80 Core Processor !!!???

Intel has announced a research chip that contains 80 (yes, eighty!!) cores. Each is a dual floating point execution unit. That's a record of maximum integration! This achieves a performance of 1 teraflops at 3.16 Ghz. That's a supercomputer performance that can make supercomputer on a desk possible when commercially available.


All that performance at an energy expense of 62 watts only, lower than some of the PC chips today! As I have mentioned couple of times in my past posts, this is what's going to happen. Ever more performance at as low a consumption as is possible. Otherwise the way the need for more performance, whether through such high performance devices or a multitude of servers, increases the energy consumption and corresponding cooling requirements will become unmanageable.

Only thing comparable has been a supercomputer built by Intel with 10,000 Pentium chips that reached teraflop performance yet consumed 500 KW of power! This was a supercomputer housed in Sandia National Labs of USA. Mind boggles just to think of possibilities when such power would be available for personal use! Some of the applications being talked about are real time speech recognition, multimedia data mining, photo-realistic game etc. That would/could lead to immediate speech based interaction with the computer like the HAL of 2001 A Space Odyssey! Digging out a photo of some one with a smile on his face in contrast to his frowning! Photo realism particularly in real time animation would add a totally different dimension to gaming experience!

With several processors running together, system bus saturates very soon. Caches help but even then limits are reached very soon, as numbers increase. Memory interface speeds, data management between these cores, keeping them current are some of the problem areas. Particularly the interface speeds possible on this system bus.

Intels' stated aim is to research these areas with a chip like this. Innovations generated in the project as per Intel are as follows,

1. Rapid design – The tiled–design approach allows designers to use smaller cores that can easily be repeated across the chip. A single–core chip of this size (100 million transistors) would take roughly twice as long and twice as many people to design.
2. Network on a chip – In addition to the compute element, each core contains a 5–port messaging passing router. These are connected in a 2D mesh network that implement message–passing. This mesh interconnect scheme could prove much more scalable than today’s multi–core chip interconnects, allowing for better communications between the cores and delivering more processor performance.
3. Fine–grain power management – The individual compute engines and data routers in each core can be activated or put to sleep based on the performance required by the application a person is running. In addition, new circuit techniques give the chip world–class power efficiency—1 teraflops requires only 62W, comparable to desktop processors sold today.
4. And other innovations – Such as sleep transistors, mesochronous clocking, and clock gating.

It's Not Done Until It Is Shippable

James Shore is writing a book on agile methodology "The Art Of Agile Development" and parts of that was being published in his blog. The latest is "Done Done". His point is that whatever is the methodology a piece of software is not "done" until it is shippable. In the sense it has been tested, detectable bugs have been ironed out etc.

Surprising how wide a range of meaning is attached to something being done by individuals. It can really be a huge range of completeness. Some would consider it done when he has finished coding and may be the piece runs, nobody knows if rightly or wrongly. Other end of the spectrum obviously is a tested, tried, polished piece of functionality.

I still remember reading an article on "sense of closure". It was precisely this issue being discussed. I have always maintained with my colleagues that when reporting something being complete the only test one can use is, is it ready to be shipped? Would somebody pay money to buy that piece of functionality. That, of course applies to any kind of product be it software or hardware or a mix of both in the form of embedded product.

GIS/GPS Really, Truly Mainstream Now!!

Time, Nov 20 issue, Asia edition features 3 of the most portable and affordable of GPS and combination devices as "Gift of the year". The three devices are Delphi NAV200, Mio H610 digiWalker and Garmin StreetPilot c550. All three are really truly portable, actually hand-held sized. Prices range from about $300 to $750 or so. Location/navigation has become ready for mass use. These can be used for street walks as well as for driving guidance. They come with preloaded maps, cute user interfaces and has added functionality such s MP3 player, phone, PDA etc.

As these are based on quite powerful processors additional functionality become easy. Could be flight directory, weather, traffic update and so on. I can imagine a time very soon when instead of a Lonley Planet country guide, tourists carrying one such device. The device would be multimedia capable and provide all the background information these guides provide!

ADT Still Has Mileage Left

Despite newer product being introduced and being actively promoted by a company, the product due to be superceded quite often shows surprising strength. Though Autodesk is actively promoting Revit, the architectural desktop( ADT) does not show any signs of becoming obsolete yet. In fact there seems to be active 3rd party support that adds to the products vitality.

H E Goldberg talked about two such resources in the Cadalyst issue. One of the advantages of ADT pointed out by Goldberg is an open API and VisionREZ is cited as a shining example of what could be done with ADT still! VisionREZ is a customized solution of ADT for the residential market and makes many design issues much simpler than it is in the original product. AmeriCAD has other resources for customer training and provides a set of services based on ADT.

ARCHIdigm is an example of useful resources. The author cites them for very useful training material for using ADT effectively.

I have been associated with both products. Couple of years back I was part of a set up that used to produce localized versions of software from Autodesk. I never really got very familiar with usage of the product. In my current avatar, I am into Revit quite heavily. I already see some workflow compatibility issues because Revit and AutoCAD did not come out of the same roots historically. I guess that would not be much of an issue with ADT as it's built on top of AutoCAD. Need to find out more.

SCRUM Works For BBC

I have been looking for evidence to see effective these "agile" methods of software development really are. What the specific religionists say, though honest, are always biased a little in favor of the religion/process they are promoting. I do feel these methods ought to work wonders. The waterfall or any such document/process heavy schemes are not workable they way they are required to.


Here comes a case study that show how BBC has used SCRUM to their great advantage. The story was presented at JAOO. A premier European developer conference on software technology, methods and best practices. The conference presents in-depth presentations and tutorials by researchers, engineers and trend-setters in software engineering and technology.


Andrew Scotland, the presenter, is Head of Development within the BBC's New Media Division. He is a certified SCRUM master and has successfully introduced SCRUM practice into the New Media division's multidisciplinary development teams (Software Engineering, User Experience, Information Architecture, Editorial, Product Management and Project Management).


The Author tells how BBC's New Media division, characterized by a lot of uncertainty and emergent software process, decided to use Scrum to more effectively deliver software amidst all that change and uncertainty. Three years later - the difference is significant, and the journey was worthwhile.

The environment is ever-changing thus it's really good to see Scrum succeeding in a situation it is supposed to work best. I'll need to look around for more such stories.

FSB capability on Multi Core Processors

One recent processor variation of the quad core variety came out earlier than predicted. That probably is the way Intel wants to fight AMD, churning out these processors at a fast and furious pace! Lot of products have already adopted the processors. We faster performance than the dual cores processors of course.

Is it double the performance? It never could be. However how much flattening does happen will decide how many cores can one put together. If the performance starts saturating at 4 cores, will it make sense to scale up to 8!! One of major reason for the performance knee is the saturation of the system bus or the main bus to system memory.

That this is on the minds of the designers is evident from the specs for the FSB or the front side bus or the bus to the main memory has been enhanced.

Toyota Way IS Different!

On two recent posts I had talked about how innovation is essential. Innovation in defining a new product rather than a "me too" one. However, we have noted that in the same class of product quality makes a large differentiator. How big!!

Toyota made a gain in sales of 34% in 2005 from three years before
Its profit per car is $1587
60% of its cars sold in America are made in America.

Contrast that with the struggles of the big 3 makers.Between Ford and GM, 46,000 jobs have been lost, and they are closing 26 factories over the next 5 years. Toyota opened a new factory in Texas already and planning another one in Ontario by 2008.

In a story, fastcompny.com magazine talks about how the focus on quality at the Georgetown, Kentucky factory let's Toyota make half a million cars a year that are perceived by consumers to be ultimate products. Continuous improvement is almost a cliche so is statement about taking care of process so that product quality takes care of itself!

Anybody with inetrest in product quality must read this article to understand how these principle need to become the way of thinking rather than a company dictated method or an way of documentation. Or even a one time project!

Getting everybody to change to a way of thinking is a wonder! I am just curious if this is a cultural/national thing ! But, obviously it's not, this plant is in US of A! From the description in the article, just about everybody in the plant are convinced that's the way to go, it has become their mental make up! While top guys bring it from Japan, everybody else is local! Right from hiring people with the right attitude to constant emphasis on the process oriented thinking seems to do the trick. The article talks about managers and improvement examples that clearly indicate this. For people in this plant, improvements are not destinations but a journey that never ends! These things become so entrenched in the minds of people that they get into thinking of improvements of things they do at home too. AMAZING!!!!