Linux-Hardware Digest #720, Volume #10 Sat, 10 Jul 99 00:13:32 EDT
Contents:
Re: IDE ZIP Drive (also, a plug for VMWare) (David Graham)
Re: Windows easy to install? BULLSHIT! (Michel Catudal)
Re: $299 linux pc hardware questions ([EMAIL PROTECTED])
Re: Help! Can't print in Linux from a compiled kernel (Moritz Moeller-Herrmann)
Re: SoundCard (Michel Catudal)
Dump - file number=0, ide tape, Help! (Andrew Evans)
Re: Summary and Clarification (Celeron, what's the catch?) (Nack)
Flash card readers for Non-Windows? (Ken)
Re: Recompile kernel, RH 5.0 (Nektarios Lathiotakis)
Double CD-ROM Stack ("Christopher and Kelly Wood")
Re: Celeron, what's the catch? (Chris Robato Yao)
Re: Celeron, what's the catch? ("Charismo")
Re: Any CD Burners for linux? (Oliver Kurth)
Cant get Creative Ensoniq AudioPCI to work ("Muuga")
Re: Internal Modem ("James")
Re: Celeron, what's the catch? (David T. Wang)
Re: LI (Rich Piotrowski)
Re: Celeron, what's the catch? (L.Angel)
Re: Celeron, what's the catch? ("Charismo")
----------------------------------------------------------------------------
From: David Graham <[EMAIL PROTECTED]>
Subject: Re: IDE ZIP Drive (also, a plug for VMWare)
Date: Fri, 09 Jul 1999 11:29:42 -0400
Yes, they work, or, at least, mine does <g>. Fairly standard, by now.
For some reason, the "standard" partition number on a ZIP disk seems to
be 4 (.../hdd4, etc.). Need to make sure the kernel supports ZIPs
("Include IDE/ATAPI FLOPPY support" in kernel config).
Changing the subject: going back and forth ad infinitum between Linux
(for you) and NT (for the family) works, but it gets cumbersome. I
should know: that's exactly what I do at home for the same reason. You
might want to check out www.vmware.com - software that lets you run an
OS (such as NT) in a virtual machine (think of an xterm) inside another
OS (such as Linux). I am trying it out now. Still need to work out a
few kinks, so that, to my family, it looks like they are simply using NT
instead of NT-in-a-VM-inside-Linux. So far, though, it works as
advertised. (Unfortunately, ZIP drives are a problem for VMWare.)
Good luck,
David Graham
--
> I have seen conflicting information on the net about support for
> IDE Zip drives. I am buying a new system and I would like
> to have it configured with an internal IDE drive because it
> is a cheaper solution than SCSI.
>
> The new system will have NT installed (for the wife) and I
> plan to install Redhat. If support is not available today, do
> you think there will be support in the near future? Any advise
> is appreciated.
------------------------------
From: Michel Catudal <[EMAIL PROTECTED]>
Crossposted-To: comp.os.ms-windows.advocacy,comp.os.linux.setup
Subject: Re: Windows easy to install? BULLSHIT!
Date: 9 Jul 1999 20:29:52 -0500
[EMAIL PROTECTED] wrote:
>
> In comp.os.linux.hardware Martin A. Boegelund <[EMAIL PROTECTED]> wrote:
> = Touché, touché and touché :)
>
> Touch?, touch? and touch? ???
> OOH! You mean Touche'?
Touché like in hit, "hit right on the nail" ever heard this expression.
To touch would translate to toucher and not touché
touché translate to touched or hit depending on the context
--
use OS/2 for a crash proof work environment
use Linux for safe and quick internet access
use Winblows to test the latest viruses
http://www.netonecom.net/~bbcat/
We have software, food, music, news, search,
history, electronics and genealogy pages.
------------------------------
From: [EMAIL PROTECTED]
Subject: Re: $299 linux pc hardware questions
Date: 09 Jul 1999 09:44:37 -0400
Linux systems with 2 button mice....UGH!!!!!!!!
--
Tom Evans
------------------------------
From: [EMAIL PROTECTED] (Moritz Moeller-Herrmann)
Crossposted-To: comp.os.linux.misc,alt.uu.comp.os.linux.questions
Subject: Re: Help! Can't print in Linux from a compiled kernel
Date: Fri, 9 Jul 1999 14:47:17 +0200
Reply-To: [EMAIL PROTECTED]
On Thu, 8 Jul 1999 10:28:06 -0500, dkmallick <[EMAIL PROTECTED]> wrote:
>I am using Linux-Mandrake 6.0 on a Pentium II 333.Everything prints fine
>from the kernel 2.2.9 that came with the distribution. Howver, I cannot
>print anything from kernel 2.2.5 that I had to compile just so that I can
>use my sound card. I made sure that I compiled this kernel with parallel
>port support, printer support etc.
If you use modules for the parport add a setting like
alias parport_lowlevel parport_pc
and maybe
options parport_pc io=0x378 irq=none,none
to /etc/conf.modules.
[...]
--
Moritz Moeller-Herrmann [EMAIL PROTECTED] ICQ# 3585990 # Not only
Get my public pgp / gpg key from # Open Source(TM)
http://webrum.uni-mannheim.de/jura/moritz/pubkeymoritz # but also
KDE forever! Use Linux to impress your friends! # Open Minded!
------------------------------
From: Michel Catudal <[EMAIL PROTECTED]>
Crossposted-To: comp.os.linux.setup
Subject: Re: SoundCard
Date: 9 Jul 1999 21:12:03 -0500
S3/\\\\\\T3X wrote:
>
> HellNo <[EMAIL PROTECTED]> wrote in message
> news:7ldkad$khq$[EMAIL PROTECTED]...
> > I have an SB16 and I'm happy!
> > Avoid the SB Live... it needs *3* IRQ's!
> >
> > I thought a SB AWE32 would be good. I know Linux supports it and W9x
> > does too. Don't know about the others!
> >
> > Hope this helped.
> > Ed.
> >
> >
> > In article <[EMAIL PROTECTED]>,
> > Anthony Lacey <[EMAIL PROTECTED]> wrote:
> > >
> > > Hi,
> > >
> > > Im thinking of adding a soundcard to my system and wondered what
> > people
> > > thought was the best choice. Im running Linux (2.2.5) and 98 (just
> > for
> > > games). I want some decent sound but Im not sure if I need to feel
> > > immersed in some 3D experience (I just dont believe that a set of £50
> > > speakers can do that). Basically I will be playing games in 98,
> > > listening to CDs and maybe some web audio under both and I may record
> > > some of my vinyl onto cd in the furture. From my local dealer the
> > > choices seem to be:
> > >
> > > soundblaster 64 PCI - £17
> > > soundblaster AWE64 ISA - £27
> > > soundblaster 128 PCI - £30
> > > soundblaster live value - £43
> > >
> > > all oem.
> > >
> > > So what do people think is a good choice? I dont want too much hassle
> > > in setup and want the card to work as well as can be expected in both
> > > linux & 98. Im only going to spend about nother £30 on speakers too.
> > >
> > > Any advice gratefully recieved.
> > >
> > > --
> > > Dr. Tony Lacey - Imaging Science & Bio-medical Engineering, University
> > > of
> > > Manchester Stopford Building, Oxford Rd., Manchester. UK. M13 9PT
> > > [+44 (0)161 275 5570] [EMAIL PROTECTED]
> > > http://www.niac.man.ac.uk/~ajl/
> > >
> snip
>
> First off: kiss ur retailer > that's dirt cheap for all cards , compared to
> here.
> Second. The setup of soundcards in Linux will remain an utter bitch in the
> near future. Just when i thought hacking my pnpisa.conf was enough and then
> let the kernel have a go at it..........NOT! Another option would be to buy
> drivers from OSS........but that'll cost good money. 98 'll support all
> these cards no problem though. I'd say go for PCI. The AWE64 is too old and
> too hissy anyway. The 64 PCI should be fine. (just check if there already is
> linux-support for it)
>
> hope this helps, semtex
OSS sound is only $20 and if you buy SuSE at $30 at CompUSA or
Barnes And Noble you get it for free for ISA cards.
--
use OS/2 for a crash proof work environment
use Linux for safe and quick internet access
use Winblows to test the latest viruses
http://www.netonecom.net/~bbcat/
We have software, food, music, news, search,
history, electronics and genealogy pages.
------------------------------
From: Andrew Evans <[EMAIL PROTECTED]>
Subject: Dump - file number=0, ide tape, Help!
Date: Fri, 09 Jul 1999 21:50:08 -0400
Folks -
I've been successful using ide tape drives but cannot get
mt to recognize dump file numbers so that I can use mt and
fsf, or use scripts to record positions after various
operations. Typically, mt responds with:
# mt -f /dev/nht0 stat
Unknown tape drive type (type code 0)
File number=0, block number=0.
mt_resid: 0, mt_erreg: 0x0
mt_dsreg: 0x6800, mt_gstat: 0x0
General status bits on (0):
I'd really like it if "File number=" reflected reality. Has
anyone got this going, or suggestions? I have a:
hdd: CONNER CTT8000-A, ATAPI TAPE drive
among other similar devices...
Thanks for any input, I haven't seen this documented, at least
not within the searches I conducted.
- Andy
Andrew Evans Computer Science Department
Computer Specialist University of New Hampshire
[EMAIL PROTECTED] Durham, NH 03824
------------------------------
From: Nack <[EMAIL PROTECTED]>
Crossposted-To: comp.sys.ibm.pc.hardware.chips,comp.sys.intel
Subject: Re: Summary and Clarification (Celeron, what's the catch?)
Date: Fri, 09 Jul 1999 22:32:17 -0400
I looked at that price list. Very bad prices. $200 for a 128MB memory
upgrade??? I think not. That is a $75 item, RETAIL. Build your own.
Make sure it meets or exceeds their requirments. You can probably do it
for 30-50% less than they will charge you.
Nack
FM wrote:
> -> An overwhelming consensus against buying a computer from
> college
>
> I might or might not have much choice regarding this issue.
> This college has strict computer-ownership requirements and
> it will be a hassle to fit a new system into them. I have
> recently checked Dell's website and the price was fairly
> similar (Dell's definitely overpriced, at least as far as I
> know). Although I'm sure I can get a better deal outside, I
> might be eligible for financial aid if I buy one from
> college. (I'm still waiting for the mail package which
> should have all this relevent information including prices).
>
> -> Celeron's performance (favors comparably against PII/PIII
> for price/performance although trails slightly behind in
> some areas)
>
> I guess Celeron suffices for my purposes.
>
> -> Get K6-3/K7/*
>
> Well I don't think I really have any choice, if I buy one
> from college. I'll look into K6-2/3 if I get to choose my
> own system. I have neither the bucks nor the time for K7,
> having already ordered a small laptop.
>
> -> Celeron 300a has a shorter cache latency than a Celeron
> 466 (Chris Robato Yao)
>
> Somehow I didn't quite understand how this is the case. So
> for CPU's, 300@450 is fastr than genuine 450? Or is this a
> particular case for Celerons?
>
> Thanks a lot for all the replies.
>
> Dan.
------------------------------
Date: Fri, 09 Jul 1999 18:35:00 -0700
From: Ken <[EMAIL PROTECTED]>
Subject: Flash card readers for Non-Windows?
Crossposted-To: rec.photo.digital,comp.os.os2.setup.misc,comp.sys.mac.hardware.misc
Flash cards look very attractive, given their considerably higher
density than floppies.
I've heard of after-market card systems that can be installed in a spare
floppy bay on a desktop. Do any work with Linux, OS/2, or MacOS?
Do all cameras that use standard Flash cards store to them using vfat?
Are there any that store in a proprietary filesystem format that I
should avoid?
Chris Kuhi wrote:
>
> Well, I just borrowed a Nikon Digital Camera from my work which uses
> Flashcards. Ours had a pcmcia adapter for the flash cards which appears to
> a laptop as a removable IDE controller. All I had to do was compile the
> kernel to support removable IDE controllers, and the card was available as
> /dev/hde1, which I mounted with '-t vfat'. Absolutely transparent, and a
> hell of a lot quicker (and compacter) than a floppy. Of course this isn't a
> great option if you don't have a laptop :(
>
> chris
--
Ken
mailto:[EMAIL PROTECTED]
http://www.sewingwitch.com/ken/
http://www.215Now.com/
------------------------------
From: Nektarios Lathiotakis <[EMAIL PROTECTED]>
Subject: Re: Recompile kernel, RH 5.0
Date: Sat, 10 Jul 1999 00:32:03 GMT
William Horton <[EMAIL PROTECTED]> wrote:
: I get: "No rule to make target "menuconfig."
You either:
a) tried the command in the wrong directory. It must be
/usr/src/linux
b) havent installed the kernel source (its in the distribution cd).
c) corrupted source tree (e.g. removed by mistake the makefile). Then
reinstall the kernel source.
I prefer make xconfig its easier.
good luck
nektarios
------------------------------
From: "Christopher and Kelly Wood" <[EMAIL PROTECTED]>
Subject: Double CD-ROM Stack
Date: Fri, 9 Jul 1999 20:47:23 -0500
I have a DVD and CD-ROM installed on my system. DVD is recognized as
/dev/cdrom but what is the CD-ROM? Will the kernel default it to another
device or do I have to do some fiddling?
Thanks.
------------------------------
From: [EMAIL PROTECTED] (Chris Robato Yao)
Crossposted-To: comp.sys.ibm.pc.hardware.chips,comp.sys.intel
Subject: Re: Celeron, what's the catch?
Date: 10 Jul 1999 01:44:00 GMT
Reply-To: [EMAIL PROTECTED] (Chris Robato Yao)
In <[EMAIL PROTECTED]>, [EMAIL PROTECTED] (chrisv) writes:
>On Fri, 09 Jul 1999 02:21:54 GMT, [EMAIL PROTECTED] (Michael) wrote:
>
>>So you are saying that a 128K second level cache holds windows
>>operating system code, outlook express, Lotus 123, Netscape,
>>numerous background tray programs and never goes to main memory when
>>you task switch....?
>
>Idiot. Do you know how to read and think? Explain how you inferred
>that from what he said.
>
>The point is, that 128k vs 256k of L2 just doesn't make much
>difference in real-world performance. Data sets that won't fit into
>128k usually won't fit into 256k, either. Is that too difficult to
>understand?
I already mentioned this before. For the P6 core, 128K vs. 256K may not
make that much of a difference (although the original Pentium Pro had
256K.) But for the K6 core, it does. It's fast and aggressive integer
processing units coupled with a short pipeline means it's going to have
a hard time keeping that pipeline filled. That's why it has 64K of L1,
and it still eats that up faster. 128K of L2 on top of a 64K L1 won't
make much of a difference so it needs 256K at least. The K6 is a
processor that is relatively more cache "hungry" than a P6, so it
deserves a bigger cache to boot.
If you give the P6 the same size of caches as the K6, the K6 will still
be faster on general non FP code. Even if you give the P6 core L2
caches that are bigger than the K6-III, like up to 512K of on chip
L2, the K6 core is still *faster*. We know this for a fact by tracing
the scalability of K6-IIIs to 500MHz and cooled overclocked ones to
550Mhz, versus Xeons of different clock speeds.
Thus, bigger caches does not mean much on the P6 core (except for
server and SMP applications where you really
need them), but it does mean more for the K6 core.
Rgds,
Chris
>
>>So based on your qualifications how much code can fit into these
>>caches when multitasking and task context switching? Does everything
>>fit into the first 128K second level cache.
>
>No, of course not. And of course "everything" would not fit in 256k
>second level cache, either.
>
(And the NUMBER ONE top oxy-MORON
1. Microsoft Works
---From the Top 50 Oxymoro
------------------------------
From: "Charismo" <[EMAIL PROTECTED]>
Crossposted-To: comp.sys.ibm.pc.hardware.chips,comp.sys.intel
Subject: Re: Celeron, what's the catch?
Date: Sat, 10 Jul 1999 14:17:07 +1200
You're a real fire cracker arn't you?
"The fact that you would say this proves you to be clueless." - well, how
fast would your celeron be without it's L2 cache?
Oh, perhaps you should go back to school in order to learn how to spell.
"Go to school, and come bach when you have a clue." I believe you meant
"back" but then you could have confused a famous music composer with the
meaning of "back".... who knows with such a small head?
Anton
PS I'll be BACH
chrisv <[EMAIL PROTECTED]> wrote in message
news:[EMAIL PROTECTED]...
> On Thu, 08 Jul 1999 18:48:42 GMT, [EMAIL PROTECTED] (Michael) wrote:
>
> >You really don't know what your talking about. How fast is your
> >celeron without that peasly 128 cache that Intel grafed onto the
> >cacheless one? Is your Celeron a hotrod without that cache?
>
> The fact that you would say this proves you to be clueless. Have you
> ever heard of diminishing returns? Go to school, and come bach when
> you have a clue.
>
> >Go study some more and stop playing games on your voodoo.
>
> Idiot. You know nothing.
>
------------------------------
From: Oliver Kurth <[EMAIL PROTECTED]>
Subject: Re: Any CD Burners for linux?
Date: Sat, 10 Jul 1999 01:55:42 +0200
Krishna Behara wrote:
>
> Would like any information on CD burners that
> are compatible with linux.
>
> Thanks
See http://www.fokus.gmd.de/nthp/employees/schilling/cdrecord.html
There is a list somewhere of drives that are compatible with cdrecord.
I have a Mitsumi 4802 and that works as well.
Oliver
--
Oliver Kurth this mail was sent from home
Universitaetssternwarte Goettingen Geismarlandstr.11 - 37083 Goettingen
mailto:[EMAIL PROTECTED] http://www.uni-sw.gwdg.de/~okurth
phone: xx49-551-395055 home: -706164 fax: -395043
------------------------------
From: "Muuga" <[EMAIL PROTECTED]>
Crossposted-To:
comp.os.linux.help,comp.os.linux.misc,comp.os.linux.questions,comp.os.linux.setup
Subject: Cant get Creative Ensoniq AudioPCI to work
Date: Fri, 9 Jul 1999 21:31:49 -0500
Alot of ppl swear by this card(thats why I bought it), but it doesnt
configure too well under linux.
Under Win98 its irq=11 I/O=220 DMA=1
of course it works great under windoze :/
this is what it looks like under /proc/pci
#PCI devices found: Bus 0, device 10, function 0:
# Multimedia audio controller: Ensoniq Unknown device (rev 6).
# Vendor id=1274. Device id=1371. Slow devsel. IRQ 11. Master
#Capable. Latency=64. Min Gnt=12.Max Lat=128. I/O at 0xe800.
and /etc/conf.modules
#alias sound sb
#options -k sb io=0x220 irq=11 dma=1
I running RH 5.1 with a recompliled 2.0.37 kernel
on a FIC 503+ k6 300
I must have recompiled 2 dozen times(just for the sound section of make
menuconfig , since I got the card.
i get this on boot up :
#Sound initialization started
#Sound initialization complete
not once did I get something in between :(
maybe im missing something in the sound configuration part of compilation?
CONFIG_SOUND=y
CONFIG_SB=y
CONFIG_AUDIO=y
CONFIG_YM3812=y
SBC_BASE=220
SBC_IRQ=11
SBC_DMA=1
SB_DMA2=-1
SB_MPU_BASE=388
SB_MPU_IRQ=-1
DSP_BUFFSIZE=65536
if you have this card and got it working under linux , please tell me how
you have you box configured.
Thanks
------------------------------
From: "James" <[EMAIL PROTECTED]>
Crossposted-To: comp.os.linux.setup
Subject: Re: Internal Modem
Date: Thu, 08 Jul 1999 23:51:47 GMT
I think this internal modem is a Winmodem, and, as it,
it's not a real modem. In fact, those pseudo-modems
work with software and this softs are not developped
for Linux by the manufacturer. Winmodem emulate a
real modem thanks to CPU (the software). So, I'm
really sad to tell you that your "modem" will never work
under Linux, except if the manufacturer provide the soft !
Sorry.
Asim Shankar a écrit dans le message <7m1fpt$jup$[EMAIL PROTECTED]>...
>Hi!
>
>I have an internal ISA Plug-N-Play USRobotics 33.6Kbps FAX modem.
>I just installed Caldera OpenLinux 2.2
>
>How do I get the modem working in Linux??
>
>I retrieved some info from the Windows' Device Manager, namely the IO
>addresses and IRQ for the modem, if that helps. It's also assigned COM3 in
>Windows.
>
>IO - 03E8-03EF
>IRQ - 5
>
>Please tell me how to get this modem functional for Kppp etc.
>
>Thanks,
>
>-- Asim Shankar
>
>
>
------------------------------
From: [EMAIL PROTECTED]@[EMAIL PROTECTED] (David T. Wang)
Crossposted-To: comp.sys.ibm.pc.hardware.chips,comp.sys.intel
Subject: Re: Celeron, what's the catch?
Date: 10 Jul 1999 02:06:50 GMT
Stephen M. Caplan ([EMAIL PROTECTED]) wrote:
: Andrzej Popowski ([EMAIL PROTECTED]) wrote:
: > 9 Jul 1999 05:09:57 GMT, [EMAIL PROTECTED] (Stephen M. Caplan)
: > wrote:
: > >> CPUs are synchronous,
: > >
: > >Maybe we're running off a different definition of "synchronous". From your
: > >description, the bus speeds are synchronous not the CPU speeds (since the
: > >multipliers are different).
: > For each 11 CPU clock periods of Celeron550, Celeron450 has 9 periods.
: > Different speed but synchronius operation :-)
: Not to be agrumentative but ...
: From webster's dictionary:
:
: synchronous, adjective
: 2 : recurring or operating at exactly the same periods
: The period off a Celeron 550 is 1.82ns ( 1/550 MHz).
: The period of a Celeron 450 is 2.22ns ( 1/450 MHz).
: Since 1.82 != 2.22, the CPU's are not synchronous. As I've mentioned, their
: bus speeds are synchronous (10ns each); apperently that is all that matters.
: (which makes me wonder why I'm argueing the definition of "synchronous" as
: it applies to CPUs -- oh right, this is a usenet article, that explains it.)
"synchronous" itself has no real meaning in the SMP environment, as the
processors have (usually) different loads, and they make drastically different
request to I/O, memory etc. The only thing that was ever "synchronous"
between them is the memory bus speed. That has to be synchronous, and
the multipliers need not be the same. (although you introduce a variable
which is not exhaustively tested, and may be fully buggy)
So at the interface which the CPU's "talk" to each other, that interface is
still fully "synchronous". Internal to each CPU, the clock signals are
not themselves internally synchronized between the two CPU's.
: --
: Steve
--
main(){while(1){switch(rand()%7){case 0:printf("Illogical.\n");break;case 1:
printf("Balderdash.\n");break;case 2:printf("Non sequitur.\n");break;case 3:
printf("Incorrect.\n");break;case 4: printf("See what I mean\?\n");break;
case 5:printf("Irrelevant.\n");break;case 6:printf("Poppycock\n");break;}}}
------------------------------
From: Rich Piotrowski <rpiotrow*nospammin'*@worldnet.att.net>
Crossposted-To: alt.os.linux.caldera,alt.linux,alt.linux.sux,alt.os.linux
Subject: Re: LI
Date: Fri, 9 Jul 1999 22:39:11 -0500
On Thu, 08 Jul 1999, TURBO1010 wrote:
>Help. Finally got Linux installed again, my computer. I have a Tyan 1564/D
>256 megs of ram. Adaptec 2940U2W, with an IBM 9.1 gig LVD drive. The
>install went smooth, was able to recompile the kernel, and enable smp
>support. So I decide to throw in a Promise UDMA controller, that went
>pretty good too. The card was detected with no problems. I added 2 more
>ide hard drives, connected to the controller, was able to fdisk them, and
>format them in linux. Edited fstab, and moved /home and /usr over to the
>new drives. Cool, everything is working perfect. I decide to IP
>masquerade, and so I rebuild the kernel. That went smooth, no problems. I
>run Lilo, now that the new drives are mounted, and it complains that
>/dev/sda1 is not the first drive, but it still installs on sda1. I go to
>reboot, and get LI. That's all that I get. I can't boot back in. I try
>the lisa disk, type in boot root=/dev/sda1 and it appears to start, but it
>throws me right back into installing Caldera. It wont let me boot. I tried
>the install/boot disk, with the same parameters, boot root=/dev/sda1 and get
>the same thing, throws me right back to the install. Tried booting from CD
>with the same parameters, and I get the same error message. I reboot and
>get LI. Anyone know what I need to do to get back into my system, without
>reinstalling the software? I figure if I can get in there, and umount the
>other drives, then I could run lilo, and configure my system.
>
>Thanks in advance.
Go to:
http://metalab.unc.edu/LDP/HOWTO/mini/LILO-4.html
"Seek and ye shall find"
Rich Piotrowski
------------------------------
From: a?n?g?e?l?@lovergirl-DOT.com (L.Angel)
Crossposted-To: comp.sys.ibm.pc.hardware.chips,comp.sys.intel
Subject: Re: Celeron, what's the catch?
Date: Sat, 10 Jul 1999 02:25:17 GMT
Reply-To: ?a?n?g?e?[EMAIL PROTECTED]
"Charismo" <[EMAIL PROTECTED]> wrote:
>This is true, the K7 does additional instructions within the 3dnow! set.
>But! The main reason that ISSE has more instructions is because the majority
>of them are MMX instructions that have been simply copied over to save the
DUH!!!
>processor having to switch to the MMX unit and back to the ISSE whenever it
>wants to blend in an MMX instruction. Quite clever, but not terribly
>efficient...
so EXACTLY how many of the vaunted ISSE instructions are actually
original ones? :P
The little lost angel & her featherhead's 2 cents of dreaminess. :)
Email : Figure out what to remove, I'm getting tired of spam
------------------------------
From: "Charismo" <[EMAIL PROTECTED]>
Crossposted-To: comp.sys.ibm.pc.hardware.chips,comp.sys.intel
Subject: Re: Celeron, what's the catch?
Date: Sat, 10 Jul 1999 14:10:07 +1200
This is true, the K7 does additional instructions within the 3dnow! set.
But! The main reason that ISSE has more instructions is because the majority
of them are MMX instructions that have been simply copied over to save the
processor having to switch to the MMX unit and back to the ISSE whenever it
wants to blend in an MMX instruction. Quite clever, but not terribly
efficient...
Anton
> >comperable. ISSE has more instructions and a bit more flexibility,
> But 3DNow! supposed to have added instructions in the K7 isn't it? :P
>
> For some reason, K7 still sounds better than Athlon... :P
>
> The little lost angel & her featherhead's 2 cents of dreaminess. :)
> Email : Figure out what to remove, I'm getting tired of spam
>
------------------------------
** FOR YOUR REFERENCE **
The service address, to which questions about the list itself and requests
to be added to or deleted from it should be directed, is:
Internet: [EMAIL PROTECTED]
You can send mail to the entire list (and comp.os.linux.hardware) via:
Internet: [EMAIL PROTECTED]
Linux may be obtained via one of these FTP sites:
ftp.funet.fi pub/Linux
tsx-11.mit.edu pub/linux
sunsite.unc.edu pub/Linux
End of Linux-Hardware Digest
******************************
