|
Vestnik Yuzhno-Ural'skogo Universiteta. Seriya Matematicheskoe Modelirovanie i Programmirovanie, 2011, Issue 9, Pages 98–106
(Mi vyuru178)
|
|
|
|
This article is cited in 1 scientific paper (total in 1 paper)
Programming
SkifCh: high performance communication interface
Yu. A. Klimova, A. Yu. Orlovb, A. B. Shvorinb a M. V. Keldysh Institute for Applied Mathematics, Russian Academy of Sciences, Moscow
b Program Systems Institute of RAS, Yaroslavskaya obl., Pereslavskii raion, s. Ves'kovo
Abstract:
We present highly efficient low level message passing interface named SkifCh. This interface is easily supported by network hardware which can be implemented in FPGA (as is in the case for SKIF-Aurora supercomputer) or in specific microchips. SkifCh interface is intended for use as highly efficient communication layer by applications or higher level communication libraries. For the moment there are several libraries implemented on top of SkifCh: MPI, SHMEM, GASNet, and ARMCI. We also provide a performance comparison for SkifCh versus MPI using the SKIF-Aurora supercomputer.
Keywords:
supercomputer, HPC, interconnect, message passing interface, SkifCh.
Received: 04.03.2011
Citation:
Yu. A. Klimov, A. Yu. Orlov, A. B. Shvorin, “SkifCh: high performance communication interface”, Vestnik YuUrGU. Ser. Mat. Model. Progr., 2011, no. 9, 98–106
Linking options:
https://www.mathnet.ru/eng/vyuru178 https://www.mathnet.ru/eng/vyuru/y2011/i9/p98
|
Statistics & downloads: |
Abstract page: | 94 | Full-text PDF : | 56 | References: | 53 |
|