Posts by [VENETO] boboviz

1) (Message 7434)
Posted 22 Nov 2022 by [VENETO] boboviz
Post:
don't want to get into too many details, but we got the green light on that. there need to be some things setup on the backend for access to the code. but Petri should get access soon.


Great!!
2) (Message 7433)
Posted 22 Nov 2022 by [VENETO] boboviz
Post:
We've asked for the source code and haven't received any response so far. Our developers are champing at the bit to further optimize the applications as we have done at all the projects we crunch for.


I asked about source code because, years ago, i found this page.
But the code seems not open.
3) (Message 7421)
Posted 22 Nov 2022 by [VENETO] boboviz
Post:
Hi folks,

We also would like to have it already done. Unfortunately the past two years messed up pretty well with our plans, as many others.
So at this momment I can't give any prognosis.

One thing is sure though, we'll find a way to have that OpenCL work finished at some point.

Thanks for understanding,
Georgi


No problem.
P.S. Is the code open source? Do you need help from community to develop it?
4) (Message 7420)
Posted 22 Nov 2022 by [VENETO] boboviz
Post:
It has to be a generalist and never will have the performance of CUDA.


This is an old myth.
Now OpenCl, with LITTLE optimization, has the SAME performance of Cuda (and, sometimes, better).
You can also convert, almost automaticaly, the Cuda code to OpenCl with a lot of tools.
5) (Message 5051)
Posted 9 Nov 2016 by [VENETO] boboviz
Post:
Hi all,
I'm not a developer but maybe there is a tool to convert cuda application on OpenCL: HIP : C++ Heterogeneous-Compute Interface for Portability


Just yesterday Amd released version 1.0 of HIP, with a lot of new features and bugfix.
6) (Message 5048)
Posted 5 Nov 2016 by [VENETO] boboviz
Post:
Hi all,
I'm not a developer but maybe there is a tool to convert cuda application on OpenCL: HIP : C++ Heterogeneous-Compute Interface for Portability


This is also very interesting
https://github.com/hughperkins/cuda-on-cl
7) (Message 3725)
Posted 28 Oct 2014 by [VENETO] boboviz
Post:
And AMD, finally, starts to publish OpenCL 2.0 examples,....waiting for SDK
8) (Message 3724)
Posted 28 Oct 2014 by [VENETO] boboviz
Post:
AMD does not help Boinc, Nvidia does help which is why alot of projects have Nvidia gpu crunching first.


I don't know...
http://developer.amd.com/partners/tools-partners/apps-running-on-boinc/