Tatsuo Nogi

Learn More
A new parallel computer, ADENART (previously it was called ADENA,) for numerical applications has been developed. It is composed of 256 processing elements (:PEs) and interconnection networtcHXnet.) Each PE consists of a dedicated floating-point processor VLSI whose sustained performance is 10 MFLOPS, a communication controller VLSI and locally-distributed(More)
This paper reports NAS Parallel Benchmark results on parallel machine ADENART, which has been developed through collaboration between Kyoto University and Matsushita Electric Industrial Co.[KKT]. The results show that ADENART has comparable or two/three times power of Y-MP/1, though it is very compact as a deskside machine and consumes only about several(More)
This paper presents parallel algorithm and performance in three-dimensional device simulation on a super parallel computer : ADENA (Alternating Direction Editing Nexus Array) [ 1 ], [ 2 ]. The massively parallel computation of the splitting-up CG and BCG methods is easily obtained on the ADENA computer. To realize the physical device modeling as a practical(More)
This paper presents a new parallel algorithm and performance results of iterative solution methods for three-dimensional MOSFET simulation with Gummel's method. A splitting-up operator method is proposed for incomplete factorization of sparse matrices arising from semiconductor device equations, suitable for parallel computations. This method is combined(More)
  • 1