On Wed, 19 May 2010 22:03:02 +0100, Samuel Powell spow...@medphys.ucl.ac.uk
wrote:
Hi,
I have written a PyCuda based simulation code that successfully executes
when run normally with Python. I need to distribute this code to my
colleagues - owing to the large number of package dependencies
Hi Tomasz,
On Wed, 19 May 2010 23:55:08 +0200, Tomasz Rybak bogom...@post.pl wrote:
After advices from list and some reading I have put new version
of PyCUDA (and pytools) pacages:
http://www.bogomips.w.tkb.pl/cuda.html#Debian
http://www.bogomips.w.tkb.pl/cuda/
Nice! Thanks for the work
Hi all,
At the recent PyCon Quattro, which took place in early May in the
beautiful Tuscan city of Florence, Fabrizio Milo gave a talk on PyCUDA
entitled
PyCUDA: Come sfruttare la potenza delle schede video nelle
applicazioni python (PyCUDA: How to make use of the power of
graphics
Hi Georg,
On Fri, 21 May 2010 15:10:27 +0200, Teichtmeister, Georg
georg.teichtmeis...@joanneum.at wrote:
I installed PyCuda 0.93/Cuda 2.3 on my computer (Win7-32bit, Xeon
W3520 , GTX285) and after some troubles it seemed to execute the
examples without problems. Then I started
On Fri, 21 May 2010 16:56:49 +0200, Dan Goodman d...@thesamovar.net wrote:
On 21/05/2010 12:55, Andreas Kloeckner wrote:
On Wed, 19 May 2010 17:22:03 +0200, Dan Goodmand...@thesamovar.net wrote:
Hi Andreas,
Sorry about posting that overly large file strace.txt to the list -
hadn't
On Wed, 23 Jun 2010 15:13:39 -0400, Louis Theran the...@temple.edu wrote:
I would second this request. Being able to obtain a DeviceAllocation from a
specified (runtime) context would help me a lot.
There's only *the* current runtime context for the current
thread. Specified makes no
On Thu, 24 Jun 2010 12:45:39 -0400, Louis Theran the...@temple.edu wrote:
A pre-alpha release of PyCULA, which provides support for the CULA port of
LAPACK to CUDA is available from:
http://math.temple.edu/research/geometry/PyCULA/
The main features are:
* ctypes/numpy bindings for
On Tue, 29 Jun 2010 16:44:18 +0100, Ian Ozsvald i...@ianozsvald.com wrote:
Andreas, I'm attaching two patches.
0001 removes the #warning lines in cuda.hpp that make msvc (2008 on WinxP)
fail.
0002 adds GPUArray comparisons for == != = =
Merged, thanks!
Assuming you're cool with the
Hi Julien,
On Fri, 9 Jul 2010 21:16:36 -0700, Julien Cornebise
julien.corneb...@gmail.com wrote:
New to pyCuda, and very excited by the possibilities, I'm
unfortunately having a LaunchError problem with test_driver.py. I have
tried to trace it down using printf() and such, and it seems that
Hi Frédéric,
On Thu, 15 Jul 2010 12:34:45 -0400, Frédéric Bastien no...@nouiz.org wrote:
1) elemwise1.patch: This modification allow to pass the block and grid
to the ElementwiseKernel generated fct. If not provided, it continue
as before.
Can you comment on the necessity of this patch? What
On Sat, 17 Jul 2010 17:40:27 -0400, Julien Cornebise
julien.corneb...@gmail.com wrote:
The daemon of forgotten attachment strikes again. Corrected. Sorry about that.
On Sat, Jul 17, 2010 at 5:39 PM, Julien Cornebise
julien.corneb...@gmail.com wrote:
Awesome, thanks Andreas ! Indeed
A few comments here:
On Tue, 20 Jul 2010 08:19:39 -0700, reckoner recko...@gmail.com wrote:
as you may know, there is a Windows installer for PyCUDA here:
http://www.lfd.uci.edu/~gohlke/pythonlibs/#cython
Note that I have my own build of boost and PyCUDA, but I installed this
just to
On Mon, 26 Jul 2010 11:03:33 -0700, reckoner recko...@gmail.com wrote:
Hi,
I just downloaded the latest distribution using git. I ran configure and
tried building using
% python setup.py build
Can you please post the entire error message? Were there missing Python
headers earlier? Also,
Hi David,
On Wed, 28 Jul 2010 09:21:30 +1000, Dave Reynolds d.reyno...@gmail.com wrote:
I would like to make use of your sparse conjugate gradient solver to speed
up some python code I am working on, however I am having no end of trouble
getting it to work. Can somebody please explain to me
On Tue, 29 Jun 2010 15:42:14 -0600, Art grenan...@gmail.com wrote:
=
test session starts
==
platform darwin -- Python 2.6.5 -- pytest-1.3.1
Hi Simone,
sorry for the late reply. July was pretty crazy, but I'm slowly
recovering.
I've never seen your particular error, but I would recommend two
things. First, configure.py is *not* necessary to install PyCUDA, it's
just a handy way of editing the build configuration. Instead, you may
On Tue, 17 Aug 2010 13:07:30 -0400, Daniel Lepage dplep...@gmail.com wrote:
I've tested this code on a different machine and had no problem. Has
anyone run into this before?
It seems like plenty of people have--something very odd is going on with
64-bit CUDA on Mac. If you're looking for an
Hi Brian,
first off, sorry for the long wait for a reply--I've recently moved to a
new job and am just slowly working my way through the backlog.
On Mon, 30 Aug 2010 23:02:56 +, Brian Menounos menou...@unbc.ca wrote:
Hello - I'm running pycuda (linux), and I can run many of the examples and
Hi Vince,
On Sat, 21 Aug 2010 09:51:29 -0400, Vince Fulco vful...@gmail.com wrote:
To follow up on install failure detailed below, went ahead and removed
python-setuptools while installing distribute-0.6.4. The ongoing
unresolved issue is that to re-install numpy, scipy, rpy prior to
PyCuda
On Fri, 20 Aug 2010 13:34:59 -0400, Lev Givon l...@columbia.edu wrote:
Given that the latest revision of PyCUDA apparently needs to remove
setuptools before downloading and installing distribute, is it
effectively no longer possible to build/install PyCUDA locally (i.e.,
within a user
On Sun, 5 Sep 2010 17:27:07 -0400, Vince Fulco vful...@gmail.com wrote:
Dear Andreas- Thanks for your patience.
...Further, which of those packages actually requires setuptools? A
quick look at their repositories suggests none of them do.
I can only state that using yum install for the
On Sun, 5 Sep 2010 23:50:56 -0400, Lev Givon l...@columbia.edu wrote:
If I create a distribute-based virtualenv named CUDA in my home
directory (using virtualenv 1.4.9), activate it, and then install the
latest revision of pycuda using the installation root ~/CUDA after
specifying the
Hi Janick,
On Mon, 06 Sep 2010 11:11:44 +0200, Janick Martinez Esturo
marti...@isg.cs.uni-magdeburg.de wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
As the numpy package does officially support python 3 since
last weeks release 1.5.0 I was wondering if there are any
plans to move
On Sun, 5 Sep 2010 17:48:57 -0400, Vince Fulco vful...@gmail.com wrote:
Working off my current install prior to retrying a clean one,
On FC12, installing numpy 1.3.0-9 requires python-nose-0.11.3-1 which
then requires python-setuptools-0.6c9-5. Once all are installed,
running test_driver.py
On Mon, 6 Sep 2010 15:38:47 -0400, Vince Fulco vful...@gmail.com wrote:
After a new clean install, the test scripts: test_driver.py and
test_cumath.py work without fail. test_gpuarray.py gives 6 errors
which I am exploring further (looks to be precision issues since
pytools libraries not
On Tue, 07 Sep 2010 15:30:21 -0700, reckoner recko...@gmail.com wrote:
Just to be sure, if I have 3 GPU devices, I just do
dev=drv.Device(2)
dev.make_context()
at the top of my program to use the third (numbered from zero) GPU.
Is that right?
Yes, that's right. If you're using
On Thu, 9 Sep 2010 23:31:36 +1000, Bogdan Opanchuk manti...@gmail.com wrote:
Hi all,
I'm observing the following behavior with latest (git-fetched today)
pycuda and opencl versions on Snow Leopard 10.6.4:
$ python
import pycuda.driver
import pyopencl
Traceback (most recent call last):
On Fri, 10 Sep 2010 00:38:38 +1000, Bogdan Opanchuk manti...@gmail.com wrote:
On Fri, Sep 10, 2010 at 12:18 AM, Andreas Kloeckner
li...@informa.tiker.net wrote:
Are you using the shipped version of Boost in both libraries? If so,
that might present an issue.
Yep, in both. Does it behave
On Sat, 11 Sep 2010 15:59:50 +0200, Tomasz Rybak bogom...@post.pl wrote:
Hello everyone.
Recently I started looking into cooperation between PyCUDA and OpenGL.
It works (I am getting segfaults at the end of my program but I might
not be cleaning some object properly).
Shouldn't happen. Can
Hi Tim,
On Tue, 14 Sep 2010 23:24:15 -0400, Timothy O'Keefe
timothy.oke...@gmail.com wrote:
New user here and anxious to get my feet wet with PyCUDA.
I installed v0.94rc today on an Ubuntu 8.10 box w/ a Quadro FX 1700. I
also Installed the CUDA toolkit v3.1. Everything appeared to compile
On Wed, 15 Sep 2010 10:27:39 -0700, reckoner recko...@gmail.com wrote:
Hi,
According to dump_properties.py ( shown below ), I have
Total Memory: 261824 KB
How much of this can I allocate using gpuarray as in the following:
On Tue, 14 Sep 2010 10:14:34 -0700, Fabrizio Milo aka misto
mistob...@gmail.com wrote:
Hey folks
Now that the cuda driver and the cuda runtime can be used at the same
time from the toolkit 3.0 and more, are there any plans to integrate
this two libraries inside pycuda ?
I see that Ying
Hi all,
You may be aware that Nvidia's GPU Technology Conference is next
week. I'll be there, giving an intro+update talk on PyCUDA:
Wednesday, September, 22nd, 14:00 - 14:50
If there's interest, we could go out at night and have a few beers, and
perhaps before then even work towards library
On Thu, 16 Sep 2010 15:59:29 -0700, Adam N interf...@gmail.com wrote:
The PyCuda documentation
http://documen.tician.de/pycuda/misc.html#version-0-94 lists a sparse
matrix library, pycuda.sparse, as being in version 0.94. It isn't in 0.94rc,
and there's no other documentation for it. Does it
On Thu, 16 Sep 2010 15:07:26 -0700, reckoner recko...@gmail.com wrote:
I'm trying to implement a simple random walk equation
x_(i+1) = x_i + alpha * r_i
where r_i is random.random() and alpha is a float.
I've been looking through the examples, and I would like to avoid
writing
Hi Garrett, all,
On Wed, 15 Sep 2010 12:21:09 -0400, GARRETT B WRIGHT
garrett.wri...@temple.edu wrote:
I just downloaded Nvidia's most current developer release of CUDA3.2
toolkit and devdriver260. They installed and I have built/tested
their SDK examples on this Ubuntu10.04 box. When I
On Thu, 16 Sep 2010 14:37:31 -0400, gerald wrong psillymathh...@gmail.com
wrote:
Looking at PyCUDA setup.py, I found this:
if 'darwin' in sys.platform:
# prevent from building ppc since cuda on OS X is not compiled for
ppc
# also, default to 32-bit build, since there
Hi Brian,
On Tue, 7 Sep 2010 19:56:43 +, Brian Menounos menou...@unbc.ca wrote:
Hi Andreas - I realize you're pretty busy answering emails of late, so answer
when you can...
Yeah, sorry. Pretty swamped ATM. I hope things will clear out a bit
during the fall semester, but so far I don't
On Wed, 15 Sep 2010 16:53:04 -0400, Timothy O'Keefe
timothy.oke...@gmail.com wrote:
Given your feedback, I was able to compile CUDA and at least execute a
script that simply imports a module from pycuda package.
I do not receive the traceback mentioned earlier. The way that I
solved this
On Mon, 27 Sep 2010 04:42:00 -0700 (PDT), jmcarval jmcar...@fe.up.pt wrote:
Hi.
Installed PyCUDA 0.94.1 in several Linux boxes.
All have Ubuntu 10.4 with CUDA 3.1 (drv 256.40) and python 2.6.5
Boxes with 1.1 capability GPUs like 8600GT, 9400 GT or FX850 are ok and some
user's are already
On Fri, 24 Sep 2010 15:03:46 -0700 (PDT), meanerelk meaner...@gmail.com wrote:
Summary:
I'm trying to debug my kernel with cuda-gdb,
http://wiki.tiker.net/PyCuda/FrequentlyAskedQuestions#Is_it_possible_to_use_cuda-gdb_with_PyCUDA.3F
as described in the FAQ . However, every module and
On Thu, 23 Sep 2010 00:19:21 +0200, Tomasz Rybak bogom...@post.pl wrote:
Hello Andreas.
I hope that your talk went well.
I saw taht you have updated versions of PyCUDA (to 0.94.1)
and PyOpenCL (to 0.92).
My question is - are updates
79c10e87fc3b5ef7280442d079720ce067a96632 for PyCUDA
and
On Tue, 28 Sep 2010 15:55:26 -0700, Adam N interf...@gmail.com wrote:
Hello,
So I've looked at the sparse stuff from Git, and the SparseSolve.py
examples, and I can see how to build a sparse matrix and a dense
vector, and how to use the CG stuff, solving A * x = b for x. What I
can't seem
Hi Bryan,
On Wed, 29 Sep 2010 17:17:25 -0700, Bryan Catanzaro
catan...@eecs.berkeley.edu wrote:
I recently upgraded to CUDA 3.2 RC, and pulled PyCUDA from git, on my Mac OS
X installation (running a 32 bit Python 2.6).
For some reason, trying to create a GPUArray, using
Hi Gregory,
can you please send PyCUDA-related questions to the mailing list in the
future?
On Thu, 30 Sep 2010 18:46:55 +, Gregory Perry gregory.pe...@govirtual.tv
wrote:
How exactly does PyCuda work with Cuda? Is it an overlay on top of
the Cuda development tools or does it generate
Hi Tomasz, all,
On Fri, 15 Oct 2010 19:27:36 +0200, Tomasz Rybak bogom...@post.pl wrote:
Can anyone with Fermi (GTX 460, 470, 480 - are there other Fermi cards?)
tell whether attached patch solves problems with GPUArray on Fermi?
There has been discussion here on this list (started on
Hi Cyrus,
On Wed, 22 Sep 2010 16:30:26 -0700, Cyrus Omar cy...@cmu.edu wrote:
Using the latest git pycuda (and included boost) and CUDA 3.2 driver and
toolkit, it seems that installation works with 64-bit Python on Snow
Leopard. Both test_driver and test_cumath work. However, not all of the
On Sun, 3 Oct 2010 01:44:35 +1000, Bogdan Opanchuk manti...@gmail.com wrote:
Hello all,
I am getting LogicError from gpuarray.to_gpu_async() for some reason. Code:
Any host memory involved in *_async() must be page-locked. FTFY:
import pycuda.autoinit
import pycuda.driver as drv
import
Hi Christian,
On Thu, 30 Sep 2010 20:11:23 -0400, Christian Fobel christ...@fobel.net wrote:
I am trying to combine the use of PyCuda and straight C CUDA code
(through Boost.Python bindings). The reason is that I would like to
have the convenience of allocating memory and copying data to/from
On Mon, 18 Oct 2010 20:11:54 +1100, Bogdan Opanchuk manti...@gmail.com wrote:
Hi Andreas,
Thank you, that's what I was missing (now that I think about it, this
requirement seems perfectly logical). Probably, it is worth adding
something about it to reference entry for
Hi Arief,
On Mon, 18 Oct 2010 21:47:54 +0700, arief nur andono ariefnurand...@gmail.com
wrote:
is there anybody has implementation of LINPACK in pycuda??
There's an autotuned matrix multiply on the wiki, here:
http://wiki.tiker.net/PyCuda/Examples/DemoMetaMatrixmulCheetah
how to count gpu
On Sat, 30 Oct 2010 13:04:03 +0200, Tomasz Rybak bogom...@post.pl wrote:
Hello.
I have been trying to create some OpenGL examples for PyCUDA
and found program that segfaults.
I cannot debug it fully as the last 8 functions are from
NVIDIA libraries.
The last known function in the trace is
On Sun, 31 Oct 2010 16:07:29 -0400, Andreas Kloeckner li...@informa.tiker.net
wrote:
On Sat, 30 Oct 2010 13:04:03 +0200, Tomasz Rybak bogom...@post.pl wrote:
Hello.
I have been trying to create some OpenGL examples for PyCUDA
and found program that segfaults.
I cannot debug it fully
Hi Tomasz,
first of all, thanks for sending this patch! Much appreciated. Comments
below.
On Fri, 29 Oct 2010 19:20:17 +0200, Tomasz Rybak bogom...@post.pl wrote:
The biggest problem is that IMO (I might be wrong - do
not know PyCUDA to such intimate details) it introduces
Hi Faisal,
On Sat, 30 Oct 2010 16:24:32 -0400, Faisal Moledina faisal.moled...@gmail.com
wrote:
I decided to try CUDA on OS X again now that there is 64-bit support.
I downloaded PyCUDA from the git repository
http://git.tiker.net/trees/pycuda.git . I installed PyCUDA using a
siteconf.py
Hi Daniel,
Thanks for contacting me regarding PyCUDA. I would like to request that
in the future you use the mailing list for such discussions, though.
On Sun, 07 Nov 2010 21:57:49 -, Daniel White dswhit...@skytopia.com
wrote:
I'd like to create an application which allows the user to
On Wed, 10 Nov 2010 22:10:55 -, Daniel White twinbe...@skytopia.com
wrote:
Hi Tomasz and Andreas,
Thanks both for the info. I've considered OpenCL, but from what I've
seen, it's
CL myth debunking below
- not quite as mature as CUDA
To make up for that, it avoids some of CUDA's design
Hi David,
On Thu, 18 Nov 2010 16:47:26 +0200, David Martin avid...@gmail.com wrote:
Can anyone definitively confirm or deny the compatibility of PyCUDA
with Python 2.4?
2.4 and above is the explicit compatibility goal.
Oddly enough, _pycuda_struct.c is also largely the only thing preventing
Hi Dan,
On Thu, 25 Nov 2010 14:10:24 +1030, Dan Kortschak
dan.kortsc...@adelaide.edu.au wrote:
I have just installed PyCuda after CUDA tools, and the latest
devdrivers, but examples and tests fail with:
error invoking 'nvcc --cubin -arch sm_13
On Thu, 25 Nov 2010 17:08:16 +1030, Dan Kortschak
dan.kortsc...@adelaide.edu.au wrote:
Hi Andreas,
It gives the following:
# touch kernel.cu
# nvcc --cubin -arch sm_13
-I/usr/local/lib/python2.6/dist-packages/pycuda-0.94.1-py2.6-linux-x86_64.egg/pycuda/../include/pycuda
kernel.cu
On Fri, 26 Nov 2010 06:37:04 +1030, Dan Kortschak
dan.kortsc...@adelaide.edu.au wrote:
# locate cuda_runtime.h
/usr/local/cuda/include/cuda_runtime.h
# which nvcc
/usr/local/bin/nvcc
Can you run that nvcc with -v and post the output? Did you move your
CUDA toolkit after installation?
On Fri, 26 Nov 2010 08:16:15 +1030, Dan Kortschak
dan.kortsc...@adelaide.edu.au wrote:
CUDA toolkit is still in the installed location at /usr/local/cuda,
there is a symlink bundle from /usr/local/bin/ to /usr/local/cuda/bin/*
rather than adding .../cuda/bin to $PATH, but apart from that
Hi Tomasz,
I've committed your patch, with a few changes.
git diff 69a355d0 master
will show you what I changed. Some comments below. I'd appreciate your
feedback on my changes.
Thanks for your contribution,
Andreas
On Wed, 24 Nov 2010 23:58:01 +0100, Tomasz Rybak bogom...@post.pl wrote:
On Sat, 27 Nov 2010 23:20:40 +0100, Tomasz Rybak bogom...@post.pl wrote:
I do not know how to force Boost::Python to allow
for accepting optional argument for map(stream) function,
so I changed documentation to say that stream is mandatory
argument.
I made the change to make that argument
On Thu, 2 Dec 2010 17:05:35 -0500, Vivek Venugopal vivek.meno...@gmail.com
wrote:
I am trying to install pycuda 0.94.2 on a CentOS 5.5 machine.
After going through the installation instructions on the pycuda Linux page,
http://wiki.tiker.net/PyCuda/Installation/Linux I see the
Hi Frank,
On Mon, 29 Nov 2010 17:04:40 -0500, Frank D. Lind fl...@haystack.mit.edu
wrote:
I'm attempting to use complex numbers in a reduction. It appears that
complex numbers are not allowed as return values from reductions.
A simple example using gpuarray and the sum reduction:
A fix
Hi Martin,
On Mon, 13 Dec 2010 17:04:28 -0800, Martin Laprise mlaprise...@gmail.com
wrote:
I have the exact same error on CentOS. I just installed g++4.4. How do I
change the compiler setting ?
you can set the 'CC' environment variable before compiling PyCUDA to
decide which compiler is used,
Dear omom omomom,
On Thu, 9 Dec 2010 22:06:59 -0600, omom omomom omomomo...@gmail.com wrote:
I can't run the pycuda debugging example from the wiki. Here is my
terminal output. I'm tried a million ways to get around this with no
luck. I'm using the version 2011 code on funtoo. Any suggestions?
On Mon, 20 Dec 2010 21:41:16 +0100, Tomasz Rybak bogom...@post.pl wrote:
At the same time - could you look into CURAND patch I have sent
to the list (attached here)? Last email I have sent on 2010-12-15 22:06
I would like to finish it and then finish prefix scan.
I've taken a look at your
On Sun, 26 Dec 2010 07:25:24 -0800 (PST), om omomomom omomomo...@gmail.com
wrote:
Am using 260.19.29 drivers.
Just upgraded to 260.19.26, which is the latest driver from
http://developer.nvidia.com/object/cuda_3_2_downloads.html
Maybe try that one?
Andreas
pgpzFbisa8Ijr.pgp
Description:
Hi Nathan,
On Sat, 8 Jan 2011 18:53:31 -0500, Nathan Clay clay.nathan...@gmail.com wrote:
Is it possible to update an array using array slices on device memory? e.g
cut the top row off an array and then append a row to the bottom. Would a
array slice operation if allowed on device memory incur
Hi Marie,
I think I've seen this error before. I've quoted the relevant bit from
my reply to Dave Reynolds below.
On Fri, 28 Jan 2011 05:03:43 -0800 (PST), elafrit afrit.mar...@gmail.com
wrote:
Hello - I'm trying to run the SparseSolve.py example. I installed PyMetis
package after fixing
Hi Riaan,
On Fri, 28 Jan 2011 14:49:10 +0200, Riaan van den Dool riaanvdd...@gmail.com
wrote:
Would it be possible at all to create a version of PyOpenCL that does not
link to and does not need any proprietary drivers? Maybe via a make option.
I think it will help adoption of pyOpenCL if
On Fri, 28 Jan 2011 12:39:44 +0200, avidday avid...@gmail.com wrote:
I have hit a wall moving some existing pycuda code to a distributed
memory cluster and am hoping someone cleverer than I can suggest a
work around.
Try calling pytools.prefork.enable_prefork before you call MPI_Init().
Hi Lev,
On Sun, 2 Jan 2011 17:45:46 -0500, Lev Givon l...@columbia.edu wrote:
I recently attempted to run the following code with CUDA 3.2 and
Pycuda 0.94.2 on a Quadro NVS 290 installed on a Linux x86_64 system:
import pycuda.gpuarray as gpuarray
import pycuda.driver as drv
import
Hi there,
On Tue, 1 Feb 2011 04:37:32 -0800 (PST), elafrit afrit.mar...@gmail.com wrote:
starting...
building...
Traceback (most recent call last):
File SparseSolve.py, line 85, in module
main_cg()
File SparseSolve.py, line 32, in main_cg
spmv = PacketedSpMV(csr_mat,
On Thu, 3 Feb 2011 02:47:16 -0800 (PST), elafrit afrit.mar...@gmail.com wrote:
Hi Andreas,
In fact I'm trying to construct a sparse matrix on GPU using PyCUDA. And to
do multiplication of two sparse matrices. Do you have any idea ?
The current code will not help you do either of those two
Hi Tobjan,
On Mon, 7 Feb 2011 19:45:37 -0500, Tobjan Brejicz toba...@gmail.com wrote:
I'm have some problem with my testing of pycuda, which I don't understand.
I want to understand example of how to pointwise multiply large vector (like
1 length) use pycuda.
So I am trying the code
Hi,
On Tue, 8 Feb 2011 07:03:46 -0800 (PST), elafrit afrit.mar...@gmail.com wrote:
Is there any way to hold persistent storage of data on the gpu so that we
don't have to repeatedly the data sent each time.
If I do the next for example :
a_gpu = gpuarray.to_gpu(a)
b_gpu =
Hi Jaime,
On Mon, 7 Feb 2011 08:20:22 -0500, JAIME CISTERNAS jecister...@miuandes.cl
wrote:
Let's meet tomorrow tuesday 8th.
As I said I'll be there around 10:30am,
depending on the train schedule.
Ranged elementwise expressions are now in PyCUDA's git.
On Wed, 9 Feb 2011 10:07:09 +1300, kevin.buck...@ecs.vuw.ac.nz wrote:
Hi there,
looking to install pyCUDA on an Ubuntu box for some academics
interested in investigating its capabilities.
Have a fairly basic Ubuntu 10.04 system without direct access
for pulling in required packages.
On Tue, 8 Feb 2011 16:30:19 -0500, Tobjan Brejicz toba...@gmail.com wrote:
Hello again,
Thank you for quick reply before. This was very helping, I now run things
correctly on that example.
But here is one new question I have.I am trying example
DemoMetaMatrixmulCheetah.py.
So the
On Thu, 10 Feb 2011 11:20:25 +0100, Fran Garcia fj.garci...@gmail.com wrote:
Hi!
I'm trying to install PyCUDA in my W7 64 bits computer with Enthought 64
bits too. I have followed the instructions shown in
http://wiki.tiker.net/PyCuda/Installation/Windows for Vista 64 bits and MVS
2008, but
On Tue, 8 Feb 2011 21:18:14 -0500, Tobjan Brejicz toba...@gmail.com wrote:
I've had similar problems with OS X, writing custom CUDA C code. Mine
were fixed with an
#include stdint.h
Thank you for helping Josh!
Well so I did make change you said. Still uint is not defined.But
Hi Tomasz,
On Wed, 09 Feb 2011 22:00:22 +0100, Tomasz Rybak bogom...@post.pl wrote:
Recently I have been playing with profiler and logger in CUDA.
Detailed description is in
http://wiki.tiker.net/ToolCheatSheet
and
Hi Tomasz,
Thanks for submitting the CURAND wrapper for inclusion in PyCUDA!
On Thu, 03 Feb 2011 12:01:55 +0100, Tomasz Rybak bogom...@post.pl wrote:
Sorry if you have received my previous mail (from 2011-02-01 22:52)
but I have not got any reply - so here I am sending it again.
I have seen
Hi Tomasz,
On Thu, 03 Feb 2011 12:01:25 +0100, Tomasz Rybak bogom...@post.pl wrote:
Sorry if you have received my previous mail (from 2011-02-01 22:52)
but I have not got any reply - so here I am sending it again.
I have seen your email from 2010-12-26. I was in Germany, so I was
able to
Hi David,
On Thu, 3 Feb 2011 17:23:52 +0200, avidday avid...@gmail.com wrote:
On Sun, Jan 30, 2011 at 7:11 AM, Andreas Kloeckner
li...@informa.tiker.net wrote:
Try calling pytools.prefork.enable_prefork before you call MPI_Init().
(PyCUDA is already prepared for this under the hood
On Mon, 14 Feb 2011 00:51:13 +0100, Tomasz Rybak bogom...@post.pl wrote:
After discussion with Martin Laprise I have come with the following code
(see attachment). It uses all available MPs, but I think it needs
some code to decide whether to use entire GPU (in case generated
vector is long)
Hi Nathan,
On Sun, 13 Feb 2011 23:05:14 -0800, Nathan Hillier nathan.hill...@gmail.com
wrote:
Hello, I'm trying to get set up with PyCUDA and I'm running into some
difficulties.
There seems to be something amiss in the PyTools package Importing
pycuda.autoinit generates the following
On Mon, 14 Feb 2011 21:03:55 +0100, Tomasz Rybak bogom...@post.pl wrote:
Dnia 2011-02-13, nie o godzinie 19:12 -0500, Andreas Kloeckner pisze:
On Mon, 14 Feb 2011 00:51:13 +0100, Tomasz Rybak bogom...@post.pl wrote:
After discussion with Martin Laprise I have come with the following code
On Mon, 14 Feb 2011 15:39:27 -0500, Lev Givon l...@columbia.edu wrote:
If one attempts to pass a slice of an existing 1D GPUArray instance to
a kernel compiled by SourceModule, an exception is raised because the
gpudata member is a longint rather than a DeviceAllocation instance.
Is there some
On Mon, 14 Feb 2011 22:15:22 +0100, Tomasz Rybak bogom...@post.pl wrote:
Added to the FAQ, also decided to add to documentation;
see attached diff.
Actually, stop the presses. I just analyzed the situation in a bit more
detail. Turns out that detach() should get called automatically. It
isn't,
On Mon, 14 Feb 2011 10:59:02 -0800, Nathan Hillier nathan.hill...@gmail.com
wrote:
Yeah, I definitely don't remember it mentioning decorator. Just to make sure
I uninstalled and tried again. Here is the full output if it is of any use:
Never mind, my bad. Should be fixed in pytools 2011.1,
On Wed, 16 Feb 2011 00:24:05 -0800, Nathan Hillier nathan.hill...@gmail.com
wrote:
Traceback (most recent call last):
File C:\Users\Nathan\workspace\PyCUDA Demo\src\main.py, line 13, in
module
)
File C:\Python27\lib\site-packages\pycuda\compiler.py, line 238, in
__init__
On Thu, 17 Feb 2011 01:25:25 -0800, Christoph Gohlke cgoh...@uci.edu wrote:
4) Delete the CUDA cache directory. I found this necessary sometimes
when switching between 32 and 64 bit CUDA.
That's a bug. I've added system bitness (in the form of sys.maxint) to
the hash key for the cache.
Hi Nithin,
On Mon, 21 Feb 2011 22:27:04 +0530, nithin s nithin19...@gmail.com wrote:
I believe there are some errors in the implementation. Im
basing my comments only on the exclusive version.
The final call to finish adds the each of the partial sums to
every element of the
Hi there,
On Sun, 20 Feb 2011 08:42:36 -0800 (PST), elafrit afrit.mar...@gmail.com
wrote:
I sent a matrix M on GPU and I need to apply some instructions on a vector
from this matrix, for example a vector containing the 3 second elements from
this matrix, but without passing by CPU.
you might
Hi Nithin,
two requests:
- can you please resend this as an attachment? It's hard to fish out of
the text of an email.
- please avoid using floating point functions (log, ceil, floor) in
integer contexts. PyCUDA comes with a bitlog2 function that does what
you need, I think.
Once I get
On Thu, 24 Feb 2011 06:12:22 -0500, Thomas Wiecki thomas_wie...@brown.edu
wrote:
Hi Lev,
thanks -- I wasn't aware GPUArray supported any slicing at all.
However, my slice index is boolean which still does not seem to be
supported (is it planned?). Any other ideas?
This could be done as a
1 - 100 of 588 matches
Mail list logo