OPTIMA: Design-Space Exploration of Discharge-Based In-SRAM Computing: Quantifying Energy-Accuracy Trade-Offs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seyedfaraji, Saeed, Jager, Severin, Shakibhamedan, Salar, Aftab, Asad, Rehman, Semeen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916476941762560
author Seyedfaraji, Saeed
Jager, Severin
Shakibhamedan, Salar
Aftab, Asad
Rehman, Semeen
author_facet Seyedfaraji, Saeed
Jager, Severin
Shakibhamedan, Salar
Aftab, Asad
Rehman, Semeen
contents In-SRAM computing promises energy efficiency, but circuit nonlinearities and PVT variations pose major challenges in designing robust accelerators. To address this, we introduce OPTIMA, a modeling framework that aids in analyzing bit-line discharge and power consumption in 6T-SRAM-based accelerators. It provides insights into limiting factors and enables fast design-space exploration of circuit configurations. Leveraging OPTIMA for in-SRAM multiplications exhibits ~100x simulation speed-up while maintaining an RMS modeling error of 0.88mV. Exploration yields an optimized multiplier with 1.05pJ energy consumption per 4-bit operation and classification accuracies of 71.8% (top-1) and 90.4% (top-5) for ImageNet and 92.5% for CIFAR-10 datasets respectively when applied in quantized DNNs. To further support research and development, we made our tool flow available open source at https://github.com/sevjaeg/optima.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06846
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OPTIMA: Design-Space Exploration of Discharge-Based In-SRAM Computing: Quantifying Energy-Accuracy Trade-Offs
Seyedfaraji, Saeed
Jager, Severin
Shakibhamedan, Salar
Aftab, Asad
Rehman, Semeen
Hardware Architecture
Performance
In-SRAM computing promises energy efficiency, but circuit nonlinearities and PVT variations pose major challenges in designing robust accelerators. To address this, we introduce OPTIMA, a modeling framework that aids in analyzing bit-line discharge and power consumption in 6T-SRAM-based accelerators. It provides insights into limiting factors and enables fast design-space exploration of circuit configurations. Leveraging OPTIMA for in-SRAM multiplications exhibits ~100x simulation speed-up while maintaining an RMS modeling error of 0.88mV. Exploration yields an optimized multiplier with 1.05pJ energy consumption per 4-bit operation and classification accuracies of 71.8% (top-1) and 90.4% (top-5) for ImageNet and 92.5% for CIFAR-10 datasets respectively when applied in quantized DNNs. To further support research and development, we made our tool flow available open source at https://github.com/sevjaeg/optima.
title OPTIMA: Design-Space Exploration of Discharge-Based In-SRAM Computing: Quantifying Energy-Accuracy Trade-Offs
topic Hardware Architecture
Performance
url https://arxiv.org/abs/2411.06846