Benchmarking overlapping communication and computations with multiple streams for modern GPUs
Journal Title: Annals of Computer Science and Information Systems - Year 2018, Vol 17, Issue
Abstract
The paper presents benchmarking a multi-stream application processing a set of input data arrays. Tests have been performed and execution times measured for various numbers of streams and various compute intensities measured as the ratio of kernel compute time and data transfer time. As such, the application and benchmarking is representative of frequently used operations such as vector weighted sum, matrix multiplication etc. The paper shows benefits of using multiple data streams for various compute intensities compared to one stream, benchmarked for 4 GPUs: professional NVIDIA Tesla V100, Tesla K20m, desktop GTX 1060 and mobile GeForce 940MX. Additionally, relative performances are shown for various numbers of kernel computations for these GPUs.
Authors and Affiliations
Paweł Czarnul
Keywords
Related Articles
- EP ID EP568861
- DOI 10.15439/2018F17
- Views 41
- Downloads 0
Use of fuzzy cognitive maps for enhanced interaction with multiple mobile devices
The aim of this work was to design and implement a mechanism supporting collaborative sensemaking in a system of multiple mobile devices implementing spatial awareness. The design is based on an observation how people te...
Development of crowd investing on the basis of ICO crypto assets using block-options for the supply of electric generation capacity
Attraction of investments into the electric power industry is complicated by a number of problems related to the long payback period and instability of the conditions on the market. Investors in the electric power indust...
Adaptive Lighting System as a Smart Urban Object
In this article we present an approach to an adaptive lighting system as an intelligent object supporting urban space, especially for the elderly. This intelligent lighting system is used as an instrument to improve the...
An Approach towards economical hierarchic Search over Encrypted Cloud
In display, Cloud registering is the prevailing area in data innovation. With expanded value of information outsourcing of cloud information protection of delicate information turns into a major issue. For the security r...
Detection of Arrhythmia using Neural Network
There is an increase in cardio logical patients all over the world due to change in modern life style. It forces the medical researchers to search for smart devices that can diagnosis and predict the onset of cardiac pro...