PyOpenCL March 2013

pyopencl@tiker.net

5 participants
13 discussions

Invalid command Queue when using big data sets on nVidia

by Justin Heinermann

Dear all, we are trying to implement a K nearest neighbor search on GPUs with PyOpenCL. The goal of the algorithm is: For a given target point, find the nearest points from a given set (training data). The distance between two points is computed by the squared euclidean distance. One of our implementations is a brute force approach, which aims at processing big data sets in parallel, e.g. 1 million training data and some millions of targets (test data). For every target point one kernel instance is created which finds the k nearest points out of the training points. Our problem is the following. Everything works fine for small data sets and the results are as expected on both GPU (GeForce GTX 650 with nVidia Driver 313.09.) and CPU(Intel Core i5-3450 with AMD APP SDK) running Ubuntu 12.10, PyOpenCL 2013.1-py2.7-linux-x86_64. But if we increase the size of the data sets, the GPU version crashes with the following error: > File "brutegpu.py", line 65, in query > cl.enqueue_copy(self.queue, d_min, self.d_min_buf).wait() > File "/usr/local/lib/python2.7/dist-packages/ > pyopencl-2013.1-py2.7-linux-x86_64.egg/pyopencl/__init__.py", > line 935, in enqueue_copy > return _cl._enqueue_read_buffer(queue, src, dest, **kwargs) > pyopencl.LogicError: clEnqueueReadBuffer failed: invalid command queue The CPU-Version still works fine with 1 million training points and 1 million of test points. Attached you can find the corresponding source code as working minimal example, which consists of on Host-Python-File and one OpenCL-Kernel-File. We would highly apprecriate any help - maybe we made a mistake which is already known to you. So the big question for us is: Why is it working on CPU and why isn't it working on the GPU? Are there nVidia-specific pitfalls for such big data sets? The compiler says: > ptxas info : Compiling entry function 'find_knn' for 'sm_30' > ptxas info : Function properties for find_knn > 0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads > ptxas info : Used 17 registers, 336 bytes cmem[0], 4 bytes cmem[3] Or are there any rules for using a kernel for big data sets such as setting the work group sizes or maximum memory usage? The error message "invalid command queue" is confusing and I wasn't able to find any helpful information (except that oftentimes "invalid command queue" means segfault, but i could not find any wrong array adress yet.) Maybe one of you could have a look at our code and finds some stupid mistake. We would be very grateful for every hint. Best regards, Justin Heinermann, University Oldenburg

5 years, 10 months

Segmentation fault in pyopencl.image_from_array

by Jerome Kieffer

Dear Python/OpenCL community, I am pretty new (py)opencl and encountered a problem, maybe it a lack of understanding of openCL, but I found strange python seg-faults: test program: #!/usr/bin/python import numpy, pyopencl ctx = pyopencl.create_some_context() data=numpy.random.random((1024,1024)).astype(numpy.float32) img = pyopencl.image_from_array(ctx, ary=data, mode="r", norm_int=False, num_channels=1) print img System: debian sid: pyopencl2012.1 (the same code works with debian stable and v2011.2) Here is the backtrace obtained with GDB: 0x0000000000000000 in ?? () (gdb) bt #0 0x0000000000000000 in ?? () #1 0x00007ffff340c253 in pyopencl::create_image_from_desc(pyopencl::context const&, unsigned long, _cl_image_format const&, _cl_image_desc&, boost::python::api::object) () from /usr/lib/python2.7/dist-packages/pyopencl/_cl.so #2 0x00007ffff342de36 in _object* boost::python::detail::invoke<boost::python::detail::install_holder<pyopencl::image*>, pyopencl::image* (*)(pyopencl::context const&, unsigned long, _cl_image_format const&, _cl_image_desc&, boost::python::api::object), boost::python::arg_from_python<pyopencl::context const&>, boost::python::arg_from_python<unsigned long>, boost::python::arg_from_python<_cl_image_format const&>, boost::python::arg_from_python<_cl_image_desc&>, boost::python::arg_from_python<boost::python::api::object> >(boost::python::detail::invoke_tag_<false, false>, boost::python::detail::install_holder<pyopencl::image*> const&, pyopencl::image* (*&)(pyopencl::context const&, unsigned long, _cl_image_format const&, _cl_image_desc&, boost::python::api::object), boost::python::arg_from_python<pyopencl::context const&>&, boost::python::arg_from_python<unsigned long>&, boost::python::arg_from_python<_cl_image_format const&>&, boost::python::arg_from_python<_cl_image_desc&>&, boost::python::arg_from_python<boost::python::api::object>&) () from /usr/lib/python2.7/dist-packages/pyopencl/_cl.so #3 0x00007ffff342e06f in boost::python::detail::caller_arity<5u>::impl<pyopencl::image* (*)(pyopencl::context const&, unsigned long, _cl_image_format const&, _cl_image_desc&, boost::python::api::object), boost::python::detail::constructor_policy<boost::python::default_call_policies>, boost::mpl::vector6<pyopencl::image*, pyopencl::context const&, unsigned long, _cl_image_format const&, _cl_image_desc&, boost::python::api::object> >::operator()(_object*, _object*) () from /usr/lib/python2.7/dist-packages/pyopencl/_cl.so #4 0x00007ffff311715b in boost::python::objects::function::call(_object*, _object*) const () from /usr/lib/libboost_python-py27.so.1.49.0 #5 0x00007ffff3117378 in ?? () from /usr/lib/libboost_python-py27.so.1.49.0 #6 0x00007ffff3120593 in boost::python::detail::exception_handler::operator()(boost::function0<void> const&) const () from /usr/lib/libboost_python-py27.so.1.49.0 #7 0x00007ffff3445983 in boost::detail::function::function_obj_invoker2<boost::_bi::bind_t<bool, boost::python::detail::translate_exception<pyopencl::error, void (*)(pyopencl::error const&)>, boost::_bi::list3<boost::arg<1>, boost::arg<2>, boost::_bi::value<void (*)(pyopencl::error const&)> > >, bool, boost::python::detail::exception_handler const&, boost::function0<void> const&>::invoke(boost::detail::function::function_buffer&, boost::python::detail::exception_handler const&, boost::function0<void> const&) () from /usr/lib/python2.7/dist-packages/pyopencl/_cl.so #8 0x00007ffff3120373 in boost::python::handle_exception_impl(boost::function0<void>) () from /usr/lib/libboost_python-py27.so.1.49.0 #9 0x00007ffff3115635 in ?? () from /usr/lib/libboost_python-py27.so.1.49.0 Thanks for your help. If you are not able to reproduce this bug, I should mention it to debian. Cheers, -- Jérôme Kieffer Data analysis unit - ESRF

6 years, 4 months

create Event from cl_event

by Gregor Thalhammer

Dear Andreas, I am currently working on a cython based wrapper for the OpenCL FFT library from AMD: https://github.com/geggo/gpyfft For this I need to create a pyopencl Event instance from a cl_event returned by the library. I attached a patch against recent pyopencl that adds this possibility, similar to the from_cl_mem_as_int() method of the MemoryObject class. Could you please add this to pyopencl. Thanks for your help Gregor

6 years, 11 months

New version and prefix scan problems

by Tomasz Rybak

Sorry if there are two copies of this message. I have sent it to the list but received no confirmation (nor any error) and checked that archive does not show any message from January. I can see that there is already new version (2013.1) in docs, marked "in development". I would like for it not to be released before fixing problems with parallel prefix scan. Problems with scan are only visible on APU Loveland. They do not occur on ION, nor on GTX 460. I do not have access to machine with NVIDIA CC 3.x so I cannot test prefix scan there. I first encountered it in August, and mentioned them in email to the list from 2012-08-08 ("Python3 test failures"). Only recently I had some time and eagerness to look closer into them. Tests still fail on recent git version c31944d1e81a. Failing tests are now in test_algorithm.py, in third group (marked scan-related, starting in line 418). I'll describe my observations of test_scan function. My APU has 2 Computing Units. GenericScanKernel chooses k_group_size to be 4096, max_scan_wg_size to be 256, and max_intervals to 6. The first error occurs when there is enough work to fill two Computing Units - in my case 2**12+5. It looks like there is problem with passing partial result from computations occurring on fist CU to the second one. Prefix sum is computed correctly on the second half of the array but starting with the wrong point. I have printed interval_results array and I have observed that error (difference between the correct value of the interval's first element and actual one) is not the value of any of the elements of interval_results, nor it is difference between interval_results elements. On the other hand difference between real and wanted value is similar (i.e. in the same range) to the difference between interval_results[4] and interval_results[3]. In the test I have run just now the error is 10724571 and the difference is 10719275; I am not sure if this is relevant though. Errors are not repeatable - sometimes they occur for small arrays (e.g. for 2**12+5) sometimes for larger ones (test I have run right now failed for ExclusiveScan of size 2**24+5). The tests' failures also depend on order of tests - after changing order of elements of array scan_test_counts I got failures for different sizes, but always for sizes larger than 2**12. It might be some race condition, but I do not understand new scan fully and cannot point my finger at one place. If there is any additional test I can perform please let me know. I'll try to investigate it further but I am not sure whether it'll work. Best regards. -- Tomasz Rybak GPG/PGP key ID: 2AD5 9860 Fingerprint A481 824E 7DD3 9C0E C40A 488E C654 FB33 2AD5 9860 http://member.acm.org/~tomaszrybak

7 years, 2 months

Re: [PyOpenCL] Abort on MacOSX 10.6

by Conversy Stéphane

Hello everyone, I still have the same problems, I could not fix them. I followed the instructions on the wiki about installing on mac... Maybe this error : > examples/demo_array.py gives: > File "/Library/Frameworks/Python.framework/Versions/7.3/lib/python2.7/site-packages/pyopencl-2013.1-py2.7-macosx-10.5-i386.egg/pyopencl/compyte/dtypes.py", line 173, in dtype_to_ctype > raise ValueError, "unable to map dtype '%s'" % dtype > ValueError: unable to map dtype 'int32' is a symptom of a typical mistake that someone hopefully recognizes ? Best regards, Stéphane > Hello, > > I tried to compile pyopencl on my Mac (10.6), using the python distribution from Enthough (2.7.3). > Some of the demos work, but: > > examples/demo_array.py gives: > File "/Library/Frameworks/Python.framework/Versions/7.3/lib/python2.7/site-packages/pyopencl-2013.1-py2.7-macosx-10.5-i386.egg/pyopencl/compyte/dtypes.py", line 173, in dtype_to_ctype > raise ValueError, "unable to map dtype '%s'" % dtype > ValueError: unable to map dtype 'int32' > > examples/demo_mandelbrot.py gives: > Abort trap > > with the stack given at the end of the msg. > > Any tips ? > > Best regards, > > Stéphane > > Thread 0 Crashed: Dispatch queue: com.apple.main-thread > 0 libSystem.B.dylib 0x977a9c5a __kill + 10 > 1 libSystem.B.dylib 0x977a9c4c kill$UNIX2003 + 32 > 2 libSystem.B.dylib 0x9783c5a5 raise + 26 > 3 libSystem.B.dylib 0x97852679 __abort + 124 > 4 libSystem.B.dylib 0x97835334 release_file_streams_for_task + 0 > 5 ...pple.ATIRadeonX3000GLDriver 0x190a7c77 glrCompCreateKernel + 7015 > 6 ...pple.ATIRadeonX3000GLDriver 0x190ab2a4 glrCompLoadBinary + 2852 > 7 ...pple.ATIRadeonX3000GLDriver 0x190ab3ff glrCompBuildProgram + 287 > 8 com.apple.opencl 0x973674f6 clBuildProgram + 2643 > 9 _cl.so 0x011f9ecf pyopencl::program::build(std::string, pyopenclboost::python::api::object) + 879 > 10 _cl.so 0x011e8452 pyopenclboost::python::objects::caller_py_function_impl<pyopenclboost::python::detail::caller<void (pyopencl::program::*)(std::string, pyopenclboost::python::api::object), pyopenclboost::python::default_call_policies, pyopenclboost::mpl::vector4<void, pyopencl::program&, std::string, pyopenclboost::python::api::object> > >::operator()(_object*, _object*) + 322 > 11 _cl.so 0x01241d02 pyopenclboost::python::objects::function::call(_object*, _object*) const + 322 > 12 _cl.so 0x01241fb7 pyopenclboost::detail::function::void_function_ref_invoker0<pyopenclboost::python::objects::(anonymous namespace)::bind_return, void>::invoke(pyopenclboost::detail::function::function_buffer&) + 39 > 13 _cl.so 0x01250177 pyopenclboost::python::detail::exception_handler::operator()(pyopenclboost::function0<void> const&) const + 279 > 14 _cl.so 0x012266c4 pyopenclboost::detail::function::function_obj_invoker2<pyopenclboost::_bi::bind_t<bool, pyopenclboost::python::detail::translate_exception<pyopencl::error, void (*)(pyopencl::error const&)>, pyopenclboost::_bi::list3<pyopenclboost::arg<1>, pyopenclboost::arg<2>, pyopenclboost::_bi::value<void (*)(pyopencl::error const&)> > >, bool, pyopenclboost::python::detail::exception_handler const&, pyopenclboost::function0<void> const&>::invoke(pyopenclboost::detail::function::function_buffer&, pyopenclboost::python::detail::exception_handler const&, pyopenclboost::function0<void> const&) + 36 > 15 _cl.so 0x0124fd29 pyopenclboost::python::handle_exception_impl(pyopenclboost::function0<void>) + 153 > 16 _cl.so 0x0123ef7e function_call + 78 > 17 org.python.python 0x0000f635 PyObject_Call + 85 > 18 org.python.python 0x000c9616 PyEval_EvalFrameEx + 14294 > 19 org.python.python 0x000cd02a PyEval_EvalCodeEx + 2042 > 20 org.python.python 0x000cb253 PyEval_EvalFrameEx + 21523 > 21 org.python.python 0x000cd02a PyEval_EvalCodeEx + 2042 > 22 org.python.python 0x000cb253 PyEval_EvalFrameEx + 21523 > 23 org.python.python 0x000cd02a PyEval_EvalCodeEx + 2042 > 24 org.python.python 0x000cb253 PyEval_EvalFrameEx + 21523 > 25 org.python.python 0x000cd02a PyEval_EvalCodeEx + 2042 > 26 org.python.python 0x000cb253 PyEval_EvalFrameEx + 21523 > 27 org.python.python 0x000cc053 PyEval_EvalFrameEx + 25107 > 28 org.python.python 0x000cd02a PyEval_EvalCodeEx + 2042 > 29 org.python.python 0x000cb253 PyEval_EvalFrameEx + 21523 > 30 org.python.python 0x000cc053 PyEval_EvalFrameEx + 25107 > 31 org.python.python 0x000cd02a PyEval_EvalCodeEx + 2042 > 32 org.python.python 0x00042282 function_call + 162 > 33 org.python.python 0x0000f635 PyObject_Call + 85 > 34 org.python.python 0x00021fe6 instancemethod_call + 422 > 35 org.python.python 0x0000f635 PyObject_Call + 85 > 36 org.python.python 0x0007cff7 slot_tp_init + 87 > 37 org.python.python 0x0007ba20 type_call + 176 > 38 org.python.python 0x0000f635 PyObject_Call + 85 > 39 org.python.python 0x000c9616 PyEval_EvalFrameEx + 14294 > 40 org.python.python 0x000cd02a PyEval_EvalCodeEx + 2042 > 41 org.python.python 0x000cd1b7 PyEval_EvalCode + 87 > 42 org.python.python 0x000f1898 PyRun_FileExFlags + 168 > 43 org.python.python 0x000f27c3 PyRun_SimpleFileExFlags + 867 > 44 org.python.python 0x0010ba58 Py_Main + 3560 > 45 org.python.python 0x00001fb6 0x1000 + 4022 > Stéphane Conversy Enseignant Chercheur en IHM - ENAC http://lii-enac.fr/~conversy +33 5 62 17 40 19

7 years, 3 months

Re: [PyOpenCL] SVD for pyopencl

by Andreas Kloeckner

Ariel Guerreiro <arielguerreiro(a)gmail.com> writes: > I have become interested in heterogeneous computation, specially > OpenCl and Cuda (and their python counterparts). However, I have > noticed the lack of more advanced numerical packages (something > equivalent to scipy or numpy) or at least I haven't found anything > that good and user friendly. Currently I am looking for a way of doing > singular value decomposition for very large matrices (sparse and not > sparse, with focus on not sparse). Do you have any idea where I could > get something ready-made that works well. I am trying to avoid doing > the deed myself for I am not certain of the best algorithm and I am > not a computer programming wizard, just your plain python and scipy > user. There's currently no such thing for PyOpenCL. scikits.cuda exists for PyCUDA. If you could be convinced to do some work on this, cooking up a wrapper for Magma's linear algebra capabilities would likely be a good starting point: http://icl.cs.utk.edu/magma/ I've cc'd the mailing list. Please send future requests of this nature directly there. Thanks. Andreas

7 years, 3 months

Re: [PyOpenCL] pyopencl installation problem(with nvidia card)

by Andreas Kloeckner

Hi Sijiang, Sijiang Chen <sc30.ucc(a)gmail.com> writes: > The output of ls /etc/OpenCL/vendors is nvidia.icd. My graphic card is > notebook version GT525M. Does that mean all I need to do is download and > install ubuntu version of CUDA toolkit from nvidia and the problem will be > solved? Thank you for help. I think that might be worth trying. Andreas

7 years, 3 months

Re: [PyOpenCL] pyopencl installation problem(with nvidia card)

by Andreas Kloeckner

Hi Sijang, Sijiang Chen <sc30.ucc(a)gmail.com> writes: > I had a chat with Antonio Beamud and he helped me on how to set up pyopencl > installation on ubuntu(This installation is based on a clean ubuntu and > addition drivers(nvidia) installed). > > *sudo apt-get install python-pyopencl > python /usr/share/doc/python-pyopencl/examples/benchmark-all.py* > > When I type the second command, and error occurs. > > *Execution time of test without OpenCL: 9.42699384689 s > Traceback (most recent call last): > File "/usr/share/doc/python-pyopencl/examples/benchmark-all.py", line 24, > in <module> > for platform in cl.get_platforms(): > pyopencl.LogicError: clGetPlatformIDs failed: invalid/unknown error code* > > Antonio's card is ATI and he had no problem with it, mine is Nvidia driver > and it is installed by additional drivers, below is the additional drivers > screenshot:[image: Inline images 1] > By any chance, is there anyone could help me to solve this? Thanks. Which OpenCL library did you install? (In Debian, there are amd-libopencl1, nvidia-libopencl1, and a few more. Not sure how Ubuntu works in this regard.) What's the output of ls /etc/OpenCL/vendors/ ? Andreas

7 years, 3 months

pyopencl installation problem(with nvidia card)

by Sijiang Chen

I had a chat with Antonio Beamud and he helped me on how to set up pyopencl installation on ubuntu(This installation is based on a clean ubuntu and addition drivers(nvidia) installed). *sudo apt-get install python-pyopencl python /usr/share/doc/python-pyopencl/examples/benchmark-all.py* When I type the second command, and error occurs. *Execution time of test without OpenCL: 9.42699384689 s Traceback (most recent call last): File "/usr/share/doc/python-pyopencl/examples/benchmark-all.py", line 24, in <module> for platform in cl.get_platforms(): pyopencl.LogicError: clGetPlatformIDs failed: invalid/unknown error code* Antonio's card is ATI and he had no problem with it, mine is Nvidia driver and it is installed by additional drivers, below is the additional drivers screenshot:[image: Inline images 1] By any chance, is there anyone could help me to solve this? Thanks. Regards Sijiang CHen

7 years, 3 months

Re: [PyOpenCL] Handling Multiple kernels

by Andreas Kloeckner

Hi Calle, Calle Snickare <problembarnet(a)gmail.com> writes: > Is my question too hard or too trivial? I can't find any examples or info > on the web on this. I'll try to reformulate: > > I want to run two different kernel functions in succession, with the same > variables/input. They are both written in the same c-file. This is what I > run in the host-code: > > kernel_1 = prg.function_1 > kernelObj_1= kernel_1(queue, globalSize, localSize, ins.data, ranluxcltab) > kernelObj_1.wait() > > kernel_2 = prg.function_2 > kernelObj_2 = kernel_2(queue, globalSize, localSize, ins.data, ranluxcltab) > kernelObj_2.wait() > > Is this correct? If so - I'm running out of memory faster than I expect. Is > the same data really being used in this way, or is it duplicated? Sorry for the long delay in responding. Yes, these arrays should share memory. In general, it helps people help you if you pass along the error message and the hardware and software versions (CL implementation, OS, etc.) that you're running on. HTH, Andreas

7 years, 4 months

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

PyOpenCL March 2013