NASA Scientific and Technical Aerospace Reports

60
COMPUTER OPERATIONS AND HARDWARE
Includes hardware for computer graphics, firmware and data processing. For components see 33 Electronics and Electrical Engineering.
For computer vision see 63 Cybernetics, Artificial Intelligence and Robotics.
20040111318 NASA Langley Research Center, Hampton, VA, USA
Scalability of Parallel Spatial Direct Numerical Simulations on Intel Hypercube and IBM SP1 and SP2
Joslin, Ronald D.; Hanebutte, Ulf R.; Zubair, Mohammad; [1995]; 54 pp.; In English
Contract(s)/Grant(s): NAS1-19480; Copyright; Avail: CASI; A04, Hardcopy
The implementation and performance of a parallel spatial direct numerical simulation (PSDNS) approach on the Intel
iPSC/860 hypercube and IBM SP1 and SP2 parallel computers is documented. Spatially evolving disturbances associated with
the laminar-to-turbulent transition in boundary-layer flows are computed with the PSDNS code. The feasibility of using the
PSDNS to perform transition studies on these computers is examined. The results indicate that PSDNS approach can
effectively be parallelized on a distributed-memory parallel machine by remapping the distributed data structure during the
course of the calculation. Scalability information is provided to estimate computational costs to match the actual costs relative
to changes in the number of grid points. By increasing the number of processors, slower than linear speedups are achieved
with optimized (machine-dependent library) routines. This slower than linear speedup results because the computational cost
is dominated by FFT routine, which yields less than ideal speedups. By using appropriate compile options and optimized
library routines on the SP1, the serial code achieves 52-56 M ops on a single node of the SP1 (45 percent of theoretical peak
performance). The actual performance of the PSDNS code on the SP1 is evaluated with a ‘real world’ simulation that consists
of 1.7 million grid points. One time step of this simulation is calculated on eight nodes of the SP1 in the same time as required
by a Cray Y/MP supercomputer. For the same simulation, 32-nodes of the SP1 and SP2 are required to reach the performance
of a Cray C-90. A 32 node SP1 (SP2) configuration is 2.9 (4.6) times faster than a Cray Y/MP for this simulation, while the
hypercube is roughly 2 times slower than the Y/MP for this application. KEY WORDS: Spatial direct numerical simulations;
incompressible viscous flows; spectral methods; finite differences; parallel computing.
Author
Computers; Direct Numerical Simulation; Hypercube Multiprocessors; Parallel Computers; Parallel Processing
(Computers); Supercomputers
20040111377 NASA Langley Research Center, Hampton, VA, USA
Experiences From NASA/Langley’s DMSS Project
[1996]; 13 pp.; In English; 14th IEEE Symposium on Mass Storage Systems; No Copyright; Avail: CASI; A03, Hardcopy
There is a trend in institutions with high performance computing and data management requirements to explore mass
storage systems with peripherals directly attached to a high speed network. The Distributed Mass Storage System (DMSS)
Project at the NASA Langley Research Center (LaRC) has placed such a system into production use. This paper will present
the experiences, both good and bad, we have had with this system since putting it into production usage. The system is
comprised of: 1) National Storage Laboratory (NSL)/UniTree 2.1, 2) IBM 9570 HIPPI attached disk arrays (both RAID 3 and
RAID 5), 3) IBM RS6000 server, 4) HIPPI/IPI3 third party transfers between the disk array systems and the supercomputer
clients, a CRAY Y-MP and a CRAY 2, 5) a ‘warm spare’ file server, 6) transition software to convert from CRAY’s Data
Migration Facility (DMF) based system to DMSS, 7) an NSC PS32 HIPPI switch, and 8) a STK 4490 robotic library accessed
from the IBM RS6000 block mux interface. This paper will cover: the performance of the DMSS in the following areas: file
transfer rates, migration and recall, and file manipulation (listing, deleting, etc.); the appropriateness of a workstation class of
file server for NSL/UniTree with LaRC’s present storage requirements in mind the role of the third party transfers between
the supercomputers and the DMSS disk array systems in DMSS; a detailed comparison (both in performance and
functionality) between the DMF and DMSS systems LaRC’s enhancements to the NSL/UniTree system administration
environment the mechanism for DMSS to provide file server redundancy the statistics on the availability of DMSS the design
and experiences with the locally developed transparent transition software which allowed us to make over 1.5 million DMF
files available to NSL/UniTree with minimal system outage
Author
Supercomputers; Magnetic Disks; Computer Storage Devices; Peripheral Equipment (Computers); Distributed Processing
233