dpctl.utils

A collection of utility functions.

Classes

SyclDevice

A Python wrapper for the sycl::device C++ class.

Other Functions

intel_device_info()

For Intel(R) GPU devices returns a dictionary with device architectural details, and an empty dictionary otherwise. The dictionary contains the following keys: device_id: 32-bits device PCI identifier gpu_eu_count: Total number of execution units gpu_hw_threads_per_eu: Number of thread contexts in EU gpu_eu_simd_width: Physical SIMD width of EU gpu_slices: Total number of slices gpu_subslices_per_slice: Number of sub-slices per slice gpu_eu_count_per_subslice: Number of EUs in subslice max_mem_bandwidth: Maximum memory bandwidth in bytes/second Unsupported descriptors are omitted from the dictionary.

intel_device_info_device_id()

[FIXME]: <class ‘builtin_function_or_method’> has a docstring with no summary

intel_device_info_gpu_eu_count()

-> int Returns the number of execution units (EUs) associated with the Intel GPU.

intel_device_info_gpu_eu_count_per_subslice()

-> int Returns the number of EUs per subslice of GPU.

intel_device_info_gpu_eu_simd_width()

-> int Returns the physical SIMD width of the execution unit (EU).

intel_device_info_gpu_hw_threads_per_eu()

-> int Returns the number of hardware threads in EU.

intel_device_info_gpu_slices()

-> int Returns the number of slices in the GPU device, or zero.

intel_device_info_gpu_subslices_per_slice()

-> int Returns the number of subslices per slice.

intel_device_info_max_mem_bandwidth()

-> int Returns the maximum memory bandwidth in units of bytes/second.

onetrace_enabled()

Enable onetrace collection for kernels executed in this context.

Exceptions

ExecutionPlacementError

Exception raised when execution placement target can be determined from input arrays.