PyOpenCL

pyopencl@tiker.net

1109 discussions

by Jerome Kieffer

Dear OpenCL users, This issue is not directly related to pyopencl but rather to nvidia's OpenCL driver. I discovered that the the support for OpenCL is variable depending on the underlying hardware. The typical example is the `enqueue_fill_buffer` from OpenCL which is used for the initialisation in pyopencl.array. This function is properly exposed in recent hardware (Kepler and newer) but not is elder Fermi cards (and we still have a cluster full of Tesla M2075) In [7]: ary = pyopencl.array.zeros(queue, (10,10), "float32") --------------------------------------------------------------------------- LogicError Traceback (most recent call last) <ipython-input-7-d85341757b00> in <module>() ----> 1 ary = pyopencl.array.zeros(queue, (10,10), "float32") /usr/lib/python3/dist-packages/pyopencl/array.py in zeros(queue, shape, dtype, order, allocator) 1973 result = Array(queue, shape, dtype, 1974 order=order, allocator=allocator) -> 1975 result._zero_fill() 1976 return result 1977 /usr/lib/python3/dist-packages/pyopencl/array.py in _zero_fill(self, queue, wait_for) 1190 self.add_event( 1191 cl.enqueue_fill_buffer(queue, self.base_data, np.int8(0), -> 1192 self.offset, self.nbytes, wait_for=wait_for)) 1193 else: 1194 zero = np.zeros((), self.dtype) /usr/lib/python3/dist-packages/pyopencl/__init__.py in enqueue_fill_buffer(queue, mem, pattern, offset, size, wait_for) 1850 pattern = np.asarray(pattern) 1851 -> 1852 return _cl._enqueue_fill_buffer(queue, mem, pattern, offset, size, wait_for) 1853 1854 # }}} LogicError: clEnqueueFillBuffer failed: INVALID_OPERATION The same "bug" occurs in the PoCL driver when addressing nvidia GPU, since the corresponding low-level primitive is absent in NVVM. I wonder if we should best address this issue within our code or it could be addressed at a higher level. Getting from nvidia that they fix their code to conform for the specification is an illusion. But does it make sense to address this as part of pyopencl ? If so, I am willing to contribute with a patch. Thanks for your advice, Cheers, Jerome

1 month, 1 week

CL_MEM_HETEROGENEOUS_INTELFPGA

by Lawrence Stewart

I’m interested in using PyOpenCL with a Bittware 520MX board that has an Intel Stratix 10 with HBM memory. This shows up as 32 banks of 256 MB rather than as a single DDR memory system. In order to use it, you must specify the flag CL_MEM_HETEROGENEOUS_INTELFPGA in calls to clCreateBuffer. This seems like an easy addition to PyOpenCl and I wonder if anyone has done it already? Otherwise, I suppose I need to get a PyOpenCL source kit, add the flag and use that rather than install with PIP? So far I haven’t found instructions for how to install from source. Thanks! -Larry

1 month, 3 weeks

Issue with garbage collection ...

by Jerome Kieffer

Dear PyOpenCL community, I am facing a bug where programs crash randomly when pyopencl is used in combination while matplotlib displays results. If one or the other is not used, the program runs fine. Apparently it is the Python garbage collector which destroys C++ NannyEvents, but matplotlib is also in the stack (which I don't understand why). https://github.com/silx-kit/pyFAI/issues/1341 I tested on Debian 10, debian10 with backports from sid. Within a virtualenv with everything up to date, I do not manage to reproduce the bug. It has probably been corrected somewhere, but do you have the reference of the bug ? Thanks for you help, Jérôme

4 months, 1 week

Defining a custom Buffer-like class

by Bogdan Opanchuk

I am trying to make a class that would be passable to Kernel's set_arg() and otherwise behave like a Buffer (it will have a real pyopencl.Buffer inside). Has someone done that before? I am having a hard time going through the C++/generated code in pyopencl, and still don't understand what exactly is required from such a class. The docs for Kernel.set_arg() list a number of types that it accepts, but these are all defined at the C level and are not very easy to subclass. A question to Andreas: in PyCUDA, it is enough for a kernel argument to just have a `.gpudata` attribute that is convertible to integer - would it be possible to do the same in PyOpenCL (at least the first part, where set_arg() would use duck typing and look for a specific attribute)?

4 months, 3 weeks

Re: enqueue_task missing ???

by Andreas Kloeckner

Yves Surrel <yves(a)surrel.org> writes: > Hi Andreas > > Before logging an issue, I just want to know whether I am simply stupid… > > AttributeError: module 'pyopencl' has no attribute ‘enqueue_task’. But it is in the doc at the same level as pyopencl.enqueue_nd_range_kernel > > So what’s wrong (it does not appear in __init__.py) ? It's documented to be equivalent to be equivalent to enqueue_nd_range_kernel with unit grid size. Commit https://github.com/inducer/pyopencl/commit/6ca59dca1ae44fa6cafedaea3d193376… removed it, but (by the looks of it) left the docs in place. Do you see a good reason to keep/reintroduce it? https://gitlab.tiker.net/inducer/pyopencl/-/merge_requests/105 removes the docs. Andreas

4 months, 4 weeks

Changes to a subregion are ignored in a multi-device context on Apple + nVidia

by Bogdan Opanchuk

Hello all, I have an old macbook that has a discrete GeForce on it, and have run into the following problem. The simplified example is here: https://gist.github.com/fjarri/9aff0474868e2faf438f7e8229d194ec Basically, what I'm trying to do: - create a two-device context - create a buffer - split it into two subregions to use on each device - run a kernel on each device in parallel working with the corresponding subregion - get the result back on the host (the expected result is [0 1 2 3 4 5 6 7 0 1 2 3 4 5 6 7]) First, it turned out that if the context includes an nVidia card, the Buffer must be necessarily created with the cl.mem_flags.ALLOC_HOST_PTR flag, otherwise if one uses its subregion in a kernel, the program crashes. If the context is created on a CPU + Iris Pro (the other two devices available), everything works fine without this flag, giving the expected result. After fixing that, the program finishes without crashing when run on a CPU + GeForce or Iris Pro + GeForce context, but the result is [0 1 2 3 4 5 6 7 0 0 0 0 0 0 0 0] - that is, the second kernel (on the GeForce device) either did not run, or its changes to the subregion were not incorporated into the whole buffer. Uncommenting the explicit migration in the end does not help either. Does anyone know what I'm missing here? Or is it an nVidia/Apple bug?

6 months, 3 weeks

Hints for further debugging?

by Michael Wibral

7 months, 3 weeks

apt installing older version of pyopencl on ubuntu1604

by Shivangi Agarwal

Hi, I installed pyopencl using apt on ubuntu16.04 but it installs an older version (which doesn't work when CUDA is installed): python-pyopencl/xenial 2015.1-2build3 amd64 Python module to access OpenCL parallel computation API I was wondering if this pkg will be updated to install a new pyopencl. Thanks, Shivangi Agarwal

8 months, 2 weeks

pyopencl / pocl problem

by Samuel Garcia

Dear all, I known this is not the good mailing list to ask. So I am sorry to ask but I do it anyway. I have a simple cl kernel that totally work with nvidia-icd / neo-icd / pocl-icd. But today the pocl-icd do not compile at all. I get this error message: *pocl error: lt_dlopen("(null)") or lt_dlsym() failed with 'can't close resident module'.** **note: missing symbols in the kernel binary might be reported as 'file not found' errors.** * I don't think it is pyopencl related more pocl. I am on unbutunu 18.04, python 3.6.8, pyopencl 2019.1.2, pocl-opencl-icd 1.1-5. google do not help me so much. Maybe an opencl expert here could help me. Thank a lot. Best, Samuel

8 months, 2 weeks

Re: cl.enqueue_copy blocking when is_blocking set to False

by Andreas Kloeckner

Yves Surrel <yves(a)surrel.org> writes: > Hi Andreas > > I just had a look to the last PyOpenCL doc on the Web, memory->transfers-> pyopencl.enqueue_copy > > I think that the text in the first note: > > "Be aware that when the deletion of the blah blah… » > > should read: > > "Be aware that the deletion of the blah blah… » (‘when’ removed) > > Also, the end of the note > > "as long as necessary for the transfer to complete. » > > does not sound very well. I suggest > > "until the transfer has completed » Thanks for the suggestions, I've implemented them. (Docs should auto update in a bit.) Andreas

8 months, 3 weeks

Jump to page:

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

PyOpenCL