pyopencl
pyopencl copied to clipboard
inducer
OpenCL integration for Python, plus shiny features
The PR #212 fixed a bug in pyopencl.device_type.to_string(value) as device_type is defined as a bit-field. There are 7 types stored as bit-field: * cl_device_type * cl_device_fp_config * cl_device_exec_capabilities * cl_command_queue_properties...
When running pyopencl on a cluster with an nfs filesystem, a lock file created in my home dir on one node prevents the other nodes from progressing. I've pasted a...
It appears that OpenCL 1.2 extension cl_khr_image2d_from_buffer is not completely supported. This allows zero-copy creation of a 2D image from a buffer, provided that the buffer satisfies CL_DEVICE_IMAGE_BASE_ADDRESS_ALIGNMENT and CL_DEVICE_IMAGE_PITCH_ALIGNMENT...
The usecase is that different devices have different alignments for a particular c struct. This raises the need for different numpy datatypes to be registered as same ctype which requires...
For FPGA execution of OpenCL kernels, the board expects 64-byte aligned host arrays. However, there seems to be no way to get numpy arrays to obey custom alignments (It seems...
Some kernels using complex types seem to fail on some Macs. Using PyOpenCL pulled from github today, I see the following failures from test_clmath.py on an iMac 17,1 (ca. 2015)...
Running [this snippet](https://gist.github.com/mattwala/f131a2587f5ed597c2fde2cac998c0d3) results in the following error: File "test.py", line 11, in rand(q, shape=(), a=np.iinfo(dt).min, b=np.iinfo(dt).max, dtype=dt) File "/home/matt/src/pyopencl/pyopencl/clrandom.py", line 741, in rand gen.fill_uniform(result, a=a, b=b)) File "/home/matt/src/pyopencl/pyopencl/clrandom.py", line...
(At least in the common case in which we know the Python-side program instance.)
I'm pretty sure I'm using enqueue_fill_image according to the spec: ``` python import pyopencl as cl #... output = cl.Image(mgr.context, cl.mem_flags.READ_WRITE, cl.ImageFormat(cl.channel_order.RGBA,cl.channel_type.UNSIGNED_INT32), shape = (mgr.cell_width, mgr.cell_height*2)) fill_evt = cl.enqueue_fill_image(mgr.queue,output,np.zeros((4,),dtype=np.uint32),origin=(0,0),region=output.shape) ```...
