Ahh, what exciting times we live in. Just look at the example applications:
- autonomous vehicles
- autopilot drone
- personal assistant
- personal robots
- ...
i know it's optimistic, but it's not science-fiction.
Radeon Instinct – Optimized Machine and Deep Learning
31–40 of 88 posts
Re: Radeon Instinct – Optimized Machine and Deep Learning
#32What's particularly interesting here is that the Fiji card they propose is a very different beast than any of the NVIDIA offerings. The MI8 card's HBM has a great power and performance advantage (512 GB/s peak bandwidth) even if it's on 28 nm. NVIDIA has nothing that has even remotely comparable bandwidth in this price/perf/TDP regime. None of the NVIDIA GP10[24] Teslas have GDDR5X -- not to surprising given that it…
Those MIOpen benchmarks are a bit dubious, since MIOpen is AMDs own deep learning framework. It's unlikely that code written by AMD is optimal for the Nvidia hardware. To be realistic you need to compare AMD hardware running MIOpen to NV hardware running a framework backed by cuDNN.
It's clearly indicated on the slide that those are Deepbench [1] GEMM and GEMM-convolution numbers. Data for M40, TITAN Maxwell/Pascal and Intel KNL is actually provided by Baidu in their Github repo.
Re: Radeon Instinct – Optimized Machine and Deep Learning
#33Does anyone use AMD for deep learning in scientific / industry ? All the libraries for deep learning I have seen require CUDA and NVIDIA is winning by merely being the most popular API. Searching github it looks like they are university assignment projects see https://github.com/search?utf8=%E2%9C%93&q=opencl+deep+learn...
If AMD can release solid hardware, all they would need to do is add support for their hardware to popular open-source projects like TensorFlow. I just hope they do the second part correctly.
FYI, AMD's people are helping TF to add OpenCL support.
Re: Radeon Instinct – Optimized Machine and Deep Learning
#34I can't even look at the press picture without remembering that is the exact same metal card slot tab that I had on my IBM PC 35 years ago. They should take a picture of the other end or something.
Re: Radeon Instinct – Optimized Machine and Deep Learning
#35What's a good GPU / setup for someone doing deep learning at home? Does anyone have recommendations?
Re: Radeon Instinct – Optimized Machine and Deep Learning
#36What's a good GPU / setup for someone doing deep learning at home? Does anyone have recommendations?
I've been curious about this too. AWS does have K80 instances available for $0.90/hour which isn't too bad for playing around and as long as they keep updating their infrastructure, you can play with the newest stuff versus having to upgrade your own all the time.
Re: Radeon Instinct – Optimized Machine and Deep Learning
#37What's a good GPU / setup for someone doing deep learning at home? Does anyone have recommendations?
Nvidia 1080 is a good one.
Take a look at this write up.
http://timdettmers.com/2014/08/14/which-gpu-for-deep-learnin...
its updated in July 2016 with info about the later versions.
Re: Radeon Instinct – Optimized Machine and Deep Learning
#38Earlier quoted context omitted.
The tricky, but fun parts. It's certainly not trivial to port those, but I'm not too worried about it as long as there is solid runtime support in ROCm. More fun work for perf engineers like me. ;) Massive amount of boilerplate, heavy APIs or crappy software stack are more dangerous IMO than having to drop in replacements for NVIDIA-specific optimizations of GPU-to-NIC or GPU-to-GPU communication.
Not only not trivial to port those but they are constantly will have to play catch up and be at the mercy of NVIDIA in regards to spec. AMD is in a catch 22, support CUDA and be effectively in a constant catch up position, not support it and continue to be ignored by the market at large simply because the momentum NVIDIA has managed to achieve with CUDA over the years.
NVIDIA is playing catch-up with themselves and the shifting market too!
Just look at the Maxwell-based Tesla cards that came out of the blue (as if they were an afterthought); I bet Facebook, Baidu, Google, etc. told NVIDIA that Kepler was shit for their use-cases and they did not want to wait for Pascal.
Or look at the bizarre Pascal product line where the GP100 does support half precision, but the others don't, not even the P4 or P40. Strange, isn't it?
Things are changing so quickly that it isn't hard at all to find footing as long as you have something useful to offer. At the same time, I agree, a robust software stack is an advantage, but for the likes of Google or Baidu even that is not so big of a deal (Google wrote their own CUDA compiler!).
Re: Radeon Instinct – Optimized Machine and Deep Learning
#39What's particularly interesting here is that the Fiji card they propose is a very different beast than any of the NVIDIA offerings. The MI8 card's HBM has a great power and performance advantage (512 GB/s peak bandwidth) even if it's on 28 nm. NVIDIA has nothing that has even remotely comparable bandwidth in this price/perf/TDP regime. None of the NVIDIA GP10[24] Teslas have GDDR5X -- not to surprising given that it…
I wonder if something like AMD's SSD+GPU combo would improve the performance of this? Increasing the usable buffer size.
Re: Radeon Instinct – Optimized Machine and Deep Learning
#40Other than ML applications, what can I write on this?
OpenCL? Something comparable to CUDA? What about utilizing Vulkan?