Welcome to numba-dppy’s documentation!

numba-dppy is a standalone extension to the Numba JIT compiler that adds SYCL programming capabilities to Numba. numba-dppy uses dpctl to support SYCL features and currently Intel’s DPC++ is the only SYCL runtime supported by numba-dppy.

There are two ways to program SYCL devices using numba-dppy:

  • An explicit kernel programming mode.

    import numpy as np
    import numba_dppy, numba_dppy as dppy
    import dpctl
        def sum(a, b, c):
        i = dppy.get_global_id(0)
        c[i] = a[i] + b[i]
    a = np.array(np.random.random(20), dtype=np.float32)
    b = np.array(np.random.random(20), dtype=np.float32)
    c = np.ones_like(a)
    with dpctl.device_context("opencl:gpu"):
        sum[20, dppy.DEFAULT_LOCAL_SIZE](a, b, c)
  • An automatic offload mode for NumPy data-parallel expressions and Numba parallel loops.

    from numba import njit
    import numpy as np
    import dpctl
    def f1(a, b):
        c = a + b
        return c
    global_size = 64
    local_size = 32
    N = global_size * local_size
    a = np.ones(N, dtype=np.float32)
    b = np.ones(N, dtype=np.float32)
    with dpctl.device_context("opencl:gpu:0"):
        c = f1(a, b)


numba-dppy is developed by Intel and is part of the Intel Distribution for Python.


Refer the contributing guide for information on coding style and standards used in numba-dppy.


numba-dppy is Licensed under Apache License 2.0 that can be found in LICENSE. All usage and contributions to the project are subject to the terms and conditions of this license.