Subcube allocation and task migration in hypercube multiprocessors

Journal Article · Sat Sep 01 04:00:00 EDT 1990 · IEEE Transactions on Computers (Institute of Electrical and Electronics Engineers); (USA)

DOI:https://doi.org/10.1109/12.57056· OSTI ID:6541206

Chen, M S ^[1]; Shin, K G ^[2]

---

1. IBM Thomas J. Watson Research Center, Yorktown Heights, NY (US)
2. Real-Time Computing Lab., Dept. of Electrical Engineering and Computer Science, Univ. of Michigan, Ann Arbor, MI (US)

This paper addresses two issued in the management of processors in a hypercube: subcube allocation and task migration to eliminate the system fragmentation caused by allocation and deallocation of subcubes. The authors prove that the subcube allocation strategy using a binary reflected Gray code (BRGC), called the GC strategy, possesses the best subcube recognition ability among all strategies that use sequential searches. A binary code (BC) is defined as the binary representation of a nonnegative integer, and an extended binary code (EBC) is the one obtained by permuting the bits of a BC. Similarly, an extended Gray code (EGC) is obtained from a BRGC. The subcube recognition ability of an allocation strategy using multiple EBC's is analyzed and compared to that using multiple EGC's. The minimal number of EBC's required for complete subcube recognition in an n-cube or Q{sub n} is proved to be C{sup n}{sub n/2}, where C{sup q}{sub p} stands for the number of combinations of choosing p out of q possibilities.

• OSTI ID: 6541206
• Journal Information: IEEE Transactions on Computers (Institute of Electrical and Electronics Engineers); (USA), Journal Name: IEEE Transactions on Computers (Institute of Electrical and Electronics Engineers); (USA) Vol. 39:9; ISSN ITCOB; ISSN 0018-9340
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ARRAY PROCESSORS
COMPUTER ARCHITECTURE
COMPUTERS
HYPERCUBE COMPUTERS
PARALLEL PROCESSING
PERFORMANCE
PROGRAMMING