Related papers: ABI: A tightly integrated, unified, sparsity-aware…
The rapid development in scientific research provides a need for more compute power, which is partly being solved by GPUs. This paper presents a microarchitectural analysis of the modern NVIDIA Blackwell architecture by studying GPU…
As GPU architectures rapidly evolve to meet the growing demands of exascale computing and machine learning, the performance implications of architectural innovations remain poorly understood across diverse workloads. NVIDIA Blackwell (B200)…
Rapidly evolving GPU architectures featuring complex memory hierarchies, matrix units, and varied precision formats continue to widen the gap between theoretical peaks and achievable performance. We design and develop analytical performance…
The integration of Artificial Intelligence (AI) in education requires scalable and efficient frameworks that balance performance, adaptability, and cost. This paper addresses these needs by proposing a shared backbone model architecture…
Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…
This study introduces a novel AI microcontroller optimized for cost-effective, battery-powered edge AI applications. Unlike traditional single bit/cell memory configurations, the proposed microcontroller integrates zero-standby power weight…
Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized attention for Hopper GPUs through asynchronous execution and…
GPU accelerators have become an important backbone for scientific high performance computing, and the performance advances obtained from adopting new GPU hardware are significant. In this paper we take a first look at NVIDIA's newest server…
Atlas packing is a key step in many computer graphics applications. Packing algorithms seek to arrange a set of charts within a fixed-size atlas with as little downscaling as possible. Many packing applications such as content creation…
Transformer-based generative Artificial Intelligence (GenAI) models achieve remarkable results in a wide range of fields, including natural language processing, computer vision, and audio processing. However, this comes at the cost of…
We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the linear dependency on the vocabulary size by exploiting the…
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…
Graphics processing units (GPUs) excel at parallel processing, but remain largely unexplored in ultra-low-power edge devices (TinyAI) due to their power and area limitations, as well as the lack of suitable programming frameworks. To…
In particular, large-scale deep learning and artificial intelligence model training uses a lot of computational power and energy, so it poses serious sustainability issues. The fast rise in model complexity has resulted in exponential…
GPUs are critical for compute-intensive applications, yet emerging workloads such as recommender systems, graph analytics, and data analytics often exceed GPU memory capacity. Existing solutions allow GPUs to use CPU DRAM or SSDs as…
Implicit time integration is key to robustly simulating stiff materials and large deformations, but its performance is often dominated by repeatedly solving large linear systems. Adaptive coarsening can reduce this cost by concentrating…
Artificial Intelligence (AI) workloads drive a rapid expansion of high-performance computing (HPC) infrastructures and increase their power and energy demands towards a critical level. AI benchmarks representing state-of-the art workloads…
This paper presents a heterogeneous adaptive mesh refinement (AMR) framework for efficient simulation of moderately stiff reactive problems. This framework features an elaborate subcycling-in-time algorithm along with a specialized…
Compute-in-SRAM architectures offer a promising approach to achieving higher performance and energy efficiency across a range of data-intensive applications. However, prior evaluations have largely relied on simulators or small prototypes,…
Recent research efforts focus on reducing the computational and memory overheads of Large Language Models (LLMs) to make them feasible on resource-constrained devices. Despite advancements in compression techniques, non-linear operators…