Re:An optimization guide for assembly programmers and compil...
by kijiki on Monday February 11, 2019 @10:42PM
(#19140838)
Probably not directly faster, but "xor %rax, %rax" is still smaller (and thus faster if you're icache constrained) than "mov $0x0, %rax"
[ Parent
| on HN ]
Re:An optimization guide for assembly programmers and compil...
by userbinator on Monday February 11, 2019 @11:10PM
(#19140981)
It is still faster because the register renamer handles it --- ditto for "sub reg, reg":
https://randomascii.wordpress.com/2012/12/29/the-surprising-...
Re:An optimization guide for assembly programmers and compil...
by jabl on Tuesday February 12, 2019 @02:35AM
(#19141734)
"xor %eax, %eax" is even smaller (2 bytes vs. 3) and does the same thing since operations on the 32-bit subregisters are defined to zero the upper half [1]. This is what compilers tend to do when they want to zero a register.
[1] This is not true for 8- or 16-bit subregisters, causing all kinds of fun issues (see "partial register stalls", also discussed in Agner Fog's materials).