32,99 €
inkl. MwSt.
Versandkostenfrei*
Versandfertig in 6-10 Tagen
payback
16 °P sammeln
  • Broschiertes Buch

A parallel program is usually written using either data parallelism or task parallelism. With data parallelism, each processor executes the same code but operates on different data, whereas in task parallelism the program is divided into tasks, and each task is executed on a separate processor. Task and data parallelism have complementary strengths that are appropriate for different problems. However, some programs can benefit from their integration. One key problem with an integrated approach is the processor assignment problem, which is how to assign the different processors to tasks.…mehr

Produktbeschreibung
A parallel program is usually written using either data parallelism or task parallelism. With data parallelism, each processor executes the same code but operates on different data, whereas in task parallelism the program is divided into tasks, and each task is executed on a separate processor. Task and data parallelism have complementary strengths that are appropriate for different problems. However, some programs can benefit from their integration. One key problem with an integrated approach is the processor assignment problem, which is how to assign the different processors to tasks. Determining a good processor assignment is complex and often requires significant experimentation. We have developed a tool called TAP for executing integrated parallel programs with user defined processor assignments. This thesis describes the user interface and implementation details of TAP. We also discuss how the framework was used to study the behavior of PHOENIX, a scientific stellar atmospheric code.
Autorenporträt
Srikanth Bhattiprolu, received his Masters degree in Computer Science from University of Georgia. Before that he did his Bachelors in Computer Science from University College of Engineering, Osmania University, Hyderabad, India. He is currently working as a Senior Software Engineer in IBM. He loves hiking, running and watching movies.