Visit additional Tabor Communication Publications
August 28, 2008
Cray, known for its power and packaging prowess since 1976, when Seymour Cray bent the Cray-1 into a "C" shape, is unveiling a petascale-era cooling technology it says is more than 10 times as efficient as same-size water coils. Cray CTO Steve Scott discusses this innovation and the company that was green before green was cool.
HPCwire: What is Cray's new cooling technology?
Scott: We call it ECOphlex technology. The "phlex" part refers to multiple things. First, the cabinet infrastructure can use either Cray’s high-efficiency vertical air cooling or our new phase change cooling technology that converts an inert refrigerant, R134a, from a liquid to a gas. The other flexibility is that the liquid-cooled systems can use various chilled or unchilled datacenter water temperatures to pull heat from the R134a subsystem and to adapt to changing datacenter conditions. The phase change coil is more than 10 times as efficient at removing heat from the compute cabinets as a water coil of similar size, so the in-cabinet cooling system is much smaller and lighter than it would be with water coils. Water is only used in external heat-exchange units.
The ECOphlex technology is the first of the Cray “Baker” technologies we're introducing. We'll start using it when we ship the Cray XT5 petascale system to Oak Ridge later this year. After that, all Cray XT5 systems will ship with ECOphlex capability in the new high-efficiency cabinet.
HPCwire: With system sizes and densities increasing, liquid cooling is making headlines as if it were something new, but Cray's been at this a long time.
Scott: We've implemented six different types of liquid cooling since 1976, along with multiple air-cooled implementations. The Cray-1 used Freon with copper cold plates. Then we moved to fluorinert immersion, captive fluorinert cold plates, water cap cooling on the MTA-2, spray evaporative cooling on the X1, a water-cooled radiator on the X2, and the phase change liquid cooling on the XT5 series. We’ve gained a lot of experience with what forms of liquid cooling work best under various constraints.
HPCwire: How does your phase change cooling compare with the typical chilled water scenario datacenters use today?
Scott: Typically today, the computers put the heat into the air, and then the CRAC [Computer Room Air Conditioner] units around the room periphery have to remove the heat from the air and put it into the chilled water. This method is very inefficient. For a petascale system the area taken up by the CRAC units could exceed the computer footprint, and this would also waste a lot of power. Cray’s new cooling scheme puts the heat into a refrigerant stream inside the rack, and then sends it to an Extreme Density Pumping unit that efficiently transfers the heat to the building chilled water. So, you still use chilled water, but it's much less extensive and it doesn't intrude on the computational components of the system.
ECOphlex technology is designed to be "room air neutral" within plus or minus 10%. We’ve demonstrated the ability to remove up to 100 kilowatts from a single cabinet. A typical installation would be configured with just a few CRAC units for humidity control or to deal with some leaking from other devices. The ECOphlex technology requires only a small temperature delta in the water supply, so in cooler climates or where datacenters can run at warmer ambient room temperatures, there is the potential to completely eliminate the need for expensive water chillers.
Another advantage is that since ECOphlex uses an inert coolant, you don't have to worry about water leakage or condensation that could damage electronic components. As you know, this can be a severe problem with intrusive water-cooling technologies that bring the water-cooling close to heat-generating computer components.
HPCwire: HPC vendors have been working to advance system densities and power and cooling abilities since the start of the supercomputing era. What's changed lately?
Scott: Supercomputing began in an era of cheap electicity. When Seymour Cray bent the Cray-1 into a "C" shape and cooled it with Freon and copper cold plates, the goal was to improve performance. Today, when Cray and other HPC vendors improve densities and power and cooling technologies, it's not just to boost performance. It's also for environmental reasons. We're trying to help customers save on very expensive energy costs and facility space.
HPCwire: What about other approaches to reducing energy use and heat generation, such as using lower-power processors or accelerators?
Scott: There are two basic approaches. In the first, you drop the voltage and lower the frequency of individual processors, then compensate by using more processors in a system. Multi-core processors embody this approach to a moderate extent, and some special purpose designs have taken it even farther. The primary concern here is that this approach exacerbates the scaling problem. The memory wall gets worse, there's more memory contention, codes have to be more parallel, the communication-to-computation ratio gets worse, and you have to depend more on locality. This approach works well for highly localized, partitionable applications. The more you push this concept, however, the more potential power savings you have for certain codes, but the more special-purpose the machine becomes.
Another alternative is to design processors that have much lower control overhead and use more of their silicon area for performing computations. Streaming processors, vector processors and FPGAs are examples of this approach, which can result in much faster single processors for the right types of codes, and thus ease the requirement for greater scaling. This technique can be used to a lesser extent in traditional scalar microprocessors. SSE instructions, for example, are essentially vector instructions that can increase peak performance without a corresponding increase in control complexity. On top of all this, you can also implement adaptive power-management mechanisms to reduce power consumption by idling or voltage scaling selected blocks of logic in the processor. Microprocessor vendors have a big motive to reduce power consumption because it affects their whole market, not just the relatively small HPC segment.
HPCwire: So which techniques do you think hold the most promise?
Scott: I don't think there's one right answer. Ultimately, the important thing is matching the capabilities of the machine with the needs of the applications. The variety of applications calls for a variety of solutions, each optimized for the right system balance. This will lead to more performance efficiency and power efficiency. What you don't want to do is compromise application performance. In the end, it’s watts per sustained performance that matters, not watts per peak performance.
HPCwire: Are there any other important aspects of Green HPC?
Scott: Yes. Another really important dimension is equipment disposal, though this one doesn't get as much attention as power and cooling. In many cases, buying a new supercomputer today requires a forklift upgrade of the cabinets. This is true of some of the most efficient systems on the Green500 list, which just looks at kilowatts per flop. Recycling cabinets every two to three years, or trucking them to a landfill, isn't very environmentally friendly and can cost extra money for the customer on both the initial system purchase and the disposal. Cray has been using multi-generational cabinets with our XT series, and many of our customers have already gone through two or three processor upgrades in the same cabinets. Our new high-efficiency cabinet continues this practice.
Another important factor is power efficiency inside the cabinet. Since the Cray XT3, we've been using a single axial turbofan in our cabinets. It's a lot more efficient than a large collection of less-powerful fans and the maintenance interval is seven-and-a-half years, versus a few months with the small fans.
We're also using AC/DC power rectification with a 90%-plus efficiency rating. There's much less power loss with these power supplies, and they can support higher-power processors.
HPCwire: Any parting thoughts?
Scott: Just that as the HPC community begins to enter the petascale computing era, the challenge of cooling large-scale systems and paying for the energy costs is escalating very quickly. Cray and every other vendor serving this market will need to push "green" innovation hard to stay ahead of this curve for customers. We're fortunate at Cray to have a long history of power, cooling and packaging innovation, and we're committed to do what it takes, in cooling and other areas, to enable our customers to get to sustained petascale computing capabilites.
Jun 19, 2013 |
Supercomputer architectures have evolved considerably over the last 20 years, particularly in the number of processors that are linked together. One aspect of HPC architecture that hasn't changed is the MPI programming model.
Jun 18, 2013 |
The world's largest supercomputers, like Tianhe-2, are great at traditional, compute-intensive HPC workloads, such as simulating atomic decay or modeling tornados. But data-intensive applications--such as mining big data sets for connections--is a different sort of workload, and runs best on a different sort of computer.
Jun 18, 2013 |
Researchers are finding innovative uses for Gordon, the 285 teraflop supercomputer housed at the San Diego Supercomputer Center (SDSC) that has a unique Flash-based storage system. Since going online, researchers have put the incredibly fast I/O to use on a wide variety of workloads, ranging from chemistry to political science.
Jun 17, 2013 |
The advent of low-power mobile processors and cloud delivery models is changing the economics of computing. But just as an economy car is good at different things than a full size truck, an HPC workload still has certain computing demands that neither the fastest smartphone nor the most elastic cloud cluster can fulfill.
Jun 14, 2013 |
For all the progress we've made in IT over the last 50 years, there's one area of life that has steadfastly eluded the grasp of computers: understanding human language. Now, researchers at the Texas Advanced Computing Center (TACC) are utilizing a Hadoop cluster on its Longhorn supercomputer to move the state of the art of language processing a little bit further.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?
Join our webinar to learn how IT managers can migrate to a more resilient, flexible and scalable solution that grows with the data center. Mellanox VMS is future-proof, efficient and brings significant CAPEX and OPEX savings. The VMS is available today.