Many people in the cloud and dense computing world have data center racks that are packed that tight.  Every watt counts because at load, they are maximizing everything in their power budget per rack. 

For customers like this we have a new feature in our upcoming processors codenamed “Interlagos” and “Valencia”: TDP Power Cap. [eWeek takes a look at TDP Power Cap and potential impact for cloud/mega datacenter customers here.]

In today’s products you can cap the power of a server by turning off processor states, though that ultimately can lead to somewhat lower performance. There are a lot of our customers who value power efficiency over performance, so it is not a real issue for them.  But what if you could set low power limits AND get the performance that the platform offers?

With today’s AMD Power Cap Manager, you can limit the processor P-states and cut power consumption although this limits the processor’s ability to get to the top frequency (which is also the most power-hungry spot on the curve as you can imagine…).  By essentially “locking out” the top P-state, the processor never gets into that state, even under heavy utilization, helping cut down total power to the processor.

With the new TDP Power Cap for AMD Opteron™ processors based on the upcoming “Bulldozer” core, customers will be able to set TDP power limits in 1 watt increments.  This means that instead of having to choose between different TDPs for processors, you can actually buy any power range and then modulate down.

Why would someone want to limit TDP?

Well, let’s say that you have a maximum power draw on your fully configured server of 300W, and you have 42 slots in your rack.  The simple math says that you have 12.6Kw of power load that you need to be able to support.  Now, if your power budget only allows you to bring 12Kw to the rack, you essentially have 2 slots that need to be left open in the rack because you can only support 40 and not 42 servers.  But, by utilizing a custom TDP, you could drop the max power that some servers could draw, bringing you in under the limit of 12Kw and still getting 42 servers in the rack.

Best of all, if your workload does not exceed the new modulated power limit, you can still get top speed because you aren’t locking out the top P-state just to reach a power level.

This is truly essential for blades, clouds and other dense environments where every watt counts.

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.

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.

“The twelve-core AMD Opteron 6100 and six-core Xeon 5600 perform more or less the same”

But, do they?  Enter our OEM partner HP who has been busy during these lazy, hazy days of summer publishing white papers that evaluate the performance characteristics of its ProLiant G7 platforms. These papers provide a unique opportunity for what is as near an “apples to apples” performance evaluation as you can get for the 12-Core AMD Opteron 6100 Series processor and the 6-Core Intel Xeon 5600 Series processor – the same system vendor (HP) running the same generation hardware platform (G7) with the same software stack (Microsoft Windows and SQL Server products).

Let’s start with HP’s recently released TPC-H Benchmark Performance Brief – TWICE AS NICE: HP ProLiant DL380 G7, DL385 G7 take world records for performance, price/performance on 100GB TPC-H benchmark.  In this paper, HP highlights the performance of its ProLiant 300 G7 platforms with Windows Server 2008 R2 running Microsoft SQL Server 2008 R2. Their results:

• The HP ProLiant DL380 G7 as #1 in the TPC-H@100GB non-clustered performance category
• The HP ProLiant DL385 G7 as #1 in the TPC-H@100GB price/performance category

The TPC-H@100GB is a decision support benchmark that handles large volumes of data, executing complex queries and delivering answers to major business questions. Each posted score requires a set of disclosure documents as part of the submission process (here is the one for the Intel-based system, and here is the one for the AMD-based system, which are both summarized below). These documents provide an opportunity to go beyond the posted scores and take a more detailed look at the hardware and software used to achieve the results. The chart below details the server hardware used in these tests:

In this chart we see that the Intel-based HP Proliant DL 380 G7 system posts a QphH score that is basically on par (only about 3% higher) than the AMD-based HP DL 385 G7.

But, notice the cost of the database servers used in this test.

Comparing the server costs as published in the disclosure documents, the Intel-based DL 380 G7 configuration costs $7,452 more than the AMD-based DL 385 G7. So you could basically pay almost 30% more for a server that can deliver 3% better performance. That is essentially a 10% price premium for every percentage increase in performance.  Will your end users feel a 3% difference in performance? Hardly.  Will your CFO notice a 30% difference in price? Definitely.

Another white paper recently published by HP discusses the scalability of HP ProLiant servers HP Server Based Computing environments. This paper summarizes the results of performance characterizations for its ProLiant blade and rack servers recommended for the HP Server Based Computing (SBC) environment. The SBC environment is where applications are deployed, managed, supported, and executed on the server and not on the client – with screen information transmitted between the server and client. Since this paper provides comparisons over a range of HP ProLiant server generations, for consistency all tested servers run x86 or x64 editions of Microsoft® Windows® Server 2003.

The chart below shows the performance results for two HP ProLiant G7 2 socket platforms: the Intel Xeon processor-based DL 380 G7 and the AMD Opteron processor-based HP ProLiant BL 465c blade server.

As you can see, performance (in terms of optimal number of heavy users) is exactly equal for the Intel Xeon model X5680, which is the top of line, and the AMD Opteron processor model 6174, which is a mainstream part (one speed grade down from our top performance part). The lower power version of the AMD Opteron 6100 processor also posts a very respectable score (only about a 9% decrease in optimal number of heavy users), and when you consider the difference between their high power part and our low power part, there is a compelling argument for the cost of power and the density of systems.

So what are your thoughts on the performance comparisons? Do the AMD Opteron 6100 Series processor and the Intel Xeon 5600 processor have similar performance? I guess that depends how you measure “performance.”

Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her 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.

Test results referenced in this document were taken from HP white papers.  The tests were not conducted by AMD, nor has AMD independently verified the accuracy of these results.

Professionals have been asking about better tools to get the job done more efficiently and with less waste. This new line of ATI FirePro 3D graphics cards offer a wide variety of features that are aimed specifically at those needs:

• OpenCL™ support – ATI FirePro supports OpenCL as an industry standard API with multi-platform development for enabling broad adoption of heterogeneous computing.² ATI FirePro is enabled for accelerated compute when OpenCL supported applications come to market in the near future.
• Microsoft® DirectX® 11 and OpenGL 4.0 support – ATI FirePro is designed to meet those solutions using DirectX 11 and OpenGL® 4.0 where great performance, scalability and reliability are required.  AMD continues to work with developers spanning a wide variety of professional needs. Not only is AMD offering direct support to developers, as they bring OpenCL, OpenGL and DirectX 11 applications to market, but AMD also offers an ongoing certification process designed to ensure that ATI FirePro graphics work efficiently with major applications.

It’s encouraging to see continued market acceptance for these products as well. For example, leading workstation provider, Dell, is offering new solutions for design engineers and digital content creation professionals. ATI FirePro™ V7800, ATI FirePro™  V5700 and ATI FirePro™ V8700 power Dell Precision R5400, T7500, T5500, T3500 and T1500 Workstations available around the world.  Don Maynard, senior product manager of the Dell Precision Tower Workstations, has recognized the value that ATI FirePro brings to the market.

www.youtube.com/watch?v=RPidi7-JyHk

But you don’t have to take my word about these cards. AMD has been recognized by a variety of news outlets for the new line of ATI FirePro products.  Awards have been received from 3D Professor, Hot Hardware and PC Perspective as testament to the outstanding performance of these new graphics solutions.

If there’s one thing I’ve learned in this business, it’s that you can’t be productive without having the proper tools. Both AMD and Dell have teamed up to offer professionals the essential tools they need to help them to be both productive and efficient for virtually whatever project they have planned for the future.

Janet Matsuda is Senior Director, Professional Graphics at AMD.
Her postings are her 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.

1. ATI Eyefinity technology can support multiple displays using a single enabled ATI FirePro™ professional graphics card; the number of supported displays varies by card model. Microsoft® Windows® 7, Windows Vista®, or Linux® is required in order to support more than 2 displays. Depending on the card model, native DisplayPort™ connectors and/or certified DisplayPort™ active or passive adapters to convert your monitor’s native input to your card’s DisplayPort™ or Mini-DisplayPort™ connector(s) may be required. ATI Eyefinity technology is supported by the ATI FirePro™ V8800, ATI FirePro™ V7800, ATI FirePro™ V5800 and the ATI FirePro™ V4800 professional graphics cards. See www.amd.com/firepro for details.
2. OpenCL™ compliant driver and SDK release scheduled in 2010.

I bought my first processor in a PC back in 1987.  12MHz.  Yes, and that was considered “fast.”  Back then, I worried about 2 things: performance and price.  I could have splurged and bought the 16MHz processor, but 12MHz seemed like the best balance for me at the time.

23 years, and a lot less hair later, I’m in the same boat.  I don’t buy many processors these days, but the process really hasn’t changed.  Today in the IT world, there are not 2 variables, there are 3: performance, price and power.

Those of us in the cubes here get really excited about a lot of things.  When our propellers start spinning, we get all fired up about the features of the processors.  But in reality, when you commit your scarce budget dollars to new servers, what do you look at?  You look at performance, price and power.

How can I prove this?  A minority of our processor sales are the top bin processors.  These are the fastest, most expensive and most power hungry.  And most applications don’t need that kind of horsepower.

This is because the balance of price/performance/power tells you that a bit further down the stack is your sweet spot.  I’ve talked to the folks who do buy those top speed processors. They run trading applications where a half second can be thousands of dollars in profit.  But for the majority of workloads, everyone wants to look elsewhere in order to maximize their budget.  We understand this, and at times, it feels like only we understand this.

When you look at our existing AMD Opteron™ processors as well as our upcoming new products (the 8- and 12-core processors codenamed “Magny-Cours”), you see two big themes: we don’t compromise on features and we are going to deliver the feature customers care most about:  value.

As you look at our products, you’ll see that as you move down the stack, from those fastest processors that everyone lusts after (but few buy) down to the value-priced processors, you’ll see the same set of features.  You won’t see AMD artificially limiting the capabilities or punishing a focus on low power.  Scaling back the features for marketing purposes is really not a very appetizing prospect for us. We believe that you should have the full set of features, no matter where you buy in the stack.

You won’t see us scale back the memory speeds. You won’t see us scale back the I/O speeds. You won’t see us pull features.  That is not our way to bring products to market.

You will see our processors vary in price based on core count and clock speed.  Beyond that, if you see a feature, like our AMD-Virtualization™ (AMD-V™) technology features or our AMD-P power features, expect them across the whole stack. You won’t see us pull a feature that you count on, and you really won’t see us pull features that could impact software images across different servers. Can every processor company in the x86 server business claim this?

At AMD, we believe you should buy the capacity you need at the price that makes sense – and get everything you paid for – no surprises. That is our commitment to you, so make sure your next processor isn’t artificially limited.

Yeah, that nanometer thing; let’s talk about what you really want.  There are a lot of technologies being tossed around these days.  Nanometers, High-K metal gates, immersion lithography.  They sound pretty high tech.  They are and they’re cool, but they don’t impact what you really care about:  that holy trinity of processor value criteria: performance, price and power.

It’s funny to think that some talk about manufacturing processes driving down costs, but when you compare price stacks, you see an amazing similarity over the years.  Where are those savings going? Fact is, manufacturing process improvements do help drive down costs – for the manufacturer.  We think cost savings belong in your pocket, and you’ll see why soon enough.

Let’s not go down the path of saying “technology X will lead to lower power.”  Plug in the server and decide for yourself.  Don’t think that something is going to lead to lower prices, instead, take a look at the bill. That is the best way to know for sure.

It may seem odd to have a marketing guy tell you not to fall for marketing, but at the end of the day, you’re going to buy the best product that meets your criteria.  And for the majority of applications, those criteria are price, performance and power.

Based on that, I am pretty confident that the best choice is going to be the new AMD Opteron™ 6000 Series processors because we designed them with you in mind.

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.

At this time last year, the most energy efficient AMD Opteron^TM processor-based server (based on the SPECpower^TM_ssj benchmark) could achieve only a score of 203 overall ssj_ops/watt (95,853 ssj_ops & 276W @ 100% target load) and consumed 164W at Active Idle. A server using the newest Six-Core AMD Opteron HE processor achieved a score of 1228 overall ssj_ops/watt (419,277 ssj_ops & 221W @ 100% target load) and consumed only 120W at Active Idle¹. That’s more than 6x the performance-per-watt AND more than a 25% drop in Active Idle power.

AMD technology-based servers help increase performance-per-watt and decrease power consumption at the same time by using a suite of features we call AMD-P. AMD-P is supported by the Six-Core AMD Opteron 2400 and 8400 Series processors as well as the Quad-Core AMD Opteron 2300 and 8300 Series processors. This suite of features and the large number or processors that support them enable customers to build energy efficient two-socket, four-socket, and eight-socket servers which can efficiently meet the needs of almost any server application.

When we compare servers using the newest Six-Core AMD Opteron 2400 Series HE processors to servers using existing AMD Opteron processors, we find that a server based on the AMD Opteron 2400 Series HE processor is able to achieve 18% higher performance-per-watt than a server using Quad-Core AMD Opteron 2300 Series HE processors² and also consumes 18% lower platform-level power than a server using Six-Core AMD Opteron 2400 Series processors³.

That’s a pretty big improvement over a processor that was released just six months ago!

In addition to lowering server Active Idle power and boosting server performance-per-watt, these new Six-Core AMD Opteron HE processors are designed to provide significantly more processing performance than prior low-power AMD Opteron processors. Servers using these processors are able to achieve up to 50% higher performance than servers using Quad-Core AMD Opteron 2300 Series HE and 8300 Series HE processors in the same power and thermal envelope. That’s like getting the performance of V6-powered Ford Mustang and the fuel efficiency of a four-cylinder Ford Fusion in the same car.

Whether they’re being used in a cloud cluster or a High Performance Computing cluster, the newest AMD Opteron HE processors provide plenty of performance for only a few watts.

What do you think – is a cloud a cluster or is a cluster a cloud?

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.

¹Configuration Information: 2 x Six-Core AMD Opteron™ processors (“Istanbul”) Model 2425 HE in Supermicro 1021M-UR+ server, 16GB (4x4GB DDR2-800) memory, 500GB SATA disk drive, Coldwatt CWA2-0650-10-SM01 power supply, Microsoft® Windows Server® 2008 Enterprise Edition SP1 64-bit

²Six-Core AMD Opteron™ processor Model 2425 HE [SPECpower_ssj™2008 1228 overall ssj_ops/watt, 419,277 ssj_ops, 221W @ 100% target load] compared to Quad-Core AMD Opteron™ processor Model 2376 HE [SPECpower_ssj™2008 1044 overall ssj_ops/watt, 346,326 ssj_ops, 210W @ 100% target load]

³Six-Core AMD Opteron™ processor Model 2425 HE [SPECpower_ssj™2008 1228 overall ssj_ops/watt, 419,277 ssj_ops, 221W @ 100% target load] compared to Six-Core AMD Opteron™ processor Model 2435 [SPECpower_ssj™2008 1228 overall ssj_ops/watt, 487, 764 ssj_ops, 270W @ 100% target load]

SPEC and the benchmark name SPECpower_ssj are trademarks of the Standard Performance Evaluation Corporation. For the latest SPECpower_ssj2008 benchmark results, visit http://www.spec.org/power_ssj2008.  

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.

Not that long ago, supercomputers were large room-sized behemoths that could require hundreds of millions of dollars of investment and could crack complicated problems.  Then everything changed.  I blame Linux, but you can choose your own hero (or villain).  Suddenly the world of supercomputing went, almost overnight, from a very expensive proprietary and exclusionary world, to an open environment where people use industry-standard hardware and open source software components to construct massive supercomputers at a fraction of their previous cost.

With these supercomputers, companies, universities or governments can take a large problem, like where to drill that hole in the ground to find oil, break it up into thousands of tasks, disperse them across all the computing nodes and then compile the answer.  When it can cost up to $1M US to put that hole in the ground, a supercomputer is money well spent.

I am in Tokyo, on vacation this week, but I remember a very vivid meeting here back in the early 90’s at a Japanese auto manufacturer. They were trying to figure out how to drive down the cost of crash simulation.  Apparently it is a lot cheaper if you don’t have to build a car and then drive it into a wall.  Today crash simulation is primarily done with computers.  You can crash more cars in a morning with an HPC cluster than in a year’s worth of playing bumper cars on the Dan Ryan Expressway. Those of you from Chicago know why I picked the Ryan – it was notorious for accidents.

It is currently the rainy season in Japan, and every time I turn on the TV to see how wet we will get today, I am reminded about the accuracy of weather forecasts (insert your own joke here), another area where HPC clusters and supercomputing technology are having major impact.

The ability to lash hundreds or even thousands of low-cost x86 servers together into a supercomputer is presenting some pretty amazing results. In the most recent TOP500 Supercomputers, AMD continues to be prominently featured as a groundbreaking leader.

With the top two overall supercomputers on the www.top500.org list based on AMD technology, and 9 out of the top 20, it is clear that customers are very interested in AMD Opteron™ processors for building high performance supercomputers and for good reason.

The chief concerns for most supercomputer customers these days, believe it or not, are generally not raw performance numbers.  When you are putting thousands of processors together, a few percentage points here or there become meaningless.  The factors that do drive a lot of the decisions are price, power consumption and scalability. 

Think about the task.  You are building out thousands of servers, each with multiple processors.  For every dollar that you save per processor, you might be saving tens of thousands of dollars in total cost. Many supercomputing sites are frankly operating in tough budget constraints, especially when it’s an academic institution, for example.  And power can’t be overlooked.  The density of these deployments, along with the networking, can consume huge amounts of power.  Scalability is a given, with the large number of pieces that you are breaking a problem into in order to solve.

What makes AMD Opteron processors perfect for supercomputing? Well we excel in these three areas: power, price and scalability.  And, only AMD can give you the same 6-core processor architecture in 2P, 4P and 8P configurations, helping you achieve greater scalability.  And too, when you want to talk about HPC performance, you can’t ignore that throughput and memory performance are key.  Those are also areas where Direct Connect Architecture has and continues to excel.

That is why you see us all over the TOP500 list.  And with our 6-core “Istanbul” product now in the market, who knows what November’s list will look like?

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 customers care about it. Today, more than ever; but even in the crazy dot-com 90′s, people still gravitated to value. Who doesn’t want to get the best value for their IT investments? In the business world, people just don’t burn money; it never makes sense.

On the consumer side, people sometimes associate “value” with “cheap.” But that might be because consumers tend to buy one computer at a time. They research the purchase, they obsess, they compare. Nobody wants to go “cheap” because it is their one shot for the next few years.

However, in the enterprise world, server purchases are a constant fact of life, not a single point in time. Most companies, even in today’s environment, continue to deploy servers and look for the best value that they can get, usually with a price/performance or performance/watt metric. Rarely is the decision made just on raw performance.

I have been a critic of performance benchmarks as much as I have been a fan of them. One of the problems that we see in so many benchmarks is that they fail to comprehend the value of the solution – they only measure one vector. Typically that is raw performance.

Take VMmark for instance. If you take the results at face value, it shows you the approximate performance of different systems. But, it is showing the performance for a specific configuration. Perhaps a configuration that you may never actually deploy in real life.

We recently introduced our new Six-Core AMD Opteron™ processors, and along with those processors there were several new benchmark results introduced, including a VMmark benchmark.

Just looking at the raw benchmarks, one might conclude that a 2P Nehalem-based system is going to be a better choice because of the higher performance. However, Collin MacMillan points out in his Solution Oriented Blog that if you look at only one vector, raw performance, then you might miss the big picture. The reason is that, depending on configuration, the Six-Core AMD Opteron processor-based HP DL385 can be priced almost 2/3 less than the Nehalem-based HP DL380 server.

Just over one third of the cost. That is just stunning. Especially when you consider that the typical customer may be loading 5-10 virtual machines on a single 2P server.

Maybe I am going out on a limb here, but if I was trying to justify a virtualization project, I think that telling the CIO to replace 5-10 physical servers with a single server that costs nearly 3X as much as a competing product is simply a losing proposition.

My colleague, Margaret Lewis, takes a closer look at configurations and pricing of Six-Core AMD Opteron processor-based systems (“Istanbul”) and Quad-Core Intel Xeon processor-based systems (“Gainestown”) that have posted top VMmark scores.

In the enterprise world, value might not have the same stigma that it has in the consumer world, and that is why enterprise customers don’t seem to be afraid of it.

When you are lining expensive data centers with row after row of computing devices, someone is bound to ask you what all this is costing and where is the benefit. If you are buying servers based on our new Six-Core AMD Opteron processors you can rest assured that you are filling your data centers with a superior value – and that speaks volumes.

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.

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.

Take a look at the server market today; 70% of the volume is in the dual socket space[i].  And it’s growing. Willie Sutton was once quoted (incorrectly) with saying that he robbed banks because “that’s where the money is at.” So why are we driving so hard in the two socket space?  Because that’s where the volume is at.  And you can quote me, correctly, on that one.

With our recent server roadmap update announcement, we are introducing the world to a new strategy for addressing the 2P market – G34 platforms on the high end, and C32 on the low end.  Hi-low.  It’s a big enough market that you would have to be crazy to think that it can’t be addressed by two different platforms.  Two different platforms that are more the same than fraternal twins, but we’ll get to that in a minute.

Think for a moment about where the 2P market is going. In the past few years we have been adding more cores, more expandability and more RAS features to our products – because customers have been demanding it for virtualization and other resource-hungry applications. But at the same time, a new class of application need is being driven by the low end.  Cloud computing, the growth of SMB applications and sprawling network infrastructure are creating a demand for lower power and lower priced, reliable servers.  The same density and business needs that drove AMD to add the AMD Opteron™ EE processors to our product line are driving a new platform that we expect will give you everything you need for most applications, but at a low cost, with very low power consumption.

G34 platforms, under the platform name of “Maranello”, are designed for expandability and performance. We plan to offer four memory channels per socket and 8 or 12 core processors perfectly suited to handle the most demanding 2P environments.  As an added bonus, these processors and platforms are expected to be able to scale easily to 4P. No longer will you have different models to choose from (2000 or 8000), we expect the new G34 processors to be able to easily handle both markets, simplifying the lives of those building servers as well as those maintaining servers.

C32 platforms, which we plan to bring to market under the platform name “San Marino”, are designed for the needs of the other half of the stack.  Scaling 1P and 2P solutions, the two memory channels and 4 or 6 cores are planned to perfectly match the hundreds of thousands of applications where 12 cores and 4 memory channels may be overkill.  Especially when it comes to electricity.  These processors sip electricity, they don’t gulp it.  They deliver the right level of performance for small/medium businesses, for cloud environments, and for network infrastructure needs. By utilizing a simple design, with fewer memory channels, AMD expects to deliver a relatively lower infrastructure cost.  And with planned power envelopes below the total range of current AMD Opteron processors, we expect that fewer fans, smaller heatsinks and smaller power supplies can help you achieve greater energy efficiency, lower noise, and of course lower cost.

So what about that twins comment?  What do these processors have in common?  Plenty.  They are expected to utilize the same core.  The same chipset design.  The same BIOS base.  We expect the C32 designs to be able to span 1P to 2P and G34 to span 2P to 4P.  They overlap is at that “meat of the market” intersection where the highest volumes live, for plenty of coverage in all directions. We expect that as a system designer, it will be a trivial feat to take a C32 design and change it to G34.  More commonality across a vendor’s products is a good thing.  As a customer this can help you drive down your long term cost of management.

Of course the question “so, you’re abandoning the 1P and 4P space” naturally comes up.  Nothing is further from the truth.  The C32 is expected to allow for a much more flexible 1P.  Low cost and simplicity to meet the needs of the 1P market, but with scale up capabilities to take it to 2P. Think of it as 1P on steroids (the good kind, not the baseball kind).

And 4P?  What can help turn the tide in a market that is slowly being encroached by 2P?  How about a platform that combines the best of both and allows a company to deliver a low-cost entry-level 4P server?  Talk about breathing new life into a market that sorely needs to adjust to the new realities of business in the post Y2K work. The time is right for this hybrid approach.

We’re very excited about how we plan to help our technology partners bring these new designs to market.  Without naming names, let’s just say that there is a renewed enthusiasm amongst our industry partners who have made comments about this truly being “game changing.” One even likened this strategy to the launch of the original AMD Opteron processor, an event arguably that did more to change the dynamics of the x86 server market than anything else.

We’ve laid our cards on the table now, and it it’s clear that in 2010, we expect AMD to be holding the winning hand. Let the games begin.

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.

First, a short bit on VMmark . VMmark is a consolidation benchmark that generates an aggregate score of individual VMs for a given number of tiles. A tile is six VMs running common load-generation tools that represent typical workloads: web server, file server, mail server, database, java server as well as an idle VM. One client computer is used to generate the load for one tile.

Looking at top VMmark scores you find systems that can run over 100 VMs per server. And there is a lot of chatter about how a 2 Socket Intel Xeon “Gainestown” processor-based server can run 16 tiles (or 96 VMs). However, there is no reference to the cost of the systems posting scores. VMmark documents the system configuration for the benchmark so you can take a stab at pricing these configurations on-line at the hardware vendor sites. (See slides 3 and 4 of presentation) In doing so we found that some of the top VMmark Intel Xeon “Gainestown” processor-based server configurations price out at about 175% and in some cases even higher than the top performing AMD Opteron™ processor (“Shanghai”) configurations (based on April 16, 2009 prices). Even in the performance-oriented high performance computing world this would turn heads. Cost does matter.

Going a step further, we now have the information to evaluate the price/performance of some of these systems by taking the estimated system cost and dividing it by number of VMs achieved during the VMmark run. While large number of VMs might be impressive – most IT professionals in today’s economy are focused on balancing performance and price—looking at the cost per VM helps to better understand the cost of putting the system in action. What you find is the system with the top VMmark score is not the system that gives you the best cost per VM.

Now that we have looked at the VMmark systems configurations, what type of virtualization configurations are customers really running? When looking at customer case studies posted on hardware and software vendors’ sites we find servers configurations ranging from 16GB to 64G of memory as more of the norm. We also don’t find many data centers pushing 100 VMs on a system. Responses to SearchDataCenter.com’s 2008 Purchasing Intentions Survey reveals that only 5% of respondents are running more than 25 VMs on a server – 61% are running less than 10 VMs per server and 33% are running 10 to 25 VMs per server. And since many customers are implementing virtualization as a cost saving strategy – we don’t see many of these customers buying the top bin “performance” processor models, which by design tend to consume the most power.

We did the pricing on systems configurations using energy efficient processors and more typical memory configurations for virtualization (again based on April 16, 2009 pricing), comparing both system pricing and cost per VMs (see slide 5 of presentation). Take a look for yourself. We think you will agree considering performance and price can give you a better view of its overall value.

So the question remains: how do *you* define “simply spectacular” virtualization? Is it in terms of raw performance or is it price/performance? Hopefully after reading this post, you have a different answer than when you started.

Margaret Lewis (@margaretjlewis) is a Product Marketing Director at AMD. Her postings are her 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.

“ First, all top-tier DBMS vendors such as […] are delivering high performance and scalability to support most large workloads. Second, TPC benchmarks no longer reflect the complex workloads of today’s real-world deployments. Third, customers that need high-end performance often prefer internal benchmarks to TPC benchmarks. Finally, virtualization, cloud computing, and database-as-a-service are changing the way customers deploy databases, and TPC does not address these architectures.” (from “TPC Benchmarks Don’t Matter Anymore:  Features and Cost are Key Factors When Choosing a DBMS” by Noel Yuhanna with Mike Gilpin and David D’Silva, March 6, 2009, copyright Forrester Research)

This touches on a larger issue that we have blogged about before – we are seeing here at AMD that data center demands on the whole are changing. There is less stock being put into how a hardware or software product performs in a lab, and more emphasis on total cost of ownership and how they perform in real-life scenarios.

 I want to be clear, there is a place for benchmarks, and we absolutely value how our products perform against the competition in a standardized setting. For instance, our 45nm Quad-Core AMD Opteron™ 8384 processor just set another world record virtualization score on the VMmark test (29.11@19 tiles on a Sun Fire X4600 M2 server running VMware ESX Server 3.5.0 hypervisor.) We also just set the record on the SPECweb2005 benchmark, measuring web server performance, with 45nm Quad-Core AMD Opteron processors in the four-socket 2RU x64 Sun Fire X4440 server.

However, both AMD and our OEM partners recognize that they are merely a component of the overall value equation. The days of saying that purchasing decisions can be simplified based on a single benchmark are long gone.

Benchmarks don’t always reflect real-world implementations but they have been accepted by and large by the industry as a good initial performance indicator. In fact, benchmark progression can even sometimes be interesting to track as multicore processing is crunching data at unprecedented speeds, resulting in some eye-popping results. AMD recognizes that there are always going to be applications that require the best raw performance. However, recent processor unit data from Mercury Research shows that high-end, performance processors are less than 10 percent of the market today.  This tells us that customers ultimately buy on more than just raw performance. They look at how a system is optimized for software, what level of energy is it going to consume, how scalable is the hardware, and in today’s economic environment, price-performance and TCO are more critical than ever.

Whether it is a DBMS or not, Forrester raises a really good point here, and one that – at a minimum – is worth discussing, regardless of if you agree or disagree. There are many factors beyond TPC performance  - reliability, manageabilty, security, performance to name a few – that impact a decision to buy and are spanning all enterprise computing environments. More specifically, how these factors impact the ongoing demands of your business (something we like to call the “workloads that matter”) is only going to become increasingly important.

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.

There are plenty of reasons that companies can give for keeping virtualization at an arm’s length instead of embracing it. In my conversations with customers, it’s difficult to find somebody that is not working with virtualization at some level.

But what keeps it from moving out of the lab and into production. Or, more succinctly, where is the mythical "line in the sand" that keeps people from moving applications. We know that things like file and print services, web services messaging and network infrastructure are all areas where customers are virtualizing. However there seems to be some "off limits" applications.

In some cases, these may be line of business applications where the application vendor specifically calls out that they will not support the application in a virtualized environment. Typically this has more to do with their own reluctance to support it than the fact that it won’t run on a virtual machine.

However, one line in the sand is performance. How many times have you heard someone say "I’m not willing to take the performance hit to run this application virtualized, I need the performance of a physical server"?

Well, that excuse is getting harder and harder to accept as the performance of a virtualized environment keeps getting closer and closer to the physical performance.

As a matter of fact, this week VMware released a new performance benchmark that shows web and Java services running faster on an HP DL585 G5 server (which is AMD Opteron processor-based, of course) than the performance of the same applications running "bare metal" – directly on a physical system. Under VMware ESX 3.5 the performance just edges out the previous benchmark by a hair.

Virtualized applications beating the same applications on physical servers? Is the end of the world as we know it? To some degree, yes, but in a good way. We’re seeing the beginning of a new era, where virtualization becomes the norm for just about any workload, and the differences between the physical and virtual worlds become more blurred. By the way you can attribute this success to features like AMD-V Rapid Virtualization Indexing (RVI) and VMware’s optimized use of this technology.

Does this mean that all applications should be expected to run at native speeds in a virtualized environment? No, but more and more, that gap is quickly closing. We’re headed in that direction, in our quest for the holy grail of virtualization.

It’s going to be an interesting year, King Arthur would want a ring side seat for this one.

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.