The "I have almost no money" recommendation should include Colab. <a href="https://medium.com/deep-learning-turkey/google-colab-free-gpu-tutorial-e113627b9f5d" rel="nofollow">https://medium.com/deep-learning-turkey/google-colab-free-gp...</a><p>Somebody who has almost no money isn't going to be able to equip a desktop with a GTX 1050 Ti ($175), fast disk ($50), and RAM ($50) on an entry level cpu/motherboard/power supply/case/monitor/peripherals ($300) and pay for the electricity used during training. Colab can be accessed from a free public computer or a cheap Chromebook ($200).
The 2080Ti numbers are likely going to be a lot lower than that.<p>We’ve benched the 1080Ti vs the Titan V and the Titan V is nowhere near 2x faster at training than the 1080Ti as suggested in that graph. We observed a 30% to 40% speedup during our benchmarking:<p><a href="https://deeptalk.lambdalabs.com/t/benchmarking-the-titan-v-volta-gpu-with-tensorflow/108" rel="nofollow">https://deeptalk.lambdalabs.com/t/benchmarking-the-titan-v-v...</a><p>This is consistent with the 32% increase in FP32 flops from 11.3TFlops for the 1080Ti to 15TFlops for the Titan V. Additional speedups can be explained by the increase in memory bandwidth for HBM2 and the mixed precision fused multiply adds provided by the TensorCores.<p>Thus, given the quoted 13Tflop numbers for the 2080Ti, I would expect the 2080Ti to present something more like a 15-20% speedup over the 1080Ti. So 2080Ti is less bang for your buck. But benchmarking is the only way to tell what’s better on a FLOPS/$ basis.
This is a great article and I highly respect his opinions.<p>However, since you are probably eagerly reading this to see how fast the new RTX cards are, so you should know upfront that the numbers he has so far are just estimates based on specs:<p>> Note that the numbers for the RTX 2080 and RTX 2080 Ti should be taken with a grain of salt since no hard performance numbers existed. I estimated performance according to a roofline model of matrix multiplication and convolution under this hardware together with Tensor Core benchmarks from the V100 and Titan V.
Seems down for me:<p><a href="https://web.archive.org/web/20180821173206/http://timdettmers.com/2018/08/21/which-gpu-for-deep-learning/" rel="nofollow">https://web.archive.org/web/20180821173206/http://timdettmer...</a>
The biggest advance here is that Nvidia has produced a consumer card that has all the high-end deep-learning features. This was missing in both the Pascal and Volta Generations even though in Pascal fp32 was full power. I think the TPU scared them and that's a good thing.
Hacker news hug of death? Anyone here have any experience using AMD cards with something like PlaidML? I have a 1050Ti SSC but I'm starting to feel the limitation as my complexity grows. But getting a 1080 is a bit out of my budget right now. I'm tempted to get the new Vega 56 released recently.
The cost/performance plot - shouldn't it be "Lower is better"? It says "Higher is better".<p>Lower value would indicate lower cost per unit level of performance.<p>It should be "Lower is better" or the plot needs to say "Performance/Cost".
Am I missing something?
An open question for me is the performance of two 2080tis using NVLink as one virtual GPU. I imagine it’ll be close to linear, but I’ll be interested to know for sure.
Good article, but as a new learner, I'm interested in (your experiences on) how much time taken for the common task to train a model? 1min vs 2mins, probably I will get a cheaper GPU but if there's 5h vs 10h or 1 day vs 2 days, I'd save more money for one with good performance