Anudeep Kambapu

Hi, Thanks for this great program. Is there a SYCL Version for this program? Thanks Anudeep

Is a 2d array treated internally as 1d array at assembly level in dpcpp for NVIDIA BACKEND?

9

**Describe the bug** I am trying to run a program on NVIDIA backend. The code is similar in CUDA and DPCPP version, but dpcpp code considerably longer time(x10) compared to...

This version implements the SYCL version of CudaSift project. The base version is taken from CudaSift CUDA version and ported to SYCL version.

Hi, As a part of INTEL oneAPI work, we developed a fully functional SYCL/oneAPI version, of the program and wanted to contribute to this repo. How can I do that...

Quicksilver SYCL version

1

Adding Quicksilver SYCL version.

- Updated all three versions to run the code in main for 50 iterations. - Output average time for the 50 iterations. - This will eliminate the impact of different...

- Updated SYCL and versions to use host/device USM instead of shared to improve performance. - Updated SIMD width in SYCL version from 32 to 16 for better performance.