"Burdge, Kevin B." <kburdge(a)caltech.edu> writes:
> Hi everyone,
>
>
> I've been struggling to get PyCUDA up and running on my new machine (Ubuntu 16.04, using latest python 3 anaconda distro as python). I can get the configure and install to run without any hiccups, and have sorted out the path to the CUDA directory, but I inevitably keep arriving at the following error when I try and run the test script:
>
> python test_driver.pyTraceback (most recent call last):
> File "test_driver.py", line 6, in <module>
> from pycuda.tools import mark_cuda_test, dtype_to_ctype
> File "/home/kburdge/anaconda3/lib/python3.6/site-packages/pycuda/tools.py", line 34, in <module>
> import pycuda.driver as cuda
> File "/home/kburdge/anaconda3/lib/python3.6/site-packages/pycuda/driver.py", line 5, in <module>
> from pycuda._driver import * # noqa
> ImportError: /home/kburdge/anaconda3/lib/python3.6/site-packages/pycuda/_driver.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEED1Ev
>
> Any pointers on how to resolve this would be immensely appreciated.
https://lists.tiker.net/pipermail/pycuda/2017-January/004993.html
Andreas
Hi everyone,
I've been struggling to get PyCUDA up and running on my new machine (Ubuntu 16.04, using latest python 3 anaconda distro as python). I can get the configure and install to run without any hiccups, and have sorted out the path to the CUDA directory, but I inevitably keep arriving at the following error when I try and run the test script:
python test_driver.pyTraceback (most recent call last):
File "test_driver.py", line 6, in <module>
from pycuda.tools import mark_cuda_test, dtype_to_ctype
File "/home/kburdge/anaconda3/lib/python3.6/site-packages/pycuda/tools.py", line 34, in <module>
import pycuda.driver as cuda
File "/home/kburdge/anaconda3/lib/python3.6/site-packages/pycuda/driver.py", line 5, in <module>
from pycuda._driver import * # noqa
ImportError: /home/kburdge/anaconda3/lib/python3.6/site-packages/pycuda/_driver.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEED1Ev
Any pointers on how to resolve this would be immensely appreciated.
Best,
Kevin
Hi Everyone,
I am running a truncated mean convolution but I keep running into cuCtxSynchronize failed type errors when the kernel is called numerous times.
I guess that it's not a timeout issue in GPU issue because it's a compute only GPU.
So, I put it down to memory issues due to the use of list that I need to store in kernel for sorting/truncating values. Am I correct in thinking that the error can be avoided by using shared memory?
Thanks,
Sanjay Rana | Design Directorate
Rural Payments Agency | Room 200 | North Gate House | Reading | RG1 1AF
Jabber: 02077642065 | ext. 42065 | Email: sanjay.rana(a)rpa.gsi.gov.uk<mailto:sanjay.rana@rpa.gsi.gov.uk>
Follow us on Twitter @Ruralpay
************************************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
This footnote also confirms that this email message has been swept by
Cisco ESA for the presence of computer viruses.
************************************************************************************
Hello,
I am struggling running Theano on the GPU.
(WinPython-64bit-3.4.4.1, Theano 0.9.0)
Theano issues the following message:
Message: 'pygpu was configured but could not be imported or is too old
(version 0.6 or higher required)'
Problem is the installation of pygpu / libgpuarray.
http://deeplearning.net/software/libgpuarray/installation.html
I checked and pygpu is not installed.
Is libgpuarray the same as pycuda.gpuarray?
Kind regards,
Joe