BlockAMC: Scalable In-Memory Analog Matrix Computing for Solving Linear Systems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911760372465664 |
|---|---|
| author | Pan, Lunshuai Zuo, Pushen Luo, Yubiao Sun, Zhong Huang, Ru |
| author_facet | Pan, Lunshuai Zuo, Pushen Luo, Yubiao Sun, Zhong Huang, Ru |
| contents | Recently, in-memory analog matrix computing (AMC) with nonvolatile resistive memory has been developed for solving matrix problems in one step, e.g., matrix inversion of solving linear systems. However, the analog nature sets up a barrier to the scalability of AMC, due to the limits on the manufacturability and yield of resistive memory arrays, non-idealities of device and circuit, and cost of hardware implementations. Aiming to deliver a scalable AMC approach for solving linear systems, this work presents BlockAMC, which partitions a large original matrix into smaller ones on different memory arrays. A macro is designed to perform matrix inversion and matrix-vector multiplication with the block matrices, obtaining the partial solutions to recover the original solution. The size of block matrices can be exponentially reduced by performing multiple stages of divide-and-conquer, resulting in a two-stage solver design that enhances the scalability of this approach. BlockAMC is also advantageous in alleviating the accuracy issue of AMC, especially in the presence of device and circuit non-idealities, such as conductance variations and interconnect resistances. Compared to a single AMC circuit solving the same problem, BlockAMC improves the area and energy efficiency by 48.83% and 40%, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_10042 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BlockAMC: Scalable In-Memory Analog Matrix Computing for Solving Linear Systems Pan, Lunshuai Zuo, Pushen Luo, Yubiao Sun, Zhong Huang, Ru Hardware Architecture Distributed, Parallel, and Cluster Computing Recently, in-memory analog matrix computing (AMC) with nonvolatile resistive memory has been developed for solving matrix problems in one step, e.g., matrix inversion of solving linear systems. However, the analog nature sets up a barrier to the scalability of AMC, due to the limits on the manufacturability and yield of resistive memory arrays, non-idealities of device and circuit, and cost of hardware implementations. Aiming to deliver a scalable AMC approach for solving linear systems, this work presents BlockAMC, which partitions a large original matrix into smaller ones on different memory arrays. A macro is designed to perform matrix inversion and matrix-vector multiplication with the block matrices, obtaining the partial solutions to recover the original solution. The size of block matrices can be exponentially reduced by performing multiple stages of divide-and-conquer, resulting in a two-stage solver design that enhances the scalability of this approach. BlockAMC is also advantageous in alleviating the accuracy issue of AMC, especially in the presence of device and circuit non-idealities, such as conductance variations and interconnect resistances. Compared to a single AMC circuit solving the same problem, BlockAMC improves the area and energy efficiency by 48.83% and 40%, respectively. |
| title | BlockAMC: Scalable In-Memory Analog Matrix Computing for Solving Linear Systems |
| topic | Hardware Architecture Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2401.10042 |