Hacker News Reader

Comment by hyperman1 | Hacker News Reader

Can someone clarify something for me in that second assembly dump: It does:

  xor %eax %eax (2 bytes)
  mov $0x0,%edi (5 bytes)

Why does it decide to use 2 different ways to zero a register, the second one less efficient than the first? Or will the second one be patched while linking, i.e. the 0 is a placeholder for some other address?

View on HN

Exactly, the 0 is a placeholder for the address of the format string (first argument for printf).

Update: Looking further, there seems to be a lot of space wasted in the disas factorial example: It is 32+1=33 bytes long, or even 48 if the next function will be aligned on a 16 bytes boundary. There are 2 nop's in there, consuming 6 and 4 bytes. So at least 10/33=about 30% of the memory is traded for aligning jumps on 8 (or 16?) byte boundaries. This seems a big waste of L1I cache.

Is this a normal ratio? Does -Os much better?

Functions are usually longer than what you're seeing there.

True, but you would expect it is the ratio branches vs other code which is relevant here.

Reply on news.ycombinator.com