IEEE transactions on parallel and distributed systems, 2011-01, Vol.22 (1), p.58-68
2011
Volltextzugriff (PDF)
Details
- Autor(en) / Beteiligte
- Titel
- Comparing Hardware Accelerators in Scientific Applications: A Case Study
- Ist Teil von
- IEEE transactions on parallel and distributed systems, 2011-01, Vol.22 (1), p.58-68
- Ort / Verlag
- New York: IEEE
- Erscheinungsjahr
- 2011
- Quelle
- IEEE Xplore
- Beschreibungen/Notizen
- Multicore processors and a variety of accelerators have allowed scientific applications to scale to larger problem sizes. We present a performance, design methodology, platform, and architectural comparison of several application accelerators executing a Quantum Monte Carlo application. We compare the application's performance and programmability on a variety of platforms including CUDA with Nvidia GPUs, Brook+ with ATI graphics accelerators, OpenCL running on both multicore and graphics processors, C++ running on multicore processors, and a VHDL implementation running on a Xilinx FPGA. We show that OpenCL provides application portability between multicore processors and GPUs, but may incur a performance cost. Furthermore, we illustrate that graphics accelerators can make simulations involving large numbers of particles feasible.
- Sprache
- Englisch
- Identifikatoren
- ISSN: 1045-9219eISSN: 1558-2183DOI: 10.1109/TPDS.2010.125Titel-ID: cdi_ieee_primary_5482576
- Format
- –
- Schlagworte
- Acceleration, Accelerator, Accelerators, Bandwidth, Chemistry, Clocks, computational science, Computer simulation, CUDA, FPGA, GPU, Hardware, Integral equations, Microprocessors, Monte Carlo methods, multicore, Multicore processing, OpenCL, Parallel processing, Platforms, Processors, Running, VHDL