In Search of the Performance- and Energy-Efficient CNN Accelerators

Autor:	Stanislav G. Sedukhin, Yoichi Tomioka, Kohei Yamamoto
Rok vydání:	2022
Předmět:	Acceleration Cycles per instruction Computer science Tensor Electrical and Electronic Engineering Algorithm Residual neural network Image (mathematics) Efficient energy use Electronic Optical and Magnetic Materials
Zdroj:	COOL CHIPS
ISSN:	1745-1353 0916-8524
Popis:	In this paper, starting from the algorithm, a performance- and energy-efficient 3D structure or shape of the Tensor Processing Engine (TPE) for CNN acceleration is systematically searched and evaluated. An optimal accelerator's shape maximizes the number of concurrent MAC operations per clock cycle while minimizes the number of redundant operations. The proposed 3D vector-parallel TPE architecture with an optimal shape can be very efficiently used for considerable CNN acceleration. Due to inter-block image data independency, it is possible to use multiple of such TPEs for the additional CNN acceleration. Moreover, it was shown that proposed TPE can also be uniformly used for acceleration of the different CNN models such as VGG, ResNet, YOLO and SSD.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69c25d758c6b81879dd80f098fb77c42 https://doi.org/10.1587/transele.2021lhp0003 Zobrazit plný text záznamu