oneAPI

Deliver uncompromised performance for diverse workloads across multiple architectures.

基于OneAPI的并行化快速选择TopK算法实现

URL: https://github.com/MichaelTenma/TopK/tree/main

Description:

TopK是指在若干个数的序列中,找出K个最小(或最大)的数。本项目借助OneAPI在CPU多个核心上实现TopK算法的并行计算。本文通过并行快速选择算法寻找K个最小值,实现关键点在于将数序列划分成L块,每块的大小为B,对每块都进行快速选择算法,得出每块的前K小值,然后再对L块的全部前K小值,总计K*L个值,再进行快速选择,找出最终的前K小值,对于不同块而言,可以在不同的CPU核心上并行计算,以提高运算性能。

Posted:

Performance and Portability Evaluation of the K-Means Algorithm on SYCL with CPU-GPU architectures

URL: https://github.com/artecs-group/k-means

Description:

This work uses the k-means algorithm to asses the performance portability of one of the most advanced implementations of the literature, He-Vialle, over different programming models (DPC++, CUDA, OpenMP) and multi-vendor CPU-GPU architectures.

Posted:

Direction Field Visualization with Python

URL: https://github.com/olutosinbanjo/direction_field

Description:

This project demonstrates the visualization of a direction field with Python using the differential equation of a falling object as a case study. The effectiveness of Heterogeneous Computing is also shown by exploring optimized libraries & added functionalities in Intel® Distribution for Python*.

Posted:

Answer sheet Assessment and Checking: oneAPI Deep Neural Network Project

URL: https://github.com/AftabAhmedAbro/Answer-sheet-Assessment-and-Checking-oneAPI-Deep-Neural-Network-Project

Description:

Project on making a system using oneAPI Deep Neural Network Library to check and assess the answer sheets of thousands of candidates for various tests for organizations using ML/DL techniques Dataset: with the help of the MNIST dataset

Posted: