home *** CD-ROM | disk | FTP | other *** search
- Path: news.netspace.net.au!usenet
- From: astroboy@netspace.net.au (Paul Dossett)
- Newsgroups: comp.sys.amiga.applications
- Subject: Re: Is MUI processor intensive?
- Date: 23 Feb 1996 05:26:49 GMT
- Organization: NetSpace Online Systems
- Message-ID: <8332.6626T1047T1213@netspace.net.au>
- References: <4f80sp$m2h@due.unit.no> <1468.6611T653T370@datashopper.dk><1394.6613T995T2132@netspace.net.au><2445.6614T1150T1609@imaginet.fr>
- <4862.6619T1138T2039@netspace.net.au> <5071.6620T597T735@imaginet.fr>
- NNTP-Posting-Host: dialup-a1-2.mel.netspace.net.au
- X-Newsreader: THOR 2.22 (Amiga;TCP/IP) *UNREGISTERED*
-
- Yann-Erick Proy (yeproy@imaginet.fr) said:
-
- >> I did mention that I had a faster processor than a 1200, so don't try and
- >> use that against me.. ;)
-
- >Sorry, couldn't resist...
-
- I forgive you.. this time.. :)
-
- >>>The standard 25 MHz '040 A4000 is even better, with 51% instead of 40%.
- >>
- >> Something's wrong there, all things being equal, the 1200 board should have
- >> been faster due to the A4000's memory bus..?
-
- >Sorry for the imprecision: the 1200 was PAL, while the 4000 was NTSC. This is
- >sufficient to explain the speedup (even if the comparison screen is always
- >640x200). I don't think memory, that is to say FAST memory, is so much used
- >during this test.
-
- Okay, I'm quite happy with that.
-
- >>>AGA is not a great performer, for sure. But it is still 50% faster than
- >>>ECS.
- >>
- >> Here's the kicker, my friend!
- >>
- >> ECS: AGA:
- >>
- >> 16 bit bus 32 bit bus AGA=2x speed
- >> 7.09 MHz clockrate 14.2 MHz clockrate AGA=2x again, making a
- >> bandwidth of *4* times ECS!
- >>
- >> Do you see how shocking those benchmarks are now? You're comparing a
- >> chipset that has FOUR TIMES the bandwidth of my 1986 A2000, yet you're not
- >> even DOUBLING the speed in real-world benchmarks!
-
- >What does it may prove then? Maybe that the WritePixel test of AIBB is a
- >compound test that implies many other tasks than simply overflowing the CHIP
- >bus with data... For instance, when comparing Picasso equipped setups, this
- >test proves to be highly correlated to CPU power.
-
- Well! If it's a compound test, then it's likely been written to act as much
- like a complex process rather than something trying to funnel as much data
- through the chipset as possible. That is, it's attempting to flood caches
- and buses to correlate with real world programs, which is what I'm interested
- in. This kind of backs me up, perhaps?
-
- >Many, many parameters may alter the results of benchmarks. Original video
- >modes are ones that must be counted carefully, with screen mode, ROM
- >location, ROM version, system improvements patches and so on.
-
- Yep, so bugger 'em, that's what I say. This thread is a waste of time. If
- your machine is fast enough to do what you want, that's fine. How did we
- start this argument, anyhow? I honestly don't remember :)
-
- >> Now do you understand my statement that AGA doesn't speed things up
- >> incredibly?
-
- >Anyway, I am not stating that AGA is speedy either. As a matter of fact, in
- >the LineTest test, my Picasso (which you consider not being a decent board)
- >still outperforms AGA by 3.50 times (the Picasso being in 256 colors mode,
- >ie chunky mode). Of course winner setups such as Cyberstorm+Cybervision are
- >even better (10 times and more) thanks to better CPU and chipset.
-
- Mmmmmm... lovely! Gimme..
-
- I wasn't trying to put you or your board down, I just dislike the perception
- among some AGA folk (and one particularly vocal Australian fellow with a
- silly pseudonym) that AGA is the bees knees (or whatever). Personally, I'm
- sick of the limitations and just want to shovel data at >90Mb/sec into a PCI
- 24bit board. How long do you think I'll have to wait to do it with an Amiga?
-
- >> Ladies and gentleman, I thank you.
- >>
- >> (bows)
-
- >And tomatoes and whistles too... ;-)
-
- I don't understand this reference, but oh well.
-
- >> As you seem obsessed with the lack of speed of my computer, Yann, could you
-
- >You're overrating a bit my concern, you know...
-
- I was joking.. :)
-
- >> answer me something (not flaming, just a legitimate question)? Do you have
- >> the PD program MacBench 2.0 for the Mac, and could you tell me the speed
- >> your
-
- >Nay, I haven't this one. But since I'm err... "obsessed" with benchmarks,
- >I will manage to get it...
-
- Note that it's about 5Mb or so long! I have *no idea* what's in there to make
- it so bloody massive, it checks out as not being a fat binary..!
-
- >> 28Mhz Picasso gets on the graphics test (in 256 colours, preferably)?
- >>
- >> I'm *very* interested in how a 2000 with a 16bit graphics bus compares to a
- >> 32bit Quadra. Right now in monochrome my system gets something like:
-
- >According to some other benchmarking software I was given to try, the answer
- >is: *very* poorly. I will manage to produce the real numbers if you requires
- >me to.
-
- Please do!
-
- >By the way you must pay attention to the fact that very fast graphics boards
- >are no more great performers when installed in the Zorro II bus (max
- >bandwidth
- >3,5 MB/s). So even if the Piccolo SD64 is better than the Picasso,
- >you shouldn't expect much in ZorroII mode. Before the CyberGraphX stuff, the
- >Picasso counterbalanced it's lack of speed by good and stable WB emulation,
- >which inluenced my choice. (This was slightly off-topic, sorry.)
-
- I know this, but I don't plan to have a 2000 forever. Somewhere there is a
- cheap 3000 with my name on it (and the owner is probably getting out the
- cleaning liquid and wondering how it got there).
-
- >> Processor : 105%
- >> FPU: 98% (not sure why this is lower, but oh well)
- >> Graphics: 118% (!! This is on a chipset with half the bandwidth! I'd
- >> love to know what Christian has done to get this mark so good!).
-
- >When at school, you enjoyed to kick much smaller boys than you, didn't you ?
- >B)
-
- No, I was always picked on by the nasty grade fives. Then in high school
- I was into Dungeons and Dragons and needed glasses and got picked on
- because I blinked too much...? Maybe this is my way of getting back...
-
- Actually, it was more an attempt at praising ShapeShifter and CB... oh well,
- sycophants never prosper.
-
- >Now you're comparing monochrome graphics with 256 colors graphics (because
- >the Quadra was tested with 256 colors, wasn't it?)... :-P
-
- Well, maybe I was naive, but I had assumed a 5Mb Mac benchmark program would
- take this into account! I would *hope* it does, because there's a more
- advanced list you can check which shows my Amiga doing some things (lines,
- etc) at about 700%, but others at only 20% or so. Oh, who knows what I'm on
- about. Apologies to everybody who's spent the time and money to download
- this.
-
- >> I'm really hoping my system can run Doom, etc. nicely, but it seems
- >> illogical that it can with such a slow Zorro-II bus. Can you give me any
- >> information? Anyone?
-
- >Erm... Monochrome vs 8 bits graphics?
-
- I don't know. Like I said...
-
- Maybe the program is terminally stupid. Maybe I am.
-
- >> Then explain the shoddy results you're turned up.
-
- >The ball is yours, now...
-
- Then I'm taking my bat as well, and going home. I can't see the point. I
- don't like arguing.. it's far too hot and it doesn't make me a *big man*, so
- why should I bother? :)
-
- >>>Anyway, it could help clarify things if a user of a A600+A620 could send me
- >>>an AIBB module from his machine.
- >>
- >> Does such a creature exist?
-
- >I hope so, I'm a greedy collector, you know.
-
- Well, alright!
-
- >>>Of course one could argue that benchmarks represent vaguely (at best...)
- >>>the feeling of speed that people have in everyday life, but I guess it is
- >>>another debate...
- >>
- >> Yep, and I'll keep on bitching for as long as you like! This is fun.. ;)
-
- >It's my pleasure to teach you... ;-) ;-) ;-)
-
- Sorry, I'm sick of it now.. No, this isn't being a poor loser, I'm happy to
- keep it up via email, but I don't think this is advancing the cause for
- mankind or anything, so let's save the bandwidth, okay?
-
- >> The feeling is mutual, mate! I have no problems with differing opinions,
- >> in
-
- >Then you're not a real Amigafan, for sure...
-
- >Errr... Probably I will regret this one sooner or later... ;-)
-
- Fuck you you L0000SER! you dont know SHIT about whatt your TALKING BOUT!!!!!!
- my AMIGA is KICKASS!!!!!
- YOU probly oown a PEECEE and your a FAGOT and you SUCK!
-
- :)
-
- (Apologies to any homosexuals, PC owners and the politically correct)
-
- >> fact I thrive on them... :)
-
- >Regards,
-
- >Yann
-
- >--
- >Yann-Erick Proy yeproy@imaginet.fr - Yann-Erick.Proy@Imag.fr
- >A2000/PPS040/Picasso/USR28k Quantum730/Maxtor330/Toshiba4x/Cipher150
-
- Hey, mail me with the benchmarks you find...
-
- I don't argue well when it's 35 degrees... :(
-
-
- --
- Paul Dossett | Yamaha, Epiphone, Pearl, Paiste | Amiga 2000/040/21/365/3.1 __
- -------------| RASTER Bubble Bobble betatester | Amiga CD32/020/2/CD/3.1__///
- boo! : astroboy@netspace.net.au.. | '76 Toyota Corolla 1.2 \XX/
-
-