Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 17 Dec 1996 13:14:12 +0100 (MET)
From:      Christoph Kukulies <kuku@gilberto.physik.rwth-aachen.de>
To:        freebsd-hackers@freefall.FreeBSD.org
Subject:   PPRO lat_mem_rd figures?
Message-ID:  <199612171214.NAA19291@gilberto.physik.rwth-aachen.de>

next in thread | raw e-mail | index | archive | help

I'm still seeking for the mistery why my PPRO 200/256 seems slow:
(ASUS P6NP5)

lat_mem_rd 8 128:


$Id: lat_mem_rd.c,v 1.1 1994/11/18 08:49:48 lm Exp $
$Id: mhz.c,v 1.1 1994/11/18 08:51:55 lm Exp $
"stride=128
0.00049 10 <--
0.00098 10 <--
0.00195 10 <--
0.00293 10
0.00391 10
0.00586 10
0.00781 10
0.00977 22
0.01172 30
0.01367 30
0.01562 30
0.01758 30
0.01953 30
0.02148 30
0.02344 30
0.02539 30
0.02734 30
0.02930 30
0.03125 30
0.03516 30
0.03906 30
0.04297 30
0.04688 30
0.05078 30
0.05469 30
0.05859 30
0.06250 30
0.07031 30
0.07812 30
0.08594 67
0.09375 64
0.10156 61
0.10938 59
0.11719 57
0.12500 55
0.14062 75
0.15625 79
0.17188 93
0.18750 91
0.20312 106
0.21875 106
0.23438 131
0.25000 125
0.28125 146
0.31250 159
0.34375 166
0.37500 180
0.40625 177
0.43750 175
0.46875 181
0.50000 186
1.00000 197
1.50000 197
2.00000 196
2.50000 197
3.00000 197
3.50000 196
4.00000 196
4.50000 197
5.00000 197
5.50000 199
6.00000 197
6.50000 196
7.00000 197
7.50000 197
8.00000 197

clk=5.04

A P166 with 512K external cache gives this (ASUS P55TP4N) :

$Id: lat_mem_rd.c,v 1.1 1994/11/18 08:49:48 lm Exp $
$Id: mhz.c,v 1.1 1994/11/18 08:51:55 lm Exp $
"stride=128
0.00049 6
0.00098 6
0.00195 6
0.00293 6
0.00391 6
0.00586 6
0.00781 6
0.00977 59
0.01172 95
0.01367 95

Any better PPRO figures welcome.


--Chris Christoph P. U. Kukulies kuku@gil.physik.rwth-aachen.de



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199612171214.NAA19291>