Parallelized Monte Carlo algorithms for
analyzing photon transport in an inertially
confined fusion (ICF) plasma are consid
ered. Algorithms were developed for
shared memory (vector and scalar) and
distributed memory (scalar) parallel pro
cessors. The shared memory algorithm
was implemented on the IBM 3090/400,
and timing results are presented for dedi
cated runs with two, three, and four pro
cessors. Two alternative distributed
memory algorithms (replication and dis
patching) were implemented on a hyper
cube parallel processor (1 through 64
nodes). The replication algorithm yields
essentially full efficiency for all cube
sizes; with the 64-node configuration, the
absolute performance is nearly the same
as with the CRAY X-MP The dispatching
algorithm also yields efficiencies above
80% in a large simulation for the 64-pro
cessor configuration.
Get full access to this article
View all access options for this article.
References
1.
Amdahl, G.1967. Validity of the single processor approach to achieving large scale computing capabilities. Proc. Spring Joint Canf. AFIPS30:483-485.
2.
Bowman, K.O., and Robinson, M.T.1987. Studies of random number generators for parallel processing. In Hypercube Multiprocessors 1987, edited by M. T. Heath.Philadelphia: SIAM , pp. 445-453.
3.
Chauvet, Y.1984. Multitasking a vectorized Monte Carlo algorithm on the CRAY X-MP/2. CrayChannels6:6-9.
4.
Chauvet, Y.1985. Vectorization and multitasking with a Monte Carlo code for neutron transport problems. Presented at the LANL-CEA Meeting on Recent Applications of the Monte Carlo Method, April 22-26 , Cardarache, France. CEA-CONF 7902.
5.
Duderstadt, J.J., and Martin, W.R.1979. Transport theory. New York: Wiley.
6.
Frederickson, P.F., Hiromoto, R., Jordan, T.L., Smith, B., and Warnoek, T.1984. Pseudo-random trees in Monte Carlo. Parallel Comput.1:175.
7.
Hayes, J.P., Jain, R., Martin, W.R., Mudge, T.N., Scott, L.R., Shin, K.G., and Stout, Q.F.1987. Hypercube computer research at the University of Michigan. In Hypercube Multiprocessors 1987, edited by M. T. Heath.Philadelphia: SIAM , pp. 382-394.
8.
Knuth, D.E.1969. The art of computer programming. Vol. 2. Reading, Massachusetts: Addison-Wesley .
9.
Los Alamos Monte Carlo Group.1981. MCNP: A general Monte Carlo code for neutron and photon transport. LA-7396-M (revised). Los Alamos, New Mexico: Los Alamos National Laboratory, Group X-6.
10.
Martin, W.R., and Brown, F.B.1987. Status of vectorized Monte Carlo for particle transport analysis. Internat. J. Supercomput. Appl. 1(2):11-32.
11.
Martin, W.R., Nowak, P.F., and Rathkopf, J.A.1986. Monte Carlo photon transport on a vector supercomputer . IBM J. Res. Develop.30:193-202.
12.
Martin, W.R., Poland, D., Wan, T.C., Mudge, T.N., and Abdel-Rahman, T.S.1987. Monte Carlo photon transport on the NCUBE. In Hypercube Multiprocessors 1987, edited by M. T. Heath.Philadelphia: SIAM, pp. 454-463.
13.
Straker, E.W., Scott, W.H., and Byrn, N.R.1970. The MORSE general purpose Monte Carlo multigroup neutron and gamma ray transport code with combinational geometry. USAEC Rep. ORNL-4585 . Oak Ridge, Tennessee: Oak Ridge National Laboratory.
14.
Wan, T.C., and Martin, W.R.1986. Parallel algorithms for photon transport Monte Carlo. Trans. Amer. Nucl. Soc.53:285-286.
