基于带符号位的浮点数运算的多位宽 3D RRAM 设计

Translated title of the contribution: A Multi-Bit 3D RRAM-Based Signed Floating-Point Number Operations

Xinghua Wang, Tian Wang, Qian Wang, Xiaoran Li*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, a signed floating-point number operation with multi-bit storage three-dimensional resistive random-access memory (3D RRAM) was presented for complex convolution neutral network (CNN) systems. Comparing with other types of memory, 3D RRAM can not only perform calculations inside the memory, but also possess a higher reading rate and a lower energy consumption, providing a new solution to the bottleneck problem of the Von Neumann architecture. A single RRAM cell can reach a maximum and minimum resistance of 10 GΩ and 10 MΩ, which can be stabilized in multi-level resistance states to store high-bit-width data. The test results show that, the accuracy of the signed floating-point number convolution operation system can reach up to 99.8%, the measured peak reading speed of the 3D RRAM model is 0.529 MHz.

Translated title of the contributionA Multi-Bit 3D RRAM-Based Signed Floating-Point Number Operations
Original languageChinese (Traditional)
Pages (from-to)1299-1304
Number of pages6
JournalBeijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
Volume42
Issue number12
DOIs
Publication statusPublished - Dec 2022

Fingerprint

Dive into the research topics of 'A Multi-Bit 3D RRAM-Based Signed Floating-Point Number Operations'. Together they form a unique fingerprint.

Cite this