Numerical Wind Tunnel (Japan)

Numerical Wind Tunnel (数値風洞) was an early implementation of the vector parallel architecture developed in a joint project between National Aerospace Laboratory of Japan and Fujitsu. It was the first supercomputer with a sustained performance of close to 100 Gflop/s for a wide range of fluid dynamics application programs. It stood out at the top of the TOP500 during 1993-1996. With 140 cores, the Numerical Wind Tunnel reached a Rmax^[1] of 124.0 GFlop/s and a Rpeak^[2] of 235.8 GFlop/s in November 1993.^[3]

It consisted of parallel connected 166 vector processors with a gate delay as low as 60 ps in the Ga-As chips. The resulting cycle time was 9.5 ns. The processor had 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 was equipped with 256 Megabytes of central memory.^[4][5]

References

1. Rmax – The highest score measured using the LINPACK benchmark suite. This is the number that is used to rank the computers. Measured in quadrillions of floating point operations per second, i.e. petaflops.
2. Rpeak – This is the theoretical peak performance of the system. Measured in Pflops.
3. "Sublist Generator". top500.org. Retrieved 21 November 2012.
4. TOP500 Annual Report 1994.
5. N. Hirose and M. Fukuda (1997). Numerical Wind Tunnel (NWT) and CFD Research at National Aerospace Laboratory. Proceedings of HPC-Asia '97. IEEE Computer Society. doi:10.1109/HPC.1997.592130.