@techreport{oai:jaxa.repo.nii.ac.jp:00045367,
 author = {三好, 甫 and MIYOSHI, Hajime},
 month = {May},
 note = {計算空気力学(CFD)の研究を推進し,その成果を航空機および航空宇宙機の研究開発に役立たせる為には,CFDプログラムの処理能力がFujitsu VP400の100倍以上のCFD専用の計算機-超高速数値風洞(UHSNWT)をここ2～3年のうちに,更にこれを10倍以上上廻るUHSNWTを1990年代末に開発することが是非とも必要となる。報告はこのUHSNWTが備えるべき要件について,開発・運転コスト,信頼性,CFD計算法に対する適合性,運用環境等の視点から論ずる。同時に報告はこれ等の要件を満足するUHSNWTの構想を 1.これ迄のベクトル計算機の使用経験 2.種々のベクトル計算機モデルのベクトル処理に対するソフトウェアシミュレーション 3.LSI技術の将来の発展動向 に基づいて述べる。報告はVP400の100倍以上の性能のUHSNWTはクロスバーネットワークを採用した分散主記憶型並列計算機により実現できることを結論付けている。, In order to promote CFD (computational fluid dynamics) research activities and effectively apply their results in the research and development of future aircraft and space planes, it is necessary to develop within the next two or three years a CFD-oriented computer (ultra high-speed numerical wind tunnel/UHSNWT) whose CFD processing speed is more than 100 times higher than the currently used Fujitsu VP400, and also to subsequently develop a computer more than 1000 times faster by the end of 1990's. The requirements for the UHSNWT are discussed from a perspective of development and operation costs, reliability, affinity with CFD programs, and operation environment. In addition, a National Aerospace Laboratory (NAL) UHSNWT initiative is proposed based on the folowing: 1.Vector computer operational 2.Program processing software simulation for several vector computr configurations 3.Future trend forecasts of Large-Scala Imtegrated Circuit (LSI) technology It is concluded that developing the UHSNWT with a performance of more than 100 times higher than the VP400 is feasible using a parallel computer having a distributed memory and crossbar network., 資料番号: NALTR1108000, レポート番号: NAL TR-1108},
 title = {航技研超高速数値風洞(UHSNWT)の構想-第二期数値シミュレータ計画-},
 year = {1991}
}