paper-with-me

Papers

Systolic Array-based Accelerator for Structured State-Space Models

2025-07-29 · Shiva Raja, Cansu Demirkiran, Aakash Sarkar, Milos Popovic, Ajay Joshi arxiv

Sequence modeling is crucial for AI to understand temporal data and detect complex time-dependent patterns. While recurrent neural networks (RNNs), convolutional neural networks (CNNs), and Transformers have advanced in capturing long-range dependencies, they struggle with achieving high accuracy with very long sequences due to limited memory retention (fixed context window). State-Space Models (SSMs) leverage exponentially decaying memory enabling lengthy context window and so they process very long data sequences more efficiently than recurrent and Transformer-based models. Unlike traditional neural models like CNNs and RNNs, SSM-based models require solving differential equations through continuous integration, making training and inference both compute- and memory-intensive on conventional CPUs and GPUs. In this paper we introduce a specialized hardware accelerator, EpochCore, for accelerating SSMs. EpochCore is based on systolic arrays (SAs) and is designed to enhance the energy efficiency and throughput of inference of SSM-based models for long-range sequence tasks. Within the SA, we propose a versatile processing element (PE) called LIMA-PE to perform traditional and specialized MAC operations to support traditional DNNs and SSMs. To complement the EpochCore microarchitecture, we propose a novel dataflow, ProDF, which enables highly efficient execution of SSM-based models. By leveraging the LIMA-PE microarchitecture and ProDF, EpochCore achieves on average 2000x improvement in performance on LRA datasets compared to a GPU and 250x gains in performance and 45x improvement in energy efficiency, over traditional SA-based accelerators (TPU).

📄 PDF Abstract BibTeX arXiv:2507.21394

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 …

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…

S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN Acceleration

2021-07-16 · Zhi-Gang Liu, Paul N. Whatmough, Yuhao Zhu, Matthew Mattina

Exploiting sparsity is a key technique in accelerating quantized convolutional neural network (CNN) inference on mobile devices. Prior sparse CNN accelerators largely exploit un-structured sparsity and achieve significan…

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

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 …