Load balancing for distributed nonlocal models within asynchronous many-task systems

02/07/2021
by   Pranav Gadikar, et al.
0

In this work, we consider the challenges of developing a distributed solver for models based on nonlocal interactions. In nonlocal models, in contrast to the local model, such as the wave and heat partial differential equation, the material interacts with neighboring points on a larger-length scale compared to the mesh discretization. In developing a fully distributed solver, the interaction over a length scale greater than mesh size introduces additional data dependencies among the compute nodes and communication bottleneck. In this work, we carefully look at these challenges in the context of nonlocal models; to keep the presentation specific to the computational issues, we consider a nonlocal heat equation in a 2d setting. In particular, the distributed framework we propose pays greater attention to the bottleneck of data communication and the dynamic balancing of loads among nodes with varying compute capacity. For load balancing, we propose a novel framework that assesses the compute capacity of nodes and dynamically balances the load so that the idle time among nodes is minimal. Our framework relies heavily on HPX library, an asynchronous many-task run time system. We present several results demonstrating the effectiveness of the proposed framework.

READ FULL TEXT

page 6

page 9

page 15

research
11/02/2022

Distributed Work Stealing in a Task-Based Dataflow Runtime

The task-based dataflow programming model has emerged as an alternative ...
research
08/16/2022

Performance Assessment of Diffusive Load Balancing for Distributed Particle Advection

Particle advection is the approach for extraction of integral curves fro...
research
06/26/2020

Dynamic Constraint-based Influence Framework and its Application in Stochastic Modeling of Load Balancing

Components connected over a network influence each other and interact in...
research
08/24/2018

Asynchronous One-Level and Two-Level Domain Decomposition Solvers

Parallel implementations of linear iterative solvers generally alternate...
research
04/27/2018

Rateless Codes for Near-Perfect Load Balancing in Distributed Matrix-Vector Multiplication

Large-scale machine learning and data mining applications require comput...
research
10/06/2020

Local Deal-Agreement Based Monotonic Distributed Algorithms for Load Balancing in General Graphs

In computer networks, participants may cooperate in processing tasks, so...
research
02/06/2021

A Newcomer In The PGAS World – UPC++ vs UPC: A Comparative Study

A newcomer in the Partitioned Global Address Space (PGAS) 'world' has ar...

Please sign up or login with your details

Forgot password? Click here to reset