).
#AMD FIREPRO W4100 BENCHMARK DRIVER#
Having said that, the large VRAM should make quite a difference for medical/GISĪnd defense imaging, but then we come back to driver reliability which is a huge (Igor, ask Chris about the AE CUDA test a friend of mine is preparing). Raw specs, the W9100 ought to be a lot quicker than it is for some of the tests Is bound to show the FirePro in a more positive light. Perform when using its native CUDA for accelerating relevant tasks vs. The picture is incomplete though without comparing to how the Quadro would