Precision-Aware Workload Distribution and Dataflow for a Hybrid Digital-CIM Deep CNN Accelerator

Jui I. Kao, Wei Lu, Po Tsang Huang, Hung Ming Chen

研究成果: Conference contribution同行評審

摘要

SRAM-based Computing-in-memory (CIM) circuits have been demonstrated as a promising solution to effectively accelerate the inference of convolutional neural networks (CNNs) by shifting computation into the memory arrays. However, the advantages of CIM accelerators will disappear as increasing the bit precision and adopting advanced process technology due to the overhead caused by ADC/DAC and poor technology scaling capability of analog circuits. In this paper, a hybrid digital-CIM accelerator was proposed to solve above problems and the weights and activations of different layers are quantized to different precision (high, medium, and low precision). Moreover, precision-aware workload distribution and dataflow are proposed for the hybrid digital-CIM accelerator. Overall, the proposed accelerator can achieve 12.481 TOPS/W.

原文English
主出版物標題Proceedings - International SoC Design Conference 2022, ISOCC 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面171-172
頁數2
ISBN(電子)9781665459716
DOIs
出版狀態Published - 2022
事件19th International System-on-Chip Design Conference, ISOCC 2022 - Gangneung-si, Korea, Republic of
持續時間: 19 10月 202222 10月 2022

出版系列

名字Proceedings - International SoC Design Conference 2022, ISOCC 2022

Conference

Conference19th International System-on-Chip Design Conference, ISOCC 2022
國家/地區Korea, Republic of
城市Gangneung-si
期間19/10/2222/10/22

指紋

深入研究「Precision-Aware Workload Distribution and Dataflow for a Hybrid Digital-CIM Deep CNN Accelerator」主題。共同形成了獨特的指紋。

引用此