Hi,
> I noted some conversation on this list 2 years ago on supporting Power8.
> Nothing since.
Are you interested in using Power8 with the Pocl's CPU backend (as a compute
device), or just CPU as a host - used by the applications to handle the
runtime part of OpenCL, with CUDA backend doing the computation ?
The latter is probably easier to achieve, though right now it likely doesn't
work out-of-the-box. The former (Power8 as OpenCL device) requires LLVM support
for your CPU, including Clang vectors. I have no idea what's the state of LLVM
on PowerX.
> Has anyone tried to get POCL running on Tegra with CUDA backend
IIRC i've seen some commits which dealt with ARM in the CUDA backend, so it's
quite possible.
Cheers,
-- mb
________________________________
From: Gaurav Khanna <[email protected]>
Sent: Wednesday, August 15, 2018 3:01:34 PM
To: [email protected]
Subject: [pocl-devel] POCL on Power9, Tegra
Hey POCL Folks
I'm building a small cluster with Power9 + V100 with NVLink2. I'd like to run
some OpenCL apps. Since Nvidia's OpenCL support is lagging badly .. I was
considering using POCL on this platform, with the CUDA backend.
I noted some conversation on this list 2 years ago on supporting Power8.
Nothing since. Is anyone interested in this? I'm happy to help, supply remote
hardware, etc.
On a somewhat different end .. also interested in POCL on Nvidia Tegra .. I
have small clusters of TX1 and TX2 Jetson boards. Has anyone tried to get POCL
running on Tegra with CUDA backend?
Cheers,
Gaurav
------------------------------------------------------------------------------
Check out the vibrant tech community on one of the world's most
engaging tech sites, Slashdot.org! http://sdm.link/slashdot
_______________________________________________
pocl-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/pocl-devel
