Exploring Fine-Grained Task-Based Execution on Multi-GPU Systems

Using multi-GPU systems, including GPU clusters, is gaining popularity in scientific computing. However, when using multiple GPUs concurrently, the conventional data parallel GPU programming paradigms, e.g., CUDA, cannot satisfactorily address certain issues, such as load balancing, GPU resource uti...

Full description

Saved in:
Bibliographic Details
Published in:2011 IEEE International Conference on Cluster Computing pp. 386 - 394
Main Authors: Long Chen, Villa, O., Gao, G. R.
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2011
Subjects:
Containers
dynamic load balance
fine-grained
Force
GPGPU
Graphics processing unit
Kernel
Load management
multi-GPU
Performance evaluation
Programming
task
ISBN:9781457713552, 1457713551
ISSN:1552-5244
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Using multi-GPU systems, including GPU clusters, is gaining popularity in scientific computing. However, when using multiple GPUs concurrently, the conventional data parallel GPU programming paradigms, e.g., CUDA, cannot satisfactorily address certain issues, such as load balancing, GPU resource utilization, overlapping fine grained computation with communication, etc. In this paper, we present a fine-grained task-based execution framework for multi-GPU systems. By scheduling finer-grained tasks than what is supported in the conventional CUDA programming method among multiple GPUs, and allowing concurrent task execution on a single GPU, our framework provides means for solving the above issues and efficiently utilizing multi-GPU systems. Experiments with a molecular dynamics application show that, for nonuniform distributed workload, the solutions based on our framework achieve good load balance, and considerable performance improvement over other solutions based on the standard CUDA programming methodologies.
ISBN:9781457713552
1457713551
ISSN:1552-5244
DOI:10.1109/CLUSTER.2011.50