Document detail
ID

oai:arXiv.org:2402.18114

Topic
Computer Science - Hardware Archit...
Author
Li, Wanqian Sun, Xiaotian Wang, Xinyu Wang, Lei Han, Yinhe Chen, Xiaoming
Category

Computer Science

Year

2024

listing date

3/6/2024

Keywords
pimsyn
Metrics

Abstract

Processing-in-memory architectures have been regarded as a promising solution for CNN acceleration.

Existing PIM accelerator designs rely heavily on the experience of experts and require significant manual design overhead.

Manual design cannot effectively optimize and explore architecture implementations.

In this work, we develop an automatic framework PIMSYN for synthesizing PIM-based CNN accelerators, which greatly facilitates architecture design and helps generate energyefficient accelerators.

PIMSYN can automatically transform CNN applications into execution workflows and hardware construction of PIM accelerators.

To systematically optimize the architecture, we embed an architectural exploration flow into the synthesis framework, providing a more comprehensive design space.

Experiments demonstrate that PIMSYN improves the power efficiency by several times compared with existing works.

PIMSYN can be obtained from https://github.com/lixixi-jook/PIMSYN-NN.

Li, Wanqian,Sun, Xiaotian,Wang, Xinyu,Wang, Lei,Han, Yinhe,Chen, Xiaoming, 2024, PIMSYN: Synthesizing Processing-in-memory CNN Accelerators

Document

Open

Share

Source

Articles recommended by ES/IODE AI

Systematic druggable genome-wide Mendelian randomization identifies therapeutic targets for lung cancer
agphd1 subtypes replication hykk squamous cell gene carcinoma causal targets mendelian randomization cancer analysis