In article <23qh9i$e6@info.epfl.ch> brossard@sic.epfl.ch writes:
>In article <23o7i9$272@fred.fwi.uva.nl>, janw@fwi.uva.nl (Jan Wortelboer) writes:
>|> blymn@awadi.com.au (Brett Lymn) writes:
>|>
>|> >time man csh > /dev/null
>|>
>|> >SS2 (4.1.3): 10.5
>|> >SS1000 (5.2): 3.5
>
>|> On a SS10/41 (5.2)
>|> turing[17]/tmp# /bin/time nroff -man /usr/share/man/man1/csh.1 > /dev/null
>|>
>|> real 3.4
>|> user 3.0
>|> sys 0.1
>
> S10-512 (5.2):
>real 2.0
>user 1.9
>sys 0.0
Couldn't resist sticking my oar in:
On a SPARCstation 2 upgraded with SPARC Power uP (4.1.1):
/bin/time nroff -man /usr/man/man1/csh.1 > /dev/null
real 4.6
user 4.4
sys 0.1
I get a time for a SPARCstation 2 (4.1.1) of:
real 8.1
user 7.8
sys 0.1
Comparing the "real" times, that's a 1.8x speedup. (If I had used
the 10.5 seconds reported above for the SPARCstation 2, I could have
claimed a 2.3x speedup, but I use my own numbers whenever possible.)
I don't have any numbers for this test under Solaris -- sorry.
-- Robert
-- Robert Plamondon * WEITEK Corporation * Home of SPARC Power uP (TM) 80 MHz clock-doubled SPARC processor upgrade for the SPARCstation 2 or IPX FAX-back info line: (800) 827-8708 or (408) 522-7525 Info by ftp: in pub/weitek on netcom.com * Info by email: cpu-upgrade@weitek.com
This archive was generated by hypermail 2.1.2 : Fri Sep 28 2001 - 23:08:05 CDT