No label defined (Q4040910)

From MaRDI portal

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

scientific article; zbMATH DE number 194120
Language Label Description Also known as
default for all languages
No label defined
    English
    No label defined
    scientific article; zbMATH DE number 194120

      Statements

      0 references
      5 June 1993
      0 references
      parallel architectures
      0 references
      parallel software
      0 references
      chip design
      0 references
      parallel processing
      0 references
      SIMD
      0 references
      The book presents original results of a project in the area of specialized parallel computer systems. From a broad spectrum of parallel processing modes and architectures the author's choice is SIMD (single instruction multiple data) realized in a bit-sliced manner. This is one of the first parallel principles and it is revitalized until now due to its advantageous applicability to solving a number of important problems in computational practice. The book begins with an introductory part devoted to the history of parallel processing. The core of the book is a presentation of a reconfigurable processor array. The architecture of the system is described in a sufficiently detailed manner in order to clarify ideas of the designers. The description does not remain on the architectural level only but an implementation of the processor chip containing a subarray of processor elements in discussed deeply. Basic software routines are also formulated including floating point enhancements. The applications in signal processing area like FFT, convolution and histogramming offer an opportunity for a comparison of performance with other existing array processors. The monograph contains a collection of original ideas and worthwhile experiences. It is clearly organized. To this contribute also references which are sorted according to individual topics. The book can be recommended to those readers who are involved in study and research of advanced parallel computer systems.
      0 references

      Identifiers

      0 references
      0 references
      0 references
      0 references