Manfred Spraul wrote:
> AMD recommends to perform memory copies with backward read operations
> instead of prefetch.
>
> http://208.15.46.63/events/gdc2002.htm
>
> Attached is a test app that compares several memory copy implementations.
> Could you run it and report the results to me, together with cpu,
> chipset and memory type?
>
> Please run 2 or 3 times.
>
Athlon XP 1600+ (1400 MHz)
512 MB PC-133 memory
Host bridge: VIA Technologies, Inc. VT8363/8365 [KT133/KM133] (rev 03)
processor : 0
vendor_id : AuthenticAMD
cpu family : 6
model : 6
model name : AMD Athlon(tm) Processor
stepping : 2
cpu MHz : 1410.668
cache size : 256 KB
copy_page() tests
copy_page function 'warm up run' took 21428 cycles per page
copy_page function '2.4 non MMX' took 22404 cycles per page
copy_page function '2.4 MMX fallback' took 22426 cycles per page
copy_page function '2.4 MMX version' took 21472 cycles per page
copy_page function 'faster_copy' took 13618 cycles per page
copy_page function 'even_faster' took 13284 cycles per page
copy_page function 'no_prefetch' took 11943 cycles per page
copy_page() tests
copy_page function 'warm up run' took 21640 cycles per page
copy_page function '2.4 non MMX' took 22865 cycles per page
copy_page function '2.4 MMX fallback' took 22843 cycles per page
copy_page function '2.4 MMX version' took 21597 cycles per page
copy_page function 'faster_copy' took 13751 cycles per page
copy_page function 'even_faster' took 13407 cycles per page
copy_page function 'no_prefetch' took 11952 cycles per page
copy_page() tests
copy_page function 'warm up run' took 21681 cycles per page
copy_page function '2.4 non MMX' took 22900 cycles per page
copy_page function '2.4 MMX fallback' took 22999 cycles per page
copy_page function '2.4 MMX version' took 21679 cycles per page
copy_page function 'faster_copy' took 13782 cycles per page
copy_page function 'even_faster' took 13481 cycles per page
copy_page function 'no_prefetch' took 11969 cycles per page
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Oct 31 2002 - 22:00:24 EST