On Parallel Searching (Classic Reprint) - Hardcover

Marc Snir

 
9780656645855: On Parallel Searching (Classic Reprint)

Synopsis

A close look at parallel searching in On Parallel Searching reveals how speedups are won and lost.

This work analyzes how many processors are needed to speed up a search on large data sets, and where coordination overhead offsets gains from parallelism. It introduces concrete models of parallel machines and explains how memory access rules affect what can be computed in parallel. The material ties these ideas to range and search problems, showing that some setups resist speedups while others can achieve practical gains.

  • Learn how different memory models (EREW, CREW, CRCW) limit or enable parallel search.
  • See how a PTBM (Parallel Test and Branch Machine) is defined and used to study concurrent computation.
  • Discover why certain lower bounds arise for search and range queries in parallel settings.
  • Explore how generalized comparisons can change the leverage of parallel processing.
Ideal for readers of theoretical computer science and researchers curious about parallel algorithms, memory models, and computational limits.

"synopsis" may belong to another edition of this title.

About the Author

Snir is Senior Manager, Scalable Parallel Systems, IBM Research Division.

"About this title" may belong to another edition of this title.

Other Popular Editions of the Same Title