Titlebook: Algorithms, Software and Hardware of Parallel Computers; Jozef Miklo?ko,Vadim Evgenich Kotov Book 1984 Springer-Verlag Berlin Heidelberg 1

驕傲

學(xué)術(shù)討論會

Complexity of Parallel Algorithms,In this chapter we discuss the analysis of parallel algorithms, especially their complexity. The complexity of serial algorithms is usually measured by the number of arithmetic operations. But the complexity of parallel algorithms is measured by the time, in which they can be implemented on a .-processor computer.

Ascendancy

On Parallel Languages,The improvement of mechanisms for program representation of parallelism was, and still is, the central problem of parallel programming. In practice, this consists of two different problems:

ALERT

證實

Parallel Processors and Multicomputer Systems,The rapid development of microelectronics permits the manufacture of large-scale integrated LSI and VLSI circuits, which has a direct impact on the further development of computer systems. The cost of processors and computer systems is substantially reduced. Moreover, processors made of LSI have a higher reliability.

半身雕像

https://doi.org/10.1007/978-3-8349-9616-9processor systems, in which all processors are identical, but there are significantly fewer results about inhomogeneous multiprocessor systems. The multiprocessor system (MS) is represented here by the set {.., ..., .. }. The processors in it can differ from each other only in speed, or, more generally, they can also differ in function.

半導(dǎo)體

Algorithms for Scheduling Inhomogeneous Multiprocessor Computers,processor systems, in which all processors are identical, but there are significantly fewer results about inhomogeneous multiprocessor systems. The multiprocessor system (MS) is represented here by the set {.., ..., .. }. The processors in it can differ from each other only in speed, or, more generally, they can also differ in function.

Graphite

Automatic Construction of Parallel Programs, this holds for parallel programs which do not use the conventional step-by-step representation of computations. There are two ways to relieve the difficulties: to increase the level of computer instructions and thus to bring them closer to the programmer’s thinking, or to make parallel programming

鎮(zhèn)痛劑

interrogate

Algorithms for Scheduling Homogeneous Multiprocessor Computers,eferred to as multiprocessor systems (MS). Since these computers are capable of executing several tasks simultaneously in parallel, one of the most important problems connected with the implementation of a given computational process is the problem of effective exploitation of the resources of such