Hi,
I want to run element-wise computations on different parts of an
array. Loading each part of the array to device mem when needed turned
out to use up a lot of time and not really speed things up compared to
cpu. Instead, I want to once load the data array into device mem and
provide pointers
24, 2011 at 10:29 AM, Andreas Kloeckner
li...@informa.tiker.net wrote:
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
at 11:22 AM, Thomas Wiecki thomas_wie...@brown.edu wrote:
Hi,
I always got these warnings while compiling, but now it seems they
lead to a compile error:
pycuda.driver.CompileError: nvcc said it demoted types in source code
it compiled--this is likely not what you want.
My function
This is with the version from the trunk
(7804dc6d1b40b506b02a5f7a0b7bde8771f1446c).
import pycuda.driver as cuda
import pycuda.compiler
import pycuda.autoinit
import pycuda.gpuarray as gpuarray
from pycuda.elementwise import ElementwiseKernel
zero_kernel = ElementwiseKernel(
float *out,
...@informa.tiker.net wrote:
On Wed, 29 Jun 2011 12:56:09 -0400, Thomas Wiecki thomas_wie...@brown.edu
wrote:
This is with the version from the trunk
(7804dc6d1b40b506b02a5f7a0b7bde8771f1446c).
import pycuda.driver as cuda
import pycuda.compiler
import pycuda.autoinit
import pycuda.gpuarray
On Thu, Jun 30, 2011 at 12:02 AM, Andreas Kloeckner
li...@informa.tiker.net wrote:
On Wed, 29 Jun 2011 15:21:13 -0400, Thomas Wiecki thomas_wie...@brown.edu
wrote:
As regards to parameter input checking, would it be possible to have a
switch for type-checking as an argument to ElementWise
On Thu, Dec 8, 2011 at 3:37 PM, Thomas Wiecki thomas_wie...@brown.edu
wrote:
Hi,
I want to simulate many noisy brownian motion particles. So for each
particle I have to sum up random numbers repeatedly. I figured I'd
create a function that simulates one particle movement in cuda c
curand_normal_double(). If you compile for an architecture that does not
support doubles, you get this harmless warning.
On Dec 8, 2011, at 8:41 PM, Thomas Wiecki wrote:
Thanks, that worked like a charm!
I am trying to save back the state of the generator, like this (copied
it from
:37 PM, Thomas Wiecki thomas_wie...@brown.edu
wrote:
Hi,
I want to simulate many noisy brownian motion particles. So for each
particle I have to sum up random numbers repeatedly. I figured I'd
create a function that simulates one particle movement in cuda c and
import it to pycuda via
The problem is that I don't want an array of random numbers in the end
(as your code does), but want to pass generators to a cuda function
that then simulates a stochastic process. So I need access to the
curandState.
On Fri, Dec 9, 2011 at 5:38 AM, Tomasz Rybak bogom...@post.pl wrote:
Excuse me
() creates the maximum number of
curandStates? What happens when I call my function with idx being
greater than this number?
On Fri, Dec 9, 2011 at 8:12 AM, Tomasz Rybak bogom...@post.pl wrote:
Dnia 2011-12-09, pią o godzinie 08:01 -0500, Thomas Wiecki pisze:
The problem is that I don't want
Is there a variable that will tell me number of available threads?
On Fri, Dec 9, 2011 at 11:36 AM, Tomasz Rybak bogom...@post.pl wrote:
Dnia 2011-12-09, pią o godzinie 11:06 -0500, Thomas Wiecki pisze:
That does seem to work. Its actually what I initially thought of doing
(but didn't know
will try my hands at a doc patch but am not sure when I can get to it.
Thomas
On Sun, Dec 11, 2011 at 11:18 PM, Andreas Kloeckner
li...@informa.tiker.net wrote:
On Thu, 8 Dec 2011 20:57:22 -0500, Thomas Wiecki thomas_wie...@brown.edu
wrote:
OK, but it's bailing on this warning, any way I can
When running the GPUArray unittest, almost all of them (37/45) fail.
The most common error message is:
ValueError: unable to map dtype 'uint32'
Not sure what the problem is. I am happy to provide the full log on request.
Most recent pycuda under kubuntu 11.10.
DTYPE_TO_NAME[dtype]
*** KeyError: dtype('uint32')
!?,
Thomas
On Tue, Dec 13, 2011 at 8:49 PM, Thomas Wiecki thomas_wie...@brown.edu wrote:
I updated the submodules and reinstalled, but am still get the same errors.
On Tue, Dec 13, 2011 at 7:09 PM, Andreas Kloeckner
li...@informa.tiker.net wrote
1.5.1, the ubuntu oneiric default it seems:
http://packages.ubuntu.com/oneiric/python-numpy
On Wed, Dec 14, 2011 at 9:33 AM, Andreas Kloeckner
li...@informa.tiker.net wrote:
On Wed, 14 Dec 2011 09:15:19 -0500, Thomas Wiecki thomas_wie...@brown.edu
wrote:
This is getting very weird. I went
http://developer.nvidia.com/content/cuda-platform-source-release
___
PyCUDA mailing list
PyCUDA@tiker.net
http://lists.tiker.net/listinfo/pycuda
at it longer I could figure out what is going on. Also, is there
any way using this module to specify the number of states you want?
On Mon, Dec 12, 2011 at 5:45 AM, Thomas Wiecki thomas_wie...@brown.edu
wrote:
Hi Andreas,
yes, the warning is still an issue. I just removed the raised
exception
...@informa.tiker.net wrote:
On Fri, 30 Dec 2011 20:03:44 +0100, Thomas Wiecki thomas_wie...@brown.edu
wrote:
Hi Andreas,
glad to see that you followed up on this issue. I will try to boil it
down but noticed that when I was investigating the issue back then I
could not easily reproduce
Seems like it is a 32 bit bug, I replicated it on another 32 bit
machine and filed a bug report:
http://projects.scipy.org/numpy/ticket/2017
As for a temporary fix, I also register uintp32 (and intp32 for good
luck) to DTYPES_TO_CTYPES which seems to do the trick (on 64 bit it
will just overwrite
on why that might be or how to investigate this further?
Thanks,
Thomas
On Thu, Jan 12, 2012 at 3:44 PM, Tomasz Rybak tomasz.ry...@post.pl wrote:
On Sun, 2011-12-18 at 20:25 +0100, Thomas Wiecki wrote:
I think it just allocates the maximum number. Previously I wondered
how I could find
Hi Peter,
this has been fixed (or rather, worked around at) a little bit more
cleanly in the version in the git repo to which you might want to
upgrade to.
Thomas
On Wed, Feb 1, 2012 at 12:28 PM, Peter Rösch
peter.roe...@hs-augsburg.de wrote:
I'm as confused as you. Can you go up the call
: = fixed
* milestone: Unscheduled = 1.7.0
Comment:
Fixed in 39029f5..bb7e5e2
On Tue, Jan 17, 2012 at 2:29 AM, Andreas Kloeckner
li...@informa.tiker.net wrote:
Great, thanks!
Andreas
On Tue, 17 Jan 2012 08:07:19 +0100, Thomas Wiecki thomas_wie...@brown.edu
wrote:
Not following that list
Do you mind posting the final code here for future reference (as a
gist perhaps)?
Also, another optimization might be to remove the (slow) sqrt() in
each distance calculation and then do sqrt() of the bin labels in the
reduction step.
On Fri, Apr 6, 2012 at 3:56 AM, Francisco Villaescusa Navarro
On Tue, May 22, 2012 at 6:31 PM, Andreas Kloeckner
li...@informa.tiker.net wrote:
On Tue, 22 May 2012 18:21:56 -0400, Thomas Wiecki thomas_wie...@brown.edu
wrote:
On Tue, May 22, 2012 at 4:40 PM, Andreas Kloeckner
li...@informa.tiker.net wrote:
On Tue, 22 May 2012 15:56:33 -0400, Thomas
On Mon, Jan 30, 2012 at 8:21 PM, Andreas Kloeckner
li...@informa.tiker.net wrote:
On Sat, 28 Jan 2012 18:21:29 -0500, Thomas Wiecki thomas_wie...@brown.edu
wrote:
I am currently revisiting this but having some problems with the
random number generator.
generator.generators_per_block is 512
Hi,
I get:
Traceback (most recent call last):
File sim_drift_gpu.py, line 4, in module
import pycuda.gpuarray as gpuarray
File
/usr/local/lib/python2.7/dist-packages/pycuda-2011.2.2-py2.7-linux-i686.egg/pycuda/gpuarray.py,
line 3, in module
import pycuda.elementwise as elementwise
Sorry for posting to PyCuda, not sure where else this would fit.
The CodePy unittests give me:
==
ERROR: Failure: TypeError (No registered converter was able to produce
a C++ rvalue of type unsigned long long from this Python
I can't get the CodePy Thrust example to work:
Traceback (most recent call last):
File thrust_demo.py, line 95, in module
c = module.host_entry(b)
TypeError: No registered converter was able to produce a C++ rvalue of
type unsigned int from this Python object of type DeviceAllocation
I
involve editing
your aksetup defaults file.
- bryan
On May 26, 2012, at 9:33 AM, Thomas Wiecki thomas_wie...@brown.edu wrote:
I can't get the CodePy Thrust example to work:
Traceback (most recent call last):
File thrust_demo.py, line 95, in module
c = module.host_entry(b)
TypeError
,
Apostolis
2012/5/26 Andreas Kloeckner li...@informa.tiker.net
On Sat, 26 May 2012 14:59:28 -0400, Thomas Wiecki
thomas_wie...@brown.edu wrote:
I tried using the shipped version (bpl_subset) but couldn't get it to
work somehow (how is one supposed to get the lib files?).
I now set
and fix it as soon as i have more time in my hands.
Thanks for the help anyway.
Apostolis
2012/5/27 Thomas Wiecki thomas_wie...@brown.edu
On Sun, May 27, 2012 at 1:25 PM, Apostolis Glenis apostgle...@gmail.com
wrote:
After google searching i found no -lboost_python-gcc43-mt so I suspect
Hi,
I saw a couple of times the following idiom being used:
const int tidx = blockIdx.x*blockDim.x + threadIdx.x;
const int delta = blockDim.x*gridDim.x;
curandState local_state = global_state[tidx];
for (int idx = tidx; idx n; idx += delta)
{
Hi,
the curandom Generator class initializes generators_per_block number of
generators. This is the relevant code:
@property
@memoize_method
def generators_per_block(self):
return min(kernel.max_threads_per_block
for kernel in self._kernels())
On my machine
As this seems to be the codepy/cgen thread I thought I'd tack this on here.
I want to port thrust code that is a little bit more involved than the sort
example. Namely the example code for summary statistics (
http://code.google.com/p/thrust/source/browse/examples/summary_statistics.cu
)
I think
35 matches
Mail list logo