Messages in this thread | | | Date | Wed, 20 Jan 2010 22:28:49 -0800 | From | "H. Peter Anvin" <> | Subject | Re: [x86] Unify semaphore_32.S and rwlock_64.S |
| |
On 01/20/2010 04:02 PM, H. Peter Anvin wrote: > On 01/20/2010 03:57 PM, Linus Torvalds wrote: >> > > I'm somewhat unhappy about that notion, mostly because it means Yet > Another Thing To Verify[TM]. I would like to look at the relative code > sizes of 2^31 and 2^30, however, if all it means is that *one* > instruction in *one* asm has to be different, I'd rather leave it at 2^31. >
Well, there is no size difference within measurable limits (an x86-64-allyesconfig build is 60(!) bytes larger with 2^31 and the incl, but that's well within the good luck/bad luck with alignments threshold...)
As such, I'd personally prefer to leave it with 1:31:31:1 split, if nothing else because it reads a bit tidier to me, despite the minor wart for the incl trick.
-hpa
-- H. Peter Anvin, Intel Open Source Technology Center I work for Intel. I don't speak on their behalf.
| |