English
Related papers

Related papers: A Framework for Fine-Grained Synchronization of De…

200 papers

In the era of LLMs, dense operations such as GEMM and MHA are critical components. These operations are well-suited for parallel execution using a tilebased approach. While traditional GPU programming often relies on low level interfaces…

Computation and Language · Computer Science 2025-03-27 Dewei Wang , Wei Zhu , Liyang Ling , Ettore Tiotto , Quintin Wang , Whitney Tsang , Julian Opperman , Jacky Deng

Modern AI workloads rely heavily on optimized computing kernels for both training and inference. These AI kernels follow well-defined data-flow patterns, such as moving tiles between DRAM and SRAM and performing a sequence of computations…

Machine Learning · Computer Science 2025-04-29 Lei Wang , Yu Cheng , Yining Shi , Zhengju Tang , Zhiwen Mo , Wenhao Xie , Lingxiao Ma , Yuqing Xia , Jilong Xue , Fan Yang , Zhi Yang

Modern graphics computing units (GPUs) are designed and optimized to perform highly parallel numerical calculations. This parallelism has enabled (and promises) significant advantages, both in terms of energy performance and calculation. In…

Hardware Architecture · Computer Science 2021-10-26 Quentin Gallouédec

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Biyao Zhang , Mingkai Zheng , Debargha Ganguly , Xuecen Zhang , Vikash Singh , Vipin Chaudhary , Zhao Zhang

The ability to model, analyze, and predict execution time of computations is an important building block supporting numerous efforts, such as load balancing, performance optimization, and automated performance tuning for high performance,…

Performance · Computer Science 2020-06-22 James D. Stevens , Andreas Klöckner

With the rapid advancement of Artificial Intelligence, the Graphics Processing Unit (GPU) has become increasingly essential across a growing number of safety-critical application domains. Applying a GPU is indispensable for parallel…

Operating Systems · Computer Science 2026-02-25 Yuanhai Zhang , Songyang He , Ruizhe Gou , Mingyue Cui , Boyang Li , Shuai Zhao , Kai Huang

Finite element schemes based on discontinuous Galerkin methods possess features amenable to massively parallel computing accelerated with general purpose graphics processing units (GPUs). However, the computational performance of such…

Computational Physics · Physics 2016-04-20 Axel Modave , Amik St-Cyr , Tim Warburton

Many emerging cyber-physical systems, such as autonomous vehicles and robots, rely heavily on artificial intelligence and machine learning algorithms to perform important system operations. Since these highly parallel applications are…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-02-07 An Zou , Jing Li , Christopher D. Gill , Xuan Zhang

High-performance GPU kernels are critical to modern machine learning systems, yet developing efficient implementations remains a challenging, expert-driven process due to the tight coupling between algorithmic structure, memory hierarchy…

Machine Learning · Computer Science 2026-04-03 Tara Saba , Anne Ouyang , Xujie Si , Fan Long

The strategy of using CUDA-compatible GPUs as a parallel computation solution to improve the performance of programs has been more and more widely approved during the last two years since the CUDA platform was released. Its benefit extends…

Distributed, Parallel, and Cluster Computing · Computer Science 2010-01-12 Chang Xu , Steven R. Kirk , Samantha Jenkins

Modern high-performance computing architectures (Multicore, GPU, Manycore) are based on tightly-coupled clusters of processing elements, physically implemented as rectangular tiles. Their size and aspect ratio strongly impact the achievable…

Hardware Architecture · Computer Science 2022-09-05 Gianna Paulin , Matheus Cavalcante , Paul Scheffler , Luca Bertaccini , Yichao Zhang , Frank Gürkaynak , Luca Benini

A number of production deep learning clusters have attempted to explore inference hardware for DNN training, at the off-peak serving hours with many inference GPUs idling. Conducting DNN training with a combination of heterogeneous training…

Machine Learning · Computer Science 2024-07-03 Juntao Zhao , Borui Wan , Yanghua Peng , Haibin Lin , Yibo Zhu , Chuan Wu

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but…

Machine Learning · Computer Science 2024-08-22 Elias Frantar , Roberto L. Castro , Jiale Chen , Torsten Hoefler , Dan Alistarh

The past decade has witnessed a dramatic acceleration of lattice quantum chromodynamics calculations in nuclear and particle physics. This has been due to both significant progress in accelerating the iterative linear solvers using…

High Energy Physics - Lattice · Physics 2016-12-26 M. A. Clark , Bálint Joó , Alexei Strelchenko , Michael Cheng , Arjun Gambhir , Richard Brower

Matrix multiplication is a foundational operation in scientific computing and machine learning, yet its computational complexity makes it a significant bottleneck for large-scale applications. The shift to parallel architectures, primarily…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-30 Mufakir Qamar Ansari , Mudabir Qamar Ansari

Modern machine learning models are typically trained using Stochastic Gradient Descent (SGD) on massively parallel computing resources such as GPUs. Increasing mini-batch size is a simple and direct way to utilize the parallel computing…

Machine Learning · Statistics 2019-03-05 Siyuan Ma , Mikhail Belkin

The rapid adoption of Large Language Models (LLMs) has made GPU inference efficiency an increasingly critical system concern. The runtime of LLM workloads is largely dominated by tile-based kernels, particularly General Matrix…

Performance · Computer Science 2026-04-14 Kaixuan Zhang , Chutong Ding , Shiyou Qian , Luping Wang , Jian Cao , Guangtao Xue , Cheng Huang , Guodong Yang , Liping Zhang

Achieving high-performance GPU kernels requires optimizing algorithm implementations to the targeted GPU architecture. It is of utmost importance to fully use the compute and memory hierarchy, as well as available specialised hardware.…

Programming Languages · Computer Science 2020-03-16 Bastian Hagedorn , Archibald Samuel Elliott , Henrik Barthels , Rastislav Bodik , Vinod Grover

This paper proposes a versatile high-performance execution model, inspired by systolic arrays, for memory-bound regular kernels running on CUDA-enabled GPUs. We formulate a systolic model that shifts partial sums by CUDA warp primitives for…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-09-09 Peng Chen , Mohamed Wahib , Shinichiro Takizawa , Ryousei Takano , Satoshi Matsuoka

Modern computing platforms tend to deploy multiple GPUs (2, 4, or more) on a single node to boost system performance, with each GPU having a large capacity of global memory and streaming multiprocessors (SMs). GPUs are an expensive…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-07-20 Chao Chen , Chris Porter , Santosh Pande