paper-with-me

Papers

VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration

2025-06-01 · Shereef Helal, Alberto Garcia-Ortiz, Lennart Bamberg

Leveraging high degrees of unstructured sparsity is a promising approach to enhance the efficiency of deep neural network DNN accelerators - particularly important for emerging Edge-AI applications. We introduce VUSA, a systolic-array architecture that virtually grows based on the present sparsity to perform larger matrix multiplications with the same number of physical multiply-accumulate MAC units. The proposed architecture achieves saving by 37% and 68% in area and power efficiency, respectively, at the same peak-performance, compared to a baseline systolic array architecture in a commercial 16-nm technology. Still, the proposed architecture supports acceleration for any DNN with any sparsity - even no sparsity at all. Thus, the proposed architecture is application-independent, making it viable for general-purpose AI acceleration.

📄 PDF Abstract BibTeX arXiv:2506.01166

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training

2020-04-27 · Sangkug Lym, Mattan Erez

Modern deep learning models have high memory and computation cost. To make them fast and memory-cost efficient, structured model pruning is commonly used. We find that pruning a model using a common training accelerator …

SystolicAttention: Fusing FlashAttention within a Single Systolic Array

2025-07-15 · Jiawei Lin, Guokai Chen, Yuanlong Li, Thomas Bourgeat

Transformer models rely heavily on scaled dot-product attention (SDPA), typically implemented using the FlashAttention algorithm. However, current systolic-array-based accelerators face significant challenges when execut…

Scheduling

FORTALESA: Fault-Tolerant Reconfigurable Systolic Array for DNN Inference

2025-03-06 · Natalia Cherezova, Artur Jutman, Maksim Jenihhin

The emergence of Deep Neural Networks (DNNs) in mission- and safety-critical applications brings their reliability to the front. High performance demands of DNNs require the use of specialized hardware accelerators. Syst…

ArrayFlex: A Systolic Array Architecture with Configurable Transparent Pipelining

2022-11-22 · C. Peltekis, D. Filippas, G. Dimitrakopoulos, C. Nicopoulos 외

Convolutional Neural Networks (CNNs) are the state-of-the-art solution for many deep learning applications. For maximum scalability, their computation should combine high performance and energy efficiency. In practice, t…

Scale-out Systolic Arrays

2022-03-22 · Ahmet Caner Yüzügüler, Canberk Sönmez, Mario Drumond, Yunho Oh 외

Multi-pod systolic arrays are emerging as the architecture of choice in DNN inference accelerators. Despite their potential, designing multi-pod systolic arrays to maximize effective throughput/Watt (i.e., throughput/Wat…