December 02, 2010
This week, John Fruehe, AMD’s Director of Product Marketing for Server, Embedded and Firestream Products was asked if the company had set its sights on a special brand of Bobcat-based multi-core CPUs designed with cloud datacenters in mind.
His first response to the question was that, “It would be irresponsible for us not to consider every piece of silicon when determining what we are going to offer server customers. If we have what customers need and we can profitably bring that product to market with our OEM partners, then it makes sense to productize it.”
He recognizes, however, that “beyond power consumption, cloud customers want two other things—true server features and lower management costs… The Bobcat core, although an extremely efficient core, was designed for low power client solutions, so think like ECC memory and support for server Oss (though the AMD SR5600 series chipset) have not been figured into the product at this time.”
So as clouds grow and customers want to scale out rapidly, the Bobcat core, just like Atom, which is based on a single-processor system means that you get ultra low power but you don’t get the core density that is required in cloud environments, which certainly complicates this possibility.
Fruehe admits that there is not “100% clarity at the time about the needs of the cloud market because so much of it is evolving” but notes that AMD is getting serious making sure they have a viable product when they’ve…well, figured out what that product needs to be.
He says they will continue looking closely at the possibilities of both Bobcat and Bulldozer as core design points for upcoming system on chip products for cloud servers.
As Anton Shilov at xBit Laboratories noted, “while Bobcat does not have visible advantages compared to already available Opteron CPUs, AMD will continue to evaluate the micro architecture as a potential solution for cloud datacenters that demand the maximum number of cores.”
Shilov went on to note that it is clear that Bobcat processors “will provide lower idle power compared to AMD Opteron chips based on K10.5 or Bulldozer micro-architectures. But the big question is whether Bobcat chips will actually be able to work fast enough to provide decent performance. If those chips do not provide enough speed, then AMD’s clients will have to install more of them, which will mean that any 2W-3W per core savings may never be evident due to a high number of chips.”
Full story at AMD
The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
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.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.