tpf@jdyx.UUCP (Tom Friedel) (11/30/89)
Has anyone used this chip with 386/ix? From the manual, "Cyrix CX-83D87 is a CMOS VLSI integrated circuit that is pin compatible and software compatible with the 80387, yet ... achieves 4 to 10 times greater performance ... by implementing floating point primitives operation in hardware." Given one floating point intensive process (a ray trace) I am wondering what performance difference I would see? Tom tpf@jdyx.UUCP -- Tom Friedel (404) 320-7624 tpf@jdyx.UUCP CIS: 71131,3234 also: tpf@jdyx.atlanta.ga.us ...gatech!emory!jdyx!tpf Unix BBS: (404) 325-1719 <= 2400 ; (404) 321-5020 >= 2400 "Live simply, so that others may simply live."
jrh@mustang.UUCP (jrh) (12/01/89)
In article <1989Nov29.215150.53@jdyx.UUCP>, tpf@jdyx.UUCP (Tom Friedel) writes: > Has anyone used this chip with 386/ix? From the manual, "Cyrix > CX-83D87 is a CMOS VLSI integrated circuit that is pin compatible > and software compatible with the 80387, yet ... achieves 4 to 10 > times greater performance ... by implementing floating point primitives > operation in hardware." > Given one floating point intensive process (a ray trace) I am > wondering what performance difference I would see? > Well, there is an article in Info World (11/27/89) reporting that Intel is disputing the compatibility claims of coprocessors from other vendors. A couple cited in the article were the IIT-2C87 and the Cyrix Fasmath 83D87. Interestingly, the article states that Cyrix has released a report claiming to have "identical numerical and status results" to the chip compared to the GET THIS >>>>> Intel 80287. Notice that the comparison reported is not to the 80387. I personally don't know either way, but that's the guts of the article. +------------------------------------------------------------------------+ | James R. Howard | Insert Standard Disclaimer Here... | | cs.utexas.edu!dell!mustang!jrh | | +------------------------------------------------------------------------+
joe@junkyard.UUCP (Joseph Sarkes) (12/01/89)
In article <1989Nov29.215150.53@jdyx.UUCP>, tpf@jdyx.UUCP (Tom Friedel) writes: > Has anyone used this chip with 386/ix? From the manual, "Cyrix > CX-83D87 is a CMOS VLSI integrated circuit that is pin compatible > and software compatible with the 80387, yet ... achieves 4 to 10 > times greater performance ... by implementing floating point primitives I've read an article on this chip, and the real performance improvement was supposed to be in the transcendental functions being from 5 to 10 times faster, and generally 1.2 to 3 times faster overall. It also has a memory mapped interface capability ala weitek, but this is undoubtably not supported by any available motherboards at this time. My question is are these chips available, where, and for how much. See the november 1989 issue of High Performance magazine (the only place I've seen any info on this chip) for a good writeup on the differences between it and the 387. Joseph Sarkes (junkyard!joe)
plim@hpsgpa.HP.COM (Peter Lim) (12/01/89)
Just curious.
4 to 10 times faster than what ? A machine without Intel's 387 or
a machine with Intel's 387 ?
I know that a 25MHz no cache machine with Intel's 387 whips out close
to 1.2 Million Whetstones per second. Rumor have it that a 486 system
running at 33MHz might be able to whip out 6 Million WPS (for your
info, the HP9000 / 370 -- the current top of the line HP workstation
produces ~ 2 Million WPS). So, I don't think any '387 replacement will
be able to do 4 to 10 times that of an Intel '387 for that will means
4.8 to 12 Million WPS ! Which means a 25MHz no cache 386 will easily
out perform even the 486 with integrated '387 running at 33MHz ! Just
imagine what a 33MHz cache 386 will do ? From experience, a cache
386 will run '387 at about 20% faster throughput, so multiply by
1.2 * 33 / 25, we get 7.6 to 19 Million WPS ! Woooollll !
I don't have figures to calculate if this is possible given the
limitation of the 386 data transfer bandwidth to and from the '387.
But prove me wrong if you can and I'll buy the new CMOS 387 for
mainframe performance :-) !
Regards,
Peter Lim.
HP Singapore IC Design Center.
E-mail address: plim@hpsgwg.HP.COM
Snail Mail address: Peter Lim
Hewlett Packard Singapore,
(ICDS, ICS)
1150, Depot Road,
Singapore 0410.
Telephone: (065)-279-2289