Tim Anderson's ITWriting » intel

NVIDIA plans to merge CPU and GPU – eventually

tim — Fri, 16 Dec 2011 11:09:44 +0000

I spoke to Dr Steve Scott, NVIDIA’s CTO for Tesla, at the end of the GPU Technology Conference which has just finished here in Beijing. In the closing session, Scott talked about the future of NVIDIA’s GPU computing chips. NVIDIA releases a new generation of graphics chips every two years:

2008 Tesla
2010 Fermi
2012 Kepler
2014 Maxwell

Yes, it is confusing that the Tesla brand, meaning cards for GPU computing, has persisted even though the Tesla family is now obsolete.

Dr Steve Scott showing off the power efficiency of GPU computing

Scott talked a little about a topic that interests me: the convergence or integration of the GPU and the CPU. The background here is that while the GPU is fast and efficient for parallel number-crunching, it is of course still necessary to have a CPU, and there is a price to pay for the communication between the two. The GPU and the CPU each have their own memory, so data must be copied back and forth, which is an expensive operation.

One solution is for GPU and CPU to share memory, so that a single pointer is valid on both. I asked CEO Jen-Hsun Huang about this and he did not give much hope for this:

We think that today it is far better to have a wonderful CPU with its own dedicated cache and dedicated memory, and a dedicated GPU with a very fast frame buffer, very fast local memory, that combination is a pretty good model, and then we’ll work towards making the programmer’s view and the programmer’s perspective easier and easier.

Scott on the other hand was more forthcoming about future plans. Kepler, which is expected in the first half of 2012, will bring some changes to the CUDA architecture which will “broaden the applicability of GPU programming, tighten the integration of the CPU and GPU, and enhance programmability,” to quote Scott’s slides. This integration will include some limited sharing of memory between GPU and CPU, he said.

What caught my interest though was when he remarked that at some future date NVIDIA will probably build CPU functionality into the GPU. The form that might take, he said, is that the GPU will have a couple of cores that do the CPU functions. This will likely be an implementation of the ARM CPU.

Note that this is not promised for Kepler nor even for Maxwell but was thrown out as a general statement of direction.

There are a couple of further implications. One is that NVIDIA plans to reduce its dependence on Intel. ARM is a better partner, Scott told me, because its designs can be licensed by anyone. It is not surprising then that Intel’s multi-core evangelist James Reinders was dismissive when I asked him about NVIDIA’s claim that the GPU is far more power-efficient than the CPU. Reinders says that the forthcoming MIC (Many Integrated Core) processors codenamed Knights Corner are a better solution, referring to the:

… substantial advantages that the Intel MIC architecture has over GPGPU solutions that will allow it to have the power efficiency we all want for highly parallel workloads, but able to run an enormous volume of code that will never run on GPGPUs (and every algorithm that can run on GPGPUs will certainly be able to run on a MIC co-processor).

In other words, Intel foresees a future without the need for NVIDIA, at least in terms of general-purpose GPU programming, just as NVIDIA foresees a future without the need for Intel.

Incidentally, Scott told me that he left Cray for NVIDIA because of his belief in the superior power efficiency of GPUs. He also described how the Titan supercomputer operated by the Oak Ridge National Laboratory in the USA will be upgraded from its current CPU-only design to incorporate thousands of NVIDIA GPUs, with the intention of achieving twice the speed of Japan’s K computer, currently the world’s fastest.

This whole debate also has implications for Microsoft and Windows. Huang says he is looking forward to Windows on ARM, which makes sense given NVIDIA’s future plans. That said, the I get impression from Microsoft is that Windows on ARM is not intended to be the same as Windows on x86 save for the change of processor. My impression is that Windows on ARM is Microsoft’s iOS, a locked-down operating system that will be safer for users and more profitable for Microsoft as app sales are channelled through its store. That is all very well, but suggests that we will still need x86 Windows if only to retain open access to the operating system.

Another interesting question is what will happen to Microsoft Office on ARM. It may be that x86 Windows will still be required for the full features of Office.

This means we cannot assume that Windows on ARM will be an instant hit; much is uncertain.

C++ 11 is approved by ISO: a big day for native code development

tim — Sat, 13 Aug 2011 10:37:34 +0000

Herb Sutter reports that C++ 0x, which will be called C++ 11, has been unanimously approved by the ISO C++ committee. The “11” in the name refers to the year of approval, 2011. The current standard is C++ 98, though amended as C++ 03, so it has taken 8 or 13 years to update it depending on how you count it.

This means that compiler makers can get on with implementing the full C++ 11 standard. Most current compilers implement some of the features already. This Apache wiki shows the current status. A quick glance suggests that the open source GCC is ahead of the pack, followed by Intel C++ and then perhaps Microsoft Visual C++.

C++ 11 is pretty much compatible with C++ 03 so existing code should still work. However there are many new features, enough for Bjarne Stroustrup to say in his feature summary:

Surprisingly, C++0x feels like a new language: The pieces just fit together better than they used to and I find a higher-level style of programming more natural than before and as efficient as ever. If you timidly approach C++ as just a better C or as an object-oriented language, you are going to miss the point. The abstractions are simply more flexible and affordable than before. Rely on the old mantra: If you think of it as a separate idea or object, represent it directly in the program; model real-world objects, and abstractions directly in code. It’s easier now.

Concurrent programming is better supported in C++ 11, important for getting the best performance from modern hardware.

It is curious how the programming landscape has changed in recent year. A few years back, you might have foreseen a day when most programming would be .NET, Java or JavaScript: all varieties of managed code. While those languages do still dominate, native code has come more to the fore, thanks to factors like Apple’s focus on Objective C, and signs of internal conflict at Microsoft over the best language for coding Windows applications.

That said, C++ 11 remains a demanding language to learn and use. As Stroustrup notes, since C++ 11 is a superset of C++ 98 it is technically harder to learn all of it, though new libraries and abstractions should help beginners. The reasons for using or not using C++ are not going to change significantly with this new standard.

When will Intel’s Many Integrated Core processors be mainstream?

tim — Wed, 13 Apr 2011 14:10:32 +0000

I’m at Intel’s software tools conference in Dubrovnik, which I have attended for the last three years, and as usual the big topic is concurrent programming and how to write code that takes advantage of the multiple cores in today’s computers.

Clearly this remains a critical subject, but in some ways the progress over these last three years has been disappointing when it comes to the PCs that most of us use. Many machines are only dual-core, which is sub-optimal for concurrent programming since there is an overhead to multi-threading programming that eats into the benefit of having two cores. Quad core is now common too, and more useful, but what about having 50 or 80 or more cores? This enables massively parallel processing of the kind that you can easily do today with general-purpose GPU programming using OpenCL or NVidia’s CUDA, but not yet on the CPU unless you have a super computer. I realise that GPU cores are not the same as CPU cores; but nevertheless they enable some spectacularly fast parallel processing.

I am interested therefore in Intel’s MIC or Many Integrated Core architecture, which combines 50 or more CPU cores on a single chip. MIC is already in preview, with hardware codenamed Knight’s Corner and a development kit called Knight’s Ferry. But when will MIC hit the mainstream for servers and workstations, and how long is it until we can have 50 cores on a commodity desktop PC? I spoke to Intel’s chief evangelist James Reinders.

Reinders first gave me some background on MIC:

“We’ve made those bold steps to dual core, quad core and we’ve got even ten core now, but if you look inside those microprocessors they have a very simple structure. All the cores are hooked together and share their connection to memory, through a shared cache usually that’s on the chip. It’s a simple computer structure, and we know from experience when you build computers with more and more processors, that eventually you go to more sophisticated connections between the cores. You don’t build a 1000-processor super computer and hook them all together with a bus to one memory.

“It’s inevitable that on a chip we need to design a more sophisticated connection. That’s what MIC’s about, that’s what the Larrabee project has always been about, a belief that we should take a bunch of x86 cores and hook them together with something more sophisticated. In this case it’s a ring, a bi-directional, 512-bit wide high performance ring, with multiple connections to memory off the chip, which gives us more bandwidth.

“That’s how I look at MIC, it’s putting a cluster-type of design on a chip.”

But what about timing?

“The first place you’ll see this is in servers and in workstations, where there’s a lot of demand for a lot of computation. In that case we’ll see that availability sometime by the end of 2012. The Intel product should be out late in that year.

“When will we see it in other devices? I think that’s a ways off. It’s a very high core count part, more than 50, it’s going to consume a fair amount of power. The same part 18 months later will probably consume half the power. So inside a decade we could see this being common on desktops, I don’t know about mobile devices, it might even make it to tablets. A decade’s a long time, it gives a lot of time for people to come up with innovative uses for it in software.

“We’ll see single core disappear everywhere.”

Incidentally, it is hard to judge how much computing power is “enough”. Although having many CPU cores may seem overkill for everyday computing, things like speech recognition or on-the-fly image processing make devices smarter at the expense of intense processing under the covers. From super computers to smartphones, if more computing capability is available history tells us that we will find ways to use it.

Intel disappointed with Nokia’s Microsoft move, still backing MeeGo

tim — Sun, 13 Feb 2011 08:32:11 +0000

Intel’s Suzy Ramirez has posted about the future of MeeGo Linux following Nokia’s decision to base its smartphone strategy on Microsoft’s Windows Phone operating system. Nokia was Intel’s key partner for MeeGo, which was formed by merging Intel’s Moblin with Nokia’s Maemo.

Although Nokia has been an important partner to Intel and MeeGo and we are disappointed by this decision, it’s important to know that this is by no means the end of MeeGo or the end to Intel’s commitment

says Ramirez, adding that “MeeGo is not just a phone OS”.

True; but with the focus also moved away from netbooks it is getting hard to see where MeeGo will have an opportunity to shine.

Intel promises to outline its mobile strategy this week at Mobile World Congress. I will be reporting from Barcelona in due course.

Ten big tech trends from 2010

tim — Fri, 31 Dec 2010 12:52:02 +0000

This was an amazing year for tech. Here are some of the things that struck me as significant.

Sun Java became Oracle Java

Oracle acquired Sun and set about imposing its authority on Java. Java is still Java, but Oracle lacks Sun’s commitment to open source and community – though even in Sun days there was tension in this area. That was nothing to the fireworks we saw in 2010, with Java Community Process members resigning, IBM switching from its commitment to the Apache Harmony project to the official OpenJDK, and the Apache foundation waging a war of words against Oracle that was impassioned but, it seems, futile.

Microsoft got cloud religion

Only up to a point, of course. This is the Windows and Office company, after all. However – and this is a little subjective – this was the year when Microsoft convinced me it is serious about Windows Azure for hosting our applications and data. In addition, it seems to me that the company is willing to upset its partners if necessary for the sake of its hosted Exchange and SharePoint – BPOS (Business Productivity Online Suite), soon to become Office 365.

This is a profound change for Microsoft, bearing in mind its business model. I spoke to a few partners when researching this article for the Register and was interested by the level of unease that was expressed.

Microsoft also announced some impressive customer wins for BPOS, especially in government, though the price the customers pay for these is never mentioned in the press releases.

Microsoft Silverlight shrank towards Windows-only

Silverlight is Microsoft’s browser plug-in which delivers multimedia and the .NET Framework to Windows and Mac; it is also the development platform for Windows Phone 7. It still works on a Mac, but in 2010 Microsoft made it clear that cross-platform Silverlight is no longer its strategy (if it ever was), and undermined the Mac version by adding Windows-specific features that interoperate with the local operating system. Silverlight is still an excellent runtime, powerful, relatively lightweight, easy to deploy, and supported by strong tools in Visual Studio 2010. If you have users who do not run Windows though, it now looks a brave choice.

The Apple iPad was a hit

I still have to pinch myself when thinking about how Microsoft now needs to catch up with Apple in tablet computing. I got my first tablet in 2003, yes seven years ago, and it ran Windows. Now despite seven years of product refinement it is obvious that Windows tablets miss the mark that Apple has hit with its first attempt – though drawing heavily on what it learnt with the equally successful iPhone. I see iPads all over the place, in business as well as elsewhere, and it seems to me that the success of a touch interface on this larger screen signifies a transition in personal computing that will have a big impact.

Google Android was a hit

Just when Apple seemed to have the future of mobile computing in its hands, Google’s Android alternative took off, benefiting from mass adoption by everyone-but-Apple among hardware manufacturers. Android is not as elegantly designed or as usable as Apple’s iOS, but it is close enough; and it is a relatively open platform that runs Adobe Flash and other apps that do not meet Apple’s approval. There are other contenders: Microsoft Windows Phone 7; RIM’s QNX-based OS in the PlayBook; HP’s Palm WebOS; Nokia Symbian and Intel/Nokia MeeGo – but how many mobile operating systems can succeed? Right now, all we can safely say is that Apple has real competition from Android.

HP fell out with Microsoft

Here is an interesting one. The year kicked off with a press release announcing that HP and Microsoft love each other to the extent of $250 million over three years – but if you looked closely, that turned out to be less than a similar deal in 2006. After that, the signs were even less friendly. HP acquired Palm in April, signalling its intent to compete with Windows Mobile rather than adopting it; and later this year HP announced that it was discontinuing its Windows Home Server range. Of course HP remains a strong partner for Windows servers, desktops and laptops; but these are obvious signs of strain.

The truth though is that these two companies need one another. I think they should kiss and make up.

eBook readers were a hit

I guess this is less developer-oriented; but 2010 was the year when electronic book publishing seemed to hit the mainstream. Like any book lover I have mixed feelings about this and its implications for bookshops. I doubt we will see books disappear to the same extent as records and CDs; but I do think that book downloads will grow rapidly over the next few years and that paper-and-ink sales will diminish. It is a fascinating tech battle too: Amazon Kindle vs Apple iPad vs the rest (Sony Reader, Barnes and Noble Nook, and others which share their EPUB format). I have a suspicion that converged devices like the iPad may win this one, but displays that are readable in sunlight have special requirements so I am not sure.

HTML 5 got real

2010 was a huge year for HTML 5 – partly because Microsoft announced its support in Internet Explorer 9, currently in beta; and partly because the continued growth of browsers such as Mozilla Firefox, and the WebKit-based Google Chrome, Apple Safari and numerous mobile browsers showed that HTML 5 would be an important platform with or without Microsoft. Yes, it is fragmented and unfinished; but more and more of HTML 5 is usable now or in the near future.

Adobe Flash survived Apple and HTML 5

2010 was the year of Steve Jobs’ notorious Thoughts on Flash as well as a big year for HTML 5, which encroaches on territory that used to require the services of a browser plug-in. Many people declared Adobe Flash dead, but the reality was different and the company had a great year. Apple’s focus on design and usability helps Adobe’s design-centric approach even while Apple’s refusal to allow Flash on its mobile computers opposes it.

Windows 7 was a hit

Huge relief in Redmond as Windows 7 sold and sold. The future belongs to mobile and cloud; but Windows is not going away soon, and version 7 is driving lots of upgrades as even XP diehards move over. I’m guessing that we will get first sight of Windows 8 in 2011. Another triumph, or another Vista?

If Microsoft is serious about Silverlight, it needs to do Linux

tim — Thu, 16 Sep 2010 16:10:35 +0000

Today was a significant event for the UK broadcasting industry: the announcement of YouView, formerly called Project Canvas, which is backed by partners including the BBC, ITV, Channel 4, Channel 5, and BT. It will provide broadcasts over IP, received by a set top box, include a catch-up service, and be capable of interactive features that hook into internet services.

Interesting stuff, though it may end up battling with Google TV. But what are the implications for media streaming services and media players? One is that they will have to run on Linux, which is the official operating system for Project Canvas. Google TV, for that matter, will run Android.

If you look at the YouView specifications, you’ll find that although the operating system is specified, the application player area is more open:

Application Player executables and libraries will be provided by 3rd party software vendors.

What is an application player?

Runtime environment for the execution of applications. Examples are Flash player, MHEG engine, W3C browser

I’d suggest that Adobe will do well out of YouView. Microsoft, on the other hand, will not be able to play in this space unless it delivers Silverlight for Linux, Android, and other open platforms.

Microsoft has a curious history of cross-platform Silverlight announcements. Early on it announced that Moonlight was the official Linux player, though in practice support for Moonlight has been half-hearted. Then when Intel announced the Atom Developer Program (now AppUp) in September 2009, Microsoft stated that it would provide its own build of Silverlight for Linux, or rather, than Intel would build it with Microsoft’s code. Microsoft’s Brian Goldfarb told me that Microsoft and Intel would work together on bringing Silverlight to devices, while Moonlight would be the choice for desktop Linux.

Since then, the silence has been deafening. I’ve enquired about progress with both Intel and Microsoft, but vague rumours aside, no news. Silverlight is still listed as a future runtime for AppUp:

Microsoft® Silverlight™(future)

Silverlight is a cross-browser, cross-platform and cross-device browser plug-in that helps companies design, develop and deliver applications and experiences on the Web.

In the meantime, Adobe has gone ahead with its AIR runtime, and even if Silverlight eventually appears, has established an early presence on Intel’s netbook platform.

There have been recent rumours about internal battles between the Windows and Developer divisions at Microsoft, and I cannot help wondering if this is another symptom, with the Windows folk fighting against cross-platform Silverlight on the grounds that it could damage the Windows lock-in, while the Developer team tries to make Silverlight the ubiquitous runtime that it needs to be in order to succeed.

From my perspective, the answer is simple. Suppressing Silverlight will do nothing to safeguard Windows, whereas making it truly cross-platform could drive adoption of Microsoft’s server and cloud platform. When Silverlight was launched, just doing Windows and Mac was almost enough, but today the world looks different. If Microsoft is serious about WPF Everywhere, Linux and Android (which is Linux based) support is a necessity.

Intel AppUp is Up, but underwhelming.

tim — Wed, 15 Sep 2010 07:03:29 +0000

Intel has launched AppUp, its application store for Windows and Moblin/MeeGo Linux.

Isn’t Moblin obsolete, and now merged into MeeGo? That is the plan, but AppUp still talks about Moblin:

Apparently:

The Intel AppUp developer program will support MeeGo. The current Moblin SDK for the Intel AppUp^SM developer program is MeeGo ready and is upward compatible for Moblin and MeeGo.

The web site is pretty confusing, even though it is supposedly out of beta. Click Frequently Asked Questions, and you get a document dated December 2009, though “Last Modified” in August. It does seem to be out of date though, referring throughout to the Beta and stating that only Windows is supported by the AppUp client.

I downloaded the client and had a look. The client is a simple affair, with apps in various categories, though the current selection of apps is uninspiring. Prices currently range from free to £28.19 for Easy Flyer Creator (Desktop Publishing), the most expensive I could find. All the “Featured apps” are games, though the other categories are populated to some extent.

If you want to develop for AppUp you need the SDK, which provides the tools and libraries to link your app to the AppUp client. The SDK is native code, and the natural developer platform for AppUp is the cross-platform Qt, but the main requirement is that you can link to the SDK; there is also an approval process.

Adobe has done the work to support AIR applications, which use the Flash runtime, in AppUp. Adobe has also come up with an interesting project to address the coming proliferation of app stores. The Melrose project, now in beta, targets multiple app stores:

Melrose provides a repository that distributes applications to multiple application stores so that publishers can reach millions of users.

Intel AppUp Center and the Adobe AIR Marketplace are the first two storefronts available in Melrose. Melrose also provides analytics that let publishers measure success of their applications.

It is a shame that Melrose does not yet include Android Market.

Who knows, AppUp may have a bright future, but Intel could have done better with the launch. There is a poor selection of apps, confusing Moblin/MeeGo branding, and out of date information on the site. Of these, the biggest problem is the lack of apps themselves. The main target is netbooks, and Intel will need a greatly improved selection before AppUp comes close to enhancing netbooks in the way that Apple’s App Store enhances iPhone, iPad and iTouch, which is the obvious model.

How many app stores will there be? Alongside Apple, there is AppUp, Nokia’s Ovi, Android Market, as well as older app stores like handango. Microsoft is rumoured to have big plans for an App Store for Windows 8, and of course Windows Phone 7 will have its own store – and these are just the ones which come to mind immediately.

Not all these app stores will succeed, and Intel should have made more effort with this launch.

What is happening with Silverlight on Intel Moblin/Meego?

tim — Wed, 19 May 2010 08:25:49 +0000

Last September, Microsoft and Intel announced a port of Silverlight to Moblin Linux. I posted on the subject here, including a quote from Microsoft’s Brian Goldfarb:

Microsoft and Intel announced today that the two companies have agreed to work together to bring support for Silverlight 3 to Intel’s Atom-based Mobile Internet Devices (MID). These Atom-based devices run on Windows and Moblin, an open source, Linux-based operating system targeted at Atom-based devices. In order to help bring Silverlight content to these devices, Microsoft has provided Intel with Silverlight source code and test suites, and Intel will provide Microsoft with an optimized version of Silverlight for Moblin devices that Microsoft can then redistribute to OEMs.

Since then, Moblin has merged with Novell’s Maemo to form MeeGo (though this is still work in progress), and we’ve heard very, very little about Silverlight on either platform. The only snippet of news I have is that it was mentioned at the Intel Developer Forum in Beijing and reported by Char Zvolanek, who said that it came up in the Meego Q&A after regular sessions ended, and Silverlight will be supported in Meego version 1.1 in October:

In May, the 1.0 version will be released, and with 1.1 coming out in October, there will be support for Silverlight, Java, and Air. Developers can write native or runtime apps that can be Java-based, Web-based, Silverlight-based, or Air-based.

Today, another clue, but not a good one for Silverlight. Intel is holding an application lab on May 26th in San Jose, for developing for the Intel AppUp store, either on Windows or Moblin. On the agenda: C/C++ and Adobe AIR, and the upcoming Adobe AIR SDK for Moblin. No Silverlight.

If anyone is going along, and can discover any news about Silverlight on Moblin, I’d be interested to know.

Silverlight (and AIR) for MeeGo Linux coming in October?

tim — Sat, 17 Apr 2010 10:19:45 +0000

Back in September 2009, Intel and Microsoft announced an official port of Silverlight for Linux, or at least for what was then Intel’s Moblin project, a Linux distribution tailored for netbooks. It was surprising to learn that this would be an official port using Microsoft’s code, as opposed to something based on Moonlight, the open source and also somewhat officially blessed version of Silverlight for Linux.

Since then I have been watching for more news about this Silverlight port, but heard nothing. Then in February Moblin merged with Nokia’s Maemo to become MeeGo. What next for the Silverlight port?

Earlier this week I met Intel’s Uli Dumschat at the company’s software conference in Barcelona. He spoke on Intel’s software development products for Atom-powered devices such as those running MeeGo. I asked him about Silverlight for MeeGo and he knew nothing about it.

It seems I was at the wrong conference. Today I spotted this post from Charlene Zvolanek at Intel’s Developer Forum in Beijing:

In May, the 1.0 version will be released, and with 1.1 coming out in October, there will be support for Silverlight, Java, and Air. Developers can write native or runtime apps that can be Java-based, Web-based, Silverlight-based, or Air-based. Even though it’s open source, Intel has been working closely with Microsoft to make sure that MeeGo and Windows are friends.

I also watched the keynote from Intel’s Renee James, who said that MeeGo devices are expected in the “second half of this year”, though I imagine they will be 1.0 devices – who knows, maybe 1.1 will be an upgrade option later.

So Silverlight on MeeGo now has a date. Is this Silverlight 4.0? Will it run out of browser? Access to local resources? Does this date apply to MeeGo Smartphones as well as netbooks? All good questions, about which I know nothing. Watch this space.

Intel’s compiler is best for AMD too says software director

tim — Thu, 15 Apr 2010 09:50:23 +0000

I attended Intel’s software conference in Barcelona earlier this week, and took the opportunity to talk to Director of Software Products James Reinders. I asked him about the complaint from the FTC, which I reported on here, that Intel deliberately underperforms on non-Intel CPUs, specifically those made by AMD. Was it a valid complaint?

He was surprisingly (to me) forthright.

It’s not valid. It’s misguided. Intel’s compilers are very high performance. If you use our compiler, you’ll get better performance on Intel or AMD processors than if you used anyone else’s compiler. That’s always been our goal. We believe – I’ll use the words “in general” and that’s a legal disclaimer – in general we’re better. Why don’t I say always? Always is an absolute. Nobody is “always” anything. We are as close to always as we can figure out to be. We have many customers that use our compiler, ship code, because they believe it gets the best performance on Intel and AMD. We will back that. If you find that our compiler is getting less performance on AMD than someone else’s compiler, we consider it a bug. That includes AMD processors.

We settled the suit with AMD, we agreed that we wouldn’t do things we were accused of in future – well, we didn’t do them before. There’s a lot of proof points. AMD used our compiler for benchmarking for a long time. They didn’t do that because we were lower performance.

There are a lot of technical nuances, details of what we do in our compiler that are confusing. One of the challenges is how do we produce a binary that runs best on Nehalem, and on an older Intel processor, or on a processor that supports SSE 2.0 but not 3.0? We have technology in our compiler to try to adapt to that. We mix into that blend AMD, because AMD processors have different capabilities, in the same way that our processors have different capabilities from each other. Yes, people will say, “hey, your compiler’s checking for an AMD processor”. Yes, absolutely, we also check to see if we’re on a Intel processor that only supports SSE 2.0. We have to. AMD processors don’t support the same instructions we do. Our processors have a lot of variety too.

The short answer is that we didn’t do what we’re accused of, we’re very serious about being an excellent compiler for AMD as well as Intel, and this extends to our libraries too.

So that’s telling them. Is he correct and it was a misguided complaint? Well, as I mentioned previously, there are issues of disclosure as well as performance if you are publishing benchmarks; and it is hard to believe that Intel devotes equal effort to optimisation on AMD processors as for its own. Nevertheless I respect Reinders and don’t dismiss his statement. Perhaps Intel’s compiler is OK for AMD after all.