Study and evaluation of automatic offloading for function blocks of applications
Systems using graphical processing units (GPUs) and field-programmable gate arrays (FPGAs) have increased due to their advantages over central processing units (CPUs). However, such systems require the understanding of hardware-specific technical specifications such as Hardware Description Language...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-01-01
|
| Series: | Automatika |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/00051144.2024.2301888 |
| _version_ | 1797358052131733504 |
|---|---|
| author | Yoji Yamato |
| author_facet | Yoji Yamato |
| author_sort | Yoji Yamato |
| collection | DOAJ |
| description | Systems using graphical processing units (GPUs) and field-programmable gate arrays (FPGAs) have increased due to their advantages over central processing units (CPUs). However, such systems require the understanding of hardware-specific technical specifications such as Hardware Description Language (HDL) and compute unified device architecture (CUDA), which is a high hurdle. Based on this background, we previously proposed environment-adaptive software that enables automatic conversion, configuration and high-performance operation of existing code according to the hardware to be placed. As an element of this concept, we also proposed a method of automatically offloading loop statements of application source code for CPUs to GPUs and FPGAs. In this paper, we propose a method for offloading a function block, which is a larger unit, instead of individual loop statements in an application to achieve higher speed by automatically offloading to GPUs and FPGAs. We implemented the proposed method and evaluated it using current applications offloading to GPUs and FPGAs. |
| first_indexed | 2024-03-08T14:54:13Z |
| format | Article |
| id | doaj.art-45d4601856634be2a9677052a19b854d |
| institution | Directory Open Access Journal |
| issn | 0005-1144 1848-3380 |
| language | English |
| last_indexed | 2024-03-08T14:54:13Z |
| publishDate | 2024-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Automatika |
| spelling | doaj.art-45d4601856634be2a9677052a19b854d2024-01-10T17:14:59ZengTaylor & Francis GroupAutomatika0005-11441848-33802024-01-0165138740010.1080/00051144.2024.2301888Study and evaluation of automatic offloading for function blocks of applicationsYoji Yamato0Network Service Systems Laboratories, NTT Corporation, Tokyo, JapanSystems using graphical processing units (GPUs) and field-programmable gate arrays (FPGAs) have increased due to their advantages over central processing units (CPUs). However, such systems require the understanding of hardware-specific technical specifications such as Hardware Description Language (HDL) and compute unified device architecture (CUDA), which is a high hurdle. Based on this background, we previously proposed environment-adaptive software that enables automatic conversion, configuration and high-performance operation of existing code according to the hardware to be placed. As an element of this concept, we also proposed a method of automatically offloading loop statements of application source code for CPUs to GPUs and FPGAs. In this paper, we propose a method for offloading a function block, which is a larger unit, instead of individual loop statements in an application to achieve higher speed by automatically offloading to GPUs and FPGAs. We implemented the proposed method and evaluated it using current applications offloading to GPUs and FPGAs.https://www.tandfonline.com/doi/10.1080/00051144.2024.2301888Environment adaptive softwareGPGPUautomatic offloadingperformancefunction block |
| spellingShingle | Yoji Yamato Study and evaluation of automatic offloading for function blocks of applications Automatika Environment adaptive software GPGPU automatic offloading performance function block |
| title | Study and evaluation of automatic offloading for function blocks of applications |
| title_full | Study and evaluation of automatic offloading for function blocks of applications |
| title_fullStr | Study and evaluation of automatic offloading for function blocks of applications |
| title_full_unstemmed | Study and evaluation of automatic offloading for function blocks of applications |
| title_short | Study and evaluation of automatic offloading for function blocks of applications |
| title_sort | study and evaluation of automatic offloading for function blocks of applications |
| topic | Environment adaptive software GPGPU automatic offloading performance function block |
| url | https://www.tandfonline.com/doi/10.1080/00051144.2024.2301888 |
| work_keys_str_mv | AT yojiyamato studyandevaluationofautomaticoffloadingforfunctionblocksofapplications |