A Practical Highly Paralleled ReRAM-Based DNN Accelerator by Reusing Weight Pattern Repetitions
| Autor: | Zhaoyan Shen, Yuhao Zhang, Hongchao Du, Zili Shao, Runzhen Xue, Zhiping Jia |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 41:922-935 |
| ISSN: | 1937-4151 0278-0070 |
| DOI: | 10.1109/tcad.2021.3071116 |
| Popis: | Resistive random access memory (ReRAM)-based processing-in-memory (PIM) architecture has been designed to accelerate deep neural networks (DNN) by concurring computation and memory barriers. To further improve memory and computation efficiency, the weight sparsity characteristic has been explored to optimize the ReRAM-based DNN accelerators. However, these designs only focus on compressing zero weights to eliminate ineffectual computation. In this paper, we thoroughly analyze the weight distribution characteristics of several typical DNN models and observe many non-zero weight pattern repetitions (WPR). Therefore, there is an opportunity to further improve the performance and energy efficiency by reusing these WPR. We propose a novel ReRAM-based accelerator — PattPIM, to achieve space compression and computation reuse by exploring DNN WPR based on practical ReRAM crossbars. In PattPIM, we propose a configurable WPR-aware DNN engine and a WPR-to-OU mapping scheme to save both space and computation resources. An intra-processing engine (PE) pipeline is designed to improve the parallelism of the computation process. Furthermore, we adopt an approximate weight pattern transform algorithm to improve the DNN WPR ratio to enhance the reuse efficiency with negligible accuracy loss. Our evaluation with 6 DNN models shows that the proposed PattPIM delivers significant performance improvement, ReRAM resource efficiency and energy saving. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|