On Sat, 7 Apr 2007, Andrew Morton wrote: > andl $48, %eax #, tmp399 > cmpl $48, %eax #, tmp399 > je .L265 #, > > what's "yuck" about that? > > With the single page flag: > > movl (%ebx), %eax #* page.521, D.21940 > testb $32, %al #, D.21940 > jne .L265 #, > > So you're talking about saving one sole single silly solitary instruction. We are also using another register. The bit instructions can just go in an test. Ok. Will submit this patch. .... Maybe I can special case 64 bit. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
- References:
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- From: Andrew Morton <[email protected]>
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- From: Christoph Lameter <[email protected]>
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- From: Andrew Morton <[email protected]>
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- From: Christoph Lameter <[email protected]>
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- From: Andrew Morton <[email protected]>
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- From: Christoph Lameter <[email protected]>
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- From: Andrew Morton <[email protected]>
- Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- Prev by Date: Re: [PATCH 1/4] x86_64: (SPARSE_VIRTUAL doubles sparsemem speed)
- Next by Date: still curious about that CONFIG_FORCED_INLINING option
- Previous by thread: Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- Next by thread: Re: [PATCH 2/2] Optimize compound_head() by avoiding a shared page flag
- Index(es):
 |