Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Haobo, Qian, Zhengyang, Wu, Wei, Ren, Hongwei, Liu, Zhiwei, Ni, Leibin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2402.13798
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914688014483456
author Liu, Haobo
Qian, Zhengyang
Wu, Wei
Ren, Hongwei
Liu, Zhiwei
Ni, Leibin
author_facet Liu, Haobo
Qian, Zhengyang
Wu, Wei
Ren, Hongwei
Liu, Zhiwei
Ni, Leibin
contents Power consumption has become the major concern in neural network accelerators for edge devices. The novel non-volatile-memory (NVM) based computing-in-memory (CIM) architecture has shown great potential for better energy efficiency. However, most of the recent NVM-CIM solutions mainly focus on fixed-point calculation and are not applicable to floating-point (FP) processing. In this paper, we propose an analog-domain floating-point CIM architecture (AFPR-CIM) based on resistive random-access memory (RRAM). A novel adaptive dynamic-range FP-ADC is designed to convert the analog computation results into FP codes. Output current with high dynamic range is converted to a normalized voltage range for readout, to prevent precision loss at low power consumption. Moreover, a novel FP-DAC is also implemented which reconstructs FP digital codes into analog values to perform analog computation. The proposed AFPR-CIM architecture enables neural network acceleration with FP8 (E2M5) activation for better accuracy and energy efficiency. Evaluation results show that AFPR-CIM can achieve 19.89 TFLOPS/W energy efficiency and 1474.56 GOPS throughput. Compared to traditional FP8 accelerator, digital FP-CIM, and analog INT8-CIM, this work achieves 4.135x, 5.376x, and 2.841x energy efficiency enhancement, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2402_13798
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AFPR-CIM: An Analog-Domain Floating-Point RRAM-based Compute-In-Memory Architecture with Dynamic Range Adaptive FP-ADC
Liu, Haobo
Qian, Zhengyang
Wu, Wei
Ren, Hongwei
Liu, Zhiwei
Ni, Leibin
Systems and Control
Power consumption has become the major concern in neural network accelerators for edge devices. The novel non-volatile-memory (NVM) based computing-in-memory (CIM) architecture has shown great potential for better energy efficiency. However, most of the recent NVM-CIM solutions mainly focus on fixed-point calculation and are not applicable to floating-point (FP) processing. In this paper, we propose an analog-domain floating-point CIM architecture (AFPR-CIM) based on resistive random-access memory (RRAM). A novel adaptive dynamic-range FP-ADC is designed to convert the analog computation results into FP codes. Output current with high dynamic range is converted to a normalized voltage range for readout, to prevent precision loss at low power consumption. Moreover, a novel FP-DAC is also implemented which reconstructs FP digital codes into analog values to perform analog computation. The proposed AFPR-CIM architecture enables neural network acceleration with FP8 (E2M5) activation for better accuracy and energy efficiency. Evaluation results show that AFPR-CIM can achieve 19.89 TFLOPS/W energy efficiency and 1474.56 GOPS throughput. Compared to traditional FP8 accelerator, digital FP-CIM, and analog INT8-CIM, this work achieves 4.135x, 5.376x, and 2.841x energy efficiency enhancement, respectively.
title AFPR-CIM: An Analog-Domain Floating-Point RRAM-based Compute-In-Memory Architecture with Dynamic Range Adaptive FP-ADC
topic Systems and Control
url https://arxiv.org/abs/2402.13798