Thanks for your reports, I can actually reproduce this, it looks like a
regression in the last release. We'll try and fix it in trunk asap.
On Mon, Dec 10, 2012 at 3:50 PM, Paul Osmialowski <newch...@king.net.pl>wrote:
> Hello,
>
> I'm new here and I just heard about x10 language, although I'm rather
> focused on yet another way of using CUDA-derived technologies, therefore
> giving x10's CUDA capabilities a try is the very first thing I want to do
> before I go any deeper into x10. Unfortunately, I stuck on this infamous
> "async 72 is not a CUDA kernel" problem - I tried to run x10 CUDA examples
> on three different machines and three different CUDA toolkit versions with
> four different settings (all with different nvidia displays and plain .cu
> CUDA examples working):
> 1. x86 Gentoo Linux CUDA 4.2
> 2. x86 Gentoo Linux CUDA 3.2 (manual downgrade)
> 3. x86_64 Gentoo Linux CUDA 4.2
> 4. x86_64 MacOSX 10.6.8 CUDA 5.0
>
> The results were always the same: "not a CUDA kernel" on all x10 CUDA
> examples (except CUDATopology which actually works, exactly the same case
> as in Avinash Malik's post).
> I first tried SVN snapshot then x10-2.3.0-src.tar.bz2, result still the
> same (mabye I should check older releases too?):
>
> bash-3.2$ X10RT_ACCELS=ALL ./CUDABlackScholes
> Using the GPU at place Place(1)
> This program only supports a single GPU.
> Running 512 times on place Place(1)
> X10RT: async 72 is not a CUDA kernel.
> Abort trap
>
> (that's copied from the MacOSX build)
>
> simple CUDA status program shows following:
>
> bash-3.2$ ./mp0
> There is 1 device supporting CUDA
> Device 0 name: GeForce 320M
> Computational Capabilities: 1.2
> Maximum global memory size: 265027584
> Maximum constant memory size: 65536
> Maximum shared memory size per block: 16384
> Maximum block dimensions: 512 x 512 x 64
> Maximum grid dimensions: 65535 x 65535 x 1
> Warp size: 32
>
> Can anyone confirm that these x10 CUDA examples are working for anyone? Or
> worked in any past release? Somehow I don't believe that things written in
> http://x10-lang.org/documentation/practical-x10-programming/x10-on-gpus.htmlpage
> aren't not quite truth...
>
> Best regards,
> Paul
>
>
>
> ------------------------------------------------------------------------------
> LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial
> Remotely access PCs and mobile devices and provide instant support
> Improve your efficiency, and focus on delivering more value-add services
> Discover what IT Professionals Know. Rescue delivers
> http://p.sf.net/sfu/logmein_12329d2d
> _______________________________________________
> X10-users mailing list
> X10-users@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/x10-users
>
------------------------------------------------------------------------------
LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial
Remotely access PCs and mobile devices and provide instant support
Improve your efficiency, and focus on delivering more value-add services
Discover what IT Professionals Know. Rescue delivers
http://p.sf.net/sfu/logmein_12329d2d
_______________________________________________
X10-users mailing list
X10-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/x10-users
