[PyCUDA] Re: FP16 header, extern C and preamble

Vincent Favre-Nicolin writes: > 1) if there is a way to have an element-wise kernel with > no_extern_c=True - but I don’t know how to resolve the name mangling > issue to access the kernel function ? > > 2) add a ‘cpp_preamble’ option to SourceModule and ElementwiseKernel > (and others) to add a

[PyCUDA] Re: Issues with PyCUDA on Ubuntu 20.04

Vernon Perry writes: > My CUDA install was just via apt; do you suggest doing it the > old-fashioned way from Nvidia itself? Please keep the list cc'd for archival. Via apt from Ubuntu's package sources? Or from some other sources (check your /etc/apt/sources.list*)? If it was from Ubuntu, then

[PyCUDA] Re: Issues with PyCUDA on Ubuntu 20.04

Vernon Perry writes: > Hello, > > I've installed PyCUDA using several different methods, including pip, apt, as > well as compiling from source, but there is still a conflict with the version > of CUDA that I am running it would appear: > > $ nvcc --version > nvcc: NVIDIA (R) Cuda compiler

[PyCUDA] Re: PyCUDA and cuSPARSE

"Gutenkunst, Ryan N - (rgutenk)" writes: > Hello, > > I need to access the tridiagonal solving routines gtsv2StridedBatch > and gtsvInterleavedBatch from the cuSPARSE library in a Python/C > program. Is there a way to access/link to the cuSPARSE library using > PyCUDA? > > For background, I’m

[PyCUDA] Re: PyCUDA OpenGL Build for Windows 10.

Fabio da Silva writes: > Good morning, > I was wondering if there are any binaries for OpenGL enabled PyCUDA > for Windows 10. My understanding (thanks, Andreas) is that it I will > probably need to build it on my own. Since I never did that, I went > online and found some resources here >

[PyCUDA] Re: Question about PyCUDA

"thierry.moudiki" writes: > Hi Andreas, > > I'm interested in using your package PyCUDA, and I have one question about it > (just to make sure that I understand how it works). In the example presented > here: https://documen.tician.de/pycuda/index.html, when you call the sourced > function

[PyCUDA] Re: gpuarray.zeros / to_gpu crash

Dan, Please make sure the list stays cc'd for archival. "Guralnik,Dan" writes: > Andreas, I'm so sorry, should've done it myself so you have more info. Here > is what happens: > > - > C:\Users\danguralnik\Documents\GitHub\kodlab-uma-sims\mice\smooth>python > cuda_test.py >

[PyCUDA] Re: gpuarray.zeros / to_gpu crash

Dan, Do the PyCUDA example programs (e.g. [1]) work? What happens if you run the command 'nvcc'? Andreas [1] https://github.com/inducer/pycuda/blob/master/examples/demo.py "Guralnik,Dan" writes: > Hello, > > > I have just installed pycuda on a new machine running anaconda3 and cuda >

[PyCUDA] Re: [Pycuda] LogicError: cuMemcpyDtoH failed: an illegal memory access was encountered

Jie Liu writes: > Hallo, > > I have a Pycuda code, which deals with two kernels. Both kernels run well > separately, but when I put them together, there is a memory problem > "LogicError: cuMemcpyDtoH failed: an illegal memory access was encountered". > In the second kernel "DotKernel", I can't

[PyCUDA] Re: pycuda works only from the terminal

Artur, Artur Makhmutov writes: > I am not sure if this is the right place to ask for a tech support, > please ignore the message if it is not. > > My problem is described as follows: I am trying to run one of the > example scripts (I use ubuntu, pycharm with venv python virtual >

[PyCUDA] Re: GPUArray class gives negative "s" with large size gpuarray

takayanagi.tets...@jp.panasonic.com writes: > Hi, All. > I have developed Lattice Boltzmann Method Code with PyCUDA in our company for > simulating Air flow. > Then, I need to handle large gpuarray such like arr[velocity][Z][Y][X] for > 3-dimensional fluid flow. > My code run correctly

[PyCUDA] Re: How to free page-locked memory?

Rengan Xu writes: > In PyCUDA, what is the API to free the allocated page-locked memory? In > CUDA, we have cudaFreeHost(void* ptr) to free the page-locked memory, but I > didn't find the corresponding API in PyCUDA. Any help would be appreciated.

[PyCUDA] Re: LogicError: cuMemHostAlloc failed: OS call failed or operation not supported on this OS

Dear Ali, Ali Punjani writes: > We develop scientific software for molecular biology applications using > pyCUDA. A user is having a very strange issue where the same code works > perfectly fine on the same machine (with CUDA 10.1) with GTX 1060 cards, > but not with Titan XP cards. The error

[PyCUDA] Re: Bind-less Texture Patch for PyCUDA

Binu, Binu Mathew writes: > First up, as a long time user of PyOpenCL and lately PyCUDA, thank you very > much for all the effort you have dedicated to these two extremely useful > projects. > Last year, I implemented support in PyCUDA for bind-less textures that make > programming texture

[PyCUDA] Re: returned a result with an error set

Hi Ziqiao, Do you have numpy installed on your machine? That's the only thing I can think of as getting imported during import of the PyCUDA module. I've not seen that error before---have you tried building from source? Or using Christoph Gohlke's binaries? Andreas z...@asagi.waseda.jp writes:

[PyCUDA] Re: PyCuda installation - Colab

Dear Chris, Chris Fourie writes: > Thanks for the wiki on the PyCuda installation =) > > I have just installed it on Colab following a mix of the instructions. > From these two pages... > https://wiki.tiker.net/PyCuda/Installation/Linux > https://wiki.tiker.net/PyCuda/Installation/Linux/Ubuntu >

[PyCUDA] Re: Pycuda error in windows 10 Python 3.7.3 Cuda9.0

olay...@gmail.com writes: > I installed pycuda by downloading .whl file. > > When I run the command : > > import pycuda.gpuarray as gpuarray > > I get the below error: > Traceback (most recent call last): > File "", line 1, in > File "C:\Anaconda\lib\site-packages\pycuda\gpuarray.py", line

[PyCUDA] Re: Import Error: No module named compyte.dtypes

Dan Guralnik writes: > Thanks! > > Actually, I originally got the wheel from > (https://www.lfd.uci.edu/~gohlke/pythonlibs/#pycuda). > > Then I tried again after reinstalling using "pip install pycuda". > > Finally, I've just now tried building and installing the version posted > at link

[PyCUDA] Re: Import Error: No module named compyte.dtypes

Dan Guralnik writes: > Hello, > > When attempting to run pycuda (the latest 2019 version), I encounter the > following error message from python (2.7): > > -- > File "test_cuda.py", line 9, in > import pycuda.tools >File

[PyCUDA] Re: cl.exe

Hi Ajit, "Ajit Limaye" writes: > I'm just getting started with PyCUDA. I installed it with pip (on a Win-10 + > Anaconda machine using "pip install") and then tried to run the tutorial > example here: https://documen.tician.de/pycuda/tutorial.html. When I do, I > get the following error

[PyCUDA] Re: error about index type when running sparse cg example

bren...@u.northwestern.edu writes: > I'm trying to run the cg example posted at > https://andreask.cs.illinois.edu/PyCuda/Examples/SparseSolve > > where I have copied the file into one called: py_cuda_cg_test.py > > I'm testing using a 5 by 5 sparse symmetric .mm file I found here >

[PyCUDA] Re: releasing the GIL during init and make_context

Antoine Martin writes: > We use pycuda to access NVENC and our application (xpra) if very > sensitive to latency, unfortunately it seems that pycuda will hold the > GIL during driver.init() and driver.make_context() and those calls can > take hundreds of milliseconds to complete. > Is there any

Re: [PyCUDA] simple question about PyCuda

Davide Bassano writes: > Dear Mr/Mrs > > > > I have just started working with PyCuda and I have a simple question: how > can I parallel a Python code if PyCuda wants a kernel written in C? > > > > Let me clarify: I have a Python code (with classes and other things all > suitable with Python and

Re: [PyCUDA] Tricks to avoid device2device data copy when slicing the gpuarray?

黄 瓒 writes: > Hi All, > > @inducer THANK YOU for providing PyCUDA. > > As cudaMalloc could be time-consuming, it seems even slicing would include > such operation in PyCUDA, are there any tricks to avoid frequent gpu memory > operation in PyCUDA? Slicing a GPUArray

Re: [PyCUDA] Context being sporadically destroyed when using multiple threads and contexts

Noah Young writes: > I'm trying to run jobs on several GPUs at the same time using multiple > threads, each with its own context. Sometimes this works flawlessly, but > ~75% of the time I get a cuModuleLoadDataEx error telling me the context > has been destroyed. What's frustrating is that

Re: [PyCUDA] Fwd: pycude error about importError: No module named _driver

Hilary, Hilary L writes: > I a newer to install pycuda on windows 10, 64bit, with python 2.7 version, > and GPU is NVIDIA MX150. > Firstly, I have installed the vcforpython27 to compile c++ (vs2008), and > then I installed CUDA 3.2. After that, I installed the boost (boost_1_67_0). > Then, I

Re: [PyCUDA] Quick question about GPU-CUDA

Peter, Szu-Pei Fu writes: > I followed your wiki page to run pycuda/test/python test_driver.py on porter > > and got the following error message. > > E CompileError: nvcc compilation of /tmp/tmpImcdf6/kernel.cu > failed > E [command: nvcc --cubin -arch sm_52 >

Re: [PyCUDA] Can I compute the sum over only 1 dimension of a matrix?

Rasmus Diederichsen writes: > Is it possible to use Reduction operations to reduce a 2-d array to a > 1-d one, by e.g. computing the rowwise sum or some other operations? > So far I haven't been successful. No--ReductionKernel is not meant for that. Its role is to do global reductions when

Re: [PyCUDA] PyCUDA and arch flags

Aleksandar Donev writes: > We have a machine now that has both a Titan X (Maxwell) and a Titan V > (Volta) card, which have different architectures. My students/postdocs > have been running PyCUDA codes but I am not sure if we need to do > anything different in this case -- does PyCUDA

Re: [PyCUDA] import pycuda.driver fails

Harshit, Harshit Suri writes: > I had a working installation of pycuda. However, after running updates on > my Ubuntu machine; > import pycuda.driver as cuda fails. > ( I had also updated my anaconda install and updated all packages that > anaconda found that required updates ) > > When I try

[PyCUDA] [Grace Law] An invitation to talk about PyCUDA to 500+ devs at PyBay

Hi all, see below for a message from PyBay. If you're near the bay area and would like to chat about PyCUDA, this might be a good opportunity--and please also reply to Grace and me directly in case you're planning on going. Andreas --- Begin Message --- Hi Andreas Congrats on the success and

Re: [PyCUDA] Create gpuarrays on different GPUs

Zhangsheng Lai writes: > My 'can access' simply means that I'm able to access the values in the > variable in python by typing x1 or x2. My understanding is that if the > variables are stored on different GPUs, then I should be able to type x1 > and get its values when ctx1 is active and

Re: [PyCUDA] Create gpuarrays on different GPUs

Zhangsheng Lai writes: > with the setup above, I tried to check by poping ctx2 and pushing ctx1, can > I access x1 and not x2 and vice versa, popping ctx1 and pushing ctx2, I can > access x2 and not x1. However, I realise that I can access x1 and x2 in > both contexts. Can

Re: [PyCUDA] I have been through the introduction, checked the faq, where to get help on pycuda -

Dear Anthony, "Anthony Pleticos" writes: > I would like to know where people can go for 'assistance' in difficulties in > applying the pycuda. > > I could not find it in the > https://wiki.tiker.net/PyCuda/FrequentlyAskedQuestions and StackExchange > does not

Re: [PyCUDA] Example SparseSolve

This is really tech support for PyMetis (i.e. wrong list), but oh well. Just install pyublas. Andreas MarbHarmsen writes: > I'm currently trying to build a simple FEA solver in python using an > incomplete Cholesky decomposition preconditioned conjugate

Re: [PyCUDA] Invalid resource handle error

Zhangsheng Lai writes: > Hi, > > I'm trying to do some updates to a state which is a binary array. gputid is > a GPU thread class (https://wiki.tiker.net/PyCuda/Examples/MultipleThreads) > and it stores the state and the index of the array to be updated in another > class

Re: [PyCUDA] PyCUDA ImportError

MarbHarmsen writes: > My goal is to speed up my python FEA (finite elements analysis) with my > quadro GPU. I however have issues when I import pycuda.autoinit or > pycuda.driver into my python code. See the example from my Console: > > **code > In [6] import

Re: [PyCUDA] cuModuleLoadDataEx failed: device kernel image is invalid

Zhangsheng Lai writes: > Hi Andreas, > > Thanks! It worked! Can I ask if you think cuda.memcpy_peer can be > used threads for GPUs ( > https://wiki.tiker.net/PyCuda/Examples/MultipleThreads)? I think this is > more of a threading question than a PyCUDA question but would

Re: [PyCUDA] cuModuleLoadDataEx failed: device kernel image is invalid

You're prescribing the GPU architecture (arch='...'). If this doesn't match your GPU, this could easily cause this issue. Just deleting that kwarg should be fine. Andreas Zhangsheng Lai writes: > I'm encountering this error as I run my code on the same docker environment >

Re: [PyCUDA] Multithreading with a single context per process

Emanuel Rietveld writes: > If I understand correctly, the current PyCUDA multithreading examples > assume you create a separate context for each thread. > > If I want to use CUDA 4.0+'s one-context-per-process model instead, > how would I do that in PyCUDA? > > I think

Re: [PyCUDA] PyCUDA PyPy compatibility

Emanuel Rietveld writes: > I'm trying to use PyCUDA with PyPy. With these two patches it seems to work... Thanks! Merged. > Is there anything else I'd need to be mindful of? On this PyPy page > https://bitbucket.org/pypy/compatibility/wiki/Home PyCUDA is > explicitly

Re: [PyCUDA] non-contiguous array support

Syam Gadde writes: > Sorry if this comes through multiple times, I've been having problems posting > from an email alias. > > > Andreas suggested I mail the mailing list and solicit comments here. > > I submitted a pull request that adapts the element-wise kernels to

Re: [PyCUDA] PyCuda in QThread using moveToThread

David G Grier writes: > I am using pycuda to compute holograms for an optical trapping > application that uses PyQt4 for a GUI front end. I would like to move > the pycuda computation into a QThread to keep the GUI responsive. > > Is there an up-to-date working example of

Re: [PyCUDA] pyCUDA kill app with using pyQt5

안태우 writes: > Hello, all.I'm using pycuda for making simple project with pyQt5. But when I > programed like this(in Windows 10, Python 3.6.2), app is aborted with > printing bottom > logs.​---PyCUDA > ERROR:

Re: [PyCUDA] Pycuda and boost with Python 3

Chris writes: > When running Pycuda code on Python 3.6 I get this error when executing > "import pycuda.gl as cuda_gl" > > ImportError: /usr/lib/x86_64-linux-gnu/libboost_python-py27.so.1.58.0: > undefined symbol: PyClass_Type > > It looks like it is using the python 2.7 boost

Re: [PyCUDA] Please help - can't find any answer on pycuda._driver cuModuleLoadDataEx error

"Hezy, Sharon" writes: > Hello, > > I’m pretty familiar with CUDA (writing code since CUDA3.0), but PyCUDA is > quite new for me. > > I’ve been asked to configure our code that runs on CUDA 6.5, to run on > GeForce GTX 1080 (compute capability 6.1). > > OS is Windows

Re: [PyCUDA] installation pycuda2017.1.1 cuda9 debian9

Hi Christoph, christoph writes: > I am new to pycuda and would love to to install pycuda, but I fail to use > it because of the following message. > > > ExecError: error invoking 'nvcc --version': [Errno 13] Permission denied This points to an issue with your CUDA

Re: [PyCUDA] MemoryError: cuCtxCreate failed: out of memory

Arnold Tunick writes: > Hi Andreas,     my CNN training program has the following pycuda set up: >     import pycuda.driver as drv...    # pycuda set up >     drv.init() >     dev = drv.Device(int(config['gpu'][-1])) >     ctx = dev.make_context() > When I run the program I

Re: [PyCUDA] test program hello_gpu.py and simplespeedtest.py

ephi5757 writes: > Hi Andreas > I found that the pycuda .whl was a combination install for pycuda 2017.1.1 + > Cuda 8.0.6.1 for win64 and python 3.6. > > I suspect that while the install was successful my test programs are failing > because I have Cuda 9.0. > > I am home

Re: [PyCUDA] test program hello_gpu.py and simplespeedtest.py

Arnold Tunick writes: > Hi Andreas,    I tried to reinstall pycuda from within my Miniconda3 command > window, i.e., using the command... pip install pycuda.    Everything goes > well in the build until it tries to execute the following: >    

Re: [PyCUDA] test program hello_gpu.py

Use dependency walker on _driver.pyd/dll to find the DLL you're missing. Andreas Arnold Tunick writes: > FYI, I used pip install  > pycuda-2017.1.1+cuda8061-cp36-cp36m-win_amd64.whl.. > > On ‎Wednesday‎,

Re: [PyCUDA] 3D rotation on PyCuda

ghum writes: > copy(aligned=True) > > return ary > > Is there another way to generate a 3D pycuda texture? Or maybe I am close to > fix the issue, for now I am getting the following error: > > Boost.Python.ArgumentError: Python argument types in >

Re: [PyCUDA] Pycuda installation with cuda-9.0

Baskaran, Baskaran Sankaran writes: > I am having hard time installing PyCUDA with cuda-9.0 on rhel7. Thanks for the report. CUDA 9 support was added to git a while back but was not yet part of a release. I've just released 2017.1.1 that should address (at least some of)

Re: [PyCUDA] PyCUDA installation troubles

"Burdge, Kevin B." 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

Re: [PyCUDA] Windows <--> Linux interchangeable code?

Benedikt, Benedikt Kopp writes: > I'm having a few problems with pycuda in combination with Ubuntu 16.04 and > cuda 8.0. > > I've tried to make a minimal working error-example that I run on both > Windows and Linux: You may notice that you're passing a numpy.int32 for the

Re: [PyCUDA] Handle Error in CUDA Kernel

"Rana, Sanjay" writes: > Are there any examples out there on ways to catch and handle errors in the > CUDA Kernel code ? > I have seen examples for CUDA programming in C/C++ but not so many for pycuda. Could you point us towards those examples? That would make it

Re: [PyCUDA] c1xx : fatal error C1083: Cannot open source file: 'kernel.cu': No such file or directory

Hi Sanjay, "Rana, Sanjay" writes: > Yeah. Also note that the AutoRun registry setting (i.e. the default > folder that opens when cmd is run) also causes problem even building > the C++(?) CUDA samples in the Microsoft Visual Studio IDE. > > I think it's quite

Re: [PyCUDA] c1xx : fatal error C1083: Cannot open source file: 'kernel.cu': No such file or directory

Hi Sanjay, "Rana, Sanjay" writes: > After several days of frustatation, I managed to get it working and > the reason, which I suspected before while reading through the verbose > log, but didn't think could be as simple as that and thus discarded, > turns out to be

Re: [PyCUDA] c1xx : fatal error C1083: Cannot open source file: 'kernel.cu': No such file or directory

"Rana, Sanjay" writes: > Thanks Andreas for the response. How could I check whether nvcc is work the > same way on both computers? Compile some sample cuda code. > On the problematic installation, I did try running the nvcc from a command > prompt. I only get the

Re: [PyCUDA] c1xx : fatal error C1083: Cannot open source file: 'kernel.cu': No such file or directory

"Rana, Sanjay" writes: > Hi Everyone, > > I have an identical set up of pycuda on two computers as follow : > > Windows 10 64bit > CUDA 8.0 > Pycuda 2017.1+cuda8061-cp27-cp27m-amd64.whl > Visual Studio 2013 Community > > This works perfectly on one of the computers

Re: [PyCUDA] Pycuda install: gcc: error: /EHsc: No such file or directory

张鲁宁 writes: > Hello! > Excuse me,I have met an error when i was installing the pycuda , i tried > many times but it didnt work,i already have compiled boost(by visual studio > 2010), and installed the cuda 8.0 .Here is the error traceback and my > siteconf.py. > > >

Re: [PyCUDA] Installation on Ubuntu 14.04

Guillaume Androz writes: > Hi, > I'm trying to install pyCuda 2016.1.2 on Mint 17.3 (same as Ubuntu 14.04), > I follow the procedure found at > https://wiki.tiker.net/PyCuda/Installation/Linux/Ubuntu, but I keep having > the same error > > In file included from

Re: [PyCUDA] CUDA driver compute mode

Kambiz Tavabi writes: > Following TB from test_driver.py with 2016.1.2 build on OS X 10.11 with > CUDA 8 V8.0.61; was able to workaround by changing > > if drv.Context.get_device().compute_mode == drv.compute_mode.*EXCLUSIVE*: > > to > > if drv.Context.get_device().compute_mode

Re: [PyCUDA] [PyOpenCL] New architectures for PyOpenCL in Debian

Tomasz Rybak <tomasz.ry...@post.pl> writes: > On Mon, 2016-11-21 at 22:46 -0600, Andreas Kloeckner wrote: > [ cut ] >> At the same time I have a question for you Andreas. There will be >> > freeze of Stretch on 2017-01-05. I’d like to upload PyOpenCL and >&

Re: [PyCUDA] undefined symbol error

Chris writes: > Hey Andreas, > I am having a similar issue that Kambiz Tavabi was having. Here is the error > (I have pycuda on anaconda2 just like Kambiz) > > File "main_class.py", line 17, in > import pycuda.gl as cuda_gl > File >

Re: [PyCUDA] pipwin error with runpy.py

"Slein, Ryan" writes: > I've spent a few days digging through forums without any luck so I figured > I'd post to the mailing list as per request of the forums. Any advice would > be greatly appreciated. I am new to python and cuda, and entirely > self-taught, so sorry in

Re: [PyCUDA] Autoinit failing after driver update

Josh Willis writes: > Hi, > > After updating the NVIDIA driver from 367.48 to 375.26, I can no longer get > PyCUDA to run. I have tried a fresh build of PyCUDA-2016.1.2, and the > configure/make/make install steps seem to proceed fine. However if I do: > > $ python >

Re: [PyCUDA] Elementwise operations on noncontiguous arrays

Keegan Owsley writes: > Something that I don't think I made clear before: the kernels generated by > get_elwise_module_noncontig are modified using regular expressions, so that > you don't need to change your code downstream to get strided array support. > I'm not convinced yet

Re: [PyCUDA] Unable to free shared memory array after pagelocking with register_host_memory

Jaroslaw, Jaroslaw Blusewicz writes: > I'm using numpy-sharedmem > to allocate shared memory array across multiple cpu processes. However, > after page locking it with register_host_memory, the shared memory is

Re: [PyCUDA] Elementwise operations on noncontiguous arrays

Keegan, Keegan Owsley writes: > I've just slapped together a patch to pycuda that makes most elementwise > operations work with noncontiguous arrays. There are a bunch of hacks in > there, and the code needs some reorg before it's ready to be considered for > upstream (I made

Re: [PyCUDA] Tests fail with ImportError _driver.so: undefined symbol

Kambiz Tavabi writes: > I am at a complete loss. I did a fresh reinstall of the OS (ubuntu 16.04) > and the first thing I did was: > > >- apt update; sudo apt upgrade >- apt-get install nvidia-cuda-toolkit nvidia-361 nvidia-modprobe >- Build install pycuda as before;

Re: [PyCUDA] Tests fail with ImportError _driver.so: undefined symbol

Kambiz Tavabi writes: > Hi > > I am Trying to get packages including pycuda-2016.1.2 working in a python > 2.7 (Anaconda) environment. I am Running Ubuntu 1604 with working nvidia > driver and CUDA 8. > I installed pycuda via > > $ git clone http://git.tiker.net/trees/pycuda.git

Re: [PyCUDA] Stopping Criterion in for loops

slegrand writes: > Hello everybody, > > I'm currently using pycuda and scikit-cuda to parallelize a simple code. > Basically I repeat this structure inside a for loop: > > 1-matrix/vector product (cublas.cublasDgemv) > > 2-elementwise division(cumisc.divide) > >

Re: [PyCUDA] Pixel Buffer Object Mapping Pointer

Chris writes: > I know that PyCUDA runs on the driver API, so it might be a little different > but I am looking for the equivalent of something like this > cudaGraphicsResourceGetMappedPointer(). I am manipulating an array in CUDA > and need to point the PBO to it so that it can

Re: [PyCUDA] pycuda ImportError: DLL load failed: The specified module could not be found.

Daniel Gebreiter writes: > Andreas,thanks for the quick response. Here's the link to the gist, as > per your > request:https://gist.github.com/anonymous/204d33ca84a211b2323fa9d8886d0371I > hope this works and helps resolving the issue!Thanks,Daniel This linker errors

Re: [PyCUDA] PyCuda - Bindless Textures

Chris writes: > I figure this will take a long time to implement, is there anywhere that > displays the tentative additions to PyCUDA so I can keep myself updated on > when this might be implemented? It's really not like I've got a schedule of these things. "When I need it" or

Re: [PyCUDA] PyCuda - Bindless Textures

Chris writes: > I saw that there was a post about this in 2014 and I can't find anything > about whether bindless textures were supported yet. IIRC this hasn't happened yet. I'd be happy to take a patch though. Andreas ___ PyCUDA

Re: [PyCUDA] PyCUDA rng question

Hi Peter, Please send messages like this to the mailing list in the future. There's some drama going on with Gmane, but it should be back up at some point. In the meantime, Mailman and the conventional archives are still available. Peter Walsh writes: > I have a question

Re: [PyCUDA] Questions about PyCUDA from a former CS450 student

Yiming Peng writes: > Hi Andreas​, > > I am a former student of your CS 450 and now I am a incoming PhD student in > operations research at Northwestern. > > Since I am interested in applying parallel computing, preferably using > Python, to my future research, I have

Re: [PyCUDA] Pycuda multiple gpus

Irving Enrique Reyna Nolasco writes: > I am a student in physics. I am pretty new > in pycuda. Currently I am interesting in finit volume methods running on > multiple GPUS in a single node. I have not found relevant documentation > related to

Re: [PyCUDA] New to OpenGL Interoperability

Hi Chris, Not sure what you're asking. The code you show doesn't apply--it uses the 'runtime API' (cudaXyz...), PyCUDA uses the 'driver API' (cuXyz...). And the piece of Peter's example that worries about exchanging data with PyCUDA (lines 162-192) is about the same in complexity as what you're

Re: [PyCUDA] Dynamic Parallelism

Hi Eric, Sorry about the long delay in getting back to you. Eric Scheffel writes: > I am trying to use Pycuda with a device kernel which recursively calls > itself via dynamic parallelism. I do this with a 750Ti so it should be > supported. I have also done some

Re: [PyCUDA] Problems building PyCUDA documentation

Tomasz Rybak writes: > Would you apply this patch in repository?? > Debian has policy that python means Python 3, and python3 is for Python 3 > interpreter. > If not - that's not a problem, now it is automatically applied during > building of Debian packages. Done.

Re: [PyCUDA] Problems building PyCUDA documentation

Tomasz Rybak writes: > I was trying to rebuild PyCUDA 2016.1.1 (as tagged on GitHub) package using > CUDA 7.5 and Sphinx 1.4.4. > There was warning regarding http to https redirect on documen.tician.de, > patch below: > Index: pycuda-2016.1.1/doc/source/conf.py >

Re: [PyCUDA] [Support Request] How to pass a list of lists to a Py CUDA Kernel?

Hi Frank, Frank Ihle writes: > I try to speed up my Python program with a not so trivial algorithm, so > I need to know. What is the correct way of transferring a list of lists > of floats to the (Py)CUDA Kernel? Nested, variable-sized structures are generally tricky to

Re: [PyCUDA] Pycuda Device Detection

AlexG writes: > Hello, > > I have a question on the cuda capable device detection using pycuda. > Does the driver.Device.count() function detect each gpu on dual gpu cards > such as > the nvidia K2 or K80 cards as separate?, that is if I have one K2 card > installed > does the

[PyCUDA] ARRAY'16: Workshop on Libraries, Languages and Compilers for Array Programming

Hi all, I imagine that one of the main things that PyOpenCL and PyCUDA get used for are computations with large arrays. As such, I can imagine that many of you are sympathetic to the cause of trying to come up with simpler abstractions that nonetheless yield high-performance code for such

Re: [PyCUDA] pycuda 2015.1.3 test_driver.py fails once

Dorin Niculescu writes: > Hi all, > I have a fresh installed ubuntu 14.04.3 distribution, with cuda 7.0 and > pycuda 2015.1.3. I'm using an NVIDIA GTX 960 card and the latest driver > 361.28. All the installation went well but when i run test_driver.py i get : >

Re: [PyCUDA] Installing pycuda on Win 10 notebook

Arnold Tunick writes: > 1. Updated to Visual Studio 20132. Updated to CUDA 7.5.183. downloaded pip > and pipwin and pycuda-2015.1.3+cuda7518-cp27-none-win_amd64.whl4. easily > installed pycuda by running ... >>install >

Re: [PyCUDA] BOOST dependency needed or not?

ra...@blue.alter.pl writes: >>> Here is error message during pycuda attempt: >>> >>> radek@black:~/pycuda-2015.1.3$ python setup.py build >>> running build >>> running build_py >>> running build_ext >>> building '_driver' extension >>> x86_64-linux-gnu-gcc -pthread -fwrapv -Wall -O3 -DNDEBUG >>>

Re: [PyCUDA] Not working after update

It's possible that PyCUDA didn't get entirely rebuilt. In the source directory, do rm -Rf build and then repeat the build. A workaround for the time being is to simply use the shipped version of boost. HTH, Andreas Robert writes: > Oh I posted the wrong error

Re: [PyCUDA] GPU selection (round robin)

Keith Brown writes: > I have several GPUs and I want to distribute my tasks to each GPU. I > would like to use multiprocessing.Pool() to accomplish it > > import random > import pycuda.gpuarray as gpuarray > import atexit > import pycuda.driver as cuda > import

Re: [PyCUDA] Pycuda and RDMA transfer

Baskaran Sankaran writes: > Apologies for emailing you directly. I did subscribe to the PyCuda mailing > list, but my request is not approved yet. There is no approvals process. It's likely that the subscription request went to your spam folder. I've CC'd the list. Maybe

Re: [PyCUDA] General question about CUDA compiler and early returns

Walter White writes: > Hello, > > I have a question and hope that you can help me. > I am trying to find the bottleneck in my code but I can't get a > grip at the moment. > > For a while I thought it was the writes to global memory > At the moment I am using an early

Re: [PyCUDA] device pointer to cudaArray?

Luke Pfister writes: > I'm trying to allocate a 3D cudaArray in PyCUDA, then pass the pointer to > this array through Cython. T > > This is easy to do with 'regular' memory on the device via the GPUarray > class; I can just cast GPUarray.gpudata to long and then pass

Re: [PyCUDA] Sharing a common index within a block

Joe writes: > in the meantime I added a scan function to find out how many > indices will be written by a specific thread. > These results are written to shared memory and it works > fine. > > However, the final writing of the results to global memory > is very slow and

Re: [PyCUDA] Questions on pinned memory

Walter White writes: > Hello, > > I have a question about pinned memory and hope that you can help me. > > I found out that copying data from device to host takes > a very big part of my runtime, so I read about the issue > and came across "pinned memory". > > There are

Re: [PyCUDA] updating pycuda pypi package

Tomasz Rybak tomasz.ry...@post.pl writes: Dnia 2015-06-30, wto o godzinie 14:50 -0500, Andreas Kloeckner pisze: [ cut ] configure.py is incorrect. It contains: from __future__ import #! /usr/bin/env python and because shebang is not in the first line I have troubles building

Re: [PyCUDA] updating pycuda pypi package

Scott, Scott Gray sg...@nervanasys.com writes: I'm curious if you noticed this little project: https://github.com/NVIDIA/pynvrtc With cuda 7, it seems like that could be leveraged to replace forking off an instance of nvcc. I think compiling cuda-c in this way should be much faster. I'm

Re: [PyCUDA] updating pycuda pypi package

Alex Park a...@nervanasys.com writes: Was wondering if it would be possible for you to submit the more recent pycuda version up to pypi to serve as the default version. We've made nervanagpu dependent on some of the async features and are concerned that some users might have trouble figuring

  1   2   3   4   5   6   >