Optimizing a shared virtual memory system for a heterogeneous CPU-accelerator platform
Intel Corporation
ACM SIGOPS Operating Systems Review, Volume 45 Issue 1, January 2011
@article{yan2011optimizing,
title={Optimizing a shared virtual memory system for a heterogeneous CPU-accelerator platform},
author={Yan, S. and Zhou, X. and Gao, Y. and Chen, H. and Wu, G. and Luo, S. and Saha, B.},
journal={ACM SIGOPS Operating Systems Review},
volume={45},
number={1},
pages={92–100},
year={2011},
publisher={ACM}
}
The client computing platform is moving towards a heterogeneous architecture that combines scalar-oriented CPU cores and throughput-oriented accelerator cores. Recognizing that existing programming models for such heterogeneous platforms are still difficult for most programmers, we advocate a shared virtual memory programming model to improve programmability. In this paper, we focus on performance, and demonstrate that users need not sacrifice performance for programmability. We describe our approaches, experiences, and results in optimizing MYO on a heterogeneous platform consisting of a CPU and an Aubrey Isle accelerator. Our efforts involve the whole system software stack including the OS, runtime, and application.
September 12, 2011 by hgpu
