On Mon, 20 Jun 2011 14:55:46 -0700, Scott Biersdorff <[email protected]> wrote: > Traceback (most recent call last): > File "demo.py", line 44, in <module> > a_doubled = (2*a_gpu).get() > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/gpuarray.py", > line 285, in __rmul__ > return self._axpbz(scalar, 0, result) > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/gpuarray.py", > line 160, in _axpbz > func = elementwise.get_axpbz_kernel(self.dtype) > File "<string>", line 2, in get_axpbz_kernel > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/tools.py", > line 485, in context_dependent_memoize > result = func(*args) > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/elementwise.py", > line 323, in get_axpbz_kernel > "axpb") > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/elementwise.py", > line 99, in get_elwise_kernel > arguments, operation, name, keep, options, **kwargs) > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/elementwise.py", > line 85, in get_elwise_kernel_and_types > keep, options, **kwargs) > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/elementwise.py", > line 74, in get_elwise_module > options=options, keep=keep) > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/compiler.py", > line 239, in __init__ > arch, code, cache_dir, include_dirs) > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/compiler.py", > line 229, in compile > return compile_plain(source, options, keep, nvcc, cache_dir) > File > "/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/compiler.py", > line 108, in compile_plain > cmdline, stdout=stdout, stderr=stderr) > pycuda.driver.CompileError: nvcc compilation of /tmp/tmpoQTLvI/kernel.cu > failed > [command: nvcc --cubin -arch sm_12 > -I/usr/local/lib/python2.7/dist-packages/pycuda-0.94.2-py2.7-linux-x86_64.egg/pycuda/../include/pycuda > kernel.cu] > [stderr: > In file included > from /usr/local/cuda/bin/../include/cuda_runtime.h:59:0, > from <command-line>:0: > /usr/local/cuda/bin/../include/host_config.h:82:2: error: #error -- > unsupported GNU version! gcc 4.5 and up are not supported! > > I'm I reading this right? Is the kernel being compiled twice?
No. The evidence is in your stack trace, actually. The failing compilation is trying to compile a kernel for an array operation (the 2*a in your case). I suppose we should add a way to pass options to nvcc for behind-your-back compilations? A global variable maybe (shudder)? Andreas
pgpnmqJOuclAK.pgp
Description: PGP signature
_______________________________________________ PyCUDA mailing list [email protected] http://lists.tiker.net/listinfo/pycuda
