Monte Carlo calculations on high speed machines

Asai, Kiyoshi; Higuchi, Kenji; Akimoto, Masayuki; Naito, Yoshitaka; Komuro, Y.; Kadotani, Hiroyuki

doi:10.1016/0149-1970(90)90034-3

Cited by 2 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…a=T,vIT,,=(T,-Tv,)IT,, ( 2 ) where T,, is the execution time of the vec-torized part in scalar processing, T,, the execution time of the vectorized part in vector processing, T , the execution time of the code in scalar processing and T,, the execution time of the scalar part in vector or scalar (both are the same) processing.…”

Section: Detail Analysis Of Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Development of Monte Carlo Machine for Particle Transport Problem

Higuchi¹,

Asai²,

Akimoto³

1995

Journal of Nuclear Science and Technology

View full text Add to dashboard Cite

Monte Carlo machine, Monte-4 has been developed to realize high performance computing of Monte Carlo codes for particle transport. The calculation for particle tracking in a complex geometry requires (1) classification of particles by the region types using multi-way conditional branches, and (2) determination whether intersections of particle paths with surfaces of the regions are on the boundaries of the regions or not, using nests of conditional branches. However, these procedures require scalar operations or unusual vector operations. Thus the speedup ratios have been low, i.e. nearly two times, in vector processing of Monte Carlo codes for particle transport on conventional vector processors. The Monte Carlo machine Monte-4 has been equipped with the special hardware called Monte Carlo pipelines to process these procedures with high performance. Additionally Monte-4 has been equipped with enhanced load/store pipelines to realize fast transfer of indirectly addressed data for the purpose of resolving imbalances between the performance of data transfers and arithmetic operations in vector processing of Monte Carlo codes on conventional vector processors. Finally, Monte-4 has a parallel processing capability with four processors to multiply the performance of vector processing. We have evaluated the effective performance of Monte-4 using production-level Monte Carlo codes such as vectorized KENO-IV and MCNP. In the performance evaluation, nearly ten times speedup ratios have been obtained, compared with scalar processing of the original codes.

show abstract

Section: Detail Analysis Of Resultsmentioning

confidence: 99%

“…One is to rewrite the codes or develop new one suitable to hardware features of conventional vector processors('). The other is to develop a Monte Carlo machine (2), which is suitable to the algorithms used in the existing Monte Carlo codes.…”

Section: Introductionmentioning

confidence: 99%