Fujitsu has announced the global availability of the PRIMEHPC FX10 supercomputer, which is capable of scaling to a top theoretical processing performance of 23.2 petaflops (PFLOPS).

Combining high performance, scalability, as well as reliability with energy efficiency, PRIMEHPC FX10 further builds upon the supercomputer technology that the company employed in the K computer. The latter managed to achieve the world’s top-ranked performance in June 2011, as it was capable of performing over eight quadrillion calculations per second (PFLOPS).

All of the PRIMEHPC FX10 supercomputer’s components, from processors to middleware, have been developed by Fujitsu, thereby delivering high levels of reliability and operability. The system can be scaled to meet customer needs, up to a 1024 rack configuration achieving a super-high speed of 23.2 PFLOPS.

Fujitsu stated that by leveraging the new system, companies will be possible to address societal challenges such as new drug development, disaster prevention, disaster mitigation, as well as other measures to bring about a “safe and secure society”.

Researchers will be able to pursue cutting-edge research, the likes of enabling the development and manufacturing of new materials without the need to make prototypes, which will assist companies in enhancing their competitive edge. Shipping of the PRIMEHPC FX10 kickss off in January 2012 with the company aiming to ship 50 systems over the next three years. No pricing info is available yet.

 

Besides unveiling the PRIMEHPC FX10 this week, Fujitsu along with RIKEN also revealed last week that their co-developed K computer has now achieved a LINPACK benchmark performance of 10.51 petaflops (10.51 quadrillion floating point operations per second), compared to the 8.774 petaflops as measured in June.