Cited 14 time in
Cited 20 time in
Grex: An efficient MapReduce framework for graphics processing units
- Grex: An efficient MapReduce framework for graphics processing units
- Basaran, C[Basaran, Can]; Kang, KD[Kang, Kyoung-Don]
- DGIST Authors
- Basaran, C[Basaran, Can]
- Issue Date
- Journal of Parallel and Distributed Computing, 73(4), 522-533
- Article Type
- Computer Graphics; Computer Graphics Equipment; Data Processing; GPGPU; Graphics Processing Unit; Graphics Processing Units; Map-Reduce; Memory Architecture; Parallel Data Processing; Program Processors; Shared Memory; SIMT; Storage Allocation (Computer); Thread Synchronization
- In this paper, we present a new MapReduce framework, called Grex, designed to leverage general purpose graphics processing units (GPUs) for parallel data processing. Grex provides several new features. First, it supports a parallel split method to tokenize input data of variable sizes, such as words in e-books or URLs in web documents, in parallel using GPU threads. Second, Grex evenly distributes data to map/reduce tasks to avoid data partitioning skews. In addition, Grex provides a new memory management scheme to enhance the performance by exploiting the GPU memory hierarchy. Notably, all these capabilities are supported via careful system design without requiring any locks or atomic operations for thread synchronization. The experimental results show that our system is up to 12.4× and 4.1× faster than two state-of-the-art GPU-based MapReduce frameworks for the tested applications. © 2013 Elsevier Inc. All rights reserved.
There are no files associated with this item.
- Information and Communication EngineeringRTCPS(Real-Time Cyber-Physical Systems) Lab1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.