Cray and IBM will be vying for the top spots as they deliver their 100
teraflops Red Storm and ASCI Purple parallel clusters by early 2005, and IBM's Blue Gene/L super, which will be rated at about 360
teraflops, will very likely hold the top spot for as long as Earth Simulator seems to be.
Main Configuration of the New Supercomputer System PRIMEHPC FX10 Compute Nodes Number of racks 8 Nodes (CPUs) 768 (768) Theoretical Peak Performance 181.6
teraflops Memory Capacity 24TB Interconnect Tofu Interconnect (6D Mesh/Torus) Log-in Nodes Management Servers 22 PRIMERGY RX300S7 servers Management servers shared discs 2 ETERNUS DX80S2 storage units Local Files 25 ETERNUS DX80S2 storage units 345.6TB Shared Files 17 ETERNUS DX80S2 storage units 230.4TB File System FEFS
Department of Energy to drive supercomputing technology from the hundreds of gigaflops to the hundreds of
teraflops level in the late 1990s and early 2000s.
The 100
teraflop ASCI Purple system will be powered by 12,544 POWER5 microprocessors, IBM's next generation microprocessor.
The board can achieve
teraflops performance using 800 stream processing cores and has a MRSP of USD199.
The AIST 11
teraflops cluster deal in Japan is IBM's first big deal selling Opteron machines, and IBM believes that the value of the Opteron machines over competing products is well illustrated in the deal.
At position five, this is the largest Linux cluster ever recorded with a very impressive Linpack performance of 5.7
teraFLOPS," said Erich Strohmaier, computer scientist at NERSC/Lawrence Berkeley National Laboratory and co-founder of the TOP 500 list.
A GPU-based supercomputer, SAGA-220 stands for Supercomputer for Aerospace with GPU Architecture-220
TeraFLOPS. It is made up of 400 Nvidia Tesla 2070 workstation GPUs, and 400 Intel Xeon quad-core CPUs.
(And in tongue and cheek fashion, the moniker also suggest that one of the perquisites of being the largest IT supplier in the world that will soon be able to demonstrate machines in the 100
teraflops range after a decade of hard work is being a shoe-in for this DARPA award.) IBM isn't saying exactly what PERCS is, except that it is based on its Power architecture and that it will have a new hardware-software design that will enable IBM to hit the multi-petaflops performance level while maintaining compatibility with existing HPC applications.
Along with six
teraflops of processing power, the TCS features 3.0 terabytes of memory, high-bandwidth, low-latency interconnections and remarkable capabilities for large-scale data handling, including the ability to write the entire memory to disk in under 40 seconds.
Blue Gene/L is expected to operate at about 200
teraflops (200 trillion operations per second) which is larger than the total computing power of the top 500 supercomputers in the world today.