Messages in this thread | | | Date | Fri, 22 Jan 1999 16:59:39 -0500 (EST) | From | Chuck Lever <> | Subject | Re: -fno-strength-reduce |
| |
On Fri, 22 Jan 1999, Arvind Sankar wrote: > btw, another question along these lines: how much should the alignment > specs be? The defaults are bigger than what are currently specified > (currently they are 32 bit alignment for loops, jumps and functions). > The default is 64-bit on i486 and up, and if gas >= 2.8 is used (likely) > then it is either 64-bit or 128-bit if you are less than 64 bits from > a 128-bit boundary. Wouldn't 64-bit alignment be faster for Ppros?
i'm curious about this as well.
i've set alignment on PPro and K6 machines i use to 64 bytes, since the cache lines on the K6 are 32 bytes each, and are burst loaded from RAM two-at-a-time. i assume the PPro caches work the same way, but haven't checked the spec sheet.
perhaps a more reasonable alignment might be 64 bytes for functions, and 8 or 16 bytes for loops and jumps.
the results have been inconclusive, but certainly not dangerous to performance or stability.
- Chuck Lever -- corporate: <chuckl@netscape.com> personal: <chucklever@netscape.net> or <cel@monkey.org>
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |