Related papers: Isambard-AI: a leadership class supercomputer opti…
This paper presents a comprehensive evaluation of Intel Gaudi NPUs as an alternative to NVIDIA GPUs, which is currently the de facto standard in AI system design. First, we create a suite of microbenchmarks to compare Intel Gaudi-2 with…
3D point cloud neural networks have significantly enhanced the perceptual capabilities of resource-limited mobile intelligent systems. However, despite the transformative impact, the point cloud algorithm suffers from substantial memory…
IEEE 802.11ad-based integrated sensing and communications (ISAC) have been identified as a potential solution for enabling next-generation intelligent transportation systems in the millimeter wave (mmW) spectrum. The radar functionality…
High-end ARM processors are emerging in data centers and HPC systems, posing as a strong contender to x86 machines. Memory-centric profiling is an important approach for dissecting an application's bottlenecks on memory access and guiding…
Processing-in-Memory (PIM) architectures offer promising solutions for efficiently handling AI applications in energy-constrained edge environments. While traditional PIM designs enhance performance and energy efficiency by reducing data…
This document presents a vision for a novel AI infrastructure design that has been initially validated through inference simulations on state-of-the-art large language models. Advancements in deep learning and specialized hardware have…
In this paper, we propose a 'full-stack' solution to designing high capacity and low latency on-chip cache hierarchies by starting at the circuit level of the hardware design stack. First, we propose a novel Gain Cell (GC) design using…
New types of machine learning hardware in development and entering the market hold the promise of revolutionizing deep learning in a manner as profound as GPUs. However, existing software frameworks and training algorithms for deep learning…
The rapid adaptation of data driven AI models, such as deep learning inference, training, Vision Transformers (ViTs), and other HPC applications, drives a strong need for runtime precision configurable different non linear activation…
AI acceleration has been dominated by GPUs, but the growing need for lower latency, energy efficiency, and fine-grained hardware control exposes the limits of fixed architectures. In this context, Field-Programmable Gate Arrays (FPGAs)…
In this paper we present D.A.V.I.D.E. (Development for an Added Value Infrastructure Designed in Europe), an innovative and energy efficient High Performance Computing cluster designed by E4 Computer Engineering for PRACE (Partnership for…
Optical computing has been recently proposed as a new compute paradigm to meet the demands of future AI/ML workloads in datacenters and supercomputers. However, proposed implementations so far suffer from lack of scalability, large…
In the last decade, Deep Learning has rapidly infiltrated the consumer end, mainly thanks to hardware acceleration across devices. However, as we look towards the future, it is evident that isolated hardware will be insufficient.…
The Cray T3D, an MIMD system with NUMA shared memory capabilities and in principle very low communications latency, can support the Canopy framework for grid-oriented applications. CANOPY has been ported to the T3D, with the intent of…
The field of edge computing has witnessed remarkable growth owing to the increasing demand for real-time processing of data in applications. However, challenges persist due to limitations in performance and power consumption. To overcome…
Computational resource constraints on edge devices make it difficult to develop a fully embedded AI companion system with a satisfactory user experience. AI companion and memory systems detailed in existing literature cannot be directly…
While frontier large language models (LLMs) continue to push capability boundaries, their deployment remains confined to GPU-powered cloud infrastructure. We challenge this paradigm with SmallThinker, a family of LLMs natively designed -…
Reconfigurable architectures like Field Programmable Gate Arrays (FPGAs) have been used for accelerating computations in several domains because of their unique combination of flexibility, performance, and power efficiency. However, FPGAs…
A vertically integrated, end-to-end, research prototype system combines 288 NorthPole neural inference accelerator cards, offline training algorithms, a high-performance runtime stack, and a containerized inference pipeline to deliver a…
Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…