Software overheads in parallel programming , Computer Networking

Assignment Help:

Besides these hardware overheads, there are certain software overheads imposed by libraries, parallel compilers, tools and operating systems.

The parallel programming languages are developed for parallel computer environments. These are developed either by introducing new languages (e.g. occam) or by modifying existing languages like, (C and FORTRAN).  Normally the language extension approach is preferred by most computer designs. This decreases compatibility problem.  High-level parallel constructs were added to C and FORTRAN to make these languages suitable for parallel computers. Besides these, optimizing compilers are designed to automatically detect the parallelism in program code and change the code to parallel code.

In addition to development of compilers and languages for parallel programming, a parallel programming environment should also have supporting tools for text editing and development of parallel programmes.

Let us now talk about the examples of parallel programming environments of Cray Y-MP software and Intel paragaon XP/S.

The Cray Y-MP system works with UNICOS operating system.  It has two FORTRAN compilers CFT and CFT 77 for automatic vector code generation. The system software has large library of routines, program management utilities, assembler UNICOS and debugging aids written in C. It supports optimizing, vectorizing, concurrentising facilities for FORTRAN compilers and also has vetorizing and optimizing C compiler. The Cray Y-MP has three multitasking / multiprocessing methods namely, (i) microtasking (ii) macrotasking, , (iii) autotasking. As well, it has a subroutine library, containing a variety of utilities, high performance subroutines along with scientific routines and math.

The Intel Paragaon XP/S system is an extension of Delta systems and Intel iPSC/860, and is a mesh and scalable connected multicompiler which is executed in a distributed memory system.

The processors that for nodes of the system are 50 MHz i860 XP Processors. Furthermore, it uses distributed UNIX based OS technology. The languages supported by Paragaon have C, C++, ADA and Data Parallel Fortran. The tools for integration contain FORGE and Cast parallelisation tools. The programming environment contains an Interactive Parallel Debugger (IPD).


Related Discussions:- Software overheads in parallel programming

Print Servers, Which of the following commands will display the current pri...

Which of the following commands will display the current print jobs on a printer named Office Printer 01?

Encrypted with a symmetric key, Alice sends a message to Bob, encrypted wit...

Alice sends a message to Bob, encrypted with a symmetric key. Bob decrypts the message and finds it is a purchase order for an expensive workstation. When the time comes to deliver

The ip address ranges for public and private ip address, What are the IP ad...

What are the IP address ranges for public and private IP address?

Physical configurations sonet sdh , Physical Configurations Transport ...

Physical Configurations Transport signal multiplexer de multiplexer. It either  signal from multiple   sources into a STS singles  or de multiplexes and STS signal  into diffe

Intrinsic functions, Intrinsic Functions HPF introduces some new intri...

Intrinsic Functions HPF introduces some new intrinsic functions in addition to those defined in F90. The two most regularly used in parallel programming are the system inquiry

Describe the different steps in distributed problem solving, QUESTION (...

QUESTION (a) Four important benefits of Multi-Agent Systems are modularity, efficiency, reliability and flexibility. Briefly explain these benefits (b) Agents work together

Determine power dissipated in resistor, Question: With Vout not connect...

Question: With Vout not connected to any additional circuitry, what power is dissipated in the 7 kW resistor?

Ethernet fields, ETHERNET FIELDS:  In Ethernet fields the preamble and...

ETHERNET FIELDS:  In Ethernet fields the preamble and CRC is usually not given in frame. The destination address of each is the broadcast address. There is special value reser

Merit and drawback of mpi, Merits of MPI Runs on any shared or dist...

Merits of MPI Runs on any shared or distributed memory architectures; Can be used on a wider range of troubles than OpenMP; Every process has its own local variabl

Write Your Message!

Captcha
Free Assignment Quote

Assured A++ Grade

Get guaranteed satisfaction & time on delivery in every assignment order you paid with us! We ensure premium quality solution document along with free turntin report!

All rights reserved! Copyrights ©2019-2020 ExpertsMind IT Educational Pvt Ltd