Related papers: An ultra-low-power CGRA for accelerating Transform…

The scientific community increasingly relies on machine learning (ML) for near-sensor processing, leveraging its strengths in tasks such as pattern recognition, anomaly detection, and real-time decision-making. These deployments demand…

In natural language processing (NLP), the "Transformer" architecture was proposed as the first transduction model replying entirely on self-attention mechanisms without using sequence-aligned recurrent neural networks (RNNs) or convolution,…

Processing-In-Memory (PIM) architectures offer a promising approach to accelerate Graph Neural Network (GNN) training and inference. However, various PIM devices such as ReRAM, FeFET, PCM, MRAM, and SRAM exist, with each device offering…

Coarse-Grained Reconfigurable Architectures (CGRAs) are a promising and versatile accelerator platform, offering a balance between the performance and efficiency of specialized accelerators and the software programmability. However, their…

Modern computing workloads, particularly in AI and edge applications, demand hardware-software co-design to meet aggressive performance and energy targets. Such co-design benefits from open and agile platforms that replace closed,…

General matrix multiplication (GEMM) is a ubiquitous computing kernel/algorithm for data processing in diverse applications, including artificial intelligence (AI) and deep learning (DL). Recent shift towards edge computing has inspired…

This work presents TREA, a low-precision time-multiplexed and resource-efficient edge-AI accelerator for object detection and classification, targeting stringent area-power-latency constraints of edge vision platforms. The proposed…

Transformer-based speech enhancement models yield impressive results. However, their heterogeneous and complex structure restricts model compression potential, resulting in greater complexity and reduced hardware efficiency. Additionally,…

Transformer training systems are built around dense linear algebra, yet a nontrivial fraction of end-to-end time is spent on surrounding memory-bound operators. Normalization, activations, residual updates, reductions, and related…

Transformer-based models have demonstrated superior performance in various fields, including natural language processing and computer vision. However, their enormous model size and high demands in computation, memory, and communication…

Convolutional Neural Networks (CNNs) are fundamental to deep learning, driving applications across various domains. However, their growing complexity has significantly increased computational demands, necessitating efficient hardware…

Coarse-grained reconfigurable architectures (CGRAs) are programmable logic devices with large coarse-grained ALU-like logic blocks, and multi-bit datapath-style routing. CGRAs often have relatively restricted data routing networks, so they…

Deep Neural Networks (DNNs) and Large Language Models (LLMs) have revolutionized artificial intelligence, yet their deployment faces significant memory and computational challenges, especially in resource-constrained environments.…

Increasing demands for computing power also propel the need for energy-efficient SoC accelerator architectures. One class of such accelerators are so-called processor arrays, which typically integrate a two-dimensional mesh of…

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable…

This work introduces a highly efficient implementation of the transformer architecture on a Field-Programmable Gate Array (FPGA) by using the \texttt{hls4ml} tool. Given the demonstrated effectiveness of transformer models in addressing a…

While coarse-grained reconfigurable arrays (CGRAs) have emerged as promising programmable accelerator architectures, pipelining applications running on CGRAs is required to ensure high maximum clock frequencies. Current CGRA compilers…

Coarse-Grained Reconfigurable Arrays (CGRAs) enable ease of programmability and result in low development costs. They enable the ease of use specifically in reconfigurable computing applications. The smaller cost of compilation and reduced…

General matrix-matrix multiplication (GEMM) is a cornerstone of AI computations, making tensor processing engines (TPEs) increasingly critical in GPUs and domain-specific architectures. Existing architectures primarily optimize dataflow or…

An important linear algebra routine, GEneral Matrix Multiplication (GEMM), is a fundamental operator in deep learning. Compilers need to translate these routines into low-level code optimized for specific hardware. Compiler-level…