GPU-Chariot: A Programming Framework for Stream Applications Running on Multi-GPU Systems
スポンサーリンク
概要
- 論文の詳細を見る
This paper presents a stream programming framework, named GPU-chariot, for accelerating stream applications running on graphics processing units (GPUs). The main contribution of our framework is that it realizes efficient software pipelines on multi-GPU systems by enabling out-of-order execution of CPU functions, kernels, and data transfers. To achieve this out-of-order execution, we apply a runtime scheduler that not only maximizes the utilization of system resources but also encapsulates the number of GPUs available in the system. In addition, we implement a load-balancing capability to flow data efficiently through multiple GPUs. Furthermore, a callback interface enables overlapping execution of functions in third-party libraries. By using kernels with different performance bottlenecks, we show that our out-of-order execution is up to 20% faster than in-order execution. Finally, we conduct several case studies on a 4-GPU system and demonstrate the advantages of GPU-chariot over a manually pipelined code. We conclude that GPU-chariot can be useful when developing stream applications with software pipelines on multiple GPUs and CPUs.
著者
-
Ino Fumihiko
Graduate School Of Information Science And Technology Osaka University
-
Hagihara Kenichi
Graduate School Of Information Science And Technology Osaka University
-
NAKAGAWA Shinta
Storage Division, NEC Corporation
関連論文
- Parallel Adaptive Estimation of Hip Range of Motion for Total Hip Replacement Surgery(Parallel Image Processing,Parallel/Distributed Processing and Systems)
- Grid Resource Monitoring and Selection for Rapid Turnaround Applications(Computer Systems)
- Evaluation of Performance Prediction Method for Master/Slave Parallel Programs(Computer Systems)
- THREE-DIMENSIONAL PARALLEL IMAGE PROCESSING LIBRARY(International Workshop on Advanced Image Technology 2007)
- THREE-DIMENSIONAL PARALLEL IMAGE PROCESSING LIBRARY
- Accelerating Smith-Waterman Algorithm for Biological Database Search on CUDA-Compatible GPUs
- GPU-Chariot: A Programming Framework for Stream Applications Running on Multi-GPU Systems