The race for leadership of parallel processing into the future is now well underway, and there is a chance that Sun Microsystems – not exactly a dark horse but not necessarily the first name to spring to mind as a main contender – may actually steal a march over the rest.  But this does then beg the question: how much will this directly affect enterprise users? 

It’s upcoming Rock Processor makes use of an old technology, transactional memory, but in a new way that should make developing applications and services a good deal easier than otherwise with any parallel software development technologies, such as multi-threading so far available. What is perhaps more important, however, is that Sun is also amongst a number of vendors funding, to the collective tune of $6m, Stanford University’s new Pervasive Parallelism Lab. The others include IBM, HP, AMD and Intel. 

It does not, however, include Microsoft, which has teamed with Intel to fund
Berkeley
University and the

University of
Illinois ($10m each) on similar parallel processing research. Microsoft and Intel are, of course, prime movers in multi-threading. 

Transactional memory can be implemented in software or hardware, but both can require significant levels of skill. Sun has come up with Hybrid Transaction Memory (HTM) which sets out to exploit the best capabilities of both, making development work easier than extremely difficult, and offering the chance for applications performance to improve without change as the Rock processor is developed further. 

And as the Stanford lab is headed by Kunle Olukotun, who helped design chips that are part of Sun’s UltraSPARCTx family, it might be possible to guess the general research direction the Lab may take. As IBM is also a chip maker in its own right, transactional memory could get some reasonable leverage behind it, which might just leave Microsoft ploughing a different furrow alone.

But back to that question: fundamentally, how much should an enterprise care about such things? Well, if one assumes that traditional processor and software architectures are, while by no means dead yet, widely diagnosed as terminal; and if one also assumes that what follows is parallel processing,  then every CIO and IT director needs to be considering what may be coming next, what its impact might be and what will be involved in implementing it. 

These are archetypal `big questions’ with no easy answers as yet. There might just be one, however.  

Parallel systems are going to be large – the larger the better in a way. They are also going to be expensive to buy and to run. But they are also going offer prodigious levels of performance, both in the shear grunt of throughput and in areas such as I/O management and capabilities.  

As we all know, the likes of Google, Amazon and Microsoft are building huge datacentres aimed at the nascent utility services market. They would likely find parallel systems strangely attractive, precisely for the above reasons. Then they would need to market the hell out of the service offerings.  

This could lead enterprises to seriously examine the possibility of switching to utility services simply because the cost and hassle of trying to make the parallel move alone will probably prove too expensive and/or traumatic. 

It could be that no-one need worry about making the move for it will only be the big utility players that have the half-dozen rocket scientists that ultimately need to know all this stuff.

The other week I wrote about the impact of the poor economic situation and the scope for really quite disruptive change in the building blocks of IT infrastructure that might follow as the world gets ready to spring out of the doldrums. It looks as though the IT vendors are gearing up for that eventuality, as new possibilities for inclusion in future infrastructure services are now appearing. 

Here are two of the latest that caught my eye. They are aimed, at least in part, at grabbing a quick-fix step-function jump in capacity and capabilities once the economy turns upwards.  

The first is another contribution to the latest fashion of datacentres in a container, targeting the need for finding quick ways of getting capacity without some of the hassles of installing and commissioning significant systems upgrades. 

This one comes from HP, which has christened it the Performance Optimised Datacentre – or POD. In much the same was as IBM and its container offering, HP is aiming to meet customer needs rather than provide an alternative sales option for its own systems. Users can specify any systems they like, so long as they fit in a 19 inch rack. With a planned turn-round time of six weeks between order and delivery, and a maximum capacity of around 3,500 compute nodes, this is one approach that may well have some short-term attraction for users looking for a quick scalability fix. 

The second comes from hosting company, Bytemark and, although primarily designed as hosted services engine, looks like it could also be the basis of something a little more permanent, even for in-house datacentres.  

Hosted services are not only an obvious option for meeting the requirements of rapid scalability, but also an increasingly viable option as a permanent alternative to many-an onsite datacentre. This is particularly so as server performance and virtualisation technologies continue to improve. But at the other extreme there is also the possibility of exploiting large numbers of standardised, simple servers, particularly in the Linux-running marketplace – and this exploitation can make sense both for remote hosting businesses and in-house datacentre users. This is, after all, one of the selling points of IBM’s z/10 mainframe, which can turn itself into a thousand or more virtual Linux servers. 

Bytemark’s approach is radically different to the z/10, but the potential is very similar. By using Intel’s Atom processor rather than the Xeon or AMD Athlon, it has been able to offer a low cost (£45 rental per month), reasonably-performing server, with 2 GByte of memory and two 100 GByte disc drives. Best of all, the thing only consumes 25W of power, which is a good deal less than most other systems worthy of the `server’ title. 

This type of low-cost, low-power, reasonably-performing server has the ability to hit a sweetspot for a large number of users in the Linux systems marketplace. As well as IBM, this market has been noted by HP, where very large volumes of low-cost Linux servers can be managed by a single NonStop server. This maintains a high availability server state record for each Linux server – effectively a record of what task each is performing and what applications or tools are running. Should one of the servers fail its workload can be shifted to another and the failed system replaced with no down time and a minimum effective systems redundancy requirement. It has the potential to be cheap to run, standardised so cheap to buy, easy to manage and very scalable. All of these attributes, and the latter in particular, are going to be important capabilities when the economy picks up again.

Musing on the state of the economy over the weekend I recalled the comments of AT&T cloud evangelist Joe Weinman who suggested at the recent Structure 08 conference in San Francisco that, when it came to the future of utility computing and `The Cloud’, “if the software licensing model doesn’t catch up, people will either be forced to pull from the open source world or the whole idea is going to drop dead under its own weight.”

Well, up to a point Lord Copper. I can see where he is coming from but there seems a sense of doom about the opinion that I don’t see and history, together with the cycles of economic fortune and more specifically misfortune, may even bear me out. For example, I got to thinking about the current economic slowdown and remembering others in the past. 

Economic times were pretty bleak in the late 70s when the first big disruptive technology, the personal computer, first started to appear in volume. Most of the mainstream IT vendors said it would unlikely claim a significant place in business. But who is in business now? Then the doom-laden days of the late 80s, epitomised by Black Wednesday, brought Standard High Volume (aka PC based) servers from the likes of Compaq and Dell right into the heart of enterprise client/server infrastructures. 

Now we have another economic slowdown and it is certain to impact growth in some sectors of the enterprise IT marketplace, and will provide an added spin to the fortunes of others.  

The standard response for most enterprises is likely to be a push for greater savings, so any short term investments are likely to be geared to `green’ issues, with a concentration on energy consumption savings rather than the more altruistic notions of reducing carbon footprints.  

There is also likely to be some push towards anything that gives users more Bangs for the same number of Bucks. So virtualisation is certain to grow in popularity. That is likely to bring a need for greater investment in new server platforms. These will not only be more suited to running virtualisation code, but also provide a jump in performance, a reduction in energy consumption and a reduction in maintenance costs that, collectively, should make the new investment worthwhile. 

But all that could indeed run up against the strictures Joe Weinman outlined. Yes, if the mainstream leaders of the ISV community don’t change their licencing policies, and change them soon, it could easily bring the potential of The Cloud to a grinding halt. But it could also bring those vendors to a halt instead. As Weinman said himself, users may be forced to `pull from the open source world’, to which the short response is `yes….and?’ Why not source applications and services from the open source world?  

One answer is that suitable code is not necessarily available, but this is where the current economic situation, coupled to the disruptive potential of The Cloud, may re-run old historical patterns. The Cloud most certainly represents a brand new marketplace with totally different dynamics, occurring at a time when many users will be putting current investment plans on hold for a while. 

That gives a significant opportunity for new start-up companies that do `get’ how The Cloud’ can be exploited to develop their technologies and business models. When users start to see their way clear for more concerted investment plans they will also be in the market for whatever maps best onto their needs – which are likely to encompass much greater flexibility and agility, far greater performance, lower maintenance cost through self-management and healing, and dramatically reduced energy consumption – with much of it available in practice as a pay-per-use service. 

This is likely to be beyond the scope of many of the currently leading ISVs, particularly if they stay with the old licence models. The start-ups are also likely to have far better technologies which hit the new sweet-spots that post-slump businesses will need. After all, a cynic might actually wonder why all the current crop of fancy financial risk analysis tools were unable to spot that large packages of dodgy debts were still very dodgy debts, despite being rebranded as `investment vehicles’.

When it comes to IT, the word `monopoly’ is invariably heavily loaded with portents of controlled availability and inflexible product offerings. This is certainly the perception that comes hand in glove with IBM and the mainframe marketplace.  

The truth about any monopoly, however, is that it has the potential to be at least as good for users as any perceived badness normally associated with the word. And with the recently announced acquisition of small, Sunnyvale-based rival, Platform Solutions Inc (PSI) IBM now gets the chance to demonstrate – under a very public magnifying glass – just which interpretation of `monopoly’ it is going to exercise. 

To call PSI a `rival’ to IBM in the mainframe marketplace was, of course, stretching the word to near breaking point, but its technology – a hypervisor that allows mainframe code to run on Itanium-based hardware – has (or possibly had) the capability of opening up the mainframe market outside its normal user base. Its key advantage is to offer the possibility of a lower-cost, probably lower-performing alternative platform. This could help move mainframe applications into the mainstream of event-driven web services, for example, and could run them on the same platform as a wide range of applications from other platforms. 

There were, of course, the crossed lawsuits that existed between them: IBM suing for copyright infringements and PSI countering with an anti-trust suit; but they are now gone. It would be easy to assume that IBM bought PSI just to stop the action against it, though I suspect its lawyers could have kept the legal wrangling going long past PSI’s ability to fund the fight, and IBM’s lawyers still need paying, regardless. Such an action would also be a certain mark that company favoured the `bad’ side of monopoly. 

That fear has been expressed by US Computer & Communications Industry Association president, Ed Black. He has suggested that “it is transforming a market with latent potential for competition and innovation into a sector with little prospects for anything but complete domination of IBM.”

Well, yes, that potential is now stronger than ever. But IBM has a history of allowing different divisions to compete for the same markets, and sometimes compete with extreme prejudice. In the mainframe market, where the development costs in both hardware and software (and systems software in particular) can be mind-bogglingly high, monopoly may in practice be the only way to make it work. But that does not mean the only answer needs be z/Series, and only z/Series. IBM can have an over-arching policy for, what shall we call it?, big enterprise solutions, but will happily let the divisions fight it out for a share of the business.

The company has already hinted that the PSI technology is set to be exploited for future products, though they are unlikely to appear as z/Series systems. One way (and potentially a very charitable one) this can be interpreted is as a pitch at creating a win:win:win situation.  

The market would win because it would get delivered, from a different division of IBM, the types of platform that do accommodate the mixing and interoperation of radically different operating environments. It could also open up the market for new users that could make business sense of a smaller, cheaper, slower (but just as robust and secure) `mainframe’ system. Here lies real market potential, but arguably one the z/Series team might not feel happy with. And as this is a software technology running on a standard platform, other vendors could be licenced to sell it too. 

Third party applications and tools vendors would win because new business opportunities would be opened up for them. It could also open up the market to competition from ISVs from outside the mainframe community. 

IBM would win because it would maintain control over The Mainframe at a strategic level. Despite the inevitable cries about stifled innovation, the upfront costs of playing in the mainframe market – either as vendor or user – are such that a good deal of strategic control is necessary. Innovation can be a good thing, but it can also kill.  

Let’s not forget that the wild-frontier web services sector actually exists off the back of a raft of standards that vendors actually adhere to. Thankfully, the days are now gone when the likes of dear old Ken Olsen, founder of Digital Equipment, would utter sayings such as (and I paraphrase) `we believe in the standardisation of Unix, and will differentiate ours by including this, that and the other that nobody else can offer’. 

And yes, this is a charitable view, and it is IBM. We must wait and see. But don’t cry for PSI, for its legacy may yet be marked by important changes.

There’s another phrase that has recently crept into more common parlance amongst IT vendors -  `employee-owned IT’. This is a concept that has the potential to be one of the better two-edged swords the business has ever come up with, but it is also a model that is the most likely to move everyone, ever faster, towards using remote infrastructure models based around The Cloud. 

From the point of view of any business it is something to be welcomed, for it moves the cost of end-user client systems from the business and onto the employees. The possible downside, of course, is that it may also end up as a tax, imposed by, and paid to, the employer, for the privilege of having a job. In the end, employers will need to pay bigger salaries as compensation, particularly for PAYE staff. And they will need to claim this stuff against tax, of course. 

While the coalface users might like the option of choosing their own client systems – be it on price or fashion consciousness, this opens up all sorts of problems for the employers. These things need to be standardised and controlled. Allowing staff to use what they want as a client can only cause endless grief for the IT department unless very strict controls are applied to what is bought. This can mean buying clients from the `company store’, which can look even more like a tax on having a job. 

But worst of all the employee-owned IT model has real security problems attached to it, not least being the standard ones of users either losing their clients, or having them stolen – and for every lost MOD laptop that makes the news, there a bound to be many more from private companies that hushed up (and probably more damaging). Superglueing the thing to users’ hands only shows the bad guys that this is a laptop worth stealing. 

The only sensible way of exploiting employee-owned IT is to not let them near the data. And the only way to do that is with portable, personal, thin clients that are only portals through to the corporate data back at the datacentre. But the data never leaves there and is never stored on the device itself. Once the connection is severed there is nothing worth stealing except a bunch of bits. 

And there are several ways the connection between portal and datacentre can be quickly severed in an emergency – a large red panic button, for example, or perhaps a thin, weak, chord to a wrist strap worn when the device is in use – and it won’t work without the strap fitted. Pulling the client from the user when in use breaks the chord, and the connection. 

Meanwhile the data is safe, and that is the primary role of any infrastructure. It also means that, even if the business has and onsite datacentre, it is effectively running it as an end-to-end, integrated service delivery utility. It will be the only way the employee-owned IT model can work securely. From there, it will become a much shorter step to decide just how much of an existing onsite infrastructure is actually needed next time there is a major upgrade and how much can be moved to a Cloud-based remote infrastructure provided by specialists.

The question is: do we need some new metrics and points of reference when it comes to the relationship between IT, its users, and its carbon foot-print? 

It is estimated that IT already has a carbon footprint as big as the airline industry – 2% of all carbon emissions. Somehow, that already seems a little low and not that unreasonable. After all, though many would argue about the aggravations caused by IT – Little Britain’s archetype: `the computer says “no”’ now being part of urban folklore  - its benefits-per-Kg of carbon is quite possibly better for most people than the aircraft – and most certainly will be in the future. 

More importantly, however, its carbon footprint is growing fast, while so far managing to avoid the public opprobrium now meted out to the airline business. So there is still time for the IT industry – vendors and users – to grasp the nettle of cutting energy consumption and reducing carbon foot-prints before the rest of the world notices the problem. 

Most of the big systems vendors are already trundling down this track, but there still seems a reluctance amongst users to readily jump on the bandwagon they are collectively pushing. Which is why the question arises about the need for new metrics that make the point to users more effectively. 

Sun Microsystems certainly seems to be thinking along this line, and is keen to use itself as an example. It has re-engineered its own technology and business procedures – for example, 40% of staff now work from home – and in the process has saved an estimated 29,000 tons of CO₂. This is important, but in IT usage terms perhaps a rather meaningless metric. Sun’s analogy - the equivalent of 500 planes flying round the world 10 times – doesn’t help much either: I suspect that equates to about an hour’s worth of global air travel (approximately 120,000 1 hour flights).  

A more directly obvious metric is the T5000 servers, which 10 years ago would need 128 servers in three racks, consuming 120 kW. Now it is one box using 1kW. More relevant still for many large businesses is the Sun Ray thin client, which has 5% of the energy use of a PC. With no moving parts it also has a lifecycle of 20 years or so – and all the intelligence is back at the server. And server technology is allowing significant growth in power and performance coupled to a reduction in footprint, cooling requirements and energy consumption. This combination can actually deliver growth in business service with a reduction in both energy costs and TCO, for there are also lower maintenance costs. 

For example, if a thin client uses only 5% of a PC’s energy, a large company with several thousand of them can afford to re-invest in newer, faster servers every five years, with each new server running more thin clients than the server it replaces? If the lifecycle of the thin clients is 20 years, that is four iterations of server development, each one capable of handling more client workloads than the last. Now the energy running cost per server is more than the cost of buying them, this is a model that allows users the flexibility to choose between a future of fewer servers delivery the same workload and the same number offering real growth potential.  

A specific example comes from Sun lifecycle management specialist partner, Bell Microsystems, and its customer, Rightmove. They replaced old servers with T1000 units which now deliver 500K page impressions/month with a energy saving of 92%, a similar saving on the physical footprint, and a saving of 9600 kgs of carbon/month. All must be useful at a time of a downturn in the housing market. 

What about road warriors and their need for laptops? Well Sun staff already come equipped with smart cards for Sun Ray clients, which is a model that can – with sufficient security and engineering – be extended to every hotel room at the very least. So there is a need for some new metrics for both users and vendors to work with. The ultimate figure, of course, is the overall cost of delivering relevant processes and services that are of definable value to the `user’ (business, organisation or individual) set against the cost of constructing the systems in the first place (ideally including the social costs of the impact on the raw materials excavation and processing), the costs of using and the increasingly important costs of disposal and savings of re-use. 

The need to change from bangs-per-buck to bangs-per-carbon/Kg. Define the relationship between CPU cycles/sec and what is being delivered. This is a lifecycle management issue every CIO is now facing - what application is used to meet a business requirement, how well is it written, how well the infrastructure is architected and implemented.

I love analogies, and two immediately come to mind following Bill Gates’ keynote at the recent Microsoft TechEd event. How about: Microsoft’s move into mega-datacentres and Software as a Service is like using the latest race car aerodynamics theories to design a horse and cart. It should go fast in theory, except that it is still actually pulled by horses – lots of them, to be sure, but still horses. Or, it’s like deciding that the best way to get to the moon is to start by building a very, very long bridge.   Gates’ Keynote showed that he has discovered The Cloud, but it seems he is still viewing it as just another way for Microsoft to deliver `applications’ rather than as a platform for `services’. This poses two alternative problems, one for users and one for Microsoft itself.  

If Microsoft succeeds with promoting the idea of The Cloud as an application delivery vehicle, and it certainly has the marketing muscle to achieve it, users could well find themselves disadvantaged. If they feel that they are still working with traditional applications in the traditional manner, it may well give them a great feeling of comfort. But it is quite likely that they will soon find themselves increasingly disadvantaged against competitors that do adopt a service-based approach. They are likely to gain greater operational flexibility and agility in the way they can serve their respective markets, meet changing customer demand, and adapt their business processes in order to manage those changes. 

The other problem if Microsoft succeeds is that considerable confusion may exist amongst users. The whole issue of moving users from a pay-up-front permanent licence acquisition business model to an annuity model is one of the main stumbling blocks of the shift to any service-based, per-per-use model, particularly from the vendors’ point of view. If Microsoft tries to sell the idea on the basis of users still `having their applications’ it could end up with a good deal of egg on its face from the mixed messages.  

A side issue of this is that Microsoft is joining the race to build vast datacentres, all obviously based upon multicore x86 architecture processors. But this itself poses a number of problems, not least being that the levels and volumes of service that will be required will push heavily towards the need for complex, parallel processing architectures. There are some doubts here as to how effective large, Windows-based multicore x86 devices can be in such an environment. It has to be noted that IBM’s latest supercomputer now makes extensive use of Cell architecture processors to break the PetaFlop barrier.  

Windows as an operating system has just about reached the limit of its capabilities with 8-core processors, while Microsoft’s recent track record in this area -
Vista showing that it seems to have started to miss the sweet spot for business users – suggests that this trend may become more prominent as datacentres become huge and hugely oriented towards service-delivery. There has to be some doubt as to whether the company now has the right background for building systems capable of running a Very Large Datacentre delivering billions of dynamically assembled, loosely coupled code components as millions of individual, short-lived service entities.

There are always lessons in history, if we are prepared to learn from them, and I come from the BW (Before Windows) era, a time which does have some things to teach us, I feel.  

For example, there came the point of IoW (Initiation of Windows) where a whole new golden future opened up before us – theoretically, at least. In practice, of course, it’s early days achieved very little and gained very little market traction. Then came Windows 2, which those with long memories will recall moved the world forward hardly at all. 

It was only when Windows 3 appeared that potential users not only started to understand what was possible but to make the move to adopt it. But even then, it still had its problems with bugs and the like and it was not until the arrival of Windows 3.1 that the system gained a measure of reliability that gave users real confidence in not just its capabilities but its survivability in the real world. 

But its success was such that the `Version 3.1’ tag became the accepted nomenclature of an acceptable level of product maturity for a wide range of software products. There is a learning here, I feel, which is particularly important for any business looking to make web services an integral part of their operational business process infrastructure.  

Web 2.0 has already become an important marketing tag – in fact `2.0’ is being applied to just about everything and anything to do with IT systems these days. As a catch-all handle to define the next step forward I guess it even works, up to a point at least. But history shows that `Version 2.0’ as a half-hearted miss, and we are already seeing signs of the problem now.  

Web 2.0 is demonstrating some interesting and powerful potential, particularly in the way mashup capabilities are pointing to entirely new ways in which specific composite applications can create new functionality. It is only a step to think in terms of extending the idea into exploiting enterprise infrastructures to create some potentially truly powerful services.  

The downside of this, at the moment, is that there has been little or no thought applied to the management of such capabilities or their governance. For example, the fact that an individual can think of a new way of processing insurance claims by mashing up some legacy and new applications in a novel fashion does not mean it is a good idea – in business process management terms – to do it. History shows that there needs to be a balance between the `that’s cool’ application of technology just because we can, and the `yes but….’ of ensuring that the reasons for its existence is understood and justified, and that it operates in a reliable and predictable manner. 

Historically, the `yes but….’  came with the appearance of Version 3.1, and that part of the relationship between the Web and enterprise infrastructure has still to be reached.

It was good to see both Joe Tucci, EMC chairman, president and chief executive, and Howard Elias, president of EMC’s Global Services and Resource Management Software operations confront the changing world that corporate IT is facing. Speaking at the company’s recent annual bash, EMC World, both stressed the need for IT vendors to move from an applications-centric world to an information-centric one. 

Tucci, in particular, referred to the way that information – often vital business information that should be available to all within a company – lies effectively trapped in individual machines. It should, he suggested, actually be available to all that need it (and obviously have the authority to use it) within The Cloud. He is, of course, correct. But that one sentence contains the essence of the big problem IT vendors now face – and must face down – if they are to get past being hobbled in the long term by sticking with an applications-centric focus. 

That problem is to get business users to accept the sense of an information-centric model. Many would say that they do, of course, but they themselves are largely hobbled by both a justified fear and a larger, unwarranted paranoia encompassed by that phrase: ‘and obviously have the authority to use it’. If their data is somewhere out in The Cloud, then by definition it is no longer `theirs’. If I had £1 for every time I have heard business users talk about the need to ‘own’ their own data I would be a reasonably rich man.  

There is still, and it seems will be for some time yet, a fear and dread amongst many users that not having their own data on their own systems in their own premises puts the whole business at risk. It is as if they fear that, if they cannot go and stroke or kick the very box in which their data is located then it is not really `theirs’ at all and they have lost control of it. What is worse it is, ipso facto, therefore open to all. 

This is inevitably a temporary problem. Many senior business managers – the current ones with the power to make decisions on moving away from information ownership – are still old enough to remember filing cabinets. Perhaps the next generation of managers (and certainly the one after that) brought up with the Internet and a healthy disassociation between information ownership and well managed, secure information exploitation that comes as part of using social software, will not think twice about where their data is. They will just concern themselves with its proper use. 

Some of what constitutes `proper use’ will, of course, still involve companies physically owning their own data. The most obvious example of this is any business process that involves high throughput, high speed transaction management, such as found in modern banking. There, physical issues such as the speed of light get in the way, for it sets the limit on how fast transaction messages can be delivered point-to-point. It takes light some 30ms to go coast to coast in the
US, and many big transaction management systems now need those messages delivered a good deal faster; so The Cloud will get in the way here.  

But in many other business processes, the location of the data is irrelevant – and it is arguably now more vulnerable and insecure than in a well-designed and implemented Cloud system, and can probably be accessed quicker. 

But there seems little sign yet that too many users readily accept these fundamental changes in their attitude. Indeed, I wonder whether EMC’s public lauding of such a change could work against it, with the collective paranoia driving users to walk by on the other side of the street? 

Perhaps the time is coming for EMC – and the other infrastructure players from servers to SaaS – to come together to start an educational process for the user community. A social computing site for educating business users would be a good start point.

A couple of recent announcements out of IBM once again pose questions about not only the future scope of parallel computing but also the timescale encompassed by that word `future’. 

The multicore Cell processor has so far made its name well away from corporate computing, being used in graphics-based applications in systems like Sony’s Playstation 3. A new version is just about to appear, however, and this will feature the addition of much stronger floating point capabilities. This is just what is needed to make it suitable for applications in areas such as large, complex financial calculations – things like risk management which, as our current economic situation seems to demonstrate well, is still largely at the Ouija Board/pint of brandy/take a guess level of incisiveness. 

As has been found before, where the financial community leads the rest of business starts to follow in the fullness of time. If the new Cell processor shows itself capable of giving financial calculations some real clout there could be growing pressure from business users to exploit its capabilities elsewhere. 

This could be supported by the appearance of a new idea from the company’s labs. We have all got used to hearing about High Performance Computing (HPC), the world of scientific and academic supercomputers where parallelism is a core part of the natural order. There has been a good deal of talk over the last few years about HPC making it down into the grubbier world of business and commerce, but there are some problems with this notion, mainly concerned with the fundamentals of the software architecture being geared to high level computational tasks. 

So engineers at IBM’s labs have come up with a different approach, High Throughput Computing (HTC), which is seen as being far better architected for the needs of business users. Though still a long way from being an official product, HTC is being lined up to create a software platform that can make parallel supercomputers like IBM’s Blue Gene architecture far more amenable to the commercial world. 

IBM is working with the Condor Project Team at the University of Wisconsin-Madison and a joint development effort is now in place to create the HTC environment for Blue Gene systems. One of the keys to Condor is its ability to match resource requests made by incoming jobs with resource offers from what is available in the system. It can even exploit unused desktop resources, and can work with either serial or parallel jobs. 

Such an environment could even help get round one of the fears concerning the coming of parallel computing in business – that while it is probably inevitable and will quite possibly prove to be a `good thing’ in the long term, the pain of getting from here to there could be severe and even damaging for some.  

If HTC can work effectively and contentedly with serial and parallel code, it could be the basis for a long-term bridge between here and there. If it can then work with Cell-based servers, which run Linux, the basis for a real stepping stone between serial/legacy architectures and parallelism maybe just around the corner.