With the continuous increasing on the capability of high - performance parallel computer , how to use advanced development method and friendly development environment to take full advantage of high - performance of computer is one of the prominent problems to high - performance computer 隨著高性能并行巨型機(jī)的處理能力不斷提高,如何利用先進(jìn)的開發(fā)方法和友好的開發(fā)環(huán)境將這種巨大的處理能力變成實(shí)際有效的計(jì)算能力是并行巨型機(jī)面臨的關(guān)鍵問題之一。
The combination of scaling parallel computing technologies and numerical weather forecasting research results is of great significance to develop the high performance parallel computer application , to improve the numerical weather forecasting level , and to advance the parallel computer study 可擴(kuò)展并行計(jì)算技術(shù)與數(shù)值氣象領(lǐng)域研究成果相互滲透,對發(fā)展高性能并行計(jì)算機(jī)的應(yīng)用、提高數(shù)值氣象預(yù)報(bào)水平、促進(jìn)并行計(jì)算機(jī)的研制,具有極為重要的意義。
Therefore , the design of high performance interconnection network is important to the improvement of high performance parallel computer . the " effect of the bottle - neck " of electronic interconnection network limits operation speed , clock skew and interconnection bandwidth constraints , which can not be dealed with through technology 電互連網(wǎng)絡(luò)不僅存在著“瓶頸效應(yīng)” 、運(yùn)算速度有限、時鐘歪斜、互連帶寬受限等問題,而且從工藝上也是無法解決的。
Cellular element method is a new numerical computing method . in this method the integer analysis of structure is changed into a series of part analysis by using the idea of cellular automata . it may have a good future in the aspect of large structure because it hardly have any special request on the capability of computer . simultaneity , it can be developed into a high parallel arithmetic to suit for the request of parallel computer in the future 元胞單元法是新近出現(xiàn)的一種數(shù)值計(jì)算方法,它引用元胞自動機(jī)的思想將有限元對結(jié)構(gòu)的整體分析變成局域求解,對計(jì)算機(jī)容量要求低,在大型復(fù)雜結(jié)構(gòu)的計(jì)算方面具有良好的前景,同時可望形成一種高度并行的算法,適用于未來并行機(jī)的要求,是一種富有發(fā)展?jié)摿Φ男碌臄?shù)值方法。
Ii ) we organize the parallel computing of ' the third generation ocean general circulation model from the chinese institute of atmosphere physics ( lasg / iap ) , and we also apply several parallel optimization strategies including multi - overlapping - boundary . the parallelism is implemented both on distributed memory and shared memory parallel computers , based on the spitting of latitude zones . this parallel ocean general circulation model is the first one in china 11 )發(fā)展了國內(nèi)第一個高效并行海洋環(huán)流模式:深入研究了中國科學(xué)院大氣物理所第三代海洋環(huán)流模式,分析了其串行計(jì)算特點(diǎn)和并行可擴(kuò)展性,指出了其計(jì)算方法上存在的對并行計(jì)算的某些限制,對該模式組織了有效并行計(jì)算,并成功應(yīng)用了包括多重疊邊界在內(nèi)的若干并行優(yōu)化方法,在國產(chǎn)小型mpp系統(tǒng)和sgioriginzoo 。