ISOAcc: In-situ Shift Operation-based Accelerator For Efficient in-SRAM Multiplication
Open Access
- 10 January 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 30 (2) , 1-24
Abstract
Digital SRAM-based CIM architectures must balance three critical factors: quantized neural network bitwidth, accuracy loss, and computational efficiency, each crucial to optimizing performance and efficiency. In Domain Specific Accelerators (DSAs), flexible and specific hardware design, when incorporated with tailored Power-of-2 (P-2) quantization schemes, addresses this issue. However, in CIMs, the absence of flexible and specific hardware to support dynamic switching between general and tailored quantization schemes hinders the adoption of efficient quantization methods. In this article, we propose the I n-situ S hift O peration based Acc elerator ( ISOAcc ) for efficient SRAM-based multiplication. The key idea is to introduce transmission gates near the SRAM array to enable the selection of bits from either the same or the neighbor line when data flows from one row to another. This functionally equals a shift operation. By configuring the transmission gates array in a cascade manner, ISOAcc can support 0 to 15-bit shift with a negligible overhead. The ISOAcc can directly leverage P-2 quantization schemes in hardware, thereby greatly reducing multiplication cycles. We have chosen five well-known neural networks to evaluate ISOAcc. The evaluations show that ISOAcc achieves an average performance improvement of 3.24× and an energy reduction of 75%, compared with the state-of-the-art (SOTA) SRAM-based CIM design, Bit-Parallel.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20301, 62102433, 62272477)
- NUDT Foundation (No.ZK2023-16, 2022-KJWPDL-08)
- NSF of Hunan Province (2022JJ10066)
This publication has 48 references indexed in Scilit:
- Improving Medical Speech-to-Text Accuracy using Vision-Language Pre-training ModelsIEEE Journal of Biomedical and Health Informatics, 2023
- VSPIM: SRAM Processing-in-Memory DNN Acceleration via Vector-Scalar OperationsIEEE Transactions on Computers, 2023
- SDP: Co-Designing Algorithm, Dataflow, and Architecture for In-SRAM Sparse NN AccelerationIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022
- NVIDIA A100 Tensor Core GPU: Performance and InnovationIEEE Micro, 2021
- Z-PIM: A Sparsity-Aware Processing-in-Memory Architecture With Fully Variable Weight Bit-Precision for Energy-Efficient Deep Neural NetworksIEEE Journal of Solid-State Circuits, 2021
- Towards Co-designing Neural Network Function Approximators with In-SRAM Computing2019
- A Twin-8T SRAM Computation-in-Memory Unit-Macro for Multibit CNN-Based AI Edge ProcessorsIEEE Journal of Solid-State Circuits, 2019
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- NVSim: A Circuit-Level Performance, Energy, and Area Model for Emerging Nonvolatile MemoryIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2012
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998