paper-with-me

Papers

Towards Efficient IMC Accelerator Design Through Joint Hardware-Workload Co-optimization

2024-10-22 · Olga Krestinskaya, Mohammed E. Fouda, Ahmed Eltawil, Khaled N. Salama

Designing generalized in-memory computing (IMC) hardware that efficiently supports a variety of workloads requires extensive design space exploration, which is infeasible to perform manually. Optimizing hardware individually for each workload or solely for the largest workload often fails to yield the most efficient generalized solutions. To address this, we propose a joint hardware-workload optimization framework that identifies optimised IMC chip architecture parameters, enabling more efficient, workload-flexible hardware. We show that joint optimization achieves 36%, 36%, 20%, and 69% better energy-latency-area scores for VGG16, ResNet18, AlexNet, and MobileNetV3, respectively, compared to the separate architecture parameters search optimizing for a single largest workload. Additionally, we quantify the performance trade-offs and losses of the resulting generalized IMC hardware compared to workload-specific IMC designs.

📄 PDF Abstract BibTeX arXiv:2410.16759

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Average Pooling 설명 없음
ReLU6 ReLU6 is a modification of the rectified linear unit where we limit the activation to a maximum size of $6$. This is due to increased…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Batch Normalization 설명 없음
Hard Swish Hard Swish is a type of activation function based on Swish, but replaces the computationally expensive sigmoid with a piecewise…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Similar Papers 제목 키워드 기반

Joint Hardware-Workload Co-Optimization for In-Memory Computing Accelerators

2026-03-04 · Olga Krestinskaya, Mohammed E. Fouda, Ahmed Eltawil, Khaled N. Salama arxiv

Software-hardware co-design is essential for optimizing in-memory computing (IMC) hardware accelerators for neural networks. However, most existing optimization frameworks target a single workload, leading to highly spec…

A3C3: AI Algorithm and Accelerator Co-design, Co-search, and Co-generation

2026-06-18 · Selin Yildirim, Yingbing Huang, Deming Chen arxiv

We present a holistic methodology for artificial intelligence algorithm and accelerator co-design, co-search, and co-generation (A3C3), which jointly optimizes neural network architectures and their hardware implementati…

The Pitfall of Evaluating Performance on Emerging AI Accelerators

2019-11-08 · Zihan Jiang, Jiansong Li, Jiangfeng Zhan

In recent years, domain-specific hardware has brought significant performance improvements in deep learning (DL). Both industry and academia only focus on throughput when evaluating these AI accelerators, which usually a…

An Open-Source HW-SW Co-Development Framework Enabling Efficient Multi-Accelerator Systems

2025-08-20 · Ryan Albert Antonio, Joren Dumoulin, Xiaoling Yi, Josse Van Delm 외 arxiv

Heterogeneous accelerator-centric compute clusters are emerging as efficient solutions for diverse AI workloads. However, current integration strategies often compromise data movement efficiency and encounter compatibili…

A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators

2021-05-26 · Dan Zhang, Safeen Huda, Ebrahim Songhori, Kartik Prabhu 외

The rapidly-changing deep learning landscape presents a unique opportunity for building inference accelerators optimized for specific datacenter-scale workloads. We propose Full-stack Accelerator Search Technique (FAST),…

Optical Character Recognition (OCR)Scheduling