Related papers: FEATHER: A Reconfigurable Accelerator with Data Re…

The impact of transformer networks is booming, yet, they come with significant computational complexity. It is therefore essential to understand how to optimally map and execute these networks on modern neural processor hardware. So far,…

This document is one of the deliverable reports created for the ESCAPE project. ESCAPE stands for Energy-efficient Scalable Algorithms for Weather Prediction at Exascale. The project develops world-class, extreme-scale computing…

Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced…

As artificial intelligence (AI) and machine learning (ML) technologies disrupt a wide range of industries, cloud datacenters face ever-increasing demand in inference workloads. However, conventional CPU-based servers cannot handle excessive…

The increasing complexity of transformer models in artificial intelligence expands their computational costs, memory usage, and energy consumption. Hardware acceleration tackles the ensuing challenges by designing processors and…

Federated edge learning (FEEL) enables collaborative model training across distributed clients over wireless networks without exposing raw data. While most existing studies assume static datasets, in real-world scenarios clients may…

Attention is a fundamental computational kernel that accounts for the majority of the workload in transformer and LLM computing. Optimizing dataflow is crucial for enhancing both performance and energy efficiency in attention computation.…

Computational Fluid Dynamics (CFD) simulations are essential for analyzing and optimizing fluid flows in a wide range of real-world applications. These simulations involve approximating the solutions of the Navier-Stokes differential…

The growing deployment of sensors as part of Internet of Things (IoT) is generating thousands of event streams. Complex Event Processing (CEP) queries offer a useful paradigm for rapid decision-making over such data sources. While often…

Emerging AI-enabled applications such as augmented/virtual reality (AR/VR) leverage multiple deep neural network (DNN) models for sub-tasks such as object detection, hand tracking, and so on. Because of the diversity of the sub-tasks, the…

Time-series forecasting is fundamental in industrial domains like manufacturing and smart factories. As systems evolve toward automation, models must operate on edge devices (e.g., PLCs, microcontrollers) with strict constraints on latency…

Memory bandwidth is known to be a performance bottleneck for FPGA accelerators, especially when they deal with large multi-dimensional data-sets. A large body of work focuses on reducing of off-chip transfers, but few authors try to improve…

Machine learning models deployed on edge devices have enabled numerous exciting new applications, such as humanoid robots, AR glasses, and autonomous vehicles. However, the computing resources available on these edge devices are not…

Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate results between computation kernels can significantly improve…

Large Language Models drive a wide range of modern AI applications but impose substantial challenges on large-scale serving systems due to intensive computation, strict latency constraints, and throughput bottlenecks. We introduce…

Dynamic offloading of Machine Learning (ML) model partitions across different resource orchestration services, such as Function-as-a-Service (FaaS) and Infrastructure-as-a-Service (IaaS), can balance processing and transmission delays while…

Vector processors frequently suffer from inefficient memory accesses, particularly for strided and segment patterns. While coalescing strided accesses is a natural solution, effectively gathering or scattering elements at fixed strides…

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop…

Autoregressive models, despite their commendable performance in a myriad of generative tasks, face challenges stemming from their inherently sequential structure. Inference on these models, by design, harnesses a temporal dependency, where…

Machine learning, particularly deep neural network inference, has become a vital workload for many computing systems, from data centers and HPC systems to edge-based computing. As advances in sparsity have helped improve the efficiency of…