English
Related papers

Related papers: Microbenchmarking NVIDIA's Blackwell Architecture:…

200 papers

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-23 Aaron Jarmusch , Nathan Graddon , Sunita Chandrasekaran

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…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-07 Aaron Jarmusch , Sunita Chandrasekaran

Modern datacenters increasingly rely on low-power, single-slot inference accelerators to balance performance, energy efficiency, and rack density constraints. The NVIDIA T4 GPU has become widely deployed due to strong performance per watt…

Performance · Computer Science 2026-05-07 Kathiravan Palaniappan

Every year, novel NVIDIA GPU designs are introduced. This rapid architectural and technological progression, coupled with a reluctance by manufacturers to disclose low-level details, makes it difficult for even the most proficient GPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-04-19 Zhe Jia , Marco Maggioni , Benjamin Staiger , Daniele P. Scarpazza

This paper presents datacenter power profiles, a new NVIDIA software feature released with Blackwell B200, aimed at improving energy efficiency and/or performance. The initial feature provides coarse-grain user control for HPC and AI…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-08 Sreedhar Narayanaswamy , Pratikkumar Dilipkumar Patel , Ian Karlin , Apoorv Gupta , Sudhir Saripalli , Janey Guo

This study presents a comprehensive multi-level analysis of the NVIDIA Hopper GPU architecture, focusing on its performance characteristics and novel features. We benchmark Hopper's memory subsystem, highlighting improvements in the L2…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-05 Weile Luo , Ruibo Fan , Zeyu Li , Dayou Du , Hongyuan Liu , Qiang Wang , Xiaowen Chu

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…

Computation and Language · Computer Science 2026-03-06 Ted Zadouri , Markus Hoehnerbach , Jay Shah , Timmy Liu , Vijay Thakkar , Tri Dao

Memory access efficiency is a key factor in fully utilizing the computational power of graphics processing units (GPUs). However, many details of the GPU memory hierarchy are not released by GPU vendors. In this paper, we propose a novel…

Hardware Architecture · Computer Science 2016-03-15 Xinxin Mei , Xiaowen Chu

Largely due to their increased native capacity for numerical intensity and power efficiency, reduced-precision floating-point computing resources, primarily used in artificial intelligence (AI) applications, have expanded at a greater rate…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-19 Harun Bayraktar , Cole Brower , John Gunnels , Greg Henry , Cherin Joseph , Jack Kosaian , Dmitry Lyakh , Lukas Mosimann , Victor Podlozhnyuk , Addison Richards , Paul Springer , Haicheng Wu

Finite element simulations play a critical role in a wide range of applications, from automotive design to tsunami modeling and computational electromagnetics. Performing these simulations efficiently at the high resolutions needed for…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-13 Jiqun Tu , Ian Karlin , John Camier , Veselin Dobrev , Tzanio Kolev , Stefan Henneking , Omar Ghattas

We investigate the performance of the concurrency mechanisms available on NVIDIA's new Ampere GPU microarchitecture under deep learning training and inference workloads. In contrast to previous studies that treat the GPU as a black box, we…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-04 Guin Gilman , Robert J. Walls

In 2019, the rapid rate at which GPU manufacturers refresh their designs, coupled with their reluctance to disclose microarchitectural details, is still a hurdle for those software designers who want to extract the highest possible…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-03-19 Zhe Jia , Marco Maggioni , Jeffrey Smith , Daniele Paolo Scarpazza

The efficacy of deep learning has resulted in its use in a growing number of applications. The Volta graphics processor unit (GPU) architecture from NVIDIA introduced a specialized functional unit, the "tensor core", that helps meet the…

Mathematical Software · Computer Science 2019-02-22 Md Aamir Raihan , Negar Goli , Tor Aamodt

Graphics processing units (GPUs) are continually evolving to cater to the computational demands of contemporary general-purpose workloads, particularly those driven by artificial intelligence (AI) utilizing deep learning techniques. A…

Hardware Architecture · Computer Science 2024-02-22 Weile Luo , Ruibo Fan , Zeyu Li , Dayou Du , Qiang Wang , Xiaowen Chu

The NVIDIA Volta GPU microarchitecture introduces a specialized unit, called "Tensor Core" that performs one matrix-multiply-and-accumulate on 4x4 matrices per clock cycle. The NVIDIA Tesla V100 accelerator, featuring the Volta…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-12-18 Stefano Markidis , Steven Wei Der Chien , Erwin Laure , Ivy Bo Peng , Jeffrey S. Vetter

Despite foreseeing tremendous speedups over conventional deep neural networks, the performance advantage of binarized neural networks (BNNs) has merely been showcased on general-purpose processors such as CPUs and GPUs. In fact, due to…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-12-16 Ang Li , Simon Su

Tensor Cores have been an important unit to accelerate Fused Matrix Multiplication Accumulation (MMA) in all NVIDIA GPUs since Volta Architecture. To program Tensor Cores, users have to use either legacy wmma APIs or current mma APIs.…

Hardware Architecture · Computer Science 2022-11-29 Wei Sun , Ang Li , Tong Geng , Sander Stuijk , Henk Corporaal

NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs. We…

Machine Learning · Computer Science 2026-04-28 Divakar Kumar Yadav , Tian Zhao , Deepak Kumar

Graphics processing units (GPUs) are now considered the leading hardware to accelerate general-purpose workloads such as AI, data analytics, and HPC. Over the last decade, researchers have focused on demystifying and evaluating the…

Hardware Architecture · Computer Science 2022-08-25 Hamdy Abdelkhalik , Yehia Arafa , Nandakishore Santhi , Abdel-Hameed Badawy

Modern NVIDIA GPUs like the H100 (HBM2e) and H200 (HBM3e) share similar compute characteristics but differ significantly in memory interface technology and bandwidth. By isolating memory bandwidth as a key variable, the power distribution…

Performance · Computer Science 2026-04-14 Aditya Ujeniya , Jan Eitzinger , Georg Hager , Gerhard Wellein
‹ Prev 1 2 3 10 Next ›