I wanted to ask this one Quora, but they no longer allow you to enter background/elaboration on a question.
I'm looking to build/purchase a workstation to use from home for research/data analysis (and probably some recreation, but anything able to handle my work needs will be able to run a game or two with ease). The most demanding applications it will be used for are image processing (specifically, 3D- and/or Z-projections of high-res, 16bit Z stacks, deconvolution, and deep learning / training DNNs and GANs). I'm looking at NVidia graphics cards, since it's so much easier to push parallel processing tasks to the GPU with something like CUDA than it is to jury-rig a workaround for an AMD card. Specifically, i'm trying to decide between a GTX and an RTX series card.
I know the primary difference is that RTX cards can do ray-tracing, while GTX cannot -- but it's not immediately apparent to me whether I should care, given that I won't be using the GPU for its ability to render realistic real-time action scenes.
Given that the GTX line is considerably more affordable, I'd like to know if the RTX equivalents will outperform the GTX counterparts in tasks like neural network training. Or even if I should bite the bullet and spring for a Quadro (though I sincerely hope that won't be the case).
Hi,
both actuals GTX or RTX are using the same GPU called Turing. But RTX family is probably more adapted to deep learning tasks because in addition to Ray Tracing capacities, RTX cards have Tensor Cores dedicated for DL.
Regards
For deep learning:
NVidia has SDK platform for Deep Learning:
https://developer.nvidia.com/deep-learning-software
Deep Learning SDK libraries are API compatible across all NVIDIA GPU platforms. But CUDA is required.
Here is tests:
https://towardsdatascience.com/rtx-2060-vs-gtx-1080ti-in-deep-learning-gpu-benchmarks-cheapest-rtx-vs-most-expensive-gtx-card-cd47cd9931d2
https://timdettmers.com/2019/04/03/which-gpu-for-deep-learning/
I test PNY VCQRTX4000-PB Quadro RTX 4000 8GB GDDR6 PCIE.
It was ~800USD. The results was good in deep learning , and FEA ( Finite Element Analysis )applications.
For playing:
I not know...
Regards, László
Hi,
For us as the average practitioner, the best choice would be the GTX 1080. This has been stated by many in the Deep Learning community and works very well for most applications. RTX 2080 Ti is the best GPU for Deep Learning from a price-performance perspective though. The 2080 Ti trains neural nets 80% as fast as the Tesla V100 (the fastest GPU on the market). The 2080 Ti is $1,199, whereas the Tesla V100 is close to $9,000. So the 2080 Ti is 80% as fast as the fastest GPU on the market and only 1/7th the price.
I suggest you take a look at this:
https://lambdalabs.com/blog/titan-rtx-tensorflow-benchmarks/
Best.
- Badges
- Science topic