1990 | OriginalPaper | Buchkapitel
Fundamental Operations
verfasst von : Prof. Sanjay Ranka, Prof. Sartaj Sahni
Erschienen in: Hypercube Algorithms
Verlag: Springer New York
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In a data broadcast we begin with data in the A register of processor zero of the hypercube. This data is to be transmitted to the A register of each of the remaining processors in the hypercube. This may be accomplished using the binary tree transmitting scheme of Figure 2.1. This figure is for the case of a dimension 3 hypercube. The data to be broadcast is initially only in processor 0 (root of the broadcast tree). It is transmitted along bit 0 to processor 1 (001). This is denoted by the arrow from the root to its right child. Now processors 0 and 1 (level 2 processors) have the data. Both transmit along bit 1. The data is now contained in all level 3 processors (0, 2, 1, 3). These processors now send the data to their neighbor processors along bit 2. As a result, all processors in the hypercube have the data.