Dr. Dobb's Blogs

How To Win the 20 Questions Competition ...

Wed, 16 Jun 2010 00:20:46 -0400

Last week I mentioned a 20 Questions Competition being run by Intel. I was interested in seeing how difficult the questions were, and suggesting how you might be able to find out the answers (and enter the competition). I thought I'd use three different ways to find the answers to the competition questions.

5 Reasons Why You Should Enter This Competition

Wed, 09 Jun 2010 12:36:02 -0400

I've just seen David Mackay's blog highlighting a competition where you can win money and software tools. Each day, starting on June 14 through the following 20 work days, a question will be posted here. You can win by correctly answering a question.

Testing for Scalability in Four Easy Steps

Wed, 09 Jun 2010 00:20:56 -0400

The other day I wrote a parallel program that worked very well on my 2-core laptop. The question is how well would it scale? When I run the same program on a 4- or 8-core machine will it go proportionally faster?

How To Become Stinking Rich Writing Netbook Apps (Please Don't Pass This On)

Tue, 01 Jun 2010 10:19:44 -0400

Last week I attended a conference on monetising mobile -- how to make money by writing and selling programs to run on mobile devices. Over 200 people attended the conference with 60% of them being developers.

Amazing Performance Gains Using SSE Intrinsics

Mon, 29 Mar 2010 00:34:44 -0400

I'm in the middle of writing up some case studies based on interviews with users of Intel Parallel Studio. As part of the exercise I set myself the goal of duplicating every technique the project engineers used.

How To Do Parallelism Without Getting Egg On Your Face

Tue, 09 Mar 2010 00:04:23 -0500

The other day I put together a trivial parallel code example that was going to be used in a 'how-to' document. The code was nothing much more complicated than a parallel 'hello world'. The sort of thing you could write while asleep. I then sent the code to three colleagues for review. Well, embarrassingly the code came back, the reviewers pointing out that the code had a data race and the results of the program were inconsistent.

Speeding Up Code Without Doing Anything

Sun, 15 Nov 2009 06:25:25 -0500

Of all the techniques I use to speed up code, the one I like the most comes with just the press of a button, or more precisely at the swap of a compiler Every Intel compiler has this particular option, and I consider to be a great friend. I'm making a point of keeping you in suspense for a little while longer. Let me first tell you a couple of stories that prove the point.

Sequential Programming: Like Eating Peas with a Straw.

Fri, 30 Oct 2009 05:29:01 -0400

Before the era of multicore chips, performance gains in CPUs was achieved by a combination of ever increasing speed and architectural enhancements. This resulted in more and more power being consumed by the processor -- a situation that could not continue forever.

How to choose the right programming model

Thu, 15 Oct 2009 04:42:21 -0400

Earler this week I watched a webinar on Beyond ";thinking"; parallel:How to choose the right parallel programming model. The webinar was first of a series of webinars on Real World Parallelism that will be broadcast over the coming weeks. James Reinders took us through some pertinent questions about what we should expect of a parallel programming model, he then went on to give examples of how different current and emerging parallel technologies 'fit the bill'.

Parallelism - full speed ahead!

Thu, 08 Oct 2009 22:06:27 -0400

Over recent weeks Intel have been involved in some exiting developments that continue to strengthen contribution it is making to the world of parallel programming. Aquisition of Rapidmind and Cilk I'm sure will complement and enhance today's solutions that Intel offer. See Reinders on Rapidmind and Reinders on Cilk for more opinion on this. Looking at my diary of events around multicore for the upcoming months, it seems clear to me that the world of Parallel Worlds is 'full speed ahead'.

Parallel Execution Advantage on Single Core Intel Atom

Thu, 27 Aug 2009 05:11:01 -0400

I've just had 2 weeks vacation in South America. To help me cope with the long flight I bought a Samsung N110 - which has a battery life of over 9 hours. Also I figured the smaller size would be easier to work with whilst sitting in economy class. Irony was I missed my daytime flight, ended up travelling in the evening and so I slept rather than using the Netbook on the plane. After a couple of days of being in Brazil, I got itchy fingers, and decided to test the Samsung N110 to see how it performed on parallel programs. I built and ran my favourite Pi program using the Intel® Compiler that comes with Intel Parallel Studio, and got a performance boost of 1.47.

Going Parallel: Part 5 -- Checking for Parallel Errors

Thu, 16 Jul 2009 08:24:36 -0400

In the previous blog, I created an application that calculated the value of Pi. In this blog I show how to detect and correct the errors that I inadvertently introduced in my last posting.

Going Parallel: Part 4 -- Enter Intel Parallel Studio

Mon, 08 Jun 2009 10:04:59 -0400

Previously I examined a Dhrystone app and identified hotspots. Since then Intel Parallel Studio has been released, so I thought I'd convert the project to use it. This time I concentrate on converting my project to Visual Studio, then use Parallel Studio begin implementing parallelism.

Going Parallel: Part 3: Let's Get Started!

Thu, 21 May 2009 01:18:46 -0400

When I first dipped my toes into parallel programming I hunted around for a legacy application to change from serial to parallel. Rather than work on one of my own apps, I looked for a serial application on the web that had lots of CPU activity. I ended up choosing the Dhrystone benchmark.

If It Works -- Use It!

Thu, 30 Apr 2009 00:15:50 -0400

I recently spoke at the ACCU ("Association of C and C++ Users") Conference in the UK, with the title of my talk being "Seven Tips To Help Get You Started on Multicore".

Going Parallel: Part 2: So who's really writing parallel applications?

Wed, 04 Mar 2009 00:20:35 -0500

In a crazy moment sometime ago I forked out a few UK Pounds registering a url how-parallel-is-your-software.com (not the real address). The plan was to use the site to let people register any applications they found that ran parallel. Perhaps even run a competition to see who could find the most parallel commercial application. Maybe this would be the route to me becoming the next dotcom millionaire! I never had the nerve to bring the idea to life. I suspect that the moment I published anything every lawyer in town would be knocking at my door.

Going Parallel: Part 1: Doing two things at once - impossible!

Thu, 19 Feb 2009 01:18:42 -0500

Maybe it's just me, but I have to confess I'm no good at doing more than one thing at once. For example, I'm at the breakfast table reading the paper and eating, suddenly my wife comments "did you hear that? ...". Usually I haven't. My typical reply is "no - I was reading the paper".

Welcome to Parallel Worlds

Tue, 27 Jan 2009 05:38:48 -0500

Welcome to Parallel Worlds, a blog hosted by Stephen Blair-chappell. Stephen is a Technical Consulting Engineer at Intel, and has worked in the Intel Compiler Lab for the last 10 years. Prior to joining Intel, Stephen worked as a lecturer at the University of Central England, specializing in Software Engineering and Embedded Systems. Outside of work, Stephen enjoys playing the pipe organ, and is an accomplished musical instrument restore