Re: [PATCH] Mantaining turnstile aligned to 128 bytes in i386 CPUs

2006/7/25, Attilio Rao <attilio@xxxxxxxxxxx>:
Hi,
Intel documentation points out that having a 128-bytes aligned
syncronizing primitive (which fits in a cache line) will minimize the
traffic for cache bus, so this patch implements an alignment for i386
on turnstiles.

Any comments, feedbacks?

Oh, sorry, I've unforgotten the diff.

Attilio


--
Peace can only be achieved by understanding - A. Einstein

Attachment: subr_turnstile.diff
Description: Binary data

_______________________________________________
freebsd-arch@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-arch
To unsubscribe, send any mail to "freebsd-arch-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: which loop is faster
    ... If "some code" just fits into the cache but the outer loop doesn't: ... If the inner and the outer loop fit into the cache, ...
    (comp.lang.c)
  • Re: Cache-Size vs Performance
    ... to compensate for memory access latency) and there is database cache ... There's no CPU-cache which is sufficient for dbms-execution. ... so dbms-servers mostly become domi- ... data accessed that fits in any cpu-cache. ...
    (comp.arch)
  • Re: [PATCH 1/2] slab: introduce krealloc
    ... On Thu, 22 Feb 2007, Pekka J Enberg wrote: ... The allocator avoids reallocation if the new size ... fits the currently used cache. ...
    (Linux-Kernel)
  • Re: [PATCH] Mantaining turnstile aligned to 128 bytes in i386 CPUs
    ... Intel documentation points out that having a 128-bytes aligned ... syncronizing primitive (which fits in a cache line) will minimize the ... on turnstiles. ... UMA zone and specify cache-size alignment to the zone. ...
    (freebsd-arch)
  • Re: Xeon and Events
    ... NetBurst does not implement a traditional L1 instruction cache. ... when the Intel documentation mentions "the number of retired µops ...
    (comp.lang.asm.x86)