Conditions for privatizing the elements of arrays by computing threads
The set of operations of the parallel algorithm for implementation on the GPU must be split into computation threads. The threads must be grouped into computation units that run atomically on stream processors, also called multiprocessors. For good GPU performance, it is important that as much dat...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Belarusian |
| Published: |
Belarusian State University
2019-01-01
|
| Series: | Журнал Белорусского государственного университета: Математика, информатика |
| Subjects: | |
| Online Access: | https://journals.bsu.by/index.php/mathematics/article/view/1013 |