English
Related papers

Related papers: Dynamic Memory Management on GPUs with SYCL

200 papers

Training transformer models requires substantial GPU compute and memory resources. In homogeneous clusters, distributed strategies allocate resources evenly, but this approach is inefficient for heterogeneous clusters, where GPUs differ in…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-15 Runsheng Benson Guo , Utkarsh Anand , Arthur Chen , Khuzaima Daudjee

The rapid growth of large language models is driving organizations to expand their GPU clusters, often with GPUs from multiple vendors. However, current deep learning frameworks lack support for collective communication across heterogeneous…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-02 Heehoon Kim , Jaehwan Lee , Taejeoung Kim , Jongwon Park , Jinpyo Kim , Pyongwon Suh , Ryan H. Choi , Sangwoo Lee , Jaejin Lee

State of art DL models are growing in size and complexity, with many modern models also increasing in heterogeneity of behavior. GPUs are still the dominant platform for DL applications, relying on a bulk-synchronous execution model which…

Hardware Architecture · Computer Science 2025-02-26 Michael Davies , Neal Crago , Karthikeyan Sankaralingam , Stephen W. Keckler

The demand for efficient machine learning (ML) accelerators is growing rapidly, driving the development of novel computing concepts such as resistive random access memory (RRAM)-based tiled computing-in-memory (CIM) architectures. CIM…

Hardware Architecture · Computer Science 2024-01-18 Rebecca Pelke , Jose Cubero-Cascante , Nils Bosbach , Felix Staudigl , Rainer Leupers , Jan Moritz Joseph

HiCCL (Hierarchical Collective Communication Library) addresses the growing complexity and diversity in high-performance network architectures. As GPU systems have envolved into networks of GPUs with different multilevel communication…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-08-13 Mert Hidayetoglu , Simon Garcia de Gonzalo , Elliott Slaughter , Pinku Surana , Wen-mei Hwu , William Gropp , Alex Aiken

The reversible object-oriented programming language (ROOPL) was presented in late 2016 and proved that object-oriented programming paradigms works in the reversible setting. The language featured simple statically scoped objects which made…

Programming Languages · Computer Science 2018-04-17 Martin Holm Cservenka

The evolution of the computing landscape has resulted in the proliferation of diverse hardware architectures, with different flavors of GPUs and other compute accelerators becoming more widely available. To facilitate the efficient use of…

High Energy Physics - Experiment · Physics 2023-04-05 Meifeng Lin , Zhihua Dong , Tianle Wang , Mohammad Atif , Meghna Battacharya , Kyle Knoepfel , Charles Leggett , Brett Viren , Haiwang Yu

Hardware peripherals such as GPUs and FPGAs are commonly available in server-grade computing to accelerate specific compute tasks, from database queries to machine learning. CSPs have integrated these accelerators into their infrastructure…

Cryptography and Security · Computer Science 2023-03-10 Thore Tiemann , Zane Weissman , Thomas Eisenbarth , Berk Sunar

Histograms are widely used in medical imaging, network intrusion detection, packet analysis and other stream-based high throughput applications. However, while porting such software stacks to the GPU, the computation of the histogram is a…

Distributed, Parallel, and Cluster Computing · Computer Science 2010-11-02 Sisir Koppaka , Dheevatsa Mudigere , Srihari Narasimhan , Babu Narayanan

Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. The embedding tables of DLRMs are too large to fit on GPU memory entirely. We propose a GPU-based software cache approaches to dynamically manage…

Information Retrieval · Computer Science 2022-08-11 Jiarui Fang , Geng Zhang , Jiatong Han , Shenggui Li , Zhengda Bian , Yongbin Li , Jin Liu , Yang You

Accelerator architectures specialize in executing SIMD (single instruction, multiple data) in lockstep. Because the majority of CUDA applications are parallelized loops, control flow information can provide an in-depth characterization of a…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-03-25 Robert Lim , Boyana Norris , Allen Malony

The Deep Graph Library (DGL) was designed as a tool to enable structure learning from graphs, by supporting a core abstraction for graphs, including the popular Graph Neural Networks (GNN). DGL contains implementations of all core graph…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-07-14 Sasikanth Avancha , Vasimuddin Md , Sanchit Misra , Ramanarayan Mohanty

In recent years the more and more powerful GPU's available on the PC market have attracted attention as a cost effective solution for parallel (SIMD) computing. CUDA is a solid evidence of the attention that the major companies are devoting…

High Energy Physics - Lattice · Physics 2010-01-21 Viola Anselmi , Giovanni Conti , Francesco Di Renzo

The effectiveness of in-memory dynamic graph storage (DGS) for supporting concurrent graph read and write queries is crucial for real-time graph analytics and updates. Various methods have been proposed, for example, LLAMA, Aspen,…

Databases · Computer Science 2025-02-18 Jixian Su , Chiyu Hao , Shixuan Sun , Hao Zhang , Sen Gao , Jiaxin Jiang , Yao Chen , Chenyi Zhang , Bingsheng He , Minyi Guo

The cryosphere plays a significant role in Earth's climate system. Therefore, an accurate simulation of sea ice is of great importance to improve climate projections. To enable higher resolution simulations, graphics processing units (GPUs)…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-29 Robert Jendersie , Christian Lessig , Thomas Richter

Spatial dataflow accelerators are a promising direction for next-generation computer systems because they can reduce the memory bottlenecks of traditional von Neumann machines such as CPUs and GPUs. They organize computation around…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-13 Wei Li , Zhenyu Bai , Heru Wang , Pranav Dangi , Zhiqiang Zhang , Cheng Tan , Huiying Lan , Weng-Fai Wong , Tulika Mitra

Parallel computing can offer an enormous advantage regarding the performance for very large applications in almost any field: scientific computing, computer vision, databases, data mining, and economics. GPUs are high performance many-core…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-11-24 Bogdan Oancea , Tudorel Andrei , Raluca Mariana Dragoescu

Collective communication is becoming increasingly important in data center and supercomputer workloads with an increase in distributed AI related jobs. However, existing libraries that provide collective support such as NCCL, RCCL, and…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-17 Siddharth Singh , Keshav Pradeep , Mahua Singh , Cunyang Wei , Abhinav Bhatele

We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of…

Machine Learning · Computer Science 2017-11-08 Celestine Dünner , Thomas Parnell , Martin Jaggi

GPUs are vastly underutilized, even when running resource-intensive AI applications, as GPU kernels within each job have diverse resource profiles that may saturate some parts of a device while often leaving other parts idle. Colocating…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-17 Paul Elvinger , Foteini Strati , Natalie Enright Jerger , Ana Klimovic