10355

Efficient Heterogeneous Execution on Large Multicore and Accelerator Platforms: Case Study Using a Block Tridiagonal Solver

Alfred J. Park, Kalyan S. Perumalla
Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831
Journal of Parallel and Distributed Computing, 2013

@article{park2013efficient,

   title={Efficient heterogeneous execution on large multicore and accelerator platforms: Case study using a block tridiagonal solver},

   author={Park, Alfred J and Perumalla, Kalyan S},

   journal={Journal of Parallel and Distributed Computing},

   year={2013},

   publisher={Elsevier}

}

Download Download (PDF)   View View   Source Source   

577

views

The algorithmic and implementation principles are explored in gainfully exploiting GPU accelerators in conjunction with multicore processors on high-end systems with large numbers of compute nodes, and evaluated in an implementation of a scalable block tridiagonal solver. The accelerator of each compute node is exploited in combination with multicore processors of that node in performing block-level linear algebra operations in the overall, distributed solver algorithm. Optimizations incorporated include: (1) an efficient memory mapping and synchronization interface to minimize data movement, (2) multi-process sharing of the accelerator within a node to obtain balanced load with multicore processors, and (3) an automatic memory management system to efficiently utilize accelerator memory when sub-matrices spill over the limits of device memory. Results are reported from our novel implementation that uses MAGMA and CUBLAS accelerator software systems simultaneously with ACML [5] for multithreaded execution on processors. Overall, using 940 nVidia Tesla X2090 accelerators and 15,040 cores, the best heterogeneous execution delivers a 10.9-fold reduction in run time relative to an already efficient parallel multicore-only baseline implementation that is highly optimized with intra-node and inter-node concurrency and computation-communication overlap. Detailed quantitative results are presented to explain all critical runtime components contributing to hybrid performance.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: