Looking at the list for the top supercomputers this time around I saw some interesting statistics that show the strength of the AMD Opteron™ processor for high performance computing (HPC) environments.  The top 25 supercomputers on the list – clearly the “fastest of the fast” – have a great representation of AMD Opteron processors:

• AMD Opteron processors:             11 (44%)
• Intel Xeon processors:                    8 (32%)
• IBM PowerPC processors:             4 (16%)
• Fujitsu SPARC processors:             1 (4%)
• AMD Opteron + IBM Cell:             1 (4)

Clearly AMD has a very strong representation in the very fastest computers on earth, more so than any other processor architecture. 

Even more impressive is that the AMD Opteron 6100 Series processors were integrated into a majority of the 12 top 25 AMD platforms – clearly there was a strong desire to get the higher performance of 8 and 12-core processors, and these customers were able to take advantage of a large number of cores to boost their supercomputers.

Of particular note are the Cray supercomputers: 9 of the top 25 are designed around an architecture that allows them to be easily upgraded to future technology.  Cray upgraded both the Jaguar and Kraken systems in the past and showed just how easy it is to do.  Cray has already announced its next generation supercomputer based on AMD’s upcoming 16-core processor codenamed “Interlagos”, based on the powerful and HPC-optimized new “Bulldozer” core.

These supercomputers are used for everything from weather prediction to medical research as well as helping unlock the secrets of energy to help the world find solutions to our current energy needs.  Congratulations to everyone that worked so hard on this most recent round, your efforts are going a long way towards turning computing cycles into real discoveries that are making life better for everyone around the world.

John Fruehe is the Director of Product Marketing for Server, Embedded and FireStream products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites, and references to third party trademarks, are provided for convenience and illustrative purposes only.  Unless explicitly stated, AMD is not responsible for the contents of such links, and no third party endorsement of AMD or any of its products is implied.

However, this summer, Oak Ridge embarked on a project to increase their capacity and performance – an upgrade of the 37,000 processors in the cluster to Six-Core AMD Opteron processors. 

Because of AMD’s consistent platform strategy, with processor commonality and common sockets, the task was remarkably simple.   It took approximately 5 minutes per 8P server module to do the upgrade.  (Watch the upgrade here.)

When we developed the Socket F (1207), we anticipated a long life for the socket. As a matter of fact, we anticipate that socket living through the end of 2010.  Customers who have standardized on products based on those processors will probably want some consistency across their data centers. And customers that have built out capacity on those platforms might want to upgrade, something that is easy and painless for our customers. Contrast this with our competitor’s “tick tock” approach – which threatens a continual pace of disruption.

With this upgrade, “Jaguar” now takes a new spot in the TOP500 list.  First.  That is one fast cat – and it is purring along on AMD Opteron technology.

Researchers were quickly back online and with this additional performance they now have the ability to solve complex (frankly, mind-boggling) problems faster, in addition to tackling more projects, some that have previously been out of their reach.

To get an understanding of Oak Ridge National Labs’ scientific research and their take on the TOP500, take a look at this video.  

John Fruehe is the Director of Product Marketing for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

But looks can be deceiving. While I didn’t have the flashy skills or the newest ride, I did have a dedication and a lack of technical problems that actually allowed me to finish the ride ahead of others. Sometimes the outcome isn’t always as obvious.

Too many people get caught up in the benchmarks and think that is the end of the story. Benchmarks can be important as an indicator, but they don’t tell the whole story.  As a matter of fact, they really only tell a portion of PART of the story.  In my opinion, making a decision based on benchmark alone is like buying a car because you like the color.  That is great if all you care about is a red car, but so few of us really think that way in the real world.

One of the things that I have been telling customers is that they need to step out of the “socket” world and start thinking more about the work that needs to get done when assessing the platforms. Sometimes the answer is not obvious.

The non-obvious thread for today started this morning when I went to check out the latest review on AnandTech.com of the AMD Opteron processor vs. our competitor’s processor (which my colleague Margaret Lewis also discusses here).  We sent them a review system recently and during their testing, they came up with some interesting comments.

Comparing a 2 socket Intel server to a 4 socket AMD server, you start to see that if you step outside of the raw performance area, there are plenty of other places to be looking, like threading and efficiency, not just clock speed. Here is what AnandTech had to say when comparing our six-core 2435 to a higher clock speed quad core:

“If your application scales well, two 2.6GHz Opteron 2435 will offer 15% better (and sometimes more) performance than a 2.9GHz Opteron 2389 with the same power consumption.”

More performance, at the same power envelope and lower clock speed.  Not always the most obvious answer, but clearly a great choice for threaded applications. (And don’t think that applications will be less threaded in the future.) Memory is another area less than obvious. Here is what AnandTech had to say:

“Using relatively ‘old’ technology such as DDR2, the hex-core Opteron based servers are very affordable, especially if you compare them with similar Xeon servers.”

Yeah, I was the old guy on the trail, but that didn’t mean I was the last.  I can think of a couple of younger guys finishing after me – so sometimes “newer” doesn’t me “better”.  Again, not the obvious answer, but until the prices of DDR-3 come in line with DDR-2, this is our secret weapon.  And in a tough economy, who doesn’t want to be smart with their IT budgets.

We have tremendous consistency, but people expect that.  And they expect that all processors in the family will have the same features.  That is obvious, right?  Here’s how AnandTech saw it.

“If you chose the Xeon platform, you should be aware of the fact that Intel’s low end is much less interesting: the best Xeon 55xx CPUs have a clock speed between 2.26 and 2.93GHz. The low end models, the 5504 and 5506 are pretty crippled, with no Hyper-Threading, no Turbo Boost, and only half as much L3 cache (4MB). These crippled CPUs can keep up with the quad-core Opterons at about 2.5GHz, but they are the worst Xeons when you look at idle and full load power. The performance per Watt of the Xeon EE550x is pretty bad compared to the more expensive parts.”

You’ve heard me talk a lot about “no compromises” in our products, and this is what we are talking about.  Just because you can’t afford to buy the most expensive processor in the stack shouldn’t mean that you have to compromise so much.  Cutting the cache in half?  That is not obvious to the typical customer. 

When you step back and take a look at all of this in full, you see what was obvious before – 2P servers are the best value for most workloads – is becoming somewhat less obvious. And as we get into 2010, the value that AMD will bring to market will blur the lines even more. It’s time to stop looking at the world of sockets and start looking at the workload, the power consumption and the cost.  Only then, does everything become obvious. 

Otherwise you’ll just be like that young guy tonight, standing on the trail as the old guy blew past him.  Sometimes the obvious answer isn’t always the only answer.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

When Quad-Core AMD Opteron^TM processor Model 2384 was introduced less than a year ago, servers using this processor achieved a number of performance records (here and here) and a key reviewer concluded that “Right now, it is clear that the latest AMD Opteron is in the lead.” If you look at the performance of Six-Core AMD Opteron^TM 2419 EE processor-based servers, you see that servers using this new low-power processor are outperforming servers using the Quad-Core AMD Opteron^TM processor Model 2384. That’s pretty impressive.

And the energy savings from using low-power Six-Core AMD Opteron^TM EE processors (compared to 75W ACP Six-Core AMD Opteron^TM processors) are significant. When we replaced the 75W ACP Six-Core AMD Opteron^TM processors in a ZT Systems server with 40W ACP Six-Core AMD Opteron^TM EE processors, server power consumption at 100% load dropped by 124W (40%).

Surpassing the performance of Quad-Core AMD Opteron^TM processor Model 2384-based servers using extremely energy efficient processors is quite a feat. Achieving higher performance, while consuming less power, is even more impressive. To top it off, the Six-Core AMD Opteron^TM processor Model 2419 EE is being offered at the same price that the Quad-Core AMD Opteron^TM processor Model 2384 was sold for last year².

Higher performance. Lower server power consumption. Same introductory processor price. Wow!

As excited as I am about our current products, I can’t resist the temptation to mention the Six-Core AMD Opteron^TM EE processors (codenamed “Lisbon”) that we’re planning to introduce next year. These six-core processors are planned to have a rated power consumption of less than 40W – that’s lower than the rated power consumption of most of today’s quad-core mobile processors. A processor that combines the registered memory and RAS (reliability, availability, and serviceability) features of a server processor with the power consumption of a mobile processor?

I think that I’ll be typing “Wow!” again next year.

Whether you think of “flexibility” as the ability to host more virtual machines using a Six-Core AMD Opteron^TM 8400 Series processor-based server, or you view “efficiency” as the capability to achieve higher performance while consuming less server power using Six-Core AMD Opteron^TM 2419 EE processors, it’s clear that servers using AMD’s Direct Connect Architecture are ideal for the next generation of computing.

To find out more about AMD Virtualization^TM (AMD-V^TM) technology and AMD Opteron^TM processors, visit us at booth 1408 at VMworld or visit www.amd.com/virtualization.

                             Andy Parma is a Product Marketing Manager for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

¹Based on 30 tiles x 6 VMs for 48-core HP ProLiant DL785 G6 server, as tested using the VMmark benchmark (http://www.vmware.com/products/vmmark/results.html).

²Pricing for Quad-Core AMD Opteron^TM processor Model 2384 reflects 1kU tray pricing on www.amd.com as of November 2008. Pricing for Six-Core AMD Opteron^TM processor Model 2419 EE reflects 1kU tray pricing on www.amd.com as of August 2009.

The AMD Opteron 1000 Series processor is designed for applications that are driven by cost or power concerns more than scalability.  In the past, this meant a single core in a single socket, but in today’s multi-core world, this means four high performance cores in a single socket.

Typically, these processors are used in web servers, small business servers, workstations and even cloud computing.  The flexibility of four cores and a low cost infrastructure gives customers an edge when designing for a cost-effective or power efficient platform.   

With speeds of 2.5GHz, 2.7GHz and 2.9GHz, these single-socket processors pack a punch. It’s based on the same core as the Quad-Core AMD Opteron processor codenamed “Shanghai,” so all the great features that you find in “Shanghai” are also in “Suzuka.”

One of the best parts about my job is that I have access to all the processors that I could ever want for testing.  My server at home migrated from a dual-core AMD Opteron Model 185 processor to a new system board with a quad-core “Budapest,” which is a 2.3GHz processor based on the same core as “Barcelona.”

Recently, I upgraded that server to a pre-production “Suzuka.” I went from a 2.3GHz quad-core with a 2MB cache to a 2.9GHz quad-core processor with a 6MB cache.  I saw an increase in performance, but amazingly, because Suzuka is on AMD’s 45nm process, I actually saw a decrease in total server power draw of about 10 watts. A performance increase, a big drop in power consumption – that makes the performance per watt story even better.

All I needed was a BIOS flash – the processor just dropped right into the same AM2 socket. The entire process was 5 minutes, and that included digging around under the sink to find some rubbing alcohol to clean the thermal paste off of the old processor. This incidentally, was the same process that you would have to go through in updating from a Rev F dual core processor to a “Budapest.”

Many may not know that our code names are derived from Formula 1 race tracks. Suzuka is a race course in Japan; recently it had been renovated and was re-opened in April of this year, just about the same time that we were finishing up the final touches and releasing our own “Suzuka.”

One of the biggest races at Suzuka is the 1000Km endurance race.  A 1000 kilometer race?  Sounds like the perfect compliment for an AMD Opteron 1000 Series processor.  Both are designed for the long haul.

 John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

I am reminded of this when I see the new Boston Quattro 6000GP server.  In the world of density, this product really stands out. Based on our new six-core AMD Opteron™ processor codenamed “Istanbul,” this new server manages to squeeze a total of four discrete servers into a 2U chassis. The Quattro 6000GP has four separate system boards, giving customers four individual servers that can each operate independently, all within one chassis.

If you are running a very dense data center, perhaps HPC applications or cloud applications, then a system with this type of density can help you better manage your environment.

With four dual-socket system boards, you can install up to 8 total processors, or (with the new 6-core processors) have up to 48 total cores in a 2U space.  Multiply that by the 21 slots in a standard 42U rack, and you have over 1000 cores in a 6 square foot space in your data center.

PCPro was impressed enough to give the Quattro 6000GP the PCPro Recommended award in recognition of the outstanding features and capabilities of this server.

In talking to customers, I’ve been told that data center density is often an issue, because data centers tend to be the most expensive floor space in the company. With special security, power, cooling and fire control, the cost of floor space in the data center is often not only the most expensive, but also the most difficult to expand when you need more room.

Greater density means better use of data center floor space, and the new six-core “Istanbul” processors can help customers to reach new levels of threads per square foot. In the Quattro 6000 GP, the compute nodes aren’t consuming all of the space in the server, however.  There is still room for twelve SATA hard drives, giving you up to 12TB of storage, up to 3TB per server. Featuring green WD SATA hard drives, the system is designed to be energy conscious because Boston knows that you’ll be looking for maximum density.

Every time we drop in on Boston Limited, they always have something interesting up their sleeve, and the new Quattro 6000GP is a great showcase for the dramatic core density of Istanbul. Whether you have HPC, web, cloud or are facing density challenges in the data center, this is a new emerging form factor that is worth a look.

 John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Virtualization is one of the most effective ways for companies to improve server utilization and improve data center efficiency. A few years ago Dell and AMD collaborated to create some of the industry’s first servers optimized for virtualization, the Dell PowerEdge R805 and R905 rack servers. The PowerEdge R905 based on the AMD Opteron processor is a great example of how we’ve fine-tuned our servers to provide virtualization performance. It is an ideal formula of processor technology, massive memory capacity and I/O scalability.

Our customers adopting the new Istanbul platform will see even greater virtualization performance with the new Istanbul processors. In fact, our initial benchmarks show a whopping 38 percent improvement in virtualization performance. We expect to continue to have industry-leading benchmarks for 4 socket servers with Istanbul.

With previous generations of AMD Opteron processors, we have had demand from companies with large data centers that have space and power constraints and from companies that need high availability for large databases. We have good news for these companies: the performance per watt equation just got better. The Six-Core AMD Opteron processors pack tremendous performance increases – we are seeing chart-popping 61 percent increases on SPECint benchmarks – into the same power consumption parameters.

Customers can get six-core performance in the same footprint as with Quad-Core AMD Opteron processors to run the most compute intensive applications and scale higher while conserving energy. Our customers can get improved performance in I/O intensive applications like databases and technical computing without taking up more floor space, and still operating in the same power envelope. We are pleased to offer companies in industries like high performance computing for geosciences, oil and gas exploration, life sciences and research the AMD technology-based systems they need for performance intensive virtualized applications.

Congratulations AMD on the successful, and early, launch of the Six-Core AMD Opteron processors.

 Armando Acosta is product manager for Dell PowerEdge servers. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Any claims made herein are based on Dell testing and have not been independently verified by AMD. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Sun understands our customers’ increased focus on the economics of their data centers as well as their desire to reduce overall complexity.  Sun’s enhanced line of x64 servers and blades will take advantage of the greater performance, virtualization capabilities, and energy efficiency technologies powered by the Six-Core AMD Opteron processor.  Sun systems powered by AMD’s newest processor will deliver up to 50 percent performance improvements compared to previous generation systems, giving our customers the performance and efficiency to handle demanding workloads with superior economics and energy efficiency.

Ready to scale with a single, consistent platform that spans from 2P to 8P servers, Sun’s x64 systems offer many choices for customers to realize breakthrough performance and unmatched virtualization capabilities, for enterprise and web applications, while supporting multiple operating systems . And with AMD Virtualization™ (AMD-V™) technology, the Six-Core AMD Opteron processor delivers greater virtual machine bandwidth than ever before.

Sun is committed to continued innovation along our x64 roadmap  Companies small, medium and large are turning to Sun to quickly and easily upgrade, consolidate and virtualize their data centers to drive the overall efficiency and cost improvements their businesses demand.

As we optimize our new line of Sun x64 systems for the marketplace, stay tuned for more details on availability and pricing. Sun’s enhanced product lines and unique approach to Open Network Systems helps maximize the economics of computing by delivering maximum scale, efficiency, manageability, performance and sustainability. For more information, please visit www.sun.com/x64/amd today.

Dimitrios Dovas is Director of Systems Marketing, x64 Volume Systems at Sun. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Any claims made herein are based on Sun testing and have not been independently verified by AMD. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

We have been enthusiastically preparing for the arrival of AMD’s new processor, and we are pleased to be able offer both our new and existing customers a tremendous step forward in terms of performance, efficiency, price-performance and energy optimization. Simply put, our customers are going to love the level of scalability this processor provides.

The Cray XT series of supercomputers, including the Cray XT5 and the recently introduced Cray XT5m, equipped with this processor will feature a groundbreaking 12 cores per dual-socket computational node. The XT5m system, affectionately known as the “Mighty Mini,” will provide a powerful 1,000 to 6,000 AMD Opteron processor cores in a single cost-effective, scalable and fully upgradeable mid-ranged system. With 10 to 60 teraflops in this mid-ranged system, this is certainly not your father’s mid-ranged supercomputer. The even more powerful Cray XT5 systems will provide virtually limitless scalability, ranging from 1,000 to more than 300,000 AMD Opteron processor cores in a fully scalable hardware and software infrastructure.

Since we design our infrastructure for ease of upgradeability, our existing Cray XT5 customers can easily install the new six-core processor in their current systems with a simple processor swap and BIOS update.  We have successfully migrated customers though four generations of AMD Opteron processor technology, from 1 to 2 to 4 and now to 6 AMD Opteron processor cores per socket and navigated the large system scalability challenges of each generation.

Our years of experience with these large HPC systems allows us to provide a proven, multi-core software environment that can take full advantage of this six-fold increase in scalability.  Our software, including the Cray Linux Environment (CLE) and Cray Programming Environment (CPE) masks the growing complexities of this multi-core environment and provides users and administrators a unified environment that is different from the standard “cluster” experience.

What does this new Six-Core AMD Opteron processor mean for Cray, its customers and the HPC community?

We have a simple vision of our place in high performance computing.  We want “better science” to be Cray’s sign and signature.  The Cray XT5, utilizing Quad-Core AMD Opteron processors, was the first general purpose system to break the petaflops barrier, providing a platform for groundbreaking science to hundreds of researchers in dozens of disciplines within weeks of installation.  This new Six-Core AMD Opteron processor technology from AMD included in our XT5 and XT5m systems will mean more performance at a low cost, superior efficiency and more scalability.  It means that researchers, scientists and engineers that utilize Cray supercomputers can now leverage a dramatic increase in computational power to address some of the world’s most challenging and sophisticated problems.

In short, it means “better science” and that is the most important thing of all.

Barry Bolding is Vice President of Scalable Systems at Cray. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Any claims made herein are based on Cray testing and have not been independently verified by AMD

We started shipping production units in May and today we are rolling out the red carpet to introduce “Istanbul” to the world.  Over the next few weeks you’ll see our industry partners launching their “Istanbul”-based platforms.

So where do customers want to use these two extra cores?  They want them in their databases, in their virtual environments and in their HPC/technical applications.  Six cores will allow an application to break up problems into smaller chunks for a more parallelized completion of tasks. 

We have been rapidly moving from a world of serial tasks to a world of parallel tasks.  And as this happens, having more cores helps applications run more efficiently.  Elegant design has won out over brute force in software programming. Not too long ago a single core processor delivered all of the performance that a customer needed, but now, as operating systems and applications have become more threaded, the need for more cores is becoming far more important.

So, this is the death of the Quad-Core AMD Opteron processor codenamed “Shanghai,” right?  Hardly.

There are still plenty of applications that are less threaded and will enjoy the higher clock speed of our four core processors.  The two products can live side by side in the product line, allowing customers to meet a wider range of application needs, all with a common platform underneath. Best of all, we offer both the four-core and the six-core for a range of platforms, from 2P to 4P and even 8P.  No other company on earth offers the same commonality across that range of configurations. Only AMD delivers consistent four-core and six-core configurations across all of the different form factors, from the low-end 2P 8-core systems to the high end 8P 48-core systems.  There is choice and flexibility across a highly scalable family of platforms from the leading server vendors.

With “Istanbul” we take the first important step towards the “high-low strategy” that we laid out in April.  “Istanbul” meets the needs for high performance/highly scalable applications that crave more cores and more parallel processing.  “Shanghai” fills the bill for those applications that need fewer cores and are focused more on energy efficiency or cost-effectiveness.

As the market continues to move in these two directions, we plan to be there with the product that customers need to handle their critical applications.

Now that Istanbul is “finally” out the door my wife asked me if things would quiet down and could I relax a little more.  How do I break it to her that things are just getting started?

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Well, it appears that Ralph never ran a data center.  Consistency is the holy grail of the data center, not the hobgoblin. When you have hundreds, or thousands of servers to keep track of, the more you can minimize the variances in hardware, the easier it is to manage the servers and your business.

Most IT teams typically spend the majority of their time managing software and not hardware. They realize that consistency can help reduce their software management tasks and make their lives easier.

Recently I read a blog on ZDnet where there is a potential concern about Windows XP compatibility on Windows 7 with some Intel desktop processors.  The blog author, Ed Bott states “In the case of Intel’s phenomenally confusing product matrix, VT support is added and removed from CPU models for reasons that have more to do with marketing than technology.”

(Read about our close collaboration with Microsoft to ensure stability and compatibility for Windows 7 in Nigel Dessau’s recent blog.)

How is this possibly tied to enterprise severs?  It’s all in the choices that your processor vendors make.  If they focus on consistency your life can be a lot easier; but some unnecessary forced choices can diminish your efficiency.

The newest Intel Xeon processors appear to suffer from a similar marketing decision.  At the top of the stack, the more expensive silicon has a full set of features.  But as you roll down the stack, away from the premium priced parts down to the mainstream parts (where the majority of the parts are sold) you see that many of the features and capabilities are either reduced or actually absent.

On some models the QPI bus speed is dropped, there are actually 3 different bus speeds depending on which model you buy.  Same with memory; three different memory speeds – meaning you have to stock multiple speeds of spares. Or you can choose to standardize on one speed, which means that you are either paying too much or compromising on the product, it’s your choice.  Cache is similar – sometimes it is the full amount, sometimes it is half of that.

What about software-visible features? Well, if you are tuning you applications to see a certain number of cores or to anticipate a particular performance level, then the fact that features like HyperThreading or Turbo are available on some processors and not others can create real server issues for you. Because not all Xeons have those features you start multiplying the number of software images that you have to maintain.  Or, to make your life easier, you just don’t support these features.

The AMD Opteron™ processor is different. When we design our processors, we hold the feature set consistent across the family.  That means customers can minimize their software changes and make systems easier to manage.  They can also do a better job of planning their deployments.  Knowing the features are consistent they can more accurately model the different performance levels for different processors. Cutting features like cache as you move down the stack makes it more difficult to accurately predict performance levels.

While some may counter that you can “scale performance” up and down the stack, this only works if your applications scale all resources equally.  If I/O and memory scale proportionately with CPU speed, then you are fine.  But what about web applications with their heavy I/O requirements but low CPU performance needs?  Well your choice is to overspend on the CPU to get the higher I/O performance or go with the lower priced CPU and compromise on the I/O performance that you likely need.  Neither choice is optimal.  That is why we drive for consistency. 

The reality of the situation is that having consistent features doesn’t have to prevent you from having a full stack of processors. Artificial limits only take away, they don’t enhance. And as we are finding out on the desktop side, the strategy could have downstream impacts that you hadn’t counted on.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

But literally speaking, the processor is right around the corner as well, because this week AMD announced that “Istanbul,” the code name for our upcoming 6-core AMD Opteron™ processor, is planned for launch in Q2.

How are we able to pull off such a feat?  Well, to begin with, Istanbul is based on the highly successful “Shanghai” design.  With a highly leveraged core design and a very well-behaved 45nm process, making the leap from 4-core to 6-core was a snap. In addition to the two extra cores added, we also plan to include a new feature called HT Assist, something that I have blogged about in the past.

HT Assist is expected to provide significant memory and I/O performance increases by reducing the overhead of cache lookups.  Think rifle shot instead of shotgun, cutting down on a lot of the inner-chip communications.

So starting with a robust design is half of the challenge, the other half is executing well.  And we have been executing quite well. Shanghai was delivered to market ahead of schedule, and now Istanbul is expected to follow in its footsteps. Normally, when you design any new processor, you allow for several revisions of the silicon before you get to the final production silicon.  When designing in a computer, everything looks fine, but until you start hammering away on actual silicon, you don’t really know how things are going to turn out.  Chemistry, physics and math can be funny that way.

But if you do a great job on the design, and you nail it the first time, you can shave months, or quarters, off of the project schedule.  Our current schedules are a testament to the abilities of our engineering teams around the world.  Our global design centers in Austin, Sunnyvale, India and Boston, toiled around the clock to make sure that Istanbul was a robust design.  Later this quarter, we expect you to be able to reap the rewards of their work.

So what can a 6-core processor mean for you?  If you have well-threaded applications or you are running a multi-threaded environment like virtualization, we expect that they will be able to eat up those extra cores with a smile on their face.  Greater levels of parallelism can help more work get done simultaneously for greater efficiency – and we expect it to all be possible within the same power and thermal levels that you see today with “Shanghai.”  As a matter of fact, we are designing these processors to fit into the same socket 1207 architecture as Shanghai, so you should be seeing Istanbul in all of the old familiar places. Now is a good time to ask your server vendor when they expect to be shipping Istanbul processor-based systems.  (I am guessing that you will like the answer.)

Istanbul is expected to bring 24-core computing to the 4-socket space with true interconnected and scalable performance (not 24 cores on a front-side bus).  And in the 2-way space we expect that you’ll see 12-core systems; providing the perfect balance of performance and power for scale-out virtualization. I’m sure Margaret will have a thing or two to say about that, so keep an eye on our virtualization blog.

Istanbul is the city that lies at the gateway of the world, with one foot in Europe and one foot in Asia.  If your applications are craving the greater scalability only additional physical cores can deliver, then look no further than AMD’s planned six-core Istanbul processor– designed to give you one foot in the world of greater scalability and the other one solidly planted this quarter.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Having been around IT planning teams for the past 15 years, hearing any ROI statistic always sets my radar off.  This is no exception.  To me, this claim feels very unusual and there are only 2 explanations that I can think of; Either they are trying to oversimplify a very complex calculation by only looking at one factor (power); or they simply don’t understand the complexity of enterprise applications.  Either way they risk doing a major disservice to customers.

The argument that a company can pay off the investment in a new multi-core server by retiring 9 older single core ones is akin to buying a new hybrid car and raving about how much money you are saving every time you fill the tank, ignoring that you had to purchase a car in the process. Return on investment should encompass all of the costs of a solution; otherwise it risks overstating the return.

Let’s take a look at retiring 9 single core servers by consolidating them down to one multi-core server. Simplistically you are going to incur the following costs:

·         Consolidation prep – you have to actually do all of the planning and prototyping of the system, mapping data, etc., this is not a simple “copy and paste” exercise. Let’s not forget the data center planning piece of this exercise.  You are going to have to remove all of the systems and install a new one.

·         Migration of the data – this includes the actual movement of the data.  Maybe you get lucky because all 9 servers magically had the exact same data structures and can all coexist happily with each other.  Or not.  I’m going to bet on “not”, I’ve seen enough of these projects.

·         Security – You had 9 separate servers with 9 separate ACLs or security profiles set up to manage who could – and more importantly – could not access the data.  Whenever you start consolidation of systems, it is important to make sure that the Marketing Department can’t see the Payroll Department’s files.

·         Testing – once you have the new servers in the rack, you don’t actually just flip a switch. You are going to have to touch all the applications that touch that server.  Including middleware, backup, security, and network infrastructure.  One incorrect MAC address can result in a bunch of troubleshooting if you can’t quickly diagnose the problem.

·         Unplanned consequences – Did you ever add a new user and find another suddenly can’t print?  Most project managers I’ve worked with include some measure of “overage” to the project to help compensate for having to track down the “stragglers” of any project.

·         Licensing changes – Well, 9 servers running 9 copies of the old program might be a sunk cost in ROI, but I am betting that as you consolidate these servers you may end up needing to upgrade to the newest version of the software in order to handle the complexity of the new environment.

·         Disposal – you will need to get rid of the old systems, let’s not forget that you can’t just leave them in the dumpster (don’t forget to take the time to truly destroy the hard drives…)

And this is all just the tip of the iceberg, I’m sure that each one of you can provide your own list of hidden costs in trying to do a project. There is a human cost, and with the typical cost of ~$65/hour (the fully burdened cost estimate from the last project I worked on a few years ago) the human costs will likely dwarf the hardware purchase. If you don’t comprehend these costs, you can’t accurately assess ROI.

I’m not naïve in thinking that projects like this happen every day.  But it is a bit naïve to think that power costs alone can determine ROI.

Looking at the typical server deployment, you can rest assured that the hardware is the lowest cost of the project by far.  So if you want to do yourself a favor, don’t let your company fall for the “pays for itself in 8 months” hype that’s out there – do your own research and get the full story with all the costs revealed.  Otherwise you’ll be the one explaining things to the CFO.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

This week, Fusion-io, a leading provider of enterprise-class solid state technology, announced a major milestone.  You may already be familiar with the ProLiant DL785, the 8-processor powerhouse server from HP, which features eight AMD Opteron™ processors. Fusion-io reports it was able to pump out an astonishing performance level, more than 1 million IOPS using the fio benchmark. They also claim sustained throughput was over 9GB, or roughly the capacity of two DVDs, per second.

In the past, when you talked about the million IOPS performance level, you were always talking about mainframe-class systems.  Today, we are talking about industry-standard x86 servers.

The HP DL875 takes the AMD Direct Connect architecture to new levels, providing the high end systems expertise to bring enterprise-class database and virtualization to x86 levels of value. With 8 processors and up 512GB of memory, this system provides the scalability and capacity for even the most demanding workloads.

Fusion-io uses NAND flash memory in PCI Express slots to help bring data as close to the processors as possible, helping reduce latency and helping drive up the IO throughput per second.  HP also utilizes the Fusion-io technology in its BladeSystem products through a product called the HP StorageWorks IO Accelerator. Each BladeSystem server can support 2 or 3 of these IO accelerator cards to help drive greater performance while also helping hold power consumption down.

Yes, power consumption.  And before you start thinking that power consumption and 8 processor servers don’t generally correlate well, keep in mind that the larger the server footprint is, the more energy efficiency comes into play, helping hold down the power budget for the rack.

So what does this mean to you?  Several things.

As a Fusion-io customer it means that you can utilize state of the art solid state technology to break through the traditional system bottlenecks and reach entirely new levels of I/O throughput.

As an HP customer it means that you have platforms that can handle your most demanding enterprise applications.  And you can be confident that the engineering know-how that helped reach this unprecedented level of performance in an 8P system also helps drive outstanding levels of performance in the ProLiant BladeSystems as well.

As an AMD customer, you know it means that the AMD Direct Connect architecture is scalable enough to handle any of your workloads with exception I/O throughput through our use of the industry-standard HyperTransport™ technology.

And, as a customer or Fusion-io, HP and AMD, you can smile, confident in knowing that the combination of these potent technologies and platforms is delivering just what you need to solve today’s business challenges.

You’ve got a reason to smile, or, more accurately, a million reasons to smile.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

What helped our new server processor take off? Two clear things:  innovation and a market hungry for change.  But how is that appetite today?

Understanding the market dynamic, and more importantly, the customer needs, is critical with any new product.   In 1999 millions of servers were replaced due to Y2K, so in 2003, there was a natural inflection point in the market as those servers reached their traditional lifecycles.  The economy was strong and people were open to the idea of something new. But it isn’t always like that.

Today’s economy is helping turn up the contrast on changes in the data center; more importantly, in regards to unnecessary changes, which are not viewed as positively by customers.

Take for instance the migration to DDR-3 memory.  Next year, when DDR-3 memory is expected to drop in price, you will have access to lower latency, lower cost and lower power memory.  At that time, DDR-3 could represent a savings and value to you.  Today, however, DDR-3 has higher cost, higher power consumption and higher latency.  Change can be good, but only if change is to something better. (EETimes has a strong opinion about this.) If you are struggling to make the most of your IT budget, expensive memory, which can represent up to 50% (or more) of the cost of a server, is not a good idea.

When IT staffs are being cut back and resources are being stretched to their limits, platform stability has a comparatively higher value.  New image management and more complex systems typically mean more resources required to deploy and manage the systems, something many organizations just can’t justify in today’s tight economy.

AMD’s platform strategy is built around longevity, not churn.  Our stability means that you can get more value out of the systems that you deploy because the ROI over the life of the server can be higher. 

We plan for our customers to be able to transition their purchases to “Istanbul” processors later this year, allowing them to move to the measurable benefits we offer with 6-core processing, yet still maintain the same platforms and images that they have on today’s “Shanghai”-based systems. (Watch a live migration video.)  Service spares don’t have to change.  IT teams don’t need to be trained on new systems. Customers don’t need to spend extra dollars outside of the hardware in order to take advantage of the new platforms. Managing the new “Istanbul” system will be virtually identical to managing the “Shanghai” system, with the same BIOS, drivers, and management interfaces.  This means you get the benefit of change, without the extra baggage.

And in today’s economy, who can afford the baggage?

 Update – It looks like I am not the only one saying this, CRN readers feel the same way:  http://www.crn.com/hardware/216402221

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Recently, our CMO blogged about the server transition from DDR-2 memory to DDR-3 memory. One of his key points was that the investments needed to drive the cost of DDR-3 down to DDR-2 levels might not be made as quickly these days.

For servers, memory is typically the most expensive component in the system. Perhaps I am dating myself, but I remember back in the day, when a 128MB memory footprint in a server was large.

Today, it’s a different story. 4GB of memory is the bare minimum that anyone cares to get, with 8GB and 16GB being much more common for dual processor configurations. 2GB per core seems to be the sweet spot for many customers.

While DDR-2 memory has become cheap, that isn’t driving a lower total cost on the memory, it is instead driving larger configurations. As we all know, the more memory you have, the more you can stay away from pulling data off the hard drives, which is really slow. For that reason alone memory continues to be about the same percentage of total cost, despite the falling prices.

Here in the US we are following closely how the government is going to deal with the auto industry because of market conditions. But in Taiwan, it’s the DRAM business that is struggling. High inventories are driving down the cost of DDR-2 memory and creating economic hardships for the memory business.

With conditions like these, do you expect massive investments in speeding the transition to the next technology, or do you think that scaling back the business investments is probably a more likely outcome?

Just as Detroit is probably scaling back 2009 and 2010 plans to accommodate the current economic environment, DRAM vendors on the other side of the globe are probably having the same discussions.

So where does the current economic environment leave server customers in terms of memory transitions?

Well with memory being such a large cost component in servers, it seems to me that server customers are taking advantage of DDR-2 savings today, and probably not considering DDR-3 based platforms because of the price premiums.

As a server customer I’m sure you realize the impact of the price of memory on your equipment. We do too, which is why we’re being very careful about when we move our platforms over to the next memory technology.

I’m interested in how you see this playing out in your own server plans, post up and let me know.

John Fruehe is the Director of Business Development for Server/Workstation products at AMD. His postings are his own opinions and may not represent AMD’s positions, strategies or opinions. Links to third party sites are provided for convenience and unless explicitly stated, AMD is not responsible for the contents of such linked sites and no endorsement is implied.

Sure, there’s new management at VMware, a repositioning to the operating system for the virtual datacenter, and lots of new competition. But what struck me even more than those changes are the fact that the x86 virtualization movement, started all those years ago by Diane and Mendel, is going mainstream, and that’s very very exciting for someone like me, who’s in charge of helping making sure AMD’s customers have the best experience possible in running software on AMD hardware.

One proof point is just the sheer amount of attention VMWorld is getting this year. Who would have ever thought the conference that attracted 1,600 early adopters of x86 virtualization to San Diego in Nov. 2004 would be hosting 14,000 mainstream IT professionals in Sept. 2008? And that the New York Times would write so much about a technology as enterprise focused as virtualization! I think this demonstrates the power that virtualization is already playing in shaping the future of the computing industry.

A second proof point is the amazing number of new servers I see being introduced by everyone from large OEMs to small system builders that are specifically aimed at serving as excellent virtualization solutions. For example both Dell and HP have recently introduced blades based on the energy efficient Quad-Core AMD Opteron™ processor that are designed to handle the rigors of memory-intensive virtualization.

A final proof point that virtualization has gone mainstream is the thriving ecosystem developing around virtualization. Just take a look at the presentations that were given in AMD’s own booth at the show – our “Master of Virtualization” theater was filled with small and large ISVs and IHVs who were showcasing how they are moving the needle on virtualization – including 3Leaf, Broadcom, Citrix, DataRam, Egenera, Microsoft, Novell, Sun, Transitive, Parallels, and Virtual Iron.

So what’s next in these times of change? I believe that as virtualization pushes it way into the main stream – and lights up discussions around topics such as cloud computing, virtual infrastructure, and dynamic data center fabrics –  the virtualization ecosystem needs to understand that interoperability, open standards, and vendor cooperation has to be paramount. Customers are looking for choice – and not for technologies designed to lock out competition. They want live migration of virtual machines across different processors and tools that can manage virtual machines created by any hypervisor. Feel free to contact me and we can follow up with more information.