Memory Structure, cache, DMA Architecture Analysis-[sky Original], cachedma

Source: Internet
Author: User

Memory Structure, cache, DMA Architecture Analysis-[sky Original], cachedma
Storage hierarchyCache Read cache operationsIf the cache contains data, it will be read directly from the cache because the cache speed is faster than that of the memory. If it does not contain data, it will be searched from the memory. After the cache is found, it will be placed in the cache, if you try again later, you will read it directly from the cache. The next visit will be much faster, which is equivalent to increasing the hit rate, the cpu access speed greatly increases the cache speed and greatly increases the cpu access rate.Cache DesignIt cannot be too large or too small, because the program needs to repeat the cache when viewing data. If the cache is too large, it takes too long to repeat it, if the increase rate is too small, the number of blocks stored in the memory will decrease, the hit rate will decrease, and the number of accesses to the memory will increase, cpu performance also reduces the block size Cache and memory Data Exchange Unit from small to large, from the local principle, when the hit increases more, the possibility of new data acquisition is used, the hit rate is much lower than the possibility that data that must be removed from the Cache will be used again.DMAThe cpu performance of a large amount of mobile data is fast, and the speed of peripherals is relatively slow. The cpu will always wait for the peripherals, so there is no DMA before DMA. If the data is transferred from the memory to the peripherals with DMA, the cpu tells the DMA command and writes the memory size from a specific address to the peripherals. In this way, the DMA will be done and the cpu will not need to be done, DMA extracts data from the memory and then goes to the peripherals. This mechanism is the DMA mechanism, and the cpu is liberated and more important, therefore, DMA is used to free up the cpu when the memory is copied and a large amount of data is moved. Remember that the cpu only starts at the end of the process and starts at the end of the process.

Sina Blog: http://blog.sina.com.cn/u/2049150530
Csdn blog: http://blog.csdn.net/u011749143
Blog: http://www.cnblogs.com/sky-heaven/
ChinaUnix: http://blog.chinaunix.net/uid/30049997.html
Know: http://www.zhihu.com/people/zhang-bing-hua

Related Article

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.