Hello Matthew,
I've just started my PhD, and consequently have less time for contributing.
Unfortunately, the release largely depends on me, as most of what remains
to be done has to do with filling up the database.
I've been working steadily on the auto-tuner since the beginning of my PhD,
as it is part of my research. The latest version doesn't perform quite well
on Kepler (70% of CuBlas), but it's already an improvement over ViennaCL
1.5, and should be enough for ViennaCL 1.6.
I would be curious to know what remains to be done, apart from all the
auto-tuning stuff.
Philippe
2014-09-16 13:07 GMT-04:00 Matthew Musto <matthew.mu...@gmail.com>:
> Gentlemen,
>
> Things seem to have gone silent for the last three weeks. So, I decided
> to ask how things are going and if you needed any help testing the upcoming
> release.
>
> Thanks,
> -Matt
>
>
> ------------------------------------------------------------------------------
> Want excitement?
> Manually upgrade your production database.
> When you want reliability, choose Perforce.
> Perforce version control. Predictably reliable.
>
> http://pubads.g.doubleclick.net/gampad/clk?id=157508191&iu=/4140/ostg.clktrk
> _______________________________________________
> ViennaCL-devel mailing list
> ViennaCL-devel@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/viennacl-devel
>
>
------------------------------------------------------------------------------
Want excitement?
Manually upgrade your production database.
When you want reliability, choose Perforce.
Perforce version control. Predictably reliable.
http://pubads.g.doubleclick.net/gampad/clk?id=157508191&iu=/4140/ostg.clktrk
_______________________________________________
ViennaCL-devel mailing list
ViennaCL-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/viennacl-devel
