Complex DES Using CUDA Environment

01:45 in Complex DES Using CUDA Environment, Engineering Projects, Guidance

Objective:

Objective of this thesis is to implement complex Data Encryption Standard (DES) algorithm using CUDA environment so as to study relative performance of CPUs and GPUs.

Abstract:

Multi core processors are now present in many home based systems. This chance presents a massive challenge to application developers who must design a sufficient and suited parallelism onto each parallel algorithm. Considering today's hardware performance, in order to obtain best results, a proper programming strategy for optimum mapping of all processes to existing resources is necessary. The presence of multiple cores in a single chip requires applications with a higher level of parallelism.

The use of suitable mapping algorithms can lead to a great performance improvement considering computing time at smaller energy consumption. Mapping a set of algorithms onto a multi core platform requires using a parallel programming model, which describes and controls the communication, concurrences, and synchronization of all components involved. Basic goal of CUDA is to help programmers focus on the task of parallelization of the algorithms.

General Overview:

According to websters, Architecture is an Art or Science of building; a method

or style of building". Computer architecture comprises both the art and science of

designing new and faster computer systems to satisfy ever increasing demand for more powerful systems. 

A computer architect specifies the modules that form the computer system at a functional level of detail and also species the interfaces between these modules. The exact mix of hardware, software and firmware used to implement the module depends on performance requirements, cost and availability of hardware, software and firmware. Performance and cost are the two major parameters for evaluation of architecture.

Here, the aim is to maximize performance while minimizing the cost(i.e. to maximize the performance-to-cost ratio). The progress in technologies provides new choices each year. The architect has not only base his or her decisions on the choices available today, but also keep in mind the expected changes in technology during life of system.

The architectural feature that provides the optimum performance-to-cost ratio today may not be the best feature for tomorrow's technology.