Intel Xeon processor use allows for over 1 million cores
Cray has launched its new supercomputing creation, the Cray XC30, codenamed Cascade. The new system combines Intel Xeon processors with the Aries interconnect, new cooling and power technologies and Cray's integrated software environment, to create a supercomputer capable of workloads higher than 100 petaflops.
Intel acquires Cray IP and staff for its HPC arm
Intel has entered into an agreement with Cray to acquire IP and staff related to its high-performance computing (HPC) interconnect program. According to Intel, the Cray interconnect team is responsible for the Gemini interconnect and the upcoming Aries interconnect. The Aries interconnect will form part of Cray’s next-gen supercomputer, codenamed Cascade, that will be powered by Intel’s Xeon processors.
Tesla GPUs could deliver up to 20 petaflops
The Oak Ridge National Laboratory will use the parallel processing capability of the NVIDIA Tesla M2090 GPU in a new supercomputer, a Cray XK6 nicknamed "Titan." The new supercomputer could deliver over 20 petaflops, making it more than twice as fast as the most powerful supercomputer today, the Fujitsu K supercomputer. Titan will also be three times more energy efficient.
iPad 2 benches as fast as Cray 2 from 1985
Apple's iPad 2 is as fast as a Cray 2 supercomputer from a quarter-century ago, Top 500 and Linpack co-manager Dr. Jack Dongarra said late Monday. At 1.5 to 1.65 gigaflops of computing power, Apple's tablet would compete with the eight-processor, 1985-era system despite being just a sliver of the size. Where the Cray 2 was the size of a washing machine, the NYT said, the iPad 2 can manage the same performance in the space of a large notepad.
Tianhe-1A supercomptuer fastest at 2.5 petaflops
A new Chinese supercomputer, the Tianhe-1A was revealed today at HPC 2010 in China has set a new performance benchmark, at 2.507 petaflops. In doing so, it has become the fastest supercomputer in the world, taking the title from the US-based Cray XT5, which managed a performance of 1.756 petaflops. The Tianhe-1A uses 7,168 NVIDIA Tesla M2050 GPUs and 14,336 CPUs, which combined lets it calculate much more in parallel.
Xeon 7500 can handle 1TB memory, 256 chips
Intel this afternoon sought to cement its grip on the very high end of computers with its first eight-core processor, the Xeon 7500. The two extra cores give it even more performance in highly parallel situations -- up to 16 program threads at once with Hyperthreading -- and the design itself is unique at Intel in the sheer amount of scaling compared to the outgoing 7400. A four-processor server can handle as much as 1TB of memory, and a single computer can include as many as 256 discrete processors.
Cray XT5 supercomputer beats out IBM Roadrunner
IBM's Roadrunner supercomputer has been dethroned from the TOP500 list in terms of computing performance by the Cray XT5 supercomputer, nicknamed Jaguar. The XT5 uses AMD Opteron cores and posted up a 1.75 petaflop/s speed in the Linpack test, outpacing the Roadrunner's 1 petaflop/s performance.
Intel and Cray Team
Early supercomputer developer Cray said today that it was working with Intel for mutual help on advancing supercomputers. The teamwork will see Cray help Intel develop the technology for clusters as well as to improve the in-processor technology, such as newer generations of multi-core processors. In return, Cray will make its first use Intel's processors for its own supercomputers, replacing AMD Opterons and more specialized supercomputer chips.