AT&T makes cloud-related announcements at the annual AT&T Developer Summit in Las Vegas this week.
While the IaaS market has evolved swiftly, interoperability concerns overwhelm the ability to get onboard with some PaaS offerings.
Dr. Junlei Jiang discusses the nature of adotion of grid computing versus cloud computing, noting differences in the founding and subsequent evolution of both paradigms. While both share the same vision, the processes behind them vary–as do the adoption curves. Dr. Jiang presents an overivew of the main differences, pointing out the process of computing model natural selection that he sees happening.
There is a growing feeling that merely taking the latest processor offerings from Intel, AMD or IBM will not get us to exascale in a reasonable time frame, cost budget, and power constraint. One avenue to explore is designing and building more specialized systems, aimed at the types of problems seen in HPC, or at least at the problems seen in some important subset of HPC. Of course, such a strategy loses the advantages we’ve enjoyed over the past two decades of commoditization in HPC; however, a more special purpose design may be wise, or necessary.
Moving applications to the cloud can create security issues but for many developers, there is not time or in-house expertise to help handle the shift. Organizations could be left with software that is not ready to perform securely in a virtualized environment.
Intel Corp has released Parallel Studio 2011, a set of four tools designed to mainstream software development on multicore x86 architectures. The update folds in a number of parallel programming technologies that the company has acquired or developed independently over the past few years, including the Cilk Arts and RapidMind technologies, and Intel’s own Ct data parallel language framework.
In the realm of HPC as well as for developers and enterprises, the cloud offers a range of possibilites, including the ability to create applications that would otherwise be prohibitive due to infrastructure costs for developers. There is promise on the horizon for innovations that will allow more developers to access HPC hardware and services.
A new, simplified language for programming in cloud environments called “Bloom” is set for release later this year. An interview with one of Bloom’s creators, Joseph Hellerstein of U.C. Berkeley, explains the practical elements.
The company has provided a public API for using its service, but users will have to pay fees.