Messages in this thread | | | Date | Fri, 12 Dec 1997 09:17:52 -0500 | From | "Theodore Y. Ts'o" <> | Subject | Re: copy-bit macro |
| |
From: Stefan Monnier <monnier+lists/linux/kernel/news/@TEQUILA.SYSTEMSZ.CS.YALE.EDU> Date: 11 Dec 1997 17:59:10 -0500
"Theodore Y. Ts'o" <tytso@MIT.EDU> writes: > (1 << OUT_FLAG_NUMBER) : 0") both involve an assembly language > conditional jump instruction, which is expensive, because it involves > pipeline stalls, etc.
Has it been measured ? I know that branch prediction is not 100%, but I'm just trying to make sure we're not trying to solve a non-problem (if the prediction works well, then the jump costs 0 (zero) cycles).
Branch prediction works in conditional testing when branching out of loops. In the cases where you'd use copy_bit(), it isn't in a loop condition, and yes it matters.
- Ted
| |