内存对齐：内存读取粒度

Memory access granularity

Programmers are conditioned to think of memory as a simple array of bytes. Among C and its descendants, char* is ubiquitous as meaning "a block of memory", and even Java™ has its byte[] type to represent raw memory.

Figure 1. How programmers see memory

View image at full size

However, your computer's processor does not read from and write to memory in byte-sized chunks. Instead, it accesses memory in two-, four-, eight- 16- or even 32-byte chunks. We'll call the size in which a processor accesses memory its memory access granularity.

https://www.ibm.com/developerworks/library/pa-dalign/index.html

 

CPU把内存当成是一块一块的，块的大小可以是2，4，8，16字节大小，因此CPU在读取内存时是一块一块进行读取的。块大小成为memory access granularity（粒度） 本人把它翻译为“内存读取粒度” 。

http://www.cppblog.com/snailcong/archive/2009/03/16/76705.html

转载于:https://www.cnblogs.com/feng9exe/p/10059543.html