All of these optimizations are to aid in higher performance , and are generally transparent to the user , but on multiprocessor systems , these complexities may sometimes show through . part 2 , " how will the jmm change under jsr 133 所有的这些优化是为了帮助实现更高的性能,通常这对于用户来说是透明的,但是对多处理系统来说,这些复杂的事情可能有时会完全显现出来。
Then , we give some description about the working principle , organization , function of router - cache and where it should be . we also gave out a cache coherence protocol for multiprocessors systems with router - caches 本文接着描述了路由器cache的工作原理,对其的组织、在系统中的位置、应有的功能等方面进行了讨论,并设计了含有路由器cache的多处理器系统的cache一致性协议。
But in a multiprocessors system , there may be several processors have read the same data , and then one processor will write it . this time , the copy of the data in the caches of other processors will be out of date 但在多处理器系统中,由于多个处理器可能对同一数据块进行读操作,当某个处理器对共享的数据块进行写操作时,其它处理器的cache中该数据块的副本将成为过时的数据。
In the research and implement of the multiprocessor system , we have developed a smp like structure which two cpus share a memory , and a cool backup system for the fault - tolerant . this system can meet the requirement of reliability 在多处理器系统体系结构的研究实现上,我们采用了双cpu共享内存的类smp结构,同时进行了系统冷备份冗余的容错设计,保证星载多处理器实时系统的可靠性。
We developed the support modules for multiprocessor and i / o subsystem . the satellite - carried embedded multiprocessor system adopted the high reliability 1553b bus and high speed ieee1394 bus , which have met the reliability and information processing requirement 我们研发的星载嵌入式多处理器系统的i / o子系统采用了可靠性高的1553b总线以及传输速率高的ieee1394总线,从而满足了系统对于可靠性和信息处理能力的要求。