GX-Plug: a Middleware for Plugging Accelerators to Distributed Graph Processing

by   Kai Zou, et al.

Recently, research communities highlight the necessity of formulating a scalability continuum for large-scale graph processing, which gains the scale-out benefits from distributed graph systems, and the scale-up benefits from high-performance accelerators. To this end, we propose a middleware, called the GX-plug, for the ease of integrating the merits of both. As a middleware, the GX-plug is versatile in supporting different runtime environments, computation models, and programming models. More, for improving the middleware performance, we study a series of techniques, including pipeline shuffle, synchronization caching and skipping, and workload balancing, for intra-, inter-, and beyond-iteration optimizations, respectively. Experiments show that our middleware efficiently plugs accelerators to representative distributed graph systems, e.g., GraphX and Powergraph, with up-to 20x acceleration ratio.


page 1

page 10


A Survey on Graph Processing Accelerators: Challenges and Opportunities

Graph is a well known data structure to represent the associated relatio...

Towards Performance Portable Programming for Distributed Heterogeneous Systems

Hardware heterogeneity is here to stay for high-performance computing. L...

Runtime Support for Performance Portability on Heterogeneous Distributed Platforms

Hardware heterogeneity is here to stay for high-performance computing. L...

Design Considerations for Efficient Deep Neural Networks on Processing-in-Memory Accelerators

This paper describes various design considerations for deep neural netwo...

Pathways: Asynchronous Distributed Dataflow for ML

We present the design of a new large scale orchestration layer for accel...

Processing Database Joins over a Shared-Nothing System of Multicore Machines

To process a large volume of data, modern data management systems use a ...

Please sign up or login with your details

Forgot password? Click here to reset