Performance evaluation-parallel computing, Computer Engineering

Assignment Help:

Performance Evaluation

In this part, we talk about the primary attributes used to measure the performance of a computer system. Unit 2 of block 3 is totally devoted to performance assessment of parallel computer systems. The performance attributes are:

i)  Cycle time (T): It is the part of time for all the operations of a computer system. It is the opposite of clock rate (l/f). The cycle time is represented in n sec.

ii) Cycles Per Instruction (CPI): dissimilar instructions takes different number of cycles for implementation. CPI is dimension of number of cycles per instruction

iii) Instruction count(Ic): No. of instruction in a program is called instruction count.

If we presume that all instructions have same count of cycles, then the total execution

Time of a program = number of cycle required by one instruction*number of instruction in the program*time of one cycle.

Hence, the execution time

                                                 T=Ic*CPI*Tsec.

Basically the clock frequency of the process is specified in MHz. Also, the processor speed is calculated in terms of million instructions per sec (MIPS).

 


Related Discussions:- Performance evaluation-parallel computing

What are the objectives of usb, What are the objectives of USB? a) Simp...

What are the objectives of USB? a) Simple b) Low cost c) Easy to use d) Supports wide range of data transfer characteristics e) Plug and play mode of operation

What is reducibility, What is reducibility?  The primary method of prov...

What is reducibility?  The primary method of proving some problems are computationally unsolvable.       It is known as reducibility. Reducibility always includes two problems

A subroutine can contain nested form and endform blocks, A subroutine can c...

A subroutine can contain nested form and endform blocks. False.

What is pipelining, What is pipelining? The overlapping of implementati...

What is pipelining? The overlapping of implementation of successive instructions is known as pipelining.

Data structure, Process: pid start time end time priority t...

Process: pid start time end time priority timeslice list of CPU bursts list of IO bursts (the number of IO burst will always be 1 less than the number of CPU

How debugger works internally, Whenever we compile with -g option, it will ...

Whenever we compile with -g option, it will make a symbol table, and according that table for every function and line it will call ptrace.

Why object oriented development not only allows reuse, Why object oriented ...

Why object oriented development not only allows reuse In a wider way we can say that object oriented development not only allows reuse and information sharing within an applica

Forall statement in fortran, Q. FORALL Statement in fortran? The FORALL...

Q. FORALL Statement in fortran? The FORALL statement permits for more common assignments to sections of an array. A FORALL statement has general form.   FORALL ( triplet, ..

Name the processes of oom, Name the processes of OOM In OOM the modelli...

Name the processes of OOM In OOM the modelling passes through the given processes: System Analysis System Design Object Design, and Final Implementation.

What is gdpro and magicdraw uml, What is GDPro and  MagicDraw UML GDP...

What is GDPro and  MagicDraw UML GDPro : This  is a full suite of code  management tools and UML. MagicDraw UML: UML diagrams fully support this: MagicDraw RConverter a

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