A top-down processor allocation scheme for hypercube computers

Journal Article · Tue Jan 01 04:00:00 EST 1991 · IEEE Transactions on Parallel and Distributed Systems (Institute of Electrical and Electronics Engineers); (United States)

DOI:https://doi.org/10.1109/71.80186· OSTI ID:6098173

Kim, J; Das, C R ^[1]; Lin, W ^[2]

---

1. Dept. of Electrical and Computer Engineering, Pennsylvania State Univ., University Park, PA (US)
2. Dept. of Electrical Engineering, Univ. of Hawaii at Manoa, Honolulu, HI (US)

This paper presents an efficient processor allocation policy for hypercube computers. The allocation policy is called {ital free list} since it maintains a list of free subcubes available in the system. An income request of dimension {ital k} (2{sup {ital k}} nodes) is allocated by finding a free subcube of dimension {ital k} or by decomposing an available subcube of dimension greater than {ital k}. This free list policy uses a top-down allocation rule in contrast to the bottom-up approach used by the previous bit-map allocation algorithms. This allocation scheme is compared to the {ital buddy}, {ital gray code} (GC), and {ital modified buddy} allocation policies reported for the hypercubes. It is shown that the {ital free list} policy is not only statically optimal as the other policies but it gives better subcube recognition ability compared to the previous schemes in a dynamic environment. The performance of this policy, in terms of parameters such as average delay, system utilization, and time complexity, is compared to the other schemes to demonstrate its effectiveness. Finally, the extension of the algorithm for parallel implementation, noncubic allocation, and inclusion/exclusion allocation is also given.

• OSTI ID: 6098173
• Journal Information: IEEE Transactions on Parallel and Distributed Systems (Institute of Electrical and Electronics Engineers); (United States), Journal Name: IEEE Transactions on Parallel and Distributed Systems (Institute of Electrical and Electronics Engineers); (United States) Vol. 2:1; ISSN ITDSE; ISSN 1045-9219
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ALGORITHMS
COMPARATIVE EVALUATIONS
COMPUTER CODES
COMPUTERS
EVALUATION
HYPERCUBE COMPUTERS
MATHEMATICAL LOGIC
PARALLEL PROCESSING
PROGRAMMING