Thank you! I was a little chicken at first to install the Intel OCL stuff "over" the existing stuff, but they work it out nicely. NVIDIA is platform 0, Intel is platform 1. And while cl_intel_printf throws warnings, it also works so that's all good. I am now studiously resisting the urge to figure out how to have my app balance both GPU and CPU devices while I actually do some serious debugging.
That really helped a lot. Thanks again! Jack. -- mathuin at gmail dot com On Sun, Dec 16, 2012 at 2:27 PM, Andreas Kloeckner <[email protected]>wrote: > John Twilley <[email protected]> writes: > > > First, my setup: I'm running pyopencl out of git (last update Nov 27) on > > an Ubuntu 12.04.1 LTS system with CUDA 5.0 and an NVIDIA GTX 560 Ti > > graphics card. > > > > I have no problems running the examples, and I have written some nearly > > trivial code that works just fine as well. When I move on to more > > sophisticated solutions, I get the dreaded "out of resources" result > which > > really means I have a segmentation fault or something in my code. > > > > My normal mode of debugging problems like this is to use a whole lot of > > printf statements. That approach doesn't work with OpenCL for obvious > > reasons. How do you guys debug your OpenCL code if you can't use printf? > > Easy fix: > > Step 1) Grab/install one of the CPU OpenCL implementations. > > - http://software.intel.com/en-us/vcsource/tools/opencl-sdk > - > http://developer.amd.com/tools/heterogeneous-computing/amd-accelerated-parallel-processing-app-sdk/#two > - https://bugs.launchpad.net/pocl (if you're feeling lucky) > > (The Intel one is better, IMO.) > > Step 2) Use printf. > > Also note that printf will become much more widespread as it's now part > of the CL 1.2 standard. > > HTH, > Andreas > >
_______________________________________________ PyOpenCL mailing list [email protected] http://lists.tiker.net/listinfo/pyopencl
