Abstract
A GPU cluster in which each node provides a few GPUs connected with PCIe (PCI Express) is commonly used for acceleration of a large application program requiring the performance beyond a single GPU. However, in such a system, programmers are required to describe two parallel programming between nodes in MPIs or other message passing library as well as the fine grained parallel programming for intra-GPUs. As a cost effective alternative of such clusters, we propose a novel multi-GPU system with ExpEther, a virtualization technique which extends PCIe of a host CPU to Ethernet. All devices connected by ExpEther can be treated as if they were directly connected to the host. Evaluation with two application programs with and without GPU-GPU communication revealed that the proposed system with four GPUs achieved 3.88 and 3.29 times performance improvement respectively compared with a single GPU system. Compared with GPU cluster system in which each node provides a GPU, the proposed system achieved about 7% and 30% performance improvement, respectively.
- A.Shitara, T.Nakahama, M.Yamada, T.Kamata, Y.Nishikawa, M.Yoshimi, and H.Amano. Vegeta: An implementation and evaluation of development-support middleware on multiple opencl platform. In Proc. of the 2nd ICNC, 2011, pages 141--147. IEEE, 2011. Google Scholar
Digital Library
- GSIC. Tsubame computing services. http://tsubame.gsic.titech.ac.jp/en.Google Scholar
- T. Hamada. Degima: The greenest accelerator-based supercomputer in the top500 list. http://www.cs.tsukuba.ac.jp/¿yoshiki/heart/HEART2012/keynote/HEART2012-Hamada.pdf, June 2012.Google Scholar
- Integrated Device Technology. Pci express switches. http://www.idt.com/products/interfaceconnectivity/pci-express-solutions/pci-expressswitches.Google Scholar
- Khronos. The opencl specification version: 2.0, November 2013.Google Scholar
- NEC Corporation. http://www.nec.co.jp.Google Scholar
- NVIDIA. CUDA Toolkit Documentation. http://docs.nvidia.com/cuda/index.html.Google Scholar
- PCI-SIG. Pci express. http://www.pcisig.com/specifications/pciexpress/.Google Scholar
- R. Aoki, S. Oikawa, T. Nakamura, and S. Miki. Hybrid opencl: Enhancing opencl for distributed processing. In Proc. of the 9th ISPA, 2011, pages 149--154. IEEE, 2011. Google Scholar
Digital Library
- J. Suzuki, Y. Hidaka, J. Higuchi, T. Yoshikawa, and A. Iwata. Expressether-ethernet-based virtualization technology for reconfigurable hardware platform. In High-Performance Interconnects, 14th IEEE Symposium on, pages 45--51. IEEE, 2006. Google Scholar
Digital Library
- T. Miyoshi, H. Irie, K. Shima, H. Honda, M. Kondo, and T. Yoshinaga. Flat: a gpu programming framework to provide embedded mpi. In Proc. of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units, pages 20--29. ACM, 2012. Google Scholar
Digital Library
Recommendations
Radiation modeling using the Uintah heterogeneous CPU/GPU runtime system
XSEDE '12: Proceedings of the 1st Conference of the Extreme Science and Engineering Discovery Environment: Bridging from the eXtreme to the campus and beyondThe Uintah Computational Framework was developed to provide an environment for solving fluid-structure interaction problems on structured adaptive grids on large-scale, long-running, data-intensive problems. Uintah uses a combination of fluid-flow ...
SIMD Monte-Carlo Numerical Simulations Accelerated on GPU and Xeon Phi
The efficiency of a pleasingly parallel application is studied for several computing platforms. A real world problem, i.e., Monte-Carlo numerical simulations of stratospheric balloon envelope drift descent is considered. We detail the optimization of ...
Efficient simulation of agent-based models on multi-GPU and multi-core clusters
SIMUTools '10: Proceedings of the 3rd International ICST Conference on Simulation Tools and TechniquesAn effective latency-hiding mechanism is presented in the parallelization of agent-based model simulations (ABMS) with millions of agents. The mechanism is designed to accommodate the hierarchical organization as well as heterogeneity of current state-...






Comments