Read-modify-write：修订间差异
删除的内容 添加的内容
Stella Phang（留言 | 贡献） 小无编辑摘要 |
Stella Phang（留言 | 贡献） 小无编辑摘要 |
||
| 第7行： | 第7行： | ||
Read-modify-write指令用于IO端口时，可能会产生出乎意料的结果，如无法给一个比特置位。这往往是因为写操作并不影响到读操作的源寄存器。<ref>{{Cite web |url=http://techref.massmind.org/techref/readmodwrite.htm |title=Massmind: "The read–modify–write problem" |accessdate=2017-11-22 |archive-date=2017-12-01 |archive-url=https://web.archive.org/web/20171201033821/http://techref.massmind.org/techref/readmodwrite.htm |dead-url=no }}</ref> |
Read-modify-write指令用于IO端口时，可能会产生出乎意料的结果，如无法给一个比特置位。这往往是因为写操作并不影响到读操作的源寄存器。<ref>{{Cite web |url=http://techref.massmind.org/techref/readmodwrite.htm |title=Massmind: "The read–modify–write problem" |accessdate=2017-11-22 |archive-date=2017-12-01 |archive-url=https://web.archive.org/web/20171201033821/http://techref.massmind.org/techref/readmodwrite.htm |dead-url=no }}</ref> |
||
[[RAID]]也使用这一术语描述原子操作的read-modify-write序列。<ref>{{cite web| url = http://www.ecs.umass.edu/ece/koren/architecture/Raid/basicRAID.html| title = Basic RAID Organizations | accessdate = 2013-10-04| website = umass.edu| archive-date = 2013-10-24 |
[[RAID]]也使用这一术语描述原子操作的read-modify-write序列。<ref>{{cite web| url = http://www.ecs.umass.edu/ece/koren/architecture/Raid/basicRAID.html| title = Basic RAID Organizations | accessdate = 2013-10-04| website = umass.edu| archive-date = 2013-10-24| archive-url = https://web.archive.org/web/20131024014416/http://www.ecs.umass.edu/ece/koren/architecture/Raid/basicRAID.html |
||
| archive-url = https://web.archive.org/web/20131024014416/http://www.ecs.umass.edu/ece/koren/architecture/Raid/basicRAID.html |
|||
| dead-url = no |
| dead-url = no |
||
}}</ref> Such RAID levels include [[RAID 4]], [[RAID 5]] and [[RAID 6]]. |
}}</ref> Such RAID levels include [[RAID 4]], [[RAID 5]] and [[RAID 6]]. |
||
2021年11月27日 (六) 10:26的版本
读-修改-写（read-modify-write）是计算机科学中的一个原子操作（atomic operation，类似的还有test-and-set, fetch-and-add, compare-and-swap等），操作过程是读一个内存位置（或IO端口），修改其值，再写回原位置。[1][2]
必须要先读操作的一个原因是，系统架构往往只允许字（word）级的读写，必须先读出那些不做修改的比特，保持不变再写回。写成C语言语句类似于：
*pRegister |= SOME_BIT;
Read-modify-write指令用于IO端口时，可能会产生出乎意料的结果，如无法给一个比特置位。这往往是因为写操作并不影响到读操作的源寄存器。[3]
RAID也使用这一术语描述原子操作的read-modify-write序列。[4] Such RAID levels include RAID 4, RAID 5 and RAID 6.
参见
参考文献
- ^ "Writing Lock-Free Code: A Corrected Queue" （页面存档备份，存于互联网档案馆） by Herb Sutter: "Compare-and-swap (CAS) is ... widely available ... However, some systems instead provide the equivalently powerful load-linked/store-conditional (LL/SC) instead."
- ^ Herlihy, Maurice. Wait-free synchronization (PDF). ACM Trans. Program. Lang. Syst. January 1991, 13 (1): 124–149 [2007-05-20]. doi:10.1145/114005.102808. （原始内容存档 (PDF)于2011-06-05）.
- ^ Massmind: "The read–modify–write problem". [2017-11-22]. （原始内容存档于2017-12-01）.
- ^ Basic RAID Organizations. umass.edu. [2013-10-04]. （原始内容存档于2013-10-24）.