Radeon VII, POWER9 and numba (Was: science application + opencl/rocm + AMD GPU?)
Hi Mo,
Thanks for asking.
A few humble comments follow:
I like the specs of AMD's Radeon VII GPU.
I checked a month ago if ROCm might run on it.
Unfortunately, it seemed to me at that time, ROCm
didn't yet actually work.
However, the numba compiler for scientific python apps
is already in Debian,
evidently uses the standard LLVM to compile
into parallel machine instructions and
supports the cool new open hardware POWER9.
Feel free to use my little script at
http://loaner.com/how_fast_do_various_numbers_of_cores_run
to benchmark how well apps scale to running on
more CPUs (Amdahl's law).
Maybe numba and multiple cores are fast enough for
apps hard to parallelize.
At least until ROCm works.
I hope that's right.
Or helps.
Or was at least interesting!
;-)
Happy holidays,
Kingsley
On 11/23/2019 16:34, Mo Zhou wrote:
> Hi science team,
>
> I'd like to request the team for sharing some experience on this topic:
> "scientific application + opencl/rocm + AMD GPU". Any experience will
> be very helpful to me in terms of the being-investigated ROCm
> integration[1] to Debian.
>
> I'd like to ask you the following questions:
>
> 1. how's everything going without the amdgpu-pro[2] driver, especially
> the opencl/rocm programs? Most importantly, can OpenCL work without
> any non-free component?
>
> 2. how does the consumer-grade AMD gpu perform in terms of scientific
> computing or other opencl/rocm applications?
>
> 3. do you think AMD GPU can be a practical alternative to Nvidia/CUDA
> in at least a few applications?
>
>
> [1] https://salsa.debian.org/rocm-team
> [2] non-free, https://www.amd.com/en/support/gpu-pro-eula
>
--
Time is the fire in which we all burn.
Reply to: