English
Related papers

Related papers: Node-Aware Improvements to Allreduce

200 papers

We discuss a simple, binary tree-based algorithm for the collective allreduce (reduction-to-all, MPI_Allreduce) operation for parallel systems consisting of $p$ suitably interconnected processors. The algorithm can be doubly pipelined to…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-01-21 Jesper Larsson Träff

The reduce-scatter collective operation in which $p$ processors in a network of processors collectively reduce $p$ input vectors into a result vector that is partitioned over the processors is important both in its own right and as building…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-14 Jesper Larsson Träff

Collective algorithms are an essential part of MPI, allowing application programmers to utilize underlying optimizations of common distributed operations. The MPI_Allgather gathers data, which is originally distributed across all processes,…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-25 Amanda Bienz , Shreeman Gautam , Amun Kharel

Collective communications, namely the patterns allgatherv, reduce_scatter, and allreduce in message-passing systems are optimised based on measurements at the installation time of the library. The algorithms used are set up in an…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-24 Andreas Jocksch , Noe Ohana , Emmanuel Lanti , Vasileios Karakasis , Laurent Villard

Large inter-GPU all-reduce operations, prevalent throughout deep learning, are bottlenecked by communication costs. Emerging heterogeneous architectures are comprised of complex nodes, often containing $4$ GPUs and dozens to hundreds of CPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-26 Michael Adams , Amanda Bienz

The allreduce operation is an essential building block for many distributed applications, ranging from the training of deep learning models to scientific computing. In an allreduce operation, data from multiple hosts is aggregated together…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-09-29 Daniele De Sensi , Edgar Costa Molero , Salvatore Di Girolamo , Laurent Vanbever , Torsten Hoefler

The allreduce operation is one of the most commonly used communication routines in distributed applications. To improve its bandwidth and to reduce network traffic, this operation can be accelerated by offloading it to network switches,…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-10-28 Daniele De Sensi , Salvatore Di Girolamo , Saleh Ashkboos , Shigang Li , Torsten Hoefler

MapReduce is a commonly used framework for executing data-intensive jobs on distributed server clusters. We introduce a variant implementation of MapReduce, namely "Coded MapReduce", to substantially reduce the inter-server communication…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-12-08 Songze Li , Mohammad Ali Maddah-Ali , A. Salman Avestimehr

Supercomputer architectures are trending toward higher computational throughput due to the inclusion of heterogeneous compute nodes. These multi-GPU nodes increase on-node computational efficiency, while also increasing the amount of data…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-09-14 Shelby Lockhart , Amanda Bienz , William D. Gropp , Luke N. Olson

Algebraic multigrid (AMG) is often viewed as a scalable $\mathcal{O}(n)$ solver for sparse linear systems. Yet, parallel AMG lacks scalability due to increasingly large costs associated with communication, both in the initial construction…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-04-25 Amanda Bienz , Luke Olson , William Gropp

Efficient collective communication is critical for many distributed ML and HPC applications. In this context, it is widely believed that the Ring algorithm for the AllReduce collective communication operation is optimal only for large…

Networking and Internet Architecture · Computer Science 2025-10-07 Sarah-Michelle Hammer , Stefan Schmid , Rachee Singh , Vamsi Addanki

This paper studies the computation-communication tradeoff in a heterogeneous MapReduce computing system where each distributed node is equipped with different computation capability. We first obtain an achievable communication load for any…

Information Theory · Computer Science 2019-08-20 Fan Xu , Meixia Tao

The advent of multi-/many-core processors in clusters advocates hybrid parallel programming, which combines Message Passing Interface (MPI) for inter-node parallelism with a shared memory model for on-node parallelism. Compared to the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-07-15 Huan Zhou , Jose Gracia , Ralf Schneider

We consider a MapReduce-type task running in a distributed computing model which consists of ${K}$ edge computing nodes distributed across the edge of the network and a Master node that assists the edge nodes to compute output functions.…

Information Theory · Computer Science 2020-10-22 Haoning Chen , Youlong Wu

Many modern, high-performance systems increase the cumulated node-bandwidth by offering more than a single communication network and/or by having multiple connections to the network. Efficient algorithms and implementations for collective…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-01-16 Jesper Larsson Träff

The efficient implementation of collective communiction operations has received much attention. Initial efforts produced "optimal" trees based on network communication models that assumed equal point-to-point latencies between any two…

Distributed, Parallel, and Cluster Computing · Computer Science 2007-05-23 N. T. Karonis , B. de Supinski , I. Foster , W. Gropp , E. Lusk

Two-phase I/O is a well-known strategy for implementing collective MPI-IO functions. It redistributes I/O requests among the calling processes into a form that minimizes the file access costs. As modern parallel computers continue to grow…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-23 Qiao Kang , Sunwoo Lee , Kai-yuan Hou , Robert Ross , Ankit Agrawal , Alok Choudhary , Wei-keng Liao

We introduce a memory- and compute-efficient method for low-communication distributed training. Existing methods reduce communication by performing multiple local updates between infrequent global synchronizations. We demonstrate that their…

Machine Learning · Computer Science 2025-09-29 Anastasiia Filippova , Angelos Katharopoulos , David Grangier , Ronan Collobert

The sparse matrix-vector multiply (SpMV) operation is a key computational kernel in many simulations and linear solvers. The large communication requirements associated with a reference implementation of a parallel SpMV result in poor…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-16 Amanda Bienz , William D. Gropp , Luke N. Olson

Collective operations are common features of parallel programming models that are frequently used in High-Performance (HPC) and machine/ deep learning (ML/ DL) applications. In strong scaling scenarios, collective operations can negatively…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-04-01 Roman Iakymchuk , Amandio Faustino , Andrew Emerson , Joao Barreto , Valeria Bartsch , Rodrigo Rodrigues , Jose C. Monteiro
‹ Prev 1 2 3 10 Next ›