并行计算

Parallelizing Legacy code using Fine Grained Distributed Processing

Adding parallel processing to legacy code is a desire of every software company that has an existing product which is significant in complexity and which needs to run faster. Processor clock rates are not increasing much and now multiple cores are being added to chips instead. The problem of speeding up software is moving from a hardware improvement problem to a software parallelization problem. This is a follow-on post to Why Parallel Processing? Why now?

Parallel Programming Talk #45 - Listener Questions with Tom Spyrou

Hello Parallel Programers, I'm Aaron Tersteeg, Welcome to Episode 45 of Parallel Programming Talk.

Joining me again is Dr. Clay Breshears, Master of the Parallel Universe

Today is our Listener Question Show and we've asked Tom Spyrou, Distinguished Engineer, Cadence Design Systems Inc. to join for providing an answer.

Changing partitions in Windows XP Home in order to install Moblin v2.0 Beta

A few weeks ago, I finished converting projects from Silverlight 3 Beta 1 to Silverlight 3 RTW. It took me more time than expected. Working with Beta versions is a difficult task. However, I’ve been working with Apha and Beta versions in the last 20 years. I guess I cannot live without Betas. :)

Why Parallel Processing? Why now? What about my legacy code?

Many software companies have applications which are in use by their customers that have significant runtime and for which fast runtime is a necessity or a competitive advantage. There has always been the pressure to make such applications go faster. Historically, as processors have increased their speed, the needed speedups could often be achieved by tuning the single cpu performance of the program and by utilizing the latest and fastest hardware.

Китайское искусство программирования 2, или 9,58 vs 22,317,699,616,364,044

Продолжим о задаче N-Queens, поскольку, как я упомянул в первой части данного поста (его можно прочитать здесь), 2009-й год оказался прорывным в ее решении.

Visualize this! Concurrent Collections for C/C++

Hello and welcome to another episode of Visualize this! where we talk about topics relating to Visual computing. I am Arti Gupta community manager for games development at Intel Software Network

This week we had Kath Knobe (Research Scientist at Intel) and Ganesh Rao (Technical Consulting Engineer) talk about Concurrent Collections for C/C++. Kath and Ganesh went through the specifics of the product and how being domain independent this can be used by game developers doing parallel programming.

News :

云计算与虚拟化技术相关的VMM对比介绍

介绍了云计算,也介绍了虚拟化的内容,有人问,在IA架构上实现云计算和虚拟化时,底层需要虚拟机管理器(Virtual Machine Monitor,简称VMM)来进行管理,那么VMM都有哪些呢,之间有什么区别呢?本文就对此探讨一下。


先学一下港片:“郑重声明:本部分仅是本人使用各路VMM的心得总结,不含任何广告倾向,也不保证所有内容不会随着时间流逝而失效,仅供参考。如对某种VMM有具体需求,请联系相关厂商,获得详细的最新信息,(此处略3000字)”


VMM是在底层实现对其上的虚拟机的管理和支持。以前的虚拟软件必须是装在一个OS上,然后再在虚拟软件之上安装虚拟机,装OS和应用。但现在Intel的CPU已经对虚拟化技术做了硬件支持,大多数VMM就是直接装在裸机上,在其上再装几个虚拟机… 这样就大大提升了虚拟化环境下的性能体验。如图就是目前常见的VMM工作模式:

Страсти по Любченко

Один из участников ISN - vlubch (Вячеслав Любченко) - часто упоминает конечно-автоматный подход к параллельному программированию, говорит о его превосходстве над исторически сложившимися приёмами в параллельном программировании. При этом не всегда понятны его доводы, примеры и контрпримеры. Здесь я попытаюсь описать как я понял то, что он предлагает. Ну и затем надеюсь на конструктивное обсуждение как со стороны Любченко, так и со стороны других заинтересованных лиц. И да пусть дискуссия не скатится к уровню "здесь все дураки, а я один Петросян"...

Parallel Programming Talk #44 - The PLASMA Project and Top500 with Prof. Jack Dongarra

Hello Parallel Programers, I'm Aaron Tersteeg and welcome to Episode 44 of Parallel Programming Talk. Joining me again is Master of the Parallel Universe Dr. Clay Breshears.

On today's show we talked with Prof. Jack Dongarra the director of the Innovative Computing Laboratory at the University of Tennessee.
订阅 并行计算