当前位置: 范文大全  >  个人范文  >  个人陈述范文  >  计算机专业留学个人陈述

计算机专业留学个人陈述

  选择出国留学的同学们,留学申请文书都写好了吗,大家都知道留学文书要怎么写吗,对于个人陈述的写作大家有什么自己的想法没有呢,和小编一起来看看计算机专业留学个人陈述。

  Of all the areas of puter science, parallel processing fascinates me the  most. The term first came to me when I read the book puter Organization &  Design: the Hardware/Software Interface as part of my puter Architecture  course. By teaching me how the performance of puters can be improved through  pipelining and parallel processing, the book reshaped my thinking in puter  science.

  My lab experience deepened my understanding of parallel processing. In my  third year, I worked on a GIFT project with Dr. Komatsu, chief researcher of IBM  Tokyo Research Laboratory and Dr. Koseki, one of Dr.  Komatsu&apos&aposs colleagues. The  project was to introduce the architecture supports that can allow pilers to  derive more parallelism from programs. These architecture supports include three   designs, a conditional execution mechanism to execute instructions without  normal conditional jump instructions, speculative execution mechanism, and a  dynamic memory disambiguation mechanism to execute memory access instructions  simultaneously.

  As undergraduate students seldom get to be involved in actual research, I  took full advantage of the opportunity of working in the lab. I particularly  enjoyed the seminars held twice a week as part of the lab work. At these  seminars, I engaged in in-depth discussions with Master&apos&aposs students under Dr.   Komatsu&apos&aposs seasoned guidance. The lab experience is adding weight and insights to  my graduation paper An Improvement of Software pipelining using Loop  Transformations. In this paper, I will introduce a translation algorithm using  loop interchange and loop skewing. This algorithm can minimize the initiation  interval of loop nest to improve the performance of software pipelining.

  Through my lab experience and other research, I have developed a long-term  professional objective: the advancement of the parallel processing technology.  While I have strong faith in this technology, I also know its limitations as it  is today. Some sequential algorithms can&apos&apost be easily translated into fast  parallel algorithms and most pilers can only distribute works on one   platform. Another unsettled problem is that programming parallel puters is  now still a manual work. But even the modern language (like Java, C++) can do  some automatic translation work. If a piler can be developed to translate and  distribute work into different platforms, personal puters will be able to  work like mainframe puters at a fraction of the mainframes&apos&apos costs. This will  make it possible to connect all the puters in the world and speed up all the  processes.

  To help take the parallel processing technology beyond what is capable of  today, I have to undertake more advanced studies. This, I believe, can only be  acplished in a quality graduate program like yours. I plan to pursue a  master&apos&aposs degree with a concentration on paralleling and distributing pilers,  operating systems or puter **works, a bination thereof. With the training   that goes into such an advanced degree, I think I will be able to take great  strides towards fulfilling my professional objective. When I do, I think I will  be standing on the cutting-edge of the puter science.