English
Related papers

Related papers: Dynamic Memory Management on GPUs with SYCL

200 papers

Distributed synchronized GPU training is commonly used for deep learning. The resource constraint of using a fixed number of GPUs makes large-scale training jobs suffer from long queuing time for resource allocation, and lowers the cluster…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-11-08 Mingzhen Li , Wencong Xiao , Biao Sun , Hanyu Zhao , Hailong Yang , Shiru Ren , Zhongzhi Luan , Xianyan Jia , Yi Liu , Yong Li , Wei Lin , Depei Qian

The system-level cache is a critical resource shared by processor cores and domain-specific accelerators in heterogeneous systems on chips (SoCs). The strict QoS requirements of accelerators, such as deadlines, can lead to severe…

Hardware Architecture · Computer Science 2026-05-21 Ayushi Agarwal , Anannya Mathur , Preeti Ranjan Panda

Distributed dataflow systems such as Apache Spark or Apache Flink enable parallel, in-memory data processing on large clusters of commodity hardware. Consequently, the appropriate amount of memory to allocate to the cluster is a crucial…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-08 Jonathan Will , Lauritz Thamsen , Dominik Scheinert , Odej Kao

We design and implement a fully concurrent dynamic hash table for GPUs with comparable performance to the state of the art static hash tables. We propose a warp-cooperative work sharing strategy that reduces branch divergence and provides…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-03-05 Saman Ashkiani , Martin Farach-Colton , John D. Owens

In most modern systems, the memory subsystem is managed and accessed at multiple different granularities at various resources. We observe that such multi-granularity management results in significant inefficiency in the memory subsystem.…

Hardware Architecture · Computer Science 2016-05-23 Vivek Seshadri

The global scarcity of GPUs necessitates more sophisticated strategies for Deep Learning jobs in shared cluster environments. Accurate estimation of how much GPU memory a job will require is fundamental to enabling advanced scheduling and…

Performance · Computer Science 2025-10-27 Jiabo Shi , Dimitrios Pezaros , Yehia Elkhatib

Conventional LLM inference architectures suffer from high energy and latency due to frequent data movement across memory hierarchies. We propose Ouroboros, a wafer-scale SRAM-based Computing-in-Memory (CIM) architecture that executes all…

Hardware Architecture · Computer Science 2026-03-04 Yiqi Liu , Yudong Pan , Mengdi Wang , Shixin Zhao , Haonan Zhu , Yinhe Han , Lei Zhang , Ying Wang

ASYNC is a framework that supports the implementation of asynchrony and history for optimization methods on distributed computing platforms. The popularity of asynchronous optimization methods has increased in distributed machine learning.…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-02-24 Saeed Soori , Bugra Can , Mert Gurbuzbalaba , Maryam Mehri Dehnavi

Current computational systems are heterogeneous by nature, featuring a combination of CPUs and GPUs. As the latter are becoming an established platform for high-performance computing, the focus is shifting towards the seamless programming…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-10-23 Fábio Soldado , Fernando Alexandre , Hervé Paulino

Simulations based on particle methods, such as Smoothed Particle Hydrodynamics (SPH), are known to be computationally demanding. While such methods have for long been executed in parallel on multi-core CPUs, in recent years the increasing…

Computational Engineering, Finance, and Science · Computer Science 2026-03-18 Xiangyu Hu , Alberto Guarnieri

Accelerated computing is widely used in high-performance computing. Therefore, it is crucial to experiment and discover how to better utilize GPUGPUs latest generations on relevant applications. In this paper, we present results and share…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-08-13 Baodi Shan , Mauricio Araya-Polo

Large language models (LLMs) training or inference across multiple nodes introduces significant pressure on GPU memory and interconnect bandwidth. The Compute Express Link (CXL) shared memory pool offers a scalable solution by enabling…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Dong Xu , Han Meng , Xinyu Chen , Dengcheng Zhu , Wei Tang , Fei Liu , Liguang Xie , Wu Xiang , Rui Shi , Yue Li , Henry Hu , Hui Zhang , Jianping Jiang , Dong Li

We present Synkhronos, an extension to Theano for multi-GPU computations leveraging data parallelism. Our framework provides automated execution and synchronization across devices, allowing users to continue to write serial programs without…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-10-13 Adam Stooke , Pieter Abbeel

Modern Machine Learning (ML) training on large-scale datasets is a very time-consuming workload. It relies on the optimization algorithm Stochastic Gradient Descent (SGD) due to its effectiveness, simplicity, and generalization performance.…

Hardware Architecture · Computer Science 2024-09-30 Steve Rhyner , Haocong Luo , Juan Gómez-Luna , Mohammad Sadrosadati , Jiawei Jiang , Ataberk Olgun , Harshita Gupta , Ce Zhang , Onur Mutlu

There are three domains in a modern thermally-constrained mobile system-on-chip (SoC): compute, IO, and memory. We observe that a modern SoC typically allocates a fixed power budget, corresponding to worst-case performance demands, to the…

Hardware Architecture · Computer Science 2020-05-19 Jawad Haj-Yahya , Mohammed Alser , Jeremie Kim , A. Giray Yaglıkçı , Nandita Vijaykumar , Efraim Rotem , Onur Mutlu

Applications with low data reuse and frequent irregular memory accesses, such as graph or sparse linear algebra workloads, fail to scale well due to memory bottlenecks and poor core utilization. While prior work with prefetching,…

Hardware Architecture · Computer Science 2023-05-05 Marcelo Orenes-Vera , Esin Tureci , David Wentzlaff , Margaret Martonosi

OpenCL, along with CUDA, is one of the main tools used to program GPGPUs. However, it allows running the same code on multi-core CPUs too, making it a rival for the long-established OpenMP. In this paper we compare OpenCL and OpenMP when…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-03-24 Kamran Karimi

Many applications are increasingly requiring numerical simulations for solving complex problems. Most of these numerical algorithms are massively parallel and often implemented on parallel high-performance computers. However, classic…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-11-02 Karl F. A. Friebel , Stephanie Soldavini , Gerald Hempel , Christian Pilato , Jeronimo Castrillon

GPUs exploit a high degree of thread-level parallelism to hide long-latency stalls. Due to the heterogeneous compute requirements of different applications, there is a growing need to share the GPU across multiple applications in…

The second version of Intel Software Guard Extensions (Intel SGX), or SGX2, adds dynamic management of enclave memory and threads. The first version required the address space and thread counts to be fixed before execution. The Enclave…