pyFAI.opencl package

pyFAI.opencl.OCLFullSplit module

pyFAI.opencl.azim_csr module

pyFAI.opencl.azim_hist module

pyFAI.opencl.azim_lut module

pyFAI.opencl.ocl_hist_pixelsplit module

Deprecated … restore or delete !

class pyFAI.opencl.ocl_hist_pixelsplit.OCL_Hist_Pixelsplit(pos, bins, image_size, pos0_range=None, pos1_range=None, devicetype='all', padded=False, block_size=32, platformid=None, deviceid=None, checksum=None, profile=False)

Bases: object

__init__(pos, bins, image_size, pos0_range=None, pos1_range=None, devicetype='all', padded=False, block_size=32, platformid=None, deviceid=None, checksum=None, profile=False)
Parameters:

  • lut – 3-tuple of arrays data: coefficient of the matrix in a 1D vector of float32 - size of nnz indices: Column index position for the data (same size as data) indptr: row pointer indicates the start of a given row. len nbin+1

  • image_size – size of the image (for pre-processing)

  • devicetype – can be “cpu”,”gpu”,”acc” or “all”

  • platformid (int) – number of the platform as given by clinfo

  • deviceid (int) – number of the device as given by clinfo

  • checksum – pre - calculated checksum to prevent re - calculating it :)

  • profile – store profiling elements

integrate(data, dummy=None, delta_dummy=None, dark=None, flat=None, solidAngle=None, polarization=None, dark_checksum=None, flat_checksum=None, solidAngle_checksum=None, polarization_checksum=None)
log_profile()

If we are in profiling mode, prints out all timing for every single OpenCL call

pyFAI.opencl.preproc module

pyFAI.opencl.setup module

pyFAI.opencl.setup.configuration(parent_package='', top_path=None)

pyFAI.opencl.sort module

Module contents

Contains all OpenCL implementation.

pyFAI.opencl.get_x87_volatile_option(ctx)