From owner-FreeBSD-tech-jp@jp.freebsd.org  Thu Mar 27 19:30:26 1997
Received: by jaz.jp.freebsd.org (8.8.5+2.7Wbeta5/8.7.3) id TAA17558
	Thu, 27 Mar 1997 19:30:26 +0900 (JST)
Received: by jaz.jp.freebsd.org (8.8.5+2.7Wbeta5/8.7.3) with ESMTP id TAA17553
	for <freebsd-tech-jp@jp.freebsd.org>; Thu, 27 Mar 1997 19:30:25 +0900 (JST)
Message-Id: <199703271030.TAA18433@nocs3.noc.titech.ac.jp>
Received: from noc.titech.ac.jp by nocs3.noc.titech.ac.jp (8.7+2.6Wbeta3/TM2.1-bn3.3)
	id TAA18433; Thu, 27 Mar 1997 19:30:23 +0900 (JST)
To: freebsd-tech-jp@jp.freebsd.org
X-Mailer: Mew version 1.54 on Emacs 19.28.1, Mule 2.3
Mime-Version: 1.0
Content-Type: Text/Plain; charset=iso-2022-jp
Content-Transfer-Encoding: 7bit
Date: Thu, 27 Mar 1997 19:30:23 +0900
From: IIJIMA Akihiro <aki@noc.titech.ac.jp>
Reply-To: FreeBSD-tech-jp@jp.freebsd.org
Precedence: bulk
X-Distribute: distribute [version 2.1 (Alpha) patchlevel=19]
X-Sequence: FreeBSD-tech-jp 150
Subject: [FreeBSD-tech-jp 150] Re: [FreeBSD-users-jp 11114] Let's Note 133/150 problem fixed!
Errors-To: owner-FreeBSD-tech-jp@jp.freebsd.org
Sender: owner-FreeBSD-tech-jp@jp.freebsd.org

Let's note$B$N(B npx0$B$G$9$,!"(B

  From: hosokawa@mt.cs.keio.ac.jp (HOSOKAWA Tatsumi)
  Subject: [FreeBSD-users-jp 11114] Let's Note 133/150 problem fixed!
  Date: Thu, 27 Mar 1997 11:24:31 +0900
> Let's Note 133/150 $B$G(B 2.2-ALPHA $B0J9_$,5/F0$7$J$$$H$$$&%P%0$NBP=hK!$rH/(B
> $B8+$7$^$7$?!#$H$j$"$($:8fJs9p$^$G!#(B $B2sHrK!$O!"(B
> $B!V(Bboot -c $B$N(B CLI $B%b!<%I$+$i(B flags npx0 0x07 $B$H$9$k!W$G$9!#(B

  Subject: [FreeBSD-users-jp 11140] Re: Let's Note 133/150 problem fixed!
> flags npx0 0x01 $B$@$1$G$$$$$h$&$G$9!#(B

$B$3$N(B flags$B$N0UL#$O$J$s$G$7$g$&$+!)(B

FreeBSD-current/src/i386/conf/LINT $B$r8+$k$H!"(B

# `flags' for npx0:
#       0x01    don't use the npx registers to optimize bcopy
#       0x02    don't use the npx registers to optimize bzero
#       0x04    don't use the npx registers to optimize copyin or copyout.
# The npx registers are normally used to optimize copying and zeroing when
# all of the following conditions are satisfied:
#       "I586_CPU" is an option
#       the cpu is an i586 (perhaps not a Pentium)
#       the probe for npx0 succeeds
#       INT 16 exception handling works.
# Then copying and zeroing using the npx registers is normally 30-100% faster.
# The flags can be used to control cases where it doesn't work or is slower.
# Setting them at boot time using userconfig works right (the optimizations
# are not used until later in the bootstrap when npx0 is attached).

$B$H$+=q$$$F$"$k$s$G$9$1$I(B
Lets note$B$N(B npx$B$OIe$C$F$$$k(B $B$H$$$&$3$H$K$J$k$N$G$7$g$&$+!)(B
--
	$BEl5~9)6HBg3X(B Titanet $B1?MQ%;%s%?!<(B
$BHSEg(B $B><Gn(B (Akihiro Iijima) aki@noc.titech.ac.jp
