arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.02099cs.ARcs.NE
收藏

采用分布式算术的无乘法器内存内向量-矩阵乘法

Multiplier-free In-Memory Vector-Matrix Multiplication Using Distributed Arithmetic

Felix Zeller, John Reuben, Dietmar Fey

AI总结:

本研究将分布式算术技术扩展至内存内向量-矩阵乘法,通过ReRAM外围移位-加法电路实现无乘法器运算,消除高功耗ADC,相比传统位切片方案实现4.5倍延迟降低与12倍能耗降低。

摘要:

向量-矩阵乘法(Vector-Matrix Multiplication, VMM)是神经网络(Neural Networks, NN)推理过程中基础且高频需求的计算操作。由于推理过程需要大量数据移动,VMM可从内存内计算中大幅获益,但内存内VMM所需的ADC/DAC会消耗显著的功耗与面积。分布式算术(Distributed Arithmetic, DA)是20世纪80年代盛行的计算机体系结构技术,可在其中一个向量为常量时,无需硬连线乘法器即可实现两个向量的内积(点积)。本研究将DA技术扩展至输入向量与常量矩阵的乘法运算,通过将权重和存储在内存中,DA利用ReRAM存储器外围的移位-加法电路实现VMM。我们通过晶体管级仿真验证了功能正确性,并估算了延迟、能耗、面积等非功能属性。借助低功耗传感与细粒度流水线技术,该方法的延迟比传统基于位切片的内存内VMM低4.5倍,能耗低12倍。此外,DA彻底消除了对高功耗ADC的需求,而ADC是当前内存内VMM实现中面积与能耗的主要来源。

英文摘要:

Vector-Matrix Multiplication (VMM) is the fundamental and frequently required computation in inference of Neural Networks (NN). Due to the large data movement required during inference, VMM can benefit greatly from in-memory computing. However, ADC/DACs required for in-memory VMM consume significant power and area. `Distributed Arithmetic (DA)', a technique in computer architecture prevalent in 1980s was used to achieve inner product or dot product of two vectors without using a hard-wired multiplier when one of the vectors is a constant. In this work, we extend the DA technique to multiply an input vector with a constant matrix. By storing the sum of the weights in memory, DA achieves VMM using shift-and-add circuits in the periphery of ReRAM memory. We verify functional and also estimate non-functional properties (latency, energy, area) by performing transistor-level simulations. Using energy-efficient sensing and fine grained pipelining, our approach achieves 4.5 x less latency and 12 x less energy than VMM performed in memory conventionally by bit slicing. Furthermore, DA completely eliminated the need for power-hungry ADCs which are the main source of area and energy consumption in the current VMM implementations in memory.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑