English
Related papers

Related papers: Deinsum: Practically I/O Optimal Multilinear Algeb…

200 papers

Distributed computation is a framework used to break down a complex computational task into smaller tasks and distributing them among computational nodes. Erasure correction codes have recently been introduced and have become a popular…

Information Theory · Computer Science 2021-08-17 Royee Yosibash , Ram Zamir

Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel inference performance when trying to scale up the model size. To mitigate this important…

Computation and Language · Computer Science 2026-04-21 You-Liang Huang , Xinhao Huang , Chengxi Liao , Zeyi Wen

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

Dense linear algebra kernels, such as linear solvers or tensor contractions, are fundamental components of many scientific computing applications. In this work, we present a novel method of deriving parallel I/O lower bounds for this broad…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-14 Grzegorz Kwasniewski , Tal Ben-Nun , Alexandros Nikolaos Ziogas , Timo Schneider , Maciej Besta , Torsten Hoefler

We have repurposed Google Tensor Processing Units (TPUs), application-specific chips developed for machine learning, into large-scale dense linear algebra supercomputers. The TPUs' fast inter-core interconnects (ICI)s, physically…

Computational Physics · Physics 2022-09-14 Adam G. M. Lewis , Jackson Beall , Martin Ganahl , Markus Hauru , Shrestha Basu Mallick , Guifre Vidal

We propose an adaptive scheme for distributed learning of nonlinear functions by a network of nodes. The proposed algorithm consists of a local adaptation stage utilizing multiple kernels with projections onto hyperslabs and a diffusion…

Signal Processing · Electrical Eng. & Systems 2018-09-05 Ban-Sok Shin , Masahiro Yukawa , Renato Luis Garrido Cavalcante , Armin Dekorsy

Dijkstra observed that verifying correctness of a program is difficult and conjectured that derivation of a program hand-in-hand with its proof of correctness was the answer. We illustrate this goal-oriented approach by applying it to the…

Mathematical Software · Computer Science 2017-10-13 Devangi N. Parikh , Maggie E. Myers , Robert A. van de Geijn

We present Rhino, a system for accelerating tensor programs with automatic parallelization on AI platform for real production environment. It transforms a tensor program written for a single device into an equivalent distributed program…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-02-17 Shiwei Zhang , Lansong Diao , Siyu Wang , Zongyan Cao , Yiliang Gu , Chang Si , Ziji Shi , Zhen Zheng , Chuan Wu , Wei Lin

We introduce Diffuse, a system that dynamically performs task and kernel fusion in distributed, task-based runtime systems. The key component of Diffuse is an intermediate representation of distributed computation that enables the necessary…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-17 Rohan Yadav , Shiv Sundram , Wonchan Lee , Michael Garland , Michael Bauer , Alex Aiken , Fredrik Kjolstad

Data-intensive applications, ranging from large-scale retrieval systems to advanced data pipelines, are increasingly bottlenecked by the processing of highly redundant text corpora. We present Merlin, a local-first, agnostic,…

Computation and Language · Computer Science 2026-05-12 Sietse Schelpe

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

State-of-the-art machine learning frameworks support a wide variety of design features to enable a flexible machine learning programming interface and to ease the programmability burden on machine learning developers. Identifying and using…

Machine Learning · Computer Science 2020-07-01 Yu Emma Wang , Carole-Jean Wu , Xiaodong Wang , Kim Hazelwood , David Brooks

The field of deep learning has witnessed a remarkable shift towards extremely compute- and memory-intensive neural networks. These newer larger models have enabled researchers to advance state-of-the-art tools across a variety of fields.…

Machine Learning · Computer Science 2022-07-04 Daniel Nichols , Siddharth Singh , Shu-Huai Lin , Abhinav Bhatele

To exploit both memory locality and the full performance potential of highly tuned kernels, dense linear algebra libraries such as LAPACK commonly implement operations as blocked algorithms. However, to achieve next-to-optimal performance…

Mathematical Software · Computer Science 2022-04-08 Elmar Peise , Paolo Bientinesi

Mathematical operators whose transformation rules constitute the building blocks of a multi-linear algebra are widely used in physics and engineering applications where they are very often represented as tensors. In the last century, thanks…

Mathematical Software · Computer Science 2013-07-09 Edoardo Di Napoli , Diego Fabregat-Traver , Gregorio Quintana-Ortì , Paolo Bientinesi

We consider the problem of coded distributed computing where a large linear computational job, such as a matrix multiplication, is divided into $k$ smaller tasks, encoded using an $(n,k)$ linear code, and performed over $n$ distributed…

Information Theory · Computer Science 2021-10-06 Mahdi Soleymani , Mohammad Vahid Jamali , Hessam Mahdavifar

Datacenters are increasingly becoming heterogeneous, and are starting to include specialized hardware for networking, video processing, and especially deep learning. To leverage the heterogeneous compute capability of modern datacenters, we…

Machine Learning · Computer Science 2023-08-03 Yassine Ghannane , Mohamed S. Abdelfattah

Many quantum algorithms for numerical linear algebra assume black-box access to a block-encoding of the matrix of interest, which is a strong assumption when the matrix is not sparse. Kernel matrices, which arise from discretizing a kernel…

Quantum Physics · Physics 2022-12-14 Quynh T. Nguyen , Bobak T. Kiani , Seth Lloyd

The translation of linear algebra computations into efficient sequences of library calls is a non-trivial task that requires expertise in both linear algebra and high-performance computing. Almost all high-level languages and libraries for…

Mathematical Software · Computer Science 2020-01-01 Henrik Barthels , Christos Psarras , Paolo Bientinesi

Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate results between computation kernels can significantly improve…

Hardware Architecture · Computer Science 2025-09-24 Hanchen Ye , Deming Chen