Deep Learning Accelerators’ Configuration Space Exploration Effect on Performance and Resource Utilization: A Gemmini Case Study
Open Access
Abstract
Though custom deep learning (DL) hardware accelerators are attractive for making inferences in edge computing devices, their design and implementation remain a challenge. Open-source frameworks exist for exploring DL hardware accelerators. Gemmini is an open-source systolic array generator for agile DL accelerator exploration. This paper details the hardware/software components generated using Gemmini. The general matrix-to-matrix multiplication (GEMM) of different dataflow options, including output/weight stationary (OS/WS), was explored in Gemmini to estimate the performance relative to a CPU implementation. The Gemmini hardware was implemented on an FPGA device to explore the effect of several accelerator parameters, including array size, memory capacity, and the CPU/hardware image-to-column (im2col) module, on metrics such as the area, frequency, and power. This work revealed that regarding the performance, the WS dataflow offered a speedup of 3× relative to the OS dataflow, and the hardware im2col operation offered a speedup of 1.1× relative to the operation on the CPU. For hardware resources, an increase in the array size by a factor of 2 led to an increase in both the area and power by a factor of 3.3, and the im2col module led to an increase in area and power by factors of 1.01 and 1.06, respectively.Keywords
Funding Information
- Korean government (MSIT) (2022-0-00394)
This publication has 17 references indexed in Scilit:
- A robot-based intelligent management design for agricultural cyber-physical systemsComputers and Electronics in Agriculture, 2021
- TSM22019
- A domain-specific architecture for deep neural networksCommunications of the ACM, 2018
- MAERI2018
- Optimal DNN primitive selection with partitioned boolean quadratic programming2018
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- A cloud-scale acceleration architecture2016
- Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks2016
- Why systolic architectures?Computer, 1982