Fujitsu announced that today it began shipping the computing units for Japan’s Next-Generation Supercomputer, nicknamed the “K computer”. The supercomputer is a central part of the High-Performance Computing Infrastructure (HPCI) initiative(2) led by Japan’s Ministry of Education, Culture, Sports, Science and Technology (MEXT), and is being jointly developed with RIKEN, an independent administrative institution under MEXT. The system is being delivered to the Kobe-based Advanced Institute for Computational Science of RIKEN and is expected to begin operations in autumn 2012 following the installation and tuning process.
The supercomputing system will be comprised of more than 800 computer racks, each installed with ultrafast CPUs, in a massively interconnected network, crystallizing Fujitsu’s leading-edge technologies for high performance and high reliability.
The Next-Generation Supercomputer will use the ultra-high-speed SPARC64™ VIIIfx processor developed by Fujitsu. Each of these processors possesses a computational performance of 128 gigaflops, and has a degree of reliability inherited from Fujitsu’s mainframe technology. The CPUs are also highly energy efficient, with a world-class processing power of 2.2 gigaflops per watt, a reduction of power consumption by 2/3 compared to previous levels.
The supercomputer will comprise of over 80,000 of these processors in an interconnected network (interconnect), utilizing the world’s first six-dimensional mesh-torus topology developed by Fujitsu. This will permit the system to be used more efficiently, as multiple processes can be flexibly allocated to groups of processors. If any part of the system goes down, the failed part can be isolated while overall processing continues, ensuring both high utilization rates and high availability.
The system also adopts water cooling methods to cool processors and other major heat emitters. This enables high mounting densities to be combined with improved component life and reduced failure rates.
The water-cooled chips are implemented in a 45 nanometer process and are expected to run at around 2GHz and burn at 58 watts, according to this IEEE reference from earlier this year when the Fujitsu team presented some specs. It is amazing that Fujitsu is not overclocking this puppy, especially considering Project K has water blocks on the processors and interconnects. A 3GHz clock speed would seem to be reasonable, but adding 50 per cent more performance would probably more than double the power consumption and heat dissipation of the processors. It is probably better to spread the heat out over more nodes to get to 10 petaflops and use up more data center real estate. As it is, at 58 watts per chip, the processors alone will consume 4.64 megawatts.
the building that will house the supercomputer
Fujitsu concedes now that it will take more than 80,000 processors to do the job. At a $4,000 a-piece volume street price (what a high-end Itanium or Xeon processor sells for), that would be $320m just for the processors. It is likely that the chips, even at these volumes, cost more than this.