Heterogeneous cloud computing servers provide access to different types of hardware accelerators in order to satisfy the computational demands that standalone generalpurpose multi-processors can not deliver. The combination of different technologies provides more opportunities to accelerate the most compute-intensive applications by exploiting the key features of each type of hardware accelerator. Unfortunately, the design effort drastically increases when considering complex applications. We propose a methodology which provides an early speedup prediction when combining hardware accelerators and insights about potential performance leaks. In addition, we consider a couple of metrics to analize the computational use of the accelerators and the exploitation of the heterogeneous system. Our methodology is applied to a real-time surveillance system, which is composed of Field-Programmable Gate Arrays (FPGA) and Graphic-Processing Units (GPU). The methodology is used to provide an early speedup prediction, which is used to guide the combination of both accelerators. The achieved acceleration is only a 3:5% lower than estimated by our methodology.
Da Silva Gomez, B, Cornelis, JG, Braeken, A, Erik, HD, Lemeire, J & Touhafi, A 2018, Heterogeneous Cloud Computing: Design Methodology to Combine Hardware Accelerators. in IEEE., 8713333, 2018 4th International Conference on Cloud Computing Technologies and Applications, Cloudtech 2018, IEEE, 4th international conference on cloud computing technologies and applications , Brussels, Belgium, 26/11/18. https://doi.org/10.1109/CloudTech.2018.8713333
Da Silva Gomez, B., Cornelis, J. G., Braeken, A., Erik, H. D., Lemeire, J., & Touhafi, A. (2018). Heterogeneous Cloud Computing: Design Methodology to Combine Hardware Accelerators. In IEEE Article 8713333 (2018 4th International Conference on Cloud Computing Technologies and Applications, Cloudtech 2018). IEEE. https://doi.org/10.1109/CloudTech.2018.8713333
@inproceedings{9eebaafccf7e4339ab0ebffab34a805a,
title = "Heterogeneous Cloud Computing: Design Methodology to Combine Hardware Accelerators",
abstract = "Heterogeneous cloud computing servers provide access to different types of hardware accelerators in order to satisfy the computational demands that standalone generalpurpose multi-processors can not deliver. The combination of different technologies provides more opportunities to accelerate the most compute-intensive applications by exploiting the key features of each type of hardware accelerator. Unfortunately, the design effort drastically increases when considering complex applications. We propose a methodology which provides an early speedup prediction when combining hardware accelerators and insights about potential performance leaks. In addition, we consider a couple of metrics to analize the computational use of the accelerators and the exploitation of the heterogeneous system. Our methodology is applied to a real-time surveillance system, which is composed of Field-Programmable Gate Arrays (FPGA) and Graphic-Processing Units (GPU). The methodology is used to provide an early speedup prediction, which is used to guide the combination of both accelerators. The achieved acceleration is only a 3:5% lower than estimated by our methodology. ",
keywords = "Heterogeneous Cloud Computing, High- Performance Computing, Hardware Accelerators, GPU, FPGA, Speedup",
author = "{Da Silva Gomez}, Bruno and Cornelis, {Jan G.} and An Braeken and Erik, {H. D'hollander} and Jan Lemeire and Abdellah Touhafi",
year = "2018",
month = jul,
day = "2",
doi = "10.1109/CloudTech.2018.8713333",
language = "English",
isbn = "978-1-7281-1637-2 ",
series = "2018 4th International Conference on Cloud Computing Technologies and Applications, Cloudtech 2018",
publisher = "IEEE",
booktitle = "IEEE",
note = "4th international conference on cloud computing technologies and applications : Cloudtech, Cloudtech ; Conference date: 26-11-2018 Through 28-11-2018",
}