Running multiple Unix environments across a range of locations adds increased complexity and cost to the IT environment. I came across an interesting case study and wanted to highlight some of the key findings

YPF SAis the largest company in Argentina operating in the Oil and Gas industry. The company has 29 gas plants around Argentina running different Unix environments such as HP-UX, AIX and Solaris.

YPF SA consolidated their SAP ERP and Oracle DB environment from multiple Unix environments to Red Hat Enterprise Linux 5 with integrated virtualization running on Intel Xeon based platforms from IBM System X

Some of the key findings to highlight

• Key requirement from Unix Administration Team that "migrating from old RISC/Unix and proprietary servers to open and flexible platforms would pose no risk to the reliability, availability and performance of the systems"
• Positive impact on cost and performance; Lowered costs, simplified management and increased compatibility
• Reduction in costs especially when compared to license costs of RISC based platforms
• Increased performance and availability drove decision to scale with RHEL and Xeon
• Ability to leverage Redhat integrated virtualization. Free up internal hardware and technical resources for other projects

I guess the combination of Redhat and Intel deliver the business results that customers are seeking. What do you think?

Looks like the Intel® Xeon® processor 5500 series is making lots of noise in HPC.  The QPI and integrated memory controller are really providing the boost necessary to make it an all around performance leader for HPC applications.  With all this performance why did Intel add a third memory channel?

The third memory channel enables the platform to support a boat load of memory.  Matter-of-fact, up to 192GB can be supported in a two socket configuration.  It wasn’t too long ago when only 32GB was supported in a dual socket configuration.  By having the ability to support so much memory you can now meet the needs of almost every HPC application.  The 5500 series is intended for all server markets, but let’s face it, with the design changes Intel made with the new architecture the server segment gaining the most benefit appears to be HPC. 

It seemed like yesterday when the only way to have access to large memory configurations was through expensive, proprietary SMP systems.  The HPC market for large SMP systems is still out there but it is shrinking…fast.  Today, we are clustering low cost solutions to create some of the most powerful systems in the world.  Standard components are leading to lower and lower system costs, delivering a price/performance advantage alternative solutions cannot meet.

Now that a single dual socket node can support up to 192GB’s it is important to understand how to get there.  First, to enable 192GB you need 16GB DIMMs x 12 memory slots.  There will be a premium for a 16GB DIMM.  Knowing the options and determining the best, most cost effective solution is going to be dependent upon your environment.  When a large memory node is required, do you purchase the 16GB DIMM’s or go up to a Multi-socket solution?  If I decide to scale back on the memory (use 4GB or 8GB DIMMs instead of 16GB DIMMs) what is the performance impact to my application?  If I am cost sensitive, will the lower cost outweigh the lack of performance?  Can I use SSD’s (Solid State Disk drives) to compensate for any performance loss due to lower memory capacity?  There are many questions to think about when deciding the right configuration for your application and environment and I certainly can’t answer them here.

Let’s not forget the third memory channel enables a different set of optimal memory configurations.  Think x3 when deciding on how much memory to install into your node; 12GB, 24GB, 48GB, etc.  What happens when you don’t use an optimal configuration?  Well it depends, in most cases the impact is minimal, but let me add a bit of context around minimal:

·         Low bandwidth sensitivity (more dependent upon the processor for performance)

–        E.g. Monte Carlo, Black-Scholes (financial modeling), BLAST (bioinformatics), AMBER (molecular dynamics)

–        Expect less than a 2% difference between memory configurations*

Ÿ  Medium bandwidth sensitivity (somewhat balanced between memory and CPU usage)

–        E.g. CFD, Explicit FEA, Implicit FEA (with robust I/O system)

–        Expect approx. 5% degradation for non-optimal symmetrical configurations*

Ÿ  High bandwidth sensitivity (high access to the system memory)

–        E.g. WRF (weather), POP (climate), MILC (physics), Reservoir Simulation

–        Expect approx. 10% degradation for non-optimal symmetrical configurations*

The results are interesting.  In all three cases above, the degraded performance is always better than the performance you would have with only two memory channels.

When you hear about performance impact of non-optimal memory you can see by the examples above, it is application dependent and will not have a severe impact on your overall system performance.   

The Intel Xeon processor 5500 series offers support for huge memory nodes with the addition of the third memory channel.  Memory configurations in multiples of three are ideal, but if you decide to stay with a power of two configuration the performance should still exceed that of a solution based upon only two memory channels.

*Based upon Intel internal measurements

I was thinking about what to write in my next blog and what I could share beyond what I have written previously about Intel Vs RISC in terms of TCO, performance and the customers that are choosing to move.

Luckily I didn't have to think too long on a Friday morning as a a topic came to mind instantly. There are numerous articles flying around this morning that picked up on the Oracle comments yesterday about how SPARC based systems compare to Intel. Thanks for providing me with an appropriate topic.

So in case you missed it, there was a question and answer session with Larry Ellison. When asked about SPARC, this was the reply "SPARC is much more energy efficient than Intel while delivering the same performance on a per socket basis. This is not a green issue, its an economic issue. Today, database centers are paying as much for electricity to run their computers as they pay to buy computers. SPARC machines are much less expensive to run than Intel machines"

1) SPARC more energy efficient than Intel?  Seriously, in what parallel universe does that exists?

SUN continues to use watts per thread as measure of energy efficiency. The recognized industry standard benchmark for measuring energy efficiency is SPECpowerand I don't see any SPARC based results in the 91 results published. The absence of a result certainly says something very clear to me - no story.

These UltraSPARCT2+ systems get loaded with a lot of memory to deliver the their results, so when you look at overall system power (what people care about) they are not as energy efficient as Intel based systems.

SPECpower is effectively based of SPECJbb-2005 so another way of loking at this is to look at the SPECJbb-2005 results for a 4 socket UltraSPARcT2+ system and a Xeon 7400 system. The 4s UltraSPARCT2+ delivers 693k BOPs while Xeon 7400 is 532kBOPs. So you conclude that SPARC is better than Xeon?. That would be the wrong conclusion

UltraSPARCT2+ system would consume 1525 watts Vs Xeon 7400 at 816 watts. If you look at BOPs per watt (another way of looking at energy efficiency and performance) then you would see that Xeon 7400 is 43% more energy efficient. Doing a similar comparison with Xeon 5400 (I haven't even talked about our latest Xeon 5500, Nehalem) would be up to 77% more efficient than UltraSPARCT2+.

And lastly before I forget to mention the 4s UltraSPARCT2+ had 128GB memory and costs over $150,000for the system, while Xeon 7400 based system had 64GB memory and costs around $32,000.

2) SPARC deliver same performance on a per socket basis?

2S Xeon 5500 has performance leadership over 2S UltaSPARCT2+ across a wide range of benchmarks. Up to 70% more performance and up to 60% lower system cost. 4S Xeon 7400 has price/performance leadership over 4S UltraSPARCT2+, UltraSPARCT2+ results achieved with system loaded with lots of memory that drives the cost up to 3-4Xthat of Xeon 7400 system

3) SPARC machine are less expensive to run?. I can't for the life of me work this one out!.

Hardware systems based on Intel have leading price/performance (read cheaper), lower energy needs (so electrivity bill lower) and any software product with a license per core strcuture is less expensive on Xeon system than an 8 core UltraSPARcT2+ (which also has higher multipler per core)

That's all for now folks. I just wanted to share some data on why I know that SPARC machines are much MORE expensive to run than Intel machines

OK, so we launched the Xeon 5500 processor based servers and workstations a couple of weeks ago. While I don’t have direct quotes of support from Brit, Miley, Susan or any country presidents who have signed economic stimulus into law I am pretty confident that if they were ever actually considering purchasing a server or workstation they would come to the conclusion that the new Xeon 5500 platforms would be their best choice.

I had the privilege of being at one of the thirty seven different worldwide Xeon 5500 launch events. I was on Wall Street and attended the NASDAQ launch event on March 31^st. Based on which data source estimate you look at Financial Services as a whole represents about 20% of the worldwide market for servers. It was also evident when meeting with customers in the NYC area that they are passionate about performance and power consumption. Most of them had received pre-production seed systems and had already done extensive testing prior to this launch event. I have been in Intel’s Server Platform Group for over a decade now and I have never seen so much enthusiasm for a product launch.

I won’t rehash the performance benchmarks and performance per watt data. There are many benchmarks, blogs and press articles doing that. What I took away from the conversations was a feeling of optimism from the end users I spoke to. Some people felt that these new products would be what it takes for them to deliver solutions that would give them a performance advantage over their competition. In few markets does that pay off more, and translate almost directly to the bottom line, than in Financial Services. Others felt that these systems would help them continue to add to their existing datacenters without having the need to build a new one. This was due to the performance per watt improvements and the end users ability to replace many old servers and workstations with a few new ones.

Lastly, I think human nature being what it is we are seeing that IT professionals want to work on cool new projects. These Xeon 5500 servers and workstations represent a shiny new toy that IT professionals can use to have a material impact on the bottom lines of their companies. To some degree the same applies to virtualization in that it is disruptive and provides a new cost effective way to deliver legacy solutions and also enables flexibility for future growth. The IT folks that I have met who familiarize themselves with virtualization, new hardware and advanced management techniques (power, systems, virtualization) generally are viewed internal to their companies as leaders with visionary capabilities.

As we all work through this economic morass I am hopeful that with new technology introductions, and a relentless focus on efficiency, we will all emerge with a greater level of capability and a higher degree of flexibility. I also believe IT will emerge as a key asset of differentiation for companies from Wall Street to Main Street and this will place an even greater burden on delivering solutions to meet those unique needs.

What do you think?

Shannon

shannon.poulin@intel.com

With the Nehalem architecture-based processor server/workstation launch just around the corner, customers are demonstrating how quickly they can take advantage of the performance afforded to them by our newest processor. One recent example was a Philips* CT demonstration of a beating heart at the major European IT show, CeBit*.  According to the Philips demonstration, they were able to render the human heart twice as fast using our upcoming Nehalem workstation processors as compared to the previous generation Intel® Xeon® processor 54xx series.  Check out the beating heart demonstration video in this link using our Nehalem architecture-based workstation processor.

For those of us with no medical background,  3D imaging is a tool enabling doctors to visualize the human body without invasive tools.  The patient is scanned, data is acquired, and a 3D model is assembled and they are able to show what going on in the human body without touching it.  CT tools are able to produce thousand of pictures or slices per second.  This results in large datasets that take time to process.  Software running on a server or workstation processes this vast amount of data to generate detailed 3D images and then can be interpreted by medical staff.   The primary challenge is managing large datasets generated by large volume acquisitions while speeding time to diagnosis.

The heart is a particularly challenging to visualize using CT scanning.  It is a very fast moving organ, with little control over its movement because is involuntary, and the heart needs to be frozen in time to get accurate anatomical picture.  Another challenge for volume rendering is high level image quality necessary so that anatomical structures of the heart can be depicted in an accurate way.

One interesting aspect of Philips CT solution is that image rendering takes place in the in the CPU which means that the performance of their solution is not restricted to by the memory available on a graphics card and is not slowed down by transfer of data between the CPU and the graphics card.  The Philips’ rendering software is multi-threaded and is able to take advantage of Intel advances in multi-threading /multi-core processing technology and software optimization tools for best performance improvements.

I believe Philips’ demonstration is just one example of how Nehalem architecture-based processors will provide meaningful advances in 3D visualization, not just in medical fields, but other areas such as manufacturing and digital content creation.

Jimmy Leon

*Other names and brands may be claimed as the property of others.

Today, I met with Tim Denney (a summer intern here at Intel) who is working for our performance analysis team. Tim told me that he had built a tool allowing intel employees to compare performance of certain SPEC published benchmarks (www.spec.org) across a variety of processors.

Tim demonstrated this analysis tool that searches all the integer and floating point publications on www.spec.org across a range of architectures (Intel, AMD, UltraSPARC, Power). You can input different processors and then the tool returns the published results available and a simple graphical display of the best published results for the processors chosen.

After meeting with Tim, I thought about the numerous "Ask an Expert" questions I’ve received on OpenPort in the last 6-9 months where people have asked me where and how they can compare performance across a variety of processors (dual core to quad core, different speeds, 1S to 2S to 4S, etc).

In took me about a nano-second to realize that your input would be really helpful in developing an improved user interface. So here is your chance. I encourage you to try this performance comparison tool and respond back with your ideas on how we can improve the tool and user interface. I can’t guarantee that we can implement every suggestion, however, I do guarantee that we will listen.

So … How would you like your benchmark?

During my blog post last week titled "[processors-cpus-cores-arent-they-all-the-same|p-10936]", I got a request to talk more about server terminology, going beyond the CPU. So here we go.

The processor does all your computational calculations. The chipset is attached to the processor and manages information and data flow from the processor to the other system components like memory and other I/O (input / output) devices. If the processor is the "brain", then the chipset is the "heart". Memory and I/O devices are like "arms" and "legs" - you need them all working together. The term chipset, memory controller, and memory controller hub (MCH) are often used interchangeably

At Intel, we refer to the platform as the combination of all of these devices that comprise a server. From a hardware perspective, I see the following terms used interchangeably: platform, solution, system, server, workstation, and there are probably others I'm missing. However, I have also seen platform refer to the software stack, as well as the complete hardware and software solution together.

Another term that you may also here is form factor. Form factor refers to the size and shape of the final system you would buy from a manufacturer. The most common server form factors are rack mount, pedestal, towers and blades.

Today's workstation with (2) Intel® Xeon® 5400 Series processors transforms a workstation from a simple design terminal into a powerful engineering tool that helps users potentially compress the time between an idea and a product. At Intel we call that "working differently". In the manufacturing vertical market it may also be called:

• digital prototyping,

• analysis driven design or

• simulation based product design.

No matter what you call it, these new ways of working help manufacturers virtually explore complete products before they are built-so they can create, validate, optimize, and manage designs from the conceptual design phase through the manufacturing process.

Digital prototyping processes may also require that you also rethink your workstation deployment strategy; moving from single processor workstations, to two (2) Intel Xeon 5400 processor based workstations with 8 computational cores and up to 100 peak gigaflops of floating point performance. This compute capacity coupled with the robust visualization environment enabled by two (2) PCI Gen 2 graphics adapters changes would be workstations into workstation supercomputers and enables engineers and designers to concurrently perform traditional CAD design as well moderate size analysis (e.g. over 5M degrees of freedom finite element modeling jobs or up to 10M cell fluid dynamic simulations).

This combination (CAD and Analysis) can help organization optimize CAD parts or assemblies under a wide range of physical scenarios including mechanical and thermal effects. Net result is workstation supercomputers based on Intel® Xeon® 5400 Series processor can help to bring higher quality or more innovative ideas to markets faster than ever before.