|
Journal of the Belarusian State University. Mathematics and Informatics, 2018, Volume 3, Pages 59–67
(Mi bgumi120)
|
|
|
|
This article is cited in 1 scientific paper (total in 1 paper)
Computational Mathematics
Conditions for privatizing the elements of arrays by computing threads
N. A. Likhoded, M. A. Paliashchuk Belarusian State University, 4 Niezaliežnasci Avenue, Minsk 220030, Belarus
Abstract:
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 data as possible can fit into fast register and shared memory, otherwise slow global and local memory are used. The degree of memory usage with fast access reflects the computational property of the algorithm, called locality. When implementing algorithms on multiprocessor computing devices, the use of locality plays a crucial role in achieving high performance. In this paper, necessary conditions and sufficient conditions have been formulated and proved, the use of which allows receiving threads with privatized data, i. e. it allows to receive
such computation threads that the array element is used only by one thread and therefore it is advisable to place it in the register
Keywords:
parallel computations; GPU; tiling; array privatization; registers.
Received: 12.06.2018
Citation:
N. A. Likhoded, M. A. Paliashchuk, “Conditions for privatizing the elements of arrays by computing threads”, Journal of the Belarusian State University. Mathematics and Informatics, 3 (2018), 59–67
Linking options:
https://www.mathnet.ru/eng/bgumi120 https://www.mathnet.ru/eng/bgumi/v3/p59
|
Statistics & downloads: |
Abstract page: | 47 | Full-text PDF : | 16 | References: | 15 |
|