next up previous contents
Next: Japanese Procurements Up: Scalable Vector Parallel Previous: Market Impact

Numerical Wind Tunnel

As mentioned in the introduction, an early implementation of the vector parallel architecture called the Numeric Wind Tunnel, was developed together with NAL. This early version of the VPP500 (with 140 processors) is today the fastest supercomputer in the world and stands out at the top of the TOP500 due to a Rmax value that is quite a bit higher than the Intel XP/S140 which is this year's runner-up. By using the most advanced hardware technology available the processor chips have a gate delay as low as 60 ps in the Ga-As chips. The resulting cycle time is 9.5 ns. The processor has four independent pipelines each capable of executing two Multiply-Add instructions in parallel resulting in a peak speed of 1.7 Gflop/s per processor. Each processor board is equipped with 256 Megabytes of central memory. The Numerical Wind Tunnel at the Japanese National Aerospace Laboratory is the first Supercomputer with a sustained performance of close to 100 Gflop/s for a wide range of fluid dynamics application programs. NAL has developed and demonstrated CFD codes with a performance of more than 100 Gflop/s. A very impressive example is the direct simulation of isotropical turbulence with 512x512x512 Fourier components. The Fourier transform executes at more than 60 Gflop/s on 128 processors. The Numerical Wind Tunnel was developed in a joint project between NAL and Fujitsu and is currently the most powerful computer running aerospace applications.
Tue Nov 14 15:13:46 PST 1995