Mail Archives: djgpp/1993/08/19/03:28:12
CPU & Video Benchmarks 1.0 (C) 1993 DJ Delorie. Distribute freely.
CPU: 486DX2, 66 MHz Video: #9GXE level 11 (S3-928 2Mb)
All results are Kbytes per second, s=system RAM, v=video RAM, mode 0x13
bits s->s s->v v->s v->v s-> v-> ->s ->v
8 10,504 1,543 799 547 16,457 927 10,504 1,543
waits 3.2 39.7 79.6 117.6 0.0 67.1 2.2 38.7
8 /8 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0
16 20,992 3,085 1,597 1,094 32,955 1,861 20,994 3,086
waits 3.2 39.8 79.7 117.6 0.0 66.9 2.2 38.7
16/8 1.9 1.9 1.9 2.0 2.0 2.0 1.9 2.0
32 25,996 2,953 1,683 1,117 35,532 1,861 41,874 3,089
waits 7.1 86.4 154.1 233.5 3.4 137.9 2.3 81.4
32/8 2.4 1.9 2.1 2.0 2.1 2.0 3.9 2.0
Prices on this card has here dropped below the Diamond Viper card
which is about half of the old #9 card.
I think that selling a VLB for a graphics accelerator card is like
selling orange coloured golfballs for playing in the snow.
VLB may be useful for a non accelerator card and for disc controllers,
but not for graphics accelerators. The small traffic on the bus to the
card just does not justify it.
I also wonder (forgive my ignorance but) how do I interpret the figures
your benchmark produces? what is 'waits' ? Waitstates??? What is the
source when the header says ->s or ->v and the target when it says s->
and v-> ?
-Peter
-------------------------------------------------------------------------
Me: Peter Roejsel
Org: MAX-lab, National Laboratory for Synchrotron Radiation
E-mail: Peter AT maxlab DOT lu DOT se
Amateur Radio: SM7LEK
Papermail: MAX-lab, University of Lund, Box 118, 221 00 Lund, Sweden
FAX: +46-46-104710
Phone: +46-46-109717
"And GOD said: E=mc**2 and there was matter!"
-------------------------------------------------------------------------
- Raw text -