15548

Pragma Directed Shared Memory Centric Optimizations on GPUs

Jing Li, Lei Liu, Yuan Wu, Xiang-Hua Liu, Yi Gao, Xiao-Bing Feng, Cheng-Yong Wu
State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
Journal of Computer Science and Technology 31(2): 235-252, 2016

@article{li2016pragma,

   title={Pragma Directed Shared Memory Centric Optimizations on GPUs},

   author={Li, J and Liu, L and Wu, Y and others},

   journal={SCIENCE AND TECHNOLOGY},

   volume={31},

   number={2},

   pages={235–252},

   year={2016}

}

Download Download (PDF)   View View   Source Source   

2305

views

GPUs become a ubiquitous choice as coprocessors since they have excellent ability in concurrent processing. In GPU architecture, shared memory plays a very important role in system performance as it can largely improve bandwidth utilization and accelerate memory operations. However, even for affine GPU applications that contain regular access patterns, optimizing for shared memory is not an easy work. It often requires programmer expertise and nontrivial parameter selection. Improper shared memory usage might even underutilize GPU resource. Even using state-of-the-art high level programming models (e.g., OpenACC and OpenHMPP), it is still hard to utilize shared memory since they lack inherent support in describing shared memory optimization and selecting suitable parameters, let alone maintaining high resource utilization. Targeting higher productivity for affine applications, we propose a data centric way to shared memory optimization on GPU. We design a pragma extension on OpenACC so as to convey data management hints of programmers to compiler. Meanwhile, we devise a compiler framework to automatically select optimal parameters for shared arrays, using the polyhedral model. We further propose optimization techniques to expose higher memory and instruction level parallelism. The experimental results show that our shared memory centric approaches effectively improve the performance of five typical GPU applications across four widely used platforms by 3.7x on average, and do not burden programmers with lots of pragmas.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: