ndgrigorian
ndgrigorian
When printing an array `x` with `x.ndim > 32` the following exception is raised: ``` In [1]: import dpctl.tensor as dpt, numpy as np In [2]: dpt.ones((1,) * 32) Out[2]:...
This PR adds overloads for ``sycl::vec`` input to the implementations of ``dpctl.tensor.abs``, ``dpctl.tensor.cos``, ``dpctl.tensor.expm1``, ``dpctl.tensor.log``, ``dpctl.tensor.log1p``, and ``dpctl.tensor.sqrt``. - [X] Have you provided a meaningful PR description? - [X] Have...
This PR proposes supporting the `kDLCPU` DLDeviceType as a targeted device in `from_dlpack` and `__dlpack__`. This is accomplished by `__dlpack__` by copying the array data to the host, wrapping it...
This PR modifies cmake scripts throughout dpctl to enable building for AMD. This is done by either setting the `DPCTL_TARGET_AMD` environment variable to the intended build architecture, or using `-DDPCTL_TARGET_AMD`....
OneAPI spec delineates [value_or_pointer](https://oneapi-spec.uxlfoundation.org/specifications/oneapi/latest/elements/onemkl/source/domains/blas/axpy#axpy-usm-version) which enables writing complex programs where the results of kernels can be chained together without bringing data to the host. Providing these overloads would improve usability...
The specification page for [`__dlpack__`](https://data-apis.org/array-api/latest/API_specification/generated/array_api.array.__dlpack__.html) requires the following two, conflicting things: for the `dlpack_device` argument > The v2023.12 standard only mandates that a compliant library should offer a way for...
This PR proposes a change to `dpnp_array.fill` method which leverages dpctl kernels to make `fill` asynchronous and more efficient, avoiding repeated calls to index the array and copying scalars to...