Unconventional multi- and many-core processors (e.g., IBM® Cell B.E. ™ and NVIDIA® GPU) have emerged as effective accelerators in trial climate and weather simulations. Yet these climate and weather models typically run on parallel computers with conventional processors (e.g., Intel®, AMD®, and IBM) using Message Passing Interface (MPI). To address challenges involved in efficiently and easily connecting accelerators to parallel computers, we investigated using IBM’s Dynamic Application Virtualization (DAV) software in a prototype hybrid computing system with representative climate and weather model components. The hybrid system comprises 2 Intel blades and 2 IBM QS22 Cell B.E. blades, connected with both InfiniBand® (IB) and 1-Gigabit Ethernet. The system significantly accelerates a solar radiation model component by offloading compute-intensive calculations to the Cell blades. Systematic tests show that DAV can seamlessly offload compute-intensive calculations from Intel blades to Cell B.E. blades in a scalable, load-balanced manner. However, noticeable communication overhead was observed, mainly due to IP over IB protocol. Full utilization of IB Sockets Direct Protocol (SDP) and the lower latency production version of DAV will reduce this overhead.
[1]
Samuel Williams,et al.
The potential of the cell processor for scientific computing
,
2005,
CF '06.
[2]
Manish Vachharajani,et al.
GPU acceleration of numerical weather prediction
,
2008,
2008 IEEE International Symposium on Parallel and Distributed Processing.
[3]
David Gregg,et al.
Streamlining Offload Computing to High Performance Architectures
,
2009,
ICCS.
[4]
Max J. Suarez,et al.
A solar radiation parameterization (CLIR-AD-SW) for atmospheric studies
,
1999
.
[5]
Samuel Williams,et al.
The impact of IBM Cell technology on the programming paradigm in the context of computer systems for climate and weather models
,
2009,
Concurr. Comput. Pract. Exp..
[6]
Klaus Schulten,et al.
Accelerating Molecular Modeling Applications with GPU Computing
,
2009
.