Ratko Pilipović (Author), Vladimir Risojević (Author), Janko Božič (Author), Patricio Bulić (Author), Uroš Lotrič (Author)

Abstract

Edge computing brings artificial intelligence algorithms and graphics processing units closer to data sources, making autonomy and energy-efficient processing vital for their design. Approximate computing has emerged as a popular strategy for energy-efficient circuit design, where the challenge is to achieve the best tradeoff between design efficiency and accuracy. The essential operation in artificial intelligence algorithms is the general matrix multiplication (GEMM) operation comprised of matrix multiplication and accumulation. This paper presents an approximate general matrix multiplication (AGEMM) unit that employs approximate multipliers to perform matrix–matrix operations on four-by-four matrices given in sixteen-bit signed fixed-point format. The synthesis of the proposed AGEMM unit to the 45 nm Nangate Open Cell Library revealed that it consumed only up to 36% of the area and 25% of the energy required by the exact general matrix multiplication unit. The AGEMM unit is ideally suited to convolutional neural networks, which can adapt to the error induced in the computation. We evaluated the AGEMM units’ usability for honeybee detection with the YOLOv4-tiny convolutional neural network. The results implied that we can deploy the AGEMM units in convolutional neural networks without noticeable performance degradation. Moreover, the AGEMM unit’s employment can lead to more area- and energy-efficient convolutional neural network processing, which in turn could prolong sensors’ and edge nodes’ autonomy.

Keywords

približno računanje;logaritemski množilnik;računalniška aritmetika;energijsko učinkovito procesiranje;tensorsko jedro;approximate computing;logarithmic multiplier;computer arithmetic;energy-efficient processing;tensor core;

Data

Language: English
Year of publishing:
Typology: 1.01 - Original Scientific Article
Organization: UL FRI - Faculty of Computer and Information Science
UDC: 004
COBISS: 67593475 Link will open in a new window
ISSN: 1424-8220
Views: 128
Downloads: 40
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: Slovenian
Secondary keywords: približno računanje;logaritemski množilnik;računalniška aritmetika;energijsko učinkovito procesiranje;tensorsko jedro;
Type (COBISS): Article
Pages: str. 1-19
Volume: ǂVol. ǂ21
Issue: ǂno. ǂ12
Chronology: Jun. 2021
DOI: 10.3390/s21124195
ID: 14808622