Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

devblogs.microsoft.com

Post reply on HN
Print view View original

11–20 of 231 posts

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#11

Post by phire »

NewCzech wrote: post #4

The obvious answer is that XOR is faster. To do a subtract, you have to propagate the carry bit from the least-significant bit to the most-significant bit. In XOR you don't have to do that because the output of every bit is independent of the other adjacent bits. Probably, there are ALU pipeline designs where you don't pay an explicit penalty. But not all, and so XOR is faster. Surely, someone as awesome as Raymond C…

I'm not actually aware of any CPUs that preform a XOR faster than a SUB. And more importantly, they have identical timings on the 8086, which is where this pattern comes from.

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#12

Post by feverzsj »

NewCzech wrote: post #4

The obvious answer is that XOR is faster. To do a subtract, you have to propagate the carry bit from the least-significant bit to the most-significant bit. In XOR you don't have to do that because the output of every bit is independent of the other adjacent bits. Probably, there are ALU pipeline designs where you don't pay an explicit penalty. But not all, and so XOR is faster. Surely, someone as awesome as Raymond C…

It's like 0.5 cycles vs 0.9 cycles. So both are 1 cycle, considering synchronization.

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#13

Post by Tepix »

NewCzech wrote: post #4

The obvious answer is that XOR is faster. To do a subtract, you have to propagate the carry bit from the least-significant bit to the most-significant bit. In XOR you don't have to do that because the output of every bit is independent of the other adjacent bits. Probably, there are ALU pipeline designs where you don't pay an explicit penalty. But not all, and so XOR is faster. Surely, someone as awesome as Raymond C…

From TFA:

> It encodes to the same number of bytes, executes in the same number of cycles.

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#14

Post by jojobas »

NewCzech wrote: post #4

The obvious answer is that XOR is faster. To do a subtract, you have to propagate the carry bit from the least-significant bit to the most-significant bit. In XOR you don't have to do that because the output of every bit is independent of the other adjacent bits. Probably, there are ALU pipeline designs where you don't pay an explicit penalty. But not all, and so XOR is faster. Surely, someone as awesome as Raymond C…

The non-obvious bit is why there isn't an even faster and shorter "mov ,0" instructions - the processors started short-circuiting xor , much later.

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#15

Post by Sweepi »

"Bonus bonus chatter: The xor trick doesn’t work for Itanium because mathematical operations don’t reset the NaT bit. Fortunately, Itanium also has a dedicated zero register, so you don’t need this trick. You can just move zero into your desired destination."

Will remember for the next time I write asm for Itanium!

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#17

Post by rasz »

Looking at some random 1989 Zenith 386SX bios written in assembly so purely programmer preferences:

8 'sub al, al', 14 'sub ah, ah', 3 'sub ax, ax'

26 'xor al, al', 43 'xor ah, ah', 3 'xor ax, ax'

edit: checked a 2010 bios and not a single 'sub x, x'

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#18

Post by virexene »

NewCzech wrote: post #4

The obvious answer is that XOR is faster. To do a subtract, you have to propagate the carry bit from the least-significant bit to the most-significant bit. In XOR you don't have to do that because the output of every bit is independent of the other adjacent bits. Probably, there are ALU pipeline designs where you don't pay an explicit penalty. But not all, and so XOR is faster. Surely, someone as awesome as Raymond C…

The operation is slightly more complex yes, but has there ever been an x86 CPU where SUB or XOR takes more than a single CPU cycle?

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#19

Post by stingraycharles »

tliltocatl wrote: post #16

It might be because XOR is rarely (in terms of static count, dynamically it surely appears a lot in some hot loops) used for anything else, so it is easier to spot and identify as "special" if you are writing manual assembly.

And helps with SMT

Edit: this is apparently not the case, see @tliltocatl's comment down the thread

Re: XOR'ing a register with itself is the idiom for zeroing it out. Why not sub?

#20

Post by 3form »

svnt wrote: post #9
NewCzech wrote: post #4

The obvious answer is that XOR is faster. To do a subtract, you have to propagate the carry bit from the least-significant bit to the most-significant bit. In XOR you don't have to do that because the output of every bit is independent of the other adjacent bits. Probably, there are ALU pipeline designs where you don't pay an explicit penalty. But not all, and so XOR is faster. Surely, someone as awesome as Raymond C…

His point is that in x86 there is no performance difference but everyone except his colleague/friend uses xor, while sub actually leaves cleaner flags behind. So he suspects its some kind of social convention selected at random and then propagated via spurious arguments in support (or that it “looks cooler” as a bit of a term of art). It could also be as a result of most people working in assembly being aware of the…

I think an even more likely explanation would be that x86 assembly programmers often were, or learned from other-architecture assembly programmers. Maybe there's a place where it makes more sense and it can be so attributed. 6502 and 68k being first places I would look at.
Post reply on HN