Nonnumeric search results on the EM-4 distributed-memory multiprocessor

Book · Sat Dec 31 04:00:00 EST 1994

OSTI ID:87636

Sohn, A ^[1]; Sato, Mitsuhisa; Kodama, Yuetsu; Yamaguchi, Yoshinori ^[2]; Sakai, Shuichi ^[3]

---

1. New Jersey Inst. of Technology, Newark, NJ (United States). Computer and Information Science Dept.
2. Electrotechnical Lab., Tsukuba (Japan). Computer Architecture Section
3. Real World Computing Tsukuba Research Center (Japan)

Numeric scientific problems have been the main focus of supercomputing as their numerous implementations on various multiprocessors indicate. Nonnumeric problems on the other hand have received very little attention for parallel implementation due to their irregular behaviors and a large amount of resource usage. This report presents the authors` experiences implementing difficult nonnumeric problems on the EM-4 multiprocessor, believing that supercomputers should also be able to effectively execute nonnumeric problems if they are to be considered ``supercomputers``. They selected two typical search problems, the Eight-Puzzle and the Tower-of-Hanoi. Two parallel search techniques are used to implement the search problems, unidirectional and bidirectional heuristic search. A total of eight different programs has been implemented on the EM-4 multiprocessor with realistic problem sizes. Execution results demonstrate that the parallel bidirectional heuristic search can solve the tree depth 20 to 40 of the Eight-Puzzle in an optimal or near optimal number of iterations in less than two seconds, and is highly scalable as it gives over 40-fold speedup for both problems on 80 processors.

• OSTI ID: 87636
• Report Number(s): CONF-941118--; ISBN 0-8186-6605-6
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
ARRAY PROCESSORS
ARTIFICIAL INTELLIGENCE
DISTRIBUTED DATA PROCESSING
EXPERIMENTAL DATA
MEMORY MANAGEMENT
PARALLEL PROCESSING
PERFORMANCE
SUPERCOMPUTERS
USES