# Dynamic Loop Scheduling Using MPI Passive-Target Remote Memory Access

## TL;DR

This paper introduces a novel distributed loop scheduling method leveraging MPI passive-target RMA features, eliminating master-worker bottlenecks and improving load balancing in parallel applications.

## Contribution

It proposes a masterless distributed chunk-calculation approach utilizing MPI passive-target RMA, enhancing performance over traditional master-worker models.

## Key findings

- Outperforms traditional master-worker DLS implementations
- Effective on heterogeneous hardware setups
- Compatible with latest MPI features

## Abstract

Scientific applications often contain large computationally-intensive parallel loops. Loop scheduling techniques aim to achieve load balanced executions of such applications. For distributed-memory systems, existing dynamic loop scheduling (DLS) libraries are typically MPI-based, and employ a master-worker execution model to assign variably-sized chunks of loop iterations. The master-worker execution model may adversely impact performance due to the master-level contention. This work proposes a distributed chunk-calculation approach that does not require the master-worker execution scheme. Moreover, it considers the novel features in the latest MPI standards, such as passive-target remote memory access, shared-memory window creation, and atomic read-modify-write operations. To evaluate the proposed approach, five well-known DLS techniques, two applications, and two heterogeneous hardware setups have been considered. The DLS techniques implemented using the proposed approach outperformed their counterparts implemented using the traditional master-worker execution model.