11–20 of 37 posts
The author recommends Titan V - without justifying its $3k price. The 1080 series is less than half that price with comparable benchmarks. Am I missing something?
The benchmarks where the 1080 doesn't even compete - FP16/Tensor Cores.
Earlier quoted context omitted.
The benchmarks where the 1080 doesn't even compete - FP16/Tensor Cores.
Many state-of-art models won't train well on FP16. But for inferencing it's extraordinarily good. 2x1080Ti is the sweet spot for FP32 training on "budget" at the moment.
The author recommends Titan V - without justifying its $3k price. The 1080 series is less than half that price with comparable benchmarks. Am I missing something?
I am doing experimental work where I really need to have double precision i.e. FP64. The Titan V offers the same stellar FP64 performance as the server oriented Tesla V100.
Earlier quoted context omitted.
Considering the V100 runs around $10-11k and the Titan V provides similar performance for around $3k, the author isn't wrong.
32GB vs 12GB. Enables a lot more. If you don't care about memory and FP64, 2080Ti would be a much better deal than Titan V. V100 vs Quadro RTX 8000 would be more interesting. Still, I think 2x1080Ti is a better deal than 1x2080Ti and costs the same.
Also the 2080ti can do lower precision math (int8/4) in the tensor cores, while the Titan v cannot.
Earlier quoted context omitted.
Many state-of-art models won't train well on FP16. But for inferencing it's extraordinarily good. 2x1080Ti is the sweet spot for FP32 training on "budget" at the moment.
"Inference" or "inferring". "Inferencing" isn't a word any more than "defencing" is.
Example: https://www.pugetsystems.com/nav/peak/tower_single/customize...
Does anyone know why they are using Xeon processors instead of the AMD Threadripper? Is it the support for ECC memory? If so, why is it that so important? Example: https://www.pugetsystems.com/nav/peak/tower_single/customize...
Does anyone know why they are using Xeon processors instead of the AMD Threadripper? Is it the support for ECC memory? If so, why is it that so important? Example: https://www.pugetsystems.com/nav/peak/tower_single/customize...
Does anyone know why they are using Xeon processors instead of the AMD Threadripper? Is it the support for ECC memory? If so, why is it that so important? Example: https://www.pugetsystems.com/nav/peak/tower_single/customize...
sgemm on 5000x5000 matrices takes about 600ms on a Threadrippers 1950x, but only around 150ms on the comparatively priced i9 7900x. Vector libraries for special functions, eg Intel VML or SLEEF also provide a similar performance advantage there.
If you're mostly crunching numbers, and either compiling the code you run with avx512 enabled (eg, -mprefer-vector-width=512 on gcc, otherwise it's disabled) or using explicitly vectorized libraries, you will see dramatically better performance from avx512, regardless of any thermal throttling. Number crunching is what it's made for.
Granted, you should be offloading most of those computations to the GPU, which will be many times faster. But I'd you're in the business of ML or statistics, I'd still way that more heavily than the difference in how long it takes them to compile code.