Mac OS X Intel Build 8F1111 [Archive]

MacRumors

Nov 30, 2005, 12:32 AM

http://www.macrumors.com/images/macrumorsthreadlogo.gif (http://www.macrumors.com)

Appleinsider points to (http://www.appleinsider.com/article.php?id=1389) recent developer updates to Mac OS X for Intel.

According to the rumor site, Apple has distributed Mac OS X 10.4.3 Intel Build 8F1111. The update is said to provide additional printer drivers, native version of Quicktime 7.0.4 and other improvements.

One component that saw significant updates included Rosetta - Apple's PowerPC emulation layer for the Intel Macs.

Rosetta included improved support for OpenGL as well as support for AltiVec. This report confirms a previous Page 2 report (http://www.macrumors.com/pages/2005/11/20051122093403.shtml) claiming the same.

nagromme

Nov 30, 2005, 12:39 AM

Rosetta is starting to sound really good. It may be slow in some cases... but if my apps at least will RUN, then it's a life-saving stopgap for me.

And my next (Intel) Mac will be quite a bit faster than my current one, which will help offset Rosetta's performance issues, while I await more native Intel apps.

stoid

Nov 30, 2005, 12:42 AM

Mac OS X 10.4.3 is build 8F46, right? Are build numbers comparable between architectures? Current 10.4.4 build seems to be 8G9. Are they building both at the same time? is there an Intel 10.4.4 8G9?

Staffroomer

Nov 30, 2005, 12:53 AM

I'm waiting to buy my new intel iBook.. Any developments make me a happy individual

dansgil

Nov 30, 2005, 12:57 AM

andrewm

Nov 30, 2005, 12:59 AM

http://www.macrumors.com/images/macrumorsthreadlogo.gif (http://www.macrumors.com)

...

Rosetta included improved support for OpenGL as well as support for AltiVec. This report confirms a previous Page 2 report (http://www.macrumors.com/pages/2005/11/20051122093403.shtml) claiming the same.

Seeing as this is still Page 2, perhaps the word 'confirms' should be replaced with 'corroborates'? Just splitting hairs.

Edit: Ah, scrummy. We've moved to Page 1, so never mind. Carry on!

And do hurry, Apple--I want to play with these new system when they come out, even if they act just the same! (Although don't hurry so much that you make mistakes... we're counting on you...)

treblah

Nov 30, 2005, 01:00 AM

Can we just skip December and go straight to MWSF?

mad jew

Nov 30, 2005, 01:00 AM

Well, if Rosetta supports Altivec, then there is no reason for me not to get the first Intel Powerbook. I think not having Rosetta support Altivec would deter many, many users from buying Intel Macs when they first arrive.

I've always wondered just how effective Altivec is though. I've always thought it was more of a marketing term rather than an engineering one.

SiliconAddict

Nov 30, 2005, 01:00 AM

The interesting thing is going to be on laptops. Only the most die hard fanbois would claim that the PowerBook is a match for the latest single core Pentium M's. Never mind the introduction of next year's dual core Yonah. For the rest of us who know better its going to be supremely interesting to see native apps on a 1.67Ghz PPC PowerBook go up against a dual core Yonah at 2.xGhz. I'm wondering what is the possibility that the dual core Yonah running apps in Rosetta could at least keep up, if not match, apps running natively on the 1.67Ghz PPC PowerBooks. Yes I know some of you scoff at the idea but the simple fact remains that the PowerBooks is not aging well and using two cores to aid Rosetta. . . well who knows.
Again I can't wait to see the first batch of benchmarks on FINAL Macintel PowerBooks. (None of this hack the prereleased OS onto Toshiba’s and lets see how it performs.)
Of course it won't really matter. By that time I will already have ordered mine, done a little jig, and started salivating in anticipation of the USP truck.

mad jew

Nov 30, 2005, 01:03 AM

By that time I will already have ordered mine, done a little jig, and started salivating in anticipation of the USP truck.

Count me in for a small jig too. I've already promised myself an Intel iBook. I've just got six or so months to come up with a justifiable reason.

SiliconAddict

Nov 30, 2005, 01:04 AM

Can we just skip December and go straight to MWSF?

Amen to that. Can I get a temporary coma of say 39 days? I hear they can induce comas via iv drips now a days. Wonder if my medical coverage would cover that? :D :eek:

Lacero

Nov 30, 2005, 01:06 AM

Can we just skip December and go straight to MWSF?
Christmas, for me, happens in December and January. :D

Hopefully, this Quicktime update fixes the H.264 gamma display bug and makes general speed improvements to encoding, as well. :cool:

stoid

Nov 30, 2005, 01:06 AM

toneloco2881

Nov 30, 2005, 01:07 AM

Well, if Rosetta supports Altivec, then there is no reason for me not to get the first Intel Powerbook. I think not having Rosetta support Altivec would deter many, many users from buying Intel Macs when they first arrive.
Well considering that probably 90% of people don't even have a clue what Altivec is, I don't think it will make too much of a difference. :)

dontmatter

Nov 30, 2005, 01:13 AM

Can we just skip December and go straight to MWSF?

Don't do that, December is when all the ipod sales will be!! ;)

Yeah, no kidding. It's going to be so awesomely fantastic, or so utterly dissapointing. Either way, it'll be a big day.

SiliconAddict

Nov 30, 2005, 01:23 AM

Seeing as this is still Page 2, perhaps the word 'confirms' should be replaced with 'corroborates'? Just splitting hairs.

Umm its page one. Did they move it or something? *shrugs*

obeygiant

Nov 30, 2005, 01:26 AM

GFLPraxis

Nov 30, 2005, 01:38 AM

AltiVec means Mac games will work. w00t!

will intel mac be able to run windows software?
i know this sounds like a dumb question, but intel macs
technically wont run regular mac software without rosetta,
so will the new mactel machines be able to run ANYTHING
that not written for the exclusively?

No, the same way Linux cannot run Windows applications.

However, CrossOver Office for Mac is under development, which should let you run most Windows programs on a Mac.

SiliconAddict

Nov 30, 2005, 01:41 AM

How can you tell that the PowerBook is dragging? My 2 year old 15 inch Aluminum PowerBook runs at 1.25 Ghz and still does great keeping up with a fresh out of the box top of the line current PowerBook. Until the higher screen res was introduced, my PowerBook was still almost indistinguishable from the new ones.

Go back two years before I got my PowerBook and you've got the very first G4 PBooks that ran at only 500-600 Mhz. Yeah, PowerBook development has slowed in the last few years, and a dual-core Yonah is going to be the kick that the PowerBook line NEEDS!

That’s my point. A two year old PowerBook doesn't show a marked improvement over today’s top of the line PowerBook mainly because of the starved FSB. Apple has been able to pull some magic with utilizing more and more of the GPU in each new OS for the GUI to keep things relatively snappy but http://www.barefeats.com/ and their benchmarks show that speed increases from rev to rev of the PowerBook are minor. All the while Intel and the Pentium M have been gaining momentum. Not major momentum but enough that from revision to revision of not only the CPU’s but the chipsets they just keep slowly pulling further and further away form the PowerBook. It’s the damn FSB is what is/was killing the G4. What good is a 1.6Ghz CPU and RAM running at 333MHz when the FSB runs at 167Mhz? Like trying to drive water from a firehose through a straw.
Its not hard to do the math. I have zero doubt that the Freescale would have solved this dilemma and would have brought a breath of fresh air to the G4 but unfortunately we will never know just what kinda of performance boost it would have given. My sneaking suspicion is that it would have matched up well against the low end G5 PowerMacs. (Probably even beating them in some cases.) But of course that is pure speculation.

SiliconAddict

Nov 30, 2005, 01:43 AM

AltiVec means Mac games will work. w00t!

No, the same way Linux cannot run Windows applications.

However, CrossOver Office for Mac is under development, which should let you run most Windows programs on a Mac.

It might be possible. If Windows is installed on a sep partition a app may be able to use the API's to run apps in OS X. Lindows or Linspire or whatever the heck they are calling themselves these days did this. I remember trying out Lindows when it first came out. The thing resized my system partition and installed itself alongside windows. I was able to run Internet Exploder, Office and numerous other apps through Linux.

risc

Nov 30, 2005, 01:46 AM

will intel mac be able to run windows software?
i know this sounds like a dumb question, but intel macs
technically wont run regular mac software without rosetta,
so will the new mactel machines be able to run ANYTHING
that not written for the exclusively?

With universal binaries OS X apps run on the PPC and x86 platforms so yeah OS X x86 can run OS X apps, when you say "regular" Mac apps you mean old software that hasn't been recompiled for universal binaries? I'm sure as soon as the x86 Macs hit the market you'll see a flood of updates (just like any OS X update) and these new apps will all be universal binaries. The real question though is how soon can we expect 3rd party commercial apps to be upgraded, and how will this be handled brand new apps you need to pay for, or will they bring out universal binary upgrades for free?

As for Windows software of course not, it's an OS X box not a Windows one... I'm sure things like wine will be ported though.

Mechcozmo

Nov 30, 2005, 02:03 AM

As for Windows software of course not, it's an OS X box not a Windows one... I'm sure things like wine will be ported though.

Linkety (http://darwine.opendarwin.org//)

EricNau

Nov 30, 2005, 02:09 AM

iMeowbot

Nov 30, 2005, 02:23 AM

I've always wondered just how effective Altivec is though. I've always thought it was more of a marketing term rather than an engineering one.
One thing that is very real is the push from Apple for developers to useSIMD, while in the Wintel world there has been more of a push from the marketplace to target relatively ancient processors.

Mac developers will be able to ignore legacy stuff from before 2005, and possibly even some of this year's limitations depending on what chips are available to Apple once real production machines roll out (for example, some say that we will only see SSE2 support, but that may simply be caution on the part of Apple in case Intel ship dates slip).

Catfish_Man

Nov 30, 2005, 02:27 AM

I've always wondered just how effective Altivec is though. I've always thought it was more of a marketing term rather than an engineering one.

It's real, it's effective, and it's an engineering term. If you want a less fancy name for it, use VMX. Really altivec-heavy apps are pretty rare, but it's used in smaller ways in all sorts of places. Unfortunately for the G4 (and to a much lesser extent the G5), it can't make up for crappy performance at other stuff.

displaced

Nov 30, 2005, 02:28 AM

I'm starting to get excited about the intel Apples. At first I never would have thought of buying one (for the first few years), but it sounds like Apple is working hard on making it "flawless." They know they can't blow it this time (Apple has a bad history of this).

Rosetta sounds cool also.

I'd have said Apple's track record was pretty good for this sort of thing. The 68K to PowerPC transition wasn't too bad, all things considered. And Classic support in OS X was an elegant solution to a thorny problem. The move to OS X itself was pretty astonishing, completely altering perceptions of the entire platform in a little more than 4 years (personally, I'd argue a little less than 3 years!)

aafuss1

Nov 30, 2005, 02:42 AM

Nice to see a Intel-ready version of iTunes. I wonder if the TPM code has been tightend up even more.

EricNau

Nov 30, 2005, 02:42 AM

I'd have said Apple's track record was pretty good for this sort of thing. The 68K to PowerPC transition wasn't too bad, all things considered. And Classic support in OS X was an elegant solution to a thorny problem. The move to OS X itself was pretty astonishing, completely altering perceptions of the entire platform in a little more than 4 years (personally, I'd argue a little less than 3 years!)

I should have been clearer. Apple is usually good about creating good computers, but if I recall correctly, their first models after a big switch have been lacking in features, which in the past has cost them, big time. Many say this is why Apple didn't "boom" like Windows because Apple's first computers were lacking in features.
I think after the switch to PowerPC their computers were lacking things like USB and such. (this is coming from someone who has one, can't attach anything to it :( )

nagromme

Nov 30, 2005, 02:51 AM

I'm wondering what is the possibility that the dual core Yonah running apps in Rosetta could at least keep up, if not match, apps running natively on the 1.67Ghz PPC PowerBooks.
I think it's a sure bet that Rosetta will outrun a G4 in many situations. Especially when it comes to perceived responsiveness (as opposed to the duration of lengthy renders and conversions).

I say this because of comments from game developers at InsideMacGames about some 3D games performing very well under Rosetta. Well enough that there's no NEED to port some of them. And that's on the dev kits, which are pretty ordinary single core machines.

nagromme

Nov 30, 2005, 02:55 AM

AltiVec means Mac games will work. w00t!
Note that many games that say they require a G4 do NOT require AltiVec. A moot point, possibly, but Quake 3 engine games, for instance don't use AltiVec and reportedly run great even in the OLD Rosetta. Despite their requirements stating a G4. It turns out that stating a G4 is often done just because no G3 Mac was made fast enough. Not because the game--or other app--is incompatible with a G3.

nagromme

Nov 30, 2005, 02:58 AM

I think after the switch to PowerPC their computers were lacking things like USB and such. (this is coming from someone who has one, can't attach anything to it :( )
USB wasn't even around when they went PowerPC--that was in the mid-90s. But Apple (with the iMac) was one of the first, if not THE first, PC makers to widely adopt USB.

If you mean that when a new OS or CPU architecture comes out, it takes time for apps to fully take best advantage of it, that's true. Luckily, that process has been long since underway.

(Sorry for the triple post... 8 minutes and nobody but me is posting? :D )

EricNau

Nov 30, 2005, 03:06 AM

USB wasn't even around when they went PowerPC--that was in the mid-90s. But Apple (with the iMac) was one of the first, if not THE first, PC makers to widely adopt USB.

If you mean that when a new OS or CPU architecture comes out, it takes time for apps to fully take best advantage of it, that's true. Luckily, that process has been long since underway.

(Sorry for the triple post... 8 minutes and nobody but me is posting? :D )

USB and firewire came out in 1996 - not entirely sure when the Power Mac G3 All-in-one came out, but that's te computer he was refering to. I would be surprised if he didn't know what he was talking about, he really knows a lot about Mac Computers. Maybe I got a detail wrong. :confused:

I just know he said he would never buy a intel Mac right away because of his past experiences with Apple.

GregA2

Nov 30, 2005, 03:15 AM

I'm glad to see they added altivec support to Rosetta... Do you suppose FCP would work decently on a system like that?

nagromme

Nov 30, 2005, 03:21 AM

Maybe I got a detail wrong. :confused:
He said "when they went PowerPC", not "when they went G3"--maybe that's the missing detail :)

Still, Apple was ahead of other makers when it came to introducing USB.

Of course, the later the model of anything, the better. Waiting--if you can--always has benefits!

Thomas Harte

Nov 30, 2005, 05:47 AM

I've always wondered just how effective Altivec is though. I've always thought it was more of a marketing term rather than an engineering one.
To add to what has already been said, not only is Altivec a real engineering term, but it is a feature that is likely to be comparitively less speedy in Rosetta (in terms of "how many MHz is my Rosetta CPU?") because it doesn't map very well to the Intel solutions. At least with SSE3 Rosetta only has to deal with a 50% drop in registers, but whereas Altivec does most things in three address format (i.e. ra = rb + rc) the various Intel solutions do things in two address format (i.e. rb = rb + rc) and the permutation features of Altivec seem to be entirely absent from the Intel chips, although they're mostly used for formatting the result of Altivec computations so some additional costs there aren't necessarily crippling.

Of course the Intel architecture does things that would map badly to an emulated PowerPC, but that's completely beside the point. Universal binaries will almost certainly get more vector throughput from an Intel than a PowerPC.
I'm starting to get excited about the intel Apples. At first I never would have thought of buying one (for the first few years), but it sounds like Apple is working hard on making it "flawless." They know they can't blow it this time (Apple has a bad history of this).
But we have to factor in Apple's "secret agenda" here. Darwin is open source and has been buildable and usable on Intel hardware for many years. The keynote announcing the transition was performed with Intel hardware, implying that they probably could have put out a non-"flawless" first generation Intel box immediately. And unlike the transition to PowerPC, the Intel solutions already have a long history of deployment in exactly the kind of machines Apple will produce, aesthetics and software aside, so the knowledge and expertise is already widely available.

Dorkus Maximus

Nov 30, 2005, 05:57 AM

I'm glad to see they added altivec support to Rosetta... Do you suppose FCP would work decently on a system like that?

Good question. FCP is definitely an Altivec intense application to say the least. I'm not sure how it's progressed since its move to the G5, but I know I would be "porked" to say the least without Altivec on my Powerbook. I'm guessing that the move to the G5 may have helped with this transition, since it doesn't rely on the Altivec engine (I may be wrong).

Regardless I'll be picking up a dual-core powerbook the day they're released. It's unfortunate that the first systems will be problematic and outdated quickly (on the hardware end) as Apple quickly learns what doesn't work and what does with a few million beta testers. I have tons of faith in Apple, and think they'll do a better job than anyone else ever could at such a transition... but life is life. There are going to be some very fun, and by fun I mean horrible, growing pains.

Lastly, it would've been a fun idea to sell beta intel machines to users who want 'em, or even rent them out. I'd fork out a $1,000 for one or pay a few quid a month.

mdavey

Nov 30, 2005, 06:03 AM

Can we just skip December and go straight to MWSF?

I suggest we have a poll about that. I would be in favour. I can see many benefits, including having more money available for MWSF (saving on all those xmas present purcahses - even taking into account loss of one month's salary).

Perhaps we should have an option to swap the order of December and January? Might be popular with some.

generik

Nov 30, 2005, 06:05 AM

Regardless I'll be picking up a dual-core powerbook the day they're released. It's unfortunate that the first systems will be problematic and outdated quickly (on the hardware end) as Apple quickly learns what doesn't work and what does with a few million beta testers. I have tons of faith in Apple, and think they'll do a better job than anyone else ever could at such a transition... but life is life. There are going to be some very fun, and by fun I mean horrible, growing pains.

Is FCP a SMP compatible application?

gnasher729

Nov 30, 2005, 06:08 AM

Well, if Rosetta supports Altivec, then there is no reason for me not to get the first Intel Powerbook. I think not having Rosetta support Altivec would deter many, many users from buying Intel Macs when they first arrive.

Having Rosetta _support_ Altivec would actually deter me from ever buying an Intel Mac. Emulating a vec_perm instruction takes sixteen loads and stores, and in good have Altivec code half the instructions will be vector permutes. Expect emulated Altivec code to run much slower than emulated G3 code.

generik

Nov 30, 2005, 06:21 AM

sluthy

Nov 30, 2005, 06:23 AM

aegisdesign

Nov 30, 2005, 06:42 AM

What good is a 1.6Ghz CPU and RAM running at 333MHz when the FSB runs at 167Mhz? Like trying to drive water from a firehose through a straw.

Erm, you presumably weren't aware that the Intrepid2 controller in the new Powerbooks runs at a full 333Mhz then?

Not everything has to go through the FSB. A lot of the time Intrepid2 will shove data from RAM, GPU, Network or the harddisk straight into RAM via DMA at a full 333Mhz without involving the FSB at all. ie. at exactly the same speed as a Pentium-M with PC2700 DDR2 RAM.

FSB speed isn't as important as you imagine.

mad jew

Nov 30, 2005, 06:44 AM

Altivec is an engineering term. I was saying slightly tongue in cheek that it's more of a marketing term because Apple would have you believe it's more useful than it actually is. ;)

aegisdesign

Nov 30, 2005, 06:47 AM

Having Rosetta _support_ Altivec would actually deter me from ever buying an Intel Mac. Emulating a vec_perm instruction takes sixteen loads and stores, and in good have Altivec code half the instructions will be vector permutes. Expect emulated Altivec code to run much slower than emulated G3 code.

That's what I was wondering too. It's fine and dandy saying it now 'supports' AltiVec but how fast will it really be when SSE is slower than Altivec anyway and doesn't support all the features in AltiVec. Dropping back to pretending to be a G3 may be better.

Still, if it now runs code that otherwise would just refuse to run then that's perhaps a bonus.

runninmac

Nov 30, 2005, 06:47 AM

Can we just skip December and go straight to MWSF?

No honestly can we?

MWSF is going to be like X-mas all over again. I only need 1 x-mas a year why not have it MWSF?

aegisdesign

Nov 30, 2005, 06:50 AM

Altivec is an engineering term. I was saying slightly tongue in cheek that it's more of a marketing term because Apple would have you believe it's more useful than it actually is. ;)

Bull.

I've both G3 and G4 machines running at the same Mhz. iTunes encoding, video transcoding and the whole UI runs many times faster on the AltiVec equipped G4s.

It's the reason my G5 1.8 is almost twice as fast as my Pentium-M 1.7 at some media transcodes.

aegisdesign

Nov 30, 2005, 06:52 AM

Is FCP a SMP compatible application?

Of course. It's even capable of splitting tasks out to other Macs on the network.

mad jew

Nov 30, 2005, 06:54 AM

I've both G3 and G4 machines running at the same Mhz. iTunes encoding, video transcoding and the whole UI runs many times faster on the AltiVec equipped G4s.

Weird. My experiences are quite different. Maybe it's just how I use my Macs but in the limited time I used a 700MHz G3 iBook, I didn't notice all that much of a difference with my current 800MHz G4 iBook for CPU-related tasks. The G4 has more RAM so it was snappier in that sense but I was quite taken aback at how useless AltiVec seems to be. :(

It's the reason my G5 1.8 is almost twice as fast as my Pentium-M 1.7 at some media transcodes.

And AltiVec is the only difference between those two processors. :rolleyes:

Let's compare Apples with Apples. :)

aegisdesign

Nov 30, 2005, 06:57 AM

Regardless I'll be picking up a dual-core powerbook the day they're released.

Unless Apple also release an native Intel FCP on the same day then FCP running on your old PowerPC powerbook would most likely be faster and I'd guess by some margin. If they get even 10 to 20% speed in AltiVec emulation I'd be surprised.

Bits may run a bit quicker though now that they have Quicktime 7.0.4 as intel native. I'm not sure however how much in FCP is Quicktime and how much is their own code.

aegisdesign

Nov 30, 2005, 07:06 AM

And AltiVec is the only difference between those two processors. :rolleyes:

Let's compare Apples with Apples. :)

My iMac G5 1.8Ghz has a 600Mhz FSB, 512KB L2 cache, 1GB PC3200 DDR RAM

My PentiumM 1.7Ghz has a 533Mhz FSB, 2MB L2 cache, 1GB PC4200 DDR2 RAM

They're comparable most of the time. Sometimes the iMac is faster, sometimes the PentiumM. Sometimes the difference is huge - eg. OpenGL is hugely faster on Windows, anything media related is normally faster on the Mac.

mad jew

Nov 30, 2005, 07:14 AM

My iMac G5 1.8Ghz has a 600Mhz FSB, 512KB L2 cache, 1GB PC3200 DDR RAM

My PentiumM 1.7Ghz has a 533Mhz FSB, 2MB L2 cache, 1GB PC4200 DDR2 RAM

They're comparable most of the time. Sometimes the iMac is faster, sometimes the PentiumM. Sometimes the difference is huge - eg. OpenGL is hugely faster on Windows, anything media related is normally faster on the Mac.

One is apparently PPC and the other is X86. They're running two very different operating systems. Are you saying they're similar in terms of speed or not? Do you really think AltiVec has all that much to do with any speed difference anyway?

Look, the best real-world way of measuring the effectiveness of AltiVec is to sit two similar machines side by side with one having a G3 and the other a G4. When I did this, I thought generally speaking the differences were negligible for CPU related tasks. That's merely my experience and I'm more than happy to accept that you've experienced otherwise but bringing PCs into the equation is slightly misleading and ultimately pointless. :)

aegisdesign

Nov 30, 2005, 07:16 AM

USB wasn't even around when they went PowerPC--that was in the mid-90s. But Apple (with the iMac) was one of the first, if not THE first, PC makers to widely adopt USB.

I've a Toshiba laptop from 1996 that has USB on it. I couldn't actually use the port till late 97 though when Microsoft finally got around to fixing USB support. But then I'd have to use Win95B and it only sort of worked and at the time I was using NT which never had USB support until they came out with Windows2000.

Win98 was about the first OS to have it working acceptably. The first iMac was mid 1998. The claim that the iMac introduced it is bogus. Apple would not have introduced the iMac with USB if there weren't already USB printers or other peripherals.

mdavey

Nov 30, 2005, 07:21 AM

Of course. It's even capable of splitting tasks out to other Macs on the network.

Now, that is an interesting idea!

Most consumers will probably be happy with the performance on the January MacIntel boxes most of the time (and very happy with the "it just feels more snappy" effect every time they update the OS).

I'm guessing that at least initially, most people buying a January MacIntel box for professional use (if there is even anything suitable available) will probably have a PPC Mac box elsewhere on their network. How cool would it be to pass PPC-optimised tasks to the PPC box?

One of the great things about X11 in Unix is the ability to remote display individual applications from one machine on another. Does anyone know if Aqua offers a native equivilent?

aegisdesign

Nov 30, 2005, 07:37 AM

One is apparently PPC and the other is X86. They're running two very different operating systems. Are you saying they're similar in terms of speed or not?

At most tasks they are similar. Intel is faster at integer code and OpenGL on Windows at least. PPC is slower at integer and way slower at OpenGL but faster at anything that can be vectorised into neat little cache fitting routines.

Do you really think AltiVec has all that much to do with any speed difference anyway?

Yes.

Look, the best real-world way of measuring the effectiveness of AltiVec is to sit two similar machines side by side with one having a G3 and the other a G4. When I did this, I thought generally speaking the differences were negligible for CPU related tasks.

At one point I had a G4 Ti Powerbook 400Mhz and a G3 iBook 500Mhz. Both have the same FSB speed, same graphics hardware, same memory speed. The G4 would rip in iTunes at about 4.5 - 6x, the G3 at only 2-3x.

Here's a graph from back in the days of G4 upgrades at 400Mhz...
http://www.insanely-great.com/reviews/img/400g4z.jpg

See that long bar, that's a G3 running Photoshop without AltiVec.

That's merely my experience and I'm more than happy to accept that you've experienced otherwise but bringing PCs into the equation is slightly misleading and ultimately pointless. :)

This is a thread about Intel Macs and how fast Rosetta G4 emulation will be no? It's entirely relevant as to how much of a difference AltiVec makes and how fast an Intel chip can run the same vector tasks and how fast it can emulate G4 AltiVec code.

aegisdesign

Nov 30, 2005, 07:47 AM

One of the great things about X11 in Unix is the ability to remote display individual applications from one machine on another. Does anyone know if Aqua offers a native equivilent?

No. FCP (or more precisely the DVD Studio encoding, Compressor and Shake) uses XGrid on up to 10 network nodes.

You could I supose use Apple Remote Desktop to run a remote PPC Mac headless but that's more like VNC than X.

mad jew

Nov 30, 2005, 08:00 AM

At one point I had a G4 Ti Powerbook 400Mhz and a G3 iBook 500Mhz. Both have the same FSB speed, same graphics hardware, same memory speed. The G4 would rip in iTunes at about 4.5 - 6x, the G3 at only 2-3x.

Interesting. I remember using the same test and getting roughly 7x or 8x for both my G3 and G4 iBook. I remember thinking at the time that it was a pretty interesting result.

Here's a graph from back in the days of G4 upgrades at 400Mhz...
http://www.insanely-great.com/reviews/img/400g4z.jpg

See that long bar, that's a G3 running Photoshop without AltiVec.

I'm not necessarily arguing that AltiVec technology isn't effective, but rather that it hasn't been implemented as much as it could have been. Photoshop is obviously one of the few apps that has proper support for AltiVec which would explain your results (assuming the other update cards are roughly the same in terms of other specs.

This is a thread about Intel Macs and how fast Rosetta G4 emulation will be no? It's entirely relevant as to how much of a difference AltiVec makes and how fast an Intel chip can run the same vector tasks and how fast it can emulate G4 AltiVec code.

Agreed, it's relevant how fast an X86 chip will run AltiVec emulation but there are too many other factors to take into account before we can bring a standard PC running Windows (I assume) into the equation.

SiliconAddict

Nov 30, 2005, 08:54 AM

Erm, you presumably weren't aware that the Intrepid2 controller in the new Powerbooks runs at a full 333Mhz then?

Not everything has to go through the FSB. A lot of the time Intrepid2 will shove data from RAM, GPU, Network or the harddisk straight into RAM via DMA at a full 333Mhz without involving the FSB at all. ie. at exactly the same speed as a Pentium-M with PC2700 DDR2 RAM.

FSB speed isn't as important as you imagine.

Umm no I wasn't. If this was the case why aren't we seeing greater performances increases on the latest powerbook. The proof is in the pudding as they say. Certainly faster access to RAM with DMA is going to help but it doesn't change the fact that overall system perfornace is tied to the FSB. ONe thing I noted on Apple site about the controller. . .
and the memory interface is synchronized to the MaxBus bus interface at 167 MHz.
Link (http://developer.apple.com/documentation/Hardware/Developer_Notes/Macintosh_CPUs-G4/15inchPowerBookG4/2Architecture/chapter_3_section_4.html#//apple_ref/doc/uid/TP40003165-CH206-TPXREF109)

That right there is going to throttle whatever performance benefits you get.

geerlingguy

Nov 30, 2005, 09:13 AM

Bits may run a bit quicker though now that they have Quicktime 7.0.4 as intel native. I'm not sure however how much in FCP is Quicktime and how much is their own code.

In my understanding, ALL playback, rendering, and video-handling is done by QuickTime. FCP is just a really fancy way to harness the raw video-handling capabilities of QuickTime, by letting you add FX, transitions, color corrections, etc. by means of plugins and tools.

The only thing (as far as I can tell) that might slow down FCP is running its plugins and effects; QuickTime has some built-in effects (that would, presumably, be native for Intels), but FCP doesn't use them. The rendering of these effects and transitions would have to be run through Rosetta.

Of course, I could be wrong... but it would seem that compression, importing, and playing with individual clips (without effects) will be just fine on an Intel, even if you use an older version of FCP or FCX.

gnasher729

Nov 30, 2005, 09:17 AM

Except processing power will probably scale much faster on the x86 front than PPC. With dual core *mobile* chips, I really see a good future for Intel Macs.

I think you missed the point completely.

If Rosetta indeed supports Altivec (which I doubt) then emulated Altivec code will run slower than emulated G3 code. That's why emulating Altivec is utterly pointless and counter productive. On G4, Altivec is faster. On Rosetta, it is slower. No matter how fast the Intel CPU is, emulating Altivec is slower than emulating G3 code on the same Intel CPU.

gnasher729

Nov 30, 2005, 09:28 AM

Because it CAN emulate Altivec code (Altivec being the engineering term "Velocity Engine" being the marketing term I remember), does that mean non-Altivec code HAS to be emulated the same way? If not, then why is there any reason for Altivec compatibility to be a deterrant?.

Most Altivec-aware applications have two sets of code: One for running on machines with Altivec, and one for machines without Altivec. Like

if (computer_has_altivec)
run_altivec_code ()
else
run_non_altivec_code ()

If Rosetta doesn't support Altivec, the non-altivec code will be executed. If Rosetta supports Altivec, AND Altivec emulation is slower than emulating non-altivec code, then the application will execute the Altivec code even though it is slower!

Another problem: Altivec is very very fast for things that are very suitable for Altivec. Sometimes it is used to do things where it is not so good: The original programming problem may not be very well suited for Altivec, and a programmer finds an alternative method that does five times more work but uses Altivec, which does five times as much work at ten times the speed, making it altogether twice as fast. Better than nothing on a G4.

But if you run this code under Rosetta, the application will do five times as much work, WITHOUT the advantage that Altivec executes faster, so the application will run considerably slower than it needs to.

AidenShaw

Nov 30, 2005, 09:45 AM

USB wasn't even around when they went PowerPC--that was in the mid-90s. But Apple (with the iMac) was one of the first, if not THE first, PC makers to widely adopt USB.
USB was common on mainstream PC motherboards and systems for a year or so before the iMac.

The big difference was that the iMac dropped all the other ports, *forcing* the use of USB.

The key reason that Apple was able to do that was that the iMac was introduced around the time of Windows 98 - which had native USB support in the OS (Win95 needed addons, which were often flaky).

Hardware manufacturers were developing USB peripherals for the Win98 market - when suddenly the iMac appeared which required USB peripherals. Many of them quickly adopted translucent plastic (ugh, remember that fad?) and sold them to iMac buyers.

There's no way that USB peripherals would have been ready for the iMac if they hadn't already been in development for Windows systems....

The USB parade was well underway in 1998 - Apple just cut into the front of the parade right before it came around the "Win98 corner", and to the naive viewer it looked like Apple was leading the parade. Not even close....

aegisdesign

Nov 30, 2005, 09:51 AM

Umm no I wasn't. If this was the case why aren't we seeing greater performances increases on the latest powerbook. The proof is in the pudding as they say. Certainly faster access to RAM with DMA is going to help but it doesn't change the fact that overall system perfornace is tied to the FSB.

I've not seen any decent benchmarks for them yet, Have you?

ONe thing I noted on Apple site about the controller. . .

Link (http://developer.apple.com/documentation/Hardware/Developer_Notes/Macintosh_CPUs-G4/15inchPowerBookG4/2Architecture/chapter_3_section_4.html#//apple_ref/doc/uid/TP40003165-CH206-TPXREF109)

That right there is going to throttle whatever performance benefits you get.

No. That's normal for DDR(2) RAM. Access is sync'd to both the rising edge of the clock and the falling edge of the clock hence the first D in DDR. 2x 167Mhz = 333Mhz.

sluthy

Nov 30, 2005, 09:56 AM

Most Altivec-aware applications have two sets of code: One for running on machines with Altivec, and one for machines without Altivec. Like

if (computer_has_altivec)
run_altivec_code ()
else
run_non_altivec_code ()

If Rosetta doesn't support Altivec, the non-altivec code will be executed. If Rosetta supports Altivec, AND Altivec emulation is slower than emulating non-altivec code, then the application will execute the Altivec code even though it is slower!
Ahh, that makes sense.

AidenShaw

Nov 30, 2005, 09:59 AM

I think you missed the point completely.

If Rosetta indeed supports Altivec (which I doubt) then emulated Altivec code will run slower than emulated G3 code. That's why emulating Altivec is utterly pointless and counter productive. On G4, Altivec is faster. On Rosetta, it is slower. No matter how fast the Intel CPU is, emulating Altivec is slower than emulating G3 code on the same Intel CPU.
And you're talking without understanding how QuickTransit emulates code.... You're assuming a naive one-for-one mapping of each PPC instruction to an equivalent sequence of x86 instructions. It doesn't work that way.

QuickTransit - the technology that Apple is licensing under the marketing name "Rosetta" - does a high-level decompilation of the PPC code, and then produces an optimized x86 stream. It can find a faster output than blindly doing a permute just because it found a permute in the PPC stream.

http://www.transitive.com/graphics/diagrams/tech_overview.gif

The better question is not whether QuickTransit can interpret AltiVec instructions in the input PPC stream, but whether it can produce SSE2 instructions in the output x86 stream. If that's the case, then QuickTransit would have a big advantage. In fact, it could even produce SSE2 output from G3 input - in essence rewriting old G3 code to "use" AltiVec.

Take a look at http://forums.macrumors.com/showpost.php?p=1928394&postcount=64 for a longer description of this issue, at http://forums.macrumors.com/showpost.php?p=1924389&postcount=387 for another, and at http://www.transitive.com/technology.htm for a technical brief on the QuickTransit product.

aegisdesign

Nov 30, 2005, 10:01 AM

I'm not necessarily arguing that AltiVec technology isn't effective, but rather that it hasn't been implemented as much as it could have been. Photoshop is obviously one of the few apps that has proper support for AltiVec which would explain your results (assuming the other update cards are roughly the same in terms of other specs.

Almost all creative apps use AltiVec extensively for their filters and effects. Those apps will also be the ones that take the longest to port over to native Intel code. If pros are to use Intel Powerbooks then the apps they want to use have to run at least as fast as on their old PowerPC hardware or there is no point in 'upgrading'.

Then again, most creative pros I know use desktops so until there's something faster than a quad g5, we'll be using those.

shamino

Nov 30, 2005, 10:18 AM

I've always wondered just how effective Altivec is though. I've always thought it was more of a marketing term rather than an engineering one.
SIMD instructions in a processor are critical to many classes of apps. Especially those that involve gaming, image, video and audio processing.

As for effectivity, Apple has been designing OS X to take great advantage of it. The Accelerate framework (introduced in 10.3) allows apps to use AltiVec in a way portable to other processors. Many other frameworks (like CoreImage) use AltiVec internally to speed things up. Any app that uses these frameworks takes advantage of the feature.

As for apps that call it directly, there aren't that many, but that doesn't mean they don't take advantage of the chip.

shamino

Nov 30, 2005, 10:24 AM

Good question. FCP is definitely an Altivec intense application to say the least. ...
But if it channels all its AltiVec code through the Accelerate framework, all that code will end up as SSE code when compiled for Intel or when running through Rosetta.

The fact that an app uses AltiVec doesn't mean as much as many people here seem to think. Unless you know specifically how the app is using it, you can't say how well/easily it will port to Intel.

shamino

Nov 30, 2005, 10:27 AM

Having Rosetta _support_ Altivec would actually deter me from ever buying an Intel Mac. Emulating a vec_perm instruction takes sixteen loads and stores, and in good have Altivec code half the instructions will be vector permutes. Expect emulated Altivec code to run much slower than emulated G3 code.
You assume the AltiVec code will be emulated as ordinary sequential instructions. If they are morphed into SSE instructions, performance will be better than you're assuming.

The initial Rosetta demonstration at WWDC should've demonstrated clearly that gut-feeling assumptions can't be trusted in situations like this. I'd wait to see the results before making sweeping claims about how you think it will have to suck.

Thomas Harte

Nov 30, 2005, 10:30 AM

Almost all creative apps use AltiVec extensively for their filters and effects. Those apps will also be the ones that take the longest to port over to native Intel code.
Surely you can't say that without knowledge of how the applications were written? For example, GCC has vector extensions (http://gcc.gnu.org/onlinedocs/gcc-4.0.0/gcc/Vector-Extensions.html) that allow an application to make some use Altivec or SSE without any native instructions being used. It supports all basic arithmetic and binary operations so should be enough for many applications provided the developers have chosen to use it.

shamino

Nov 30, 2005, 10:34 AM

Win98 was about the first OS to have it working acceptably. The first iMac was mid 1998. The claim that the iMac introduced it is bogus. Apple would not have introduced the iMac with USB if there weren't already USB printers or other peripherals.
You're memory is flaky.

Yes, Win98 was the first version of Windows to have useful USB support. Nevertheless, it was virtually impossible to find any USB hardware to actually use the port until after Apple started shipping iMacs.

At that time, I was exclusively a PC user, and I remember explicitly telling people to not bother paying extra for motherboards with USB ports, because there's nothing to plug into them anyway. I spent a lot of time shopping in stores for any device that could do something useful with these ports and never found anything.

At the time Apple released the iMac, there were almost no USB devices. There was one Epson printer, a Zip drive, and a floppy drive. All introduced at the same time as the iMac and sold as Mac peripherals (encased in Bondi-blue plastic, to underscore the point).

Until the iMac, PC users were perfectly happy using their PS/2, serial and parallel ports for peripherals. The fact that PC motherboards had ports and Win98 had an infrastructure for USB device drivers does not change this.

laughingboy

Nov 30, 2005, 10:43 AM

I should have been clearer. Apple is usually good about creating good computers, but if I recall correctly, their first models after a big switch have been lacking in features, which in the past has cost them, big time. Many say this is why Apple didn't "boom" like Windows because Apple's first computers were lacking in features.
I think after the switch to PowerPC their computers were lacking things like USB and such. (this is coming from someone who has one, can't attach anything to it :( )

As an aside, I was able to stick a vanilla PC USB PCI card into a Powermac 7500 (2nd generation PowerPC circa 1995) to attach printers, scanners etc under OS 9.

AidenShaw

Nov 30, 2005, 10:56 AM

At that time, I was exclusively a PC user, and I remember explicitly telling people to not bother paying extra for motherboards with USB ports, because there's nothing to plug into them anyway.
I hope that none of them held that advice against you... ;)

Yes, Win98 was the first version of Windows to have useful USB support. Nevertheless, it was virtually impossible to find any USB hardware to actually use the port until after Apple started shipping iMacs.
So, in the month or two between Win98 intro and the iMac shipment, Apple changed the world?

How about this press release:

http://www.microsoft.com/presspass/press/1998/jun98/availpr.mspx

REDMOND, Wash., June 25, 1998 — Microsoft Corp. today announced the availability of the Microsoft® Windows® 98 operating system...

The native support for USB in Windows 98 also presents hardware vendors with a tremendous opportunity to deliver exciting and innovative peripherals, from realistic "force feedback" joysticks to digital cameras, to consumers. USB dramatically simplifies the installation of these peripherals, delivering to consumers true "plug and play" functionality. Currently, a breadth of USB devices are being developed by the industry's leading manufacturers. According to David Fair, chairman of the USB Implementers Forum (USB IF) and technology initiative manager at Intel Corp., consumers can expect to see a steady increase in the number and type of USB devices available, with more than 150 new products due to hit the market over the course of the next year.

"Thanks to the support for USB in Windows 98, a wide array of easy-to-use USB devices are poised to flood the marketplace," Fair said. "USB technology enables a whole new spectrum of computing options that will help lower the barriers to broader PC adoption, expand the market and create a better end-user PC experience."
It's "flaky" memory (or flaky logic) to attribute the "flood" of USB devices to the iMac.

Apple did influence a lot of manufacturers to change their production lines to use tacky translucent plastic - but the devices were already on the way when Jobs cuddled his "space egg" in May 1998....

mdavey

Nov 30, 2005, 11:03 AM

QuickTransit ... does a high-level decompilation of the PPC code, and then produces an optimized x86 stream.

I've only quoted a tiny bit of your text, but found your post to be most informative - excellent description and including the image really helped. Thanks!

jholzner

Nov 30, 2005, 11:22 AM

You're memory is flaky.

Yes, Win98 was the first version of Windows to have useful USB support. Nevertheless, it was virtually impossible to find any USB hardware to actually use the port until after Apple started shipping iMacs.

At that time, I was exclusively a PC user, and I remember explicitly telling people to not bother paying extra for motherboards with USB ports, because there's nothing to plug into them anyway. I spent a lot of time shopping in stores for any device that could do something useful with these ports and never found anything.

At the time Apple released the iMac, there were almost no USB devices. There was one Epson printer, a Zip drive, and a floppy drive. All introduced at the same time as the iMac and sold as Mac peripherals (encased in Bondi-blue plastic, to underscore the point).

Until the iMac, PC users were perfectly happy using their PS/2, serial and parallel ports for peripherals. The fact that PC motherboards had ports and Win98 had an infrastructure for USB device drivers does not change this.

Yep! Exactly how I remember it. I wanted to say the same thing but was too lazy to write out the whole response. I remember that the first usb printers were just parallel port cables on one end and usb on the other nad some software to make it work.

jholzner

Nov 30, 2005, 11:24 AM

I hope that none of them held that advice against you... ;)

So, in the month or two between Win98 intro and the iMac shipment, Apple changed the world?

How about this press release:

It's "flaky" memory (or flaky logic) to attribute the "flood" of USB devices to the iMac.

Apple did influence a lot of manufacturers to change their production lines to use tacky translucent plastic - but the devices were already on the way when Jobs cuddled his "space egg" in May 1998....

Right, and not flaky at all to refer to a Microsoft press release for proof that Apple didn't do squat ;)

ioinc

Nov 30, 2005, 11:28 AM

AidenShaw

Nov 30, 2005, 11:32 AM

Right, and not flaky at all to refer to a Microsoft press release for proof that Apple didn't do squat ;)
Being from MS doesn't make it not true, though! ;)

USB suffered from the classic technological "chicken and egg" problem:
No PCs had USB ports
Windows95 didn't support USB

As usual, both issues had to be addressed:
- first, start building USB ports into PCs (even though they'd be rather useless for the first year or so)
- then, when OS support for USB is released, there will be a large "installed base" of USB capable systems, and a market for USB peripherals

I wonder if the single most important contribution that Apple made to USB was the decision to not put a floppy drive in the iMac. That omission triggered the first mass-market demand for USB peripherals....

jholzner

Nov 30, 2005, 12:31 PM

I wonder if the single most important contribution that Apple made to USB was the decision to not put a floppy drive in the iMac. That omission triggered the first mass-market demand for USB peripherals....

That may have been part of it but I think the bigger deal was that USB were the ONLY ports on there. Where as windows still included legacy ports plus USB Apple went USB only which may have lit a fire under some developers A**s

jelloshotsrule

Nov 30, 2005, 12:34 PM

Unless Apple also release an native Intel FCP on the same day then FCP running on your old PowerPC powerbook would most likely be faster and I'd guess by some margin.

while it still may be slower if not optimized heavily, i'm guessing that apple will have most of their apps intel ready right away (universal binaries)... for the pro apps it may not happen til the pro machines switch, as soon or late as that happens.

aegisdesign

Nov 30, 2005, 12:42 PM

Surely you can't say that without knowledge of how the applications were written? For example, GCC has vector extensions (http://gcc.gnu.org/onlinedocs/gcc-4.0.0/gcc/Vector-Extensions.html) that allow an application to make some use Altivec or SSE without any native instructions being used. It supports all basic arithmetic and binary operations so should be enough for many applications provided the developers have chosen to use it.

Adobe applications are written with their own UI libraries and with CodeWarrior. They've just finished creating an Intel native UI library. They've got 100's of thousands of lines of codewarrior code that quite possibly hasn't been touched since OS 7.

Microsoft have their own frameworks also including their own font rendering and page layout frameworks. IIRC at one point the Word engine ran as a kind of virtual machine running it's own almost Intel like bytecode - partly why it was so slow on the Mac.

aegisdesign

Nov 30, 2005, 12:52 PM

Yes, Win98 was the first version of Windows to have useful USB support. Nevertheless, it was virtually impossible to find any USB hardware to actually use the port until after Apple started shipping iMacs.

I was using an Epson printer with WIN95B so I think you're wrong. It was beige too, not Bondi Blue. WIN95B would occasionally forget the printer was there though and you'd have to reboot so it was pretty terrible. That printer also had a serial port for a Mac and a Parallel port. Very useful as you could attach a computer to each of the ports.

That was the only USB peripheral I had though. USB ZIP drives were just stupid with USB 1.x. I had a SCSI ZIP. Even my camera back then was a normal serial port. Thankfully it was only 300K pixels or something like that though.

vniow

Nov 30, 2005, 01:11 PM

All,

The rumour that Altivec is now supported in Rosetta in the latest build is likely a hoax, if you've been keeping up on the hacking community's efforts to leak and break the latest release, you'll know that one of the more reputable ones has saw no sign of the mythical 8F1111A.

8F1111 on the other hand was just cracked yesterday.

AidenShaw

Nov 30, 2005, 01:29 PM

That may have been part of it but I think the bigger deal was that USB were the ONLY ports on there. Where as windows still included legacy ports plus USB Apple went USB only which may have lit a fire under some developers A**s
I agree - but since the iMac came with a keyboard and mouse there was no sudden market for USB keyboards and mouses.

It had no floppy, so a USB floppy was a big opportunity for the first company to get a suitable one to market.

nagromme

Nov 30, 2005, 01:55 PM

The first iMac was mid 1998. The claim that the iMac introduced it is bogus. Apple would not have introduced the iMac with USB if there weren't already USB printers or other peripherals.

Thanks for the info--but to be clear, I never claimed that Apple introduced USB, nor did I downplay the importance of USB peripheral market. People may be reading something extra into my comments. I only said, quite rightly, that "Apple (with the iMac) was one of the first, if not THE first, PC makers to widely adopt USB." Define that how you wish, but the point is valid: Apple was a USB early adopter, not a USB foot-dragger--even if other companies also had the ports installed but didn't push to make them useful.

In any case, I was simply defending (also rightly) the absence of USB ports on the first PowerMacs. They DID come out before USB, so it shouldn't be held against them :) (or used as a reason to avoid the first Intel Macs.)

The first PowerMac came out in 1994. The USB 1.0 FDR standard came out in late 1995, and USB 1.1 (as used in the iMac) was out in 1998.

PS, I just learned some other trivia from Wikipedia: Apparently PowerPC stands for Power Performance Computing. Live and learn!

SiliconAddict

Nov 30, 2005, 02:57 PM

I've not seen any decent benchmarks for them yet, Have you?

No. That's normal for DDR(2) RAM. Access is sync'd to both the rising edge of the clock and the falling edge of the clock hence the first D in DDR. 2x 167Mhz = 333Mhz.

http://www.barefeats.com/pb167.html

Ahh OK. Gah. I actually know what double data rate is....brain fart this morning. What I would like to see is some Xbench results. Wonder if the folks at the Apple store would let me run them. :confused:

opq

Nov 30, 2005, 03:46 PM

What's the word on Apple's stance on Classic support? I remember something about OS9 app support being dropped starting with the Intels.

shamino

Nov 30, 2005, 05:24 PM

USB suffered from the classic technological "chicken and egg" problem:
No PCs had USB ports
Windows95 didn't support USB
Yes, and those conundrums typically go on for years without resolution. When was the last time any PC owner used his IrDA port? PC laptops have come bundled with them and Windows has supported them since Win95.

The big thing that pushed USB into the mainstream was Apple's decision to trash all the legacy ports (ADB, serial, SCSI and floppy) when there were very few USB devices in existance. This was a very risky decision that no PC maker would have ever considered, but it was also necessary to jump-start that market. It forced enough users (all those new iMac customers) into buying enough USB peripherals so that they could be profitable, starting the snowball effect leading to what we have now.

Had Apple not done this, we would all be using our legacy ports, and USB would remain a limited-use curiosity (much like FireWire is for PC users today). PC users would have continued with parallel-port devices and Mac users would have continued with SCSI devices.

shamino

Nov 30, 2005, 05:33 PM

What's the word on Apple's stance on Classic support? I remember something about OS9 app support being dropped starting with the Intels.
That's what I heard as well.

Something to do with the fact that Classic requires special kernel extensions to run, and Rosetta doesn't do kernel extensions.

If this is the case, however, then it may be possible for Apple to port those kernel extensions into native x86 code to make the whole shebang work. But I don't think they're going to. The demand for Classic is much less today than it was when OS X first came out. By the time the last PPC Mac is discontinued, the demand for it will likely be too small to make the effort worthwhile.

I suspect we'll find third-party solutions for this problem. Some kind of virtual machine system that emulates a PPC Mac and can run OS 9. It might even be able to leverage Rosetta for the CPU emulation. But this is all speculation on my part. We'll see what happens when it happens.

PPC970FX

Nov 30, 2005, 07:48 PM

Altivec suport in the OS but not on the CPU. Yeah that is wonderfull. So if the OS suports 64bit, but the CPU is only 32bit it is the same thing.

Maybe they should have the system say that the CPU is 55core 8Ghz and that would make the computer make faster??

Mechcozmo

Nov 30, 2005, 08:08 PM

They've got 100's of thousands of lines of codewarrior code that quite possibly hasn't been touched since OS 7.

Nitpick-- System 7. Apple officially called it "OS 8" with, well, OS 8. But before that, you had System Software packages, and before that, System and Finder versions that were different but sold in the same package.

I was using an Epson printer with WIN95B so I think you're wrong. It was beige too, not Bondi Blue. WIN95B would occasionally forget the printer was there though and you'd have to reboot so it was pretty terrible. That printer also had a serial port for a Mac and a Parallel port. Very useful as you could attach a computer to each of the ports.

That was the only USB peripheral I had though. USB ZIP drives were just stupid with USB 1.x. I had a SCSI ZIP. Even my camera back then was a normal serial port. Thankfully it was only 300K pixels or something like that though.

Third-party drivers for USB are found for Windows 95. So you could well have used USB under Windows 95, but the support, well, sucked. Same with 98-- the USB support was dismal, at best.

I suspect we'll find third-party solutions for this problem. Some kind of virtual machine system that emulates a PPC Mac and can run OS 9. It might even be able to leverage Rosetta for the CPU emulation. But this is all speculation on my part. We'll see what happens when it happens.

Something like PearPC? Linkety (http://pearpc.sourceforge.net/)
It has AltiVec support, too! But it isn't exactly the most stable of all things... however it is good software, and is becoming slowly better.

kwajo.com

Nov 30, 2005, 08:22 PM

I want 10.4.4 for PowerPC though!! :(

AidenShaw

Nov 30, 2005, 08:27 PM

Had Apple not done this, we would all be using our legacy ports, and USB would remain a limited-use curiosity (much like FireWire is for PC users today). PC users would have continued with parallel-port devices and Mac users would have continued with SCSI devices.
I actually think the opposite - without the iMac I believe that the USB situation today would be roughly what it is now.

Certainly, Apple had an effect on the USB market in late 1998/early 1999. No question. In the long run, however, that was just a blip due to a few systems sold by a struggling 2nd tier vendor.

Think back to the Intel quote in the MS press release - "a flood of devices coming to market". That was happening with or without Apple.... Intel was pushing USB - pushing into motherboards even when there weren't any peripherals to connect. Win98 and Win2K were coming with good USB support, with or without Apple.

Market forces (e.g. digital cameras, webcams, phones, PDAs, music players, GPS receivers...) would have pushed USB to where it is today even Apple had crashed and burned completely.

fluidinclusion

Nov 30, 2005, 08:32 PM

Yep! Exactly how I remember it. I wanted to say the same thing but was too lazy to write out the whole response. I remember that the first usb printers were just parallel port cables on one end and usb on the other nad some software to make it work.

I too had not yet purchased a Mac at that point and did NOT see many PC's with USB, even in 1999 when I bought my first Mac. Just like Firewire. Until about 3-4 years ago, it was nearly impossible to find a mainstream or low end PC with Firewire. All macs had them though. Without USB 2, what would PC users do?

Stella

Nov 30, 2005, 08:35 PM

Windows 95B, whilst claiming to have USB support, contained beta drivers and did not support much USB hardware. The majority of USB hardware that worked under windows 98 did not work for windows 95, due to the poor usb support under win95b. Very little usb devices were compatible.

Yes, and those conundrums typically go on for years without resolution. When was the last time any PC owner used his IrDA port? PC laptops have come bundled with them and Windows has supported them since Win95.

The big thing that pushed USB into the mainstream was Apple's decision to trash all the legacy ports (ADB, serial, SCSI and floppy) when there were very few USB devices in existance. This was a very risky decision that no PC maker would have ever considered, but it was also necessary to jump-start that market. It forced enough users (all those new iMac customers) into buying enough USB peripherals so that they could be profitable, starting the snowball effect leading to what we have now.

Had Apple not done this, we would all be using our legacy ports, and USB would remain a limited-use curiosity (much like FireWire is for PC users today). PC users would have continued with parallel-port devices and Mac users would have continued with SCSI devices.

fluidinclusion

Nov 30, 2005, 08:39 PM

I actually think the opposite - without the iMac I believe that the USB situation today would be roughly what it is now.

Certainly, Apple had an effect on the USB market in late 1998/early 1999. No question. In the long run, however, that was just a blip due to a few systems sold by a struggling 2nd tier vendor.

Think back to the Intel quote in the MS press release - "a flood of devices coming to market". That was happening with or without Apple.... Intel was pushing USB - pushing into motherboards even when there weren't any peripherals to connect. Win98 and Win2K were coming with good USB support, with or without Apple.

Market forces (e.g. digital cameras, webcams, phones, PDAs, music players, GPS receivers...) would have pushed USB to where it is today even Apple had crashed and burned completely.

GPS??? You mean the fact that only a couple of GPS receivers (if any) had USB support before 2004??? Many of them are STILL serial only.

DeathChill

Nov 30, 2005, 09:17 PM

AidenShaw

Nov 30, 2005, 09:47 PM

AS: "Market forces (e.g. digital cameras, webcams, phones, PDAs, music players, GPS receivers...) would have pushed USB to where it is today even Apple had crashed and burned completely."

GPS??? You mean the fact that only a couple of GPS receivers (if any) had USB support before 2004??? Many of them are STILL serial only.
Actually, that's just the list of gizmos that I connected to my laptop on my last business trip - it wasn't meant to be exhaustive or chronological, nor to imply that all of those devices were around in 1999.

My traveling GPS is the Pharos iGPS360 (http://www.pharosgps.com/products/laptopdesktoppc/Misc/PK063.htm) with USB cable for the laptop, plus a Pharos PXT09 bluetooth dock so that my Windows phone and iPaq can be used as moving-map GPS systems. (I also have an older Garmin all-in-one, which is serial.)

BenRoethig

Dec 1, 2005, 06:23 AM

I think it's a sure bet that Rosetta will outrun a G4 in many situations. Especially when it comes to perceived responsiveness (as opposed to the duration of lengthy renders and conversions).

I say this because of comments from game developers at InsideMacGames about some 3D games performing very well under Rosetta. Well enough that there's no NEED to port some of them. And that's on the dev kits, which are pretty ordinary single core machines.

With the exception of the Quake3 engine, most games have basic or no SMP support. A fast single core is going to be better for the vast majority of games.

shamino

Dec 2, 2005, 12:52 PM

With the exception of the Quake3 engine, most games have basic or no SMP support. A fast single core is going to be better for the vast majority of games.
Case in point: My copy of Snowball Run (http://www.mumbojumbo.com/retail/g.snowballrun.html) runs faster and more stably on my single 1.33GHz iBook than on my dual 1GHz PowerMac.

Which means that there isn't very much multithreading going on, and their multithreading is making unwarranted assumptions about the computing environment. (With dual processors, two threads really do execute simultaneously, which can create bugs in software that assumes otherwise.)

I've seen similar things from many games.

PPC970FX

Dec 2, 2005, 05:15 PM

Not sure if it's been posted but build 8F1111 is already publicly available as well as the fact that it has already been cracked for regular computers. :)
It just has minor improvements, but there is no Altivec in ROsetta as far as I can see.

Damn is it posible, I say it again

People the Altivec is a Hardware feature. HARDWARE. And not a SINGEL X86 CPUare having it now, and I dont think any x86 cpu will have it EVER. Now there is in the X86 world something more or less the same but much weaker. that is called SSE. Now the ONLY thing rosetta can do is to make shure that what was before a Altivec code on a PPC with altivec suport is on a X86 a SSE code.

You can not do anything more then that. It is imposible, unless the X86 CPU have altivec suport.

And I am not shure that the Altivec code can be translated into SSE in any way, but if it can be done it is the best Rosetta can do.

AidenShaw

Dec 2, 2005, 11:37 PM

Damn is it posible, I say it again

People the Altivec is a Hardware feature. HARDWARE. And not a SINGEL X86 CPUare having it now, and I dont think any x86 cpu will have it EVER. Now there is in the X86 world something more or less the same but much weaker. that is called SSE. Now the ONLY thing rosetta can do is to make shure that what was before a Altivec code on a PPC with altivec suport is oSSE Performance Programming n a X86 a SSE code.

You can not do anything more then that. It is imposible, unless the X86 CPU have altivec suport.

And I am not shure that the Altivec code can be translated into SSE in any way, but if it can be done it is the best Rosetta can do.
"much weaker" - Apple's developer documentation doesn't say that.

[b]SSE Performance Programming (http://developer.apple.com/hardware/ve/sse.html)

Intel's Streaming SIMD Extensions (hereafter called SSE) is a 128-bit SIMD vector extension to the x86 ISA that is quite similar to AltiVec.
...
AltiVec and SSE are quite similar at the highest levels. They are SIMD vector units with the same vector size (128-bits) and a similar general design. SSE adds several important new features compared to AltiVec. The single and double precision floating point engines are fully IEEE-754 compliant, which means that all four rounding modes, exceptions and flags are available. Misaligned loads and stores are handled in hardware.

There is hardware support for floating point division and square root. There is a Sum of Absolute Differences instruction for video encoding. All of the floating point operations provided are available in both scalar and packed variants.

If Apple says that SSE has "several important new features" compared to AltiVec, perhaps you should listen...

Also, consider that SSE as an architecture, and any SSE implementation in any chip, are two very different things.

Future x64 chips could run SSE instruction far faster than any AltiVec implementation - don't make the mistake of condemning an architecture for the failings of an implementation.

PPC970FX

Dec 3, 2005, 05:57 AM

"much weaker" - Apple's developer documentation doesn't say that.

If Apple says that SSE has "several important new features" compared to AltiVec, perhaps you should listen...

Also, consider that SSE as an architecture, and any SSE implementation in any chip, are two very different things.

Future x64 chips could run SSE instruction far faster than any AltiVec implementation - don't make the mistake of condemning an architecture for the failings of an implementation.

Okei do you think that they would say that they changed to a weaker vector extension? They just can not say that. And you mean future X86-64 right? And I think that X86 is far more powerfull then PPC chip by chip, scaling I am not so shure. My point is just that AltiVec is not practical to emulate, since it is a hardware feature.

I think that AltiVec is more powerfull in general then SSE3. But I can understand that some people think that it is the other way around. Then we can agree to disagree.

Dale Cooper

Dec 3, 2005, 06:09 AM

I belive in God, and his name is Stev. :D

Who's Stev anyway?

AidenShaw

Dec 3, 2005, 09:23 AM

Okei do you think that they would say that they changed to a weaker vector extension? They just can not say that.
You mean Apple is lying to us all? :eek:

And you mean future X86-64 right?
SSE3 is in current Netburst (32-bit and 64-bit), and it will be in Yonah/Merom/Conroe and all new chips. Dothan (the current Pentium M) uses SSE2.

SSE3 is very similar to SSE2, but adds a dozen or so new instructions. In general SSE2 and SSE3 are comparable, but SSE3 can be faster for some application (e.g. SSE3 can do vector calculation on imaginary numbers - very useful for some codes).

See http://www.intel.com/technology/itj/2004/volume08issue01/art01_microarchitecture/p06_sse.htm for an in-depth description of the new SSE3 instructions.

SSE2 and SSE3 are in both 32-bit and 64-bit chips. (Intel's 64-bit chips are SSE3, AMD has both SSE2 x64 and SSE3 x64.)

One difference with x64 is that there are 16 of the 128-bit SSE registers when in 64-bit mode, vs 8 registers when in 32-bit mode. This means that 64-bit SSE code should be somewhat faster than 32-bit code in most cases.

My point is just that AltiVec is not practical to emulate, since it is a hardware feature.
It is *very* practical to emulate, otherwise a program that requires AltiVec can't be run on x86.

Even scalar emulation (emulating AltiVec with standard scalar instructions) is better than nothing for many people.

It is possible, however, for Rosetta to "convert" AltiVec code to vector SSE code - to convert one hardware feature to another. This would not only let you run AltiVec code on x86, but run it at hardware accelerated speeds. That would be big.

(Note: I have no information to confirm that the rumours of AltiVec support in 8F1111 Rosetta are true, let alone confirm whether it's a scalar or vector emulation.)

I think that AltiVec is more powerfull in general then SSE3. But I can understand that some people think that it is the other way around. Then we can agree to disagree.
I won't disagree that the AltiVec implementations in the MPC7xxx and PPC970x are more powerful than the SSE2/3 implementations in the Netburst/PentiumM chips.

The main reason is that AltiVec has been implemented with a parallel ALU to perform the operations, and Intel (so far) uses the scalar ALU (pushing the separate operations quickly into the pipeline). Intel's approach is better than scalar code in the application, but not as good as having a separate parallel ALU.

In the future, however, Intel could put one or more vector ALUs into the chip, and run SSE2/3 operations truly in parallel. This could be completely, absolutely compatible with existing SSE programs.

The architecture defines the behaviour of the SSE instructions, not whether the actual implementation uses scalar, parallel or multiple execution units to produce that behaviour.

We don't know what tricks Intel has planned for the huge numbers of transistors in the new chips - but they could decide to spend some of those transistors to make an SSE3 implementation that puts the current AltiVec implementations to shame.
____________

The landscape is changing for SSE as well.

Currently, SIMD use is hampered by the several different implementations of current systems in the installed base (MMX/SSE/SSE2/SSE3). It's a pain to test for the different capabilities. Compilers can automatically generate vector code, but they don't generate all 5 versions with the necessary runtime tests.

In the x64 world, however, every system is guaranteed to be at least SSE2 compatible. Developers can use SSE2 without checking. This will give Intel more incentive to improve the SSE implementation in silicon, since the SSE units may be used much more often in 64-bit code.

shamino

Dec 4, 2005, 04:39 PM

Currently, SIMD use is hampered by the several different implementations of current systems in the installed base (MMX/SSE/SSE2/SSE3). It's a pain to test for the different capabilities. Compilers can automatically generate vector code, but they don't generate all 5 versions with the necessary runtime tests.

In the x64 world, however, every system is guaranteed to be at least SSE2 compatible. Developers can use SSE2 without checking. This will give Intel more incentive to improve the SSE implementation in silicon, since the SSE units may be used much more often in 64-bit code.
And in the case of Macs, developers can probably make the same assumption even for 32-bit code. Mac OS can be designed to require an SSE2 (or SSE3) chip, as long as Apple makes certain to only manufactuer Intel systems with compatible chips.

An added benefit of refusing to support generic PC platforms.

AidenShaw

Dec 4, 2005, 04:55 PM

And in the case of Macs, developers can probably make the same assumption even for 32-bit code. Mac OS can be designed to require an SSE2 (or SSE3) chip, as long as Apple makes certain to only manufactuer Intel systems with compatible chips.
Apple developers are being told that SSE2 is mandatory, but SSE3 is optional. (http://developer.apple.com/documentation/Performance/Conceptual/Accelerate_sse_migration/migration_sse_overview/chapter_2_section_4.html)

Strong evidence that Dothan-based Macs are coming, since Yonah will be SSE3, and current Netburst chips are SSE3. The only SSE2 chip in the current stable is Dothan.

BenRoethig

Dec 6, 2005, 12:04 AM

Apple developers are being told that SSE2 is mandatory, but SSE3 is optional. (http://developer.apple.com/documentation/Performance/Conceptual/Accelerate_sse_migration/migration_sse_overview/chapter_2_section_4.html)

Strong evidence that Dothan-based Macs are coming, since Yonah will be SSE3, and current Netburst chips are SSE3. The only SSE2 chip in the current stable is Dothan.

Dothan iBooks would make sense seeing that single core Yonahs are not expected to late spring/summer.

shamino

Dec 6, 2005, 12:34 PM

Apple developers are being told that SSE2 is mandatory, but SSE3 is optional. (http://developer.apple.com/documentation/Performance/Conceptual/Accelerate_sse_migration/migration_sse_overview/chapter_2_section_4.html)

Strong evidence that Dothan-based Macs are coming, since Yonah will be SSE3, and current Netburst chips are SSE3. The only SSE2 chip in the current stable is Dothan.
it means they've decided to keep their options open. Apple would want to hedge their bets, in case Yonah's schedule slips.

It would be a bit of a leap to take this developer note and assume that a Dothan-based system must eventually be sold as a commercial product.

AidenShaw

Dec 6, 2005, 03:28 PM

it means they've decided to keep their options open. Apple would want to hedge their bets, in case Yonah's schedule slips.

It would be a bit of a leap to take this developer note and assume that a Dothan-based system must eventually be sold as a commercial product.
Intel's roadmap has shown Dothan (single-core) and Yonah (dual-core) being sold together for some time, with the single-core Yonah coming later.

That fits in with market segmentation of iBook/MiniMac as Dothan alongside PB/iMac with Yonah.

We'll know the answer for sure by WWDC.

If you see Yonah more-or-less on time in a PB, and Dothan-based low end systems alongside them - then my "leap" wasn't so much.

If we never see a Dothan from Apple, then your skepticism was justified. (Or if Yonah isn't here for months, and a Dothan appears....)

Morn

Dec 8, 2005, 03:37 AM

What if powerbook is launched with macworld with dual core and mac mini/ibook get launched in wwdc around time of single core yonah? Could happen.

AidenShaw

Dec 8, 2005, 07:43 AM

What if powerbook is launched with macworld with dual core and mac mini/ibook get launched in wwdc around time of single core yonah? Could happen.
That would discredit my "leap", for sure.

vniow

Dec 9, 2005, 02:52 AM

Peace

Dec 9, 2005, 01:45 PM

I take it back, 8F1111A has now been leaked and cracked. Guess its real this time...

It's actually 8F1111g

iSee

Dec 9, 2005, 01:56 PM

Can we just skip December and go straight to MWSF?

Yeah! It's Christmas in January this winter!
Gotta get an intelBook, gotta get an intelBook, gotta get an intelBook, ...

ingenious

Dec 11, 2005, 10:29 PM

And I am not shure that the Altivec code can be translated into SSE in any way, but if it can be done it is the best Rosetta can do.

Isn't that what they said in the first place? I mean, isn't that what this article is about? Rosetta translating AlitVec code into SSE code?

shamino

Dec 12, 2005, 11:48 AM

Isn't that what they said in the first place? I mean, isn't that what this article is about? Rosetta translating AlitVec code into SSE code?
It mentions Rosetta now being compatible with AltiVec code. Whether this means translation into SSE code or into linear code is unknown at this time.

LimeiBook86

Dec 12, 2005, 02:45 PM

phvander

Dec 13, 2005, 07:40 AM

Well this is a good sign. Personally I belive that Mac OS X for Intel/x86 is probably almost complete. I hope that by Macworld we'll see another demo of the Mac OS X for X86. Who knows imaybe it'll be done by then and will be introduced along with some Intel Macs. Oh boy I can't wait! ;)

No you have to wait in front of your Macintel running Rosetta.

Remember OS/2 running Windows apps in a compatibility box.... and both binary were Intel code. Image an Intel processor running PowerPC code.... Yes....wait and look at the wheel

shamino

Dec 13, 2005, 12:19 PM

Remember OS/2 running Windows apps in a compatibility box.... and both binary were Intel code. Image an Intel processor running PowerPC code.... Yes....wait and look at the wheel
As someone who ran a lot of Windows apps under OS/2, I have no idea what you're talking about.

OS/2 was not running an emulation environment. They were running an actual unmodified copy of Windows 3.11 in an OS/2 DOS box. And the apps ran just fine (compared with Windows 3.11 running natively on MS-DOS.) They ran faster on 32-bit versions of Windows, but that's an unfair comparison, because OS/2 never attempted to emulate that environment.

As for Rosetta, why don't you wait until it ships before you make sweeping claims about its uselessness. Unless you're violating an NDA, the only thing you know is what Apple has demonstrated (which was very impressive) and what some bloggers have written (which is, of course, a mixed bag of random speculation.)

LimeiBook86

Dec 13, 2005, 12:52 PM

No you have to wait in front of your Macintel running Rosetta.

Remember OS/2 running Windows apps in a compatibility box.... and both binary were Intel code. Image an Intel processor running PowerPC code.... Yes....wait and look at the wheel
I'm sorry but, did this have anything to do with my post??? :confused: Please don't quote a post if your post has nothing to do with it. But, seeing as this is your first post - Welcome to MacRumors!:p

phvander

Dec 14, 2005, 07:45 AM

As someone who ran a lot of Windows apps under OS/2, I have no idea what you're talking about.

OS/2 was not running an emulation environment. They were running an actual unmodified copy of Windows 3.11 in an OS/2 DOS box. And the apps ran just fine (compared with Windows 3.11 running natively on MS-DOS.) They ran faster on 32-bit versions of Windows, but that's an unfair comparison, because OS/2 never attempted to emulate that environment.

As for Rosetta, why don't you wait until it ships before you make sweeping claims about its uselessness. Unless you're violating an NDA, the only thing you know is what Apple has demonstrated (which was very impressive) and what some bloggers have written (which is, of course, a mixed bag of random speculation.)

This exactly was I was thinking......
OS/2 runs a native code in an Intel 16 bit mode.
And the performance were awfull !!!!!

So if you expects same performance running PPC code on a Intel processor, so there is someting wrong in physical laws...

Few months ago, it has been said G5 is the most terrific processor

It seems Rosetta will run PPC code much faster on an Intel processor than on a native PPC processor! terrific!

Marketing stuff!

shamino

Dec 14, 2005, 10:33 AM

This exactly was I was thinking......
OS/2 runs a native code in an Intel 16 bit mode.
And the performance were awfull !!!!!
OS/2 version 1.x was 16-bit. Versions 2 through 5 (yes, there was a version 5, although it was never sold in retail stores) were all 32-bit.

As for performance, native OS/2 code performed incredibly well comapred with other operating systems running on the same processors.

Most of the performance problems were from brain-dead application developers that simply tried to port their Windows code over without changing any part of their design. Which, BTW, can be said for Mac code as well - quick ports of Windows apps to Mac OS usually suck as well.

I developed software for OS/2 for seven years. I found that quick-ports of Windows code could get a 4x speedup (typically outperforming the original Windows version) after re-organizing the application around OS/2's strengths and weaknesses, instead of around Windows' strengths and weaknesses.
So if you expects same performance running PPC code on a Intel processor, so there is someting wrong in physical laws...
Maybe yes, maybe no. Yes, there will be a lot of overhead due to any emulation/translation environment. On the other hand, we're talking about Intel chips in the 3-3.4GHz range, emulating PPC chips in the 1.33-2.5GHz range. A 20-150% increase in clock speed (depending on what two chips you compare) can mask a lot of overhead.
It seems Rosetta will run PPC code much faster on an Intel processor than on a native PPC processor! terrific!
I have no idea if you're being sarcastic here or not. In actual practice, this may or may not be true, depending on what PPC chips you use as your baseline, what Intel chips you're benchmarking, and what apps you use for your tests.

phvander

Dec 14, 2005, 10:47 AM

OS/2 version 1.x was 16-bit. Versions 2 through 5 (yes, there was a version 5, although it was never sold in retail stores) were all 32-bit.

As for performance, native OS/2 code performed incredibly well comapred with other operating systems running on the same processors.

Most of the performance problems were from brain-dead application developers that simply tried to port their Windows code over without changing any part of their design. Which, BTW, can be said for Mac code as well - quick ports of Windows apps to Mac OS usually suck as well.

I developed software for OS/2 for seven years. I found that quick-ports of Windows code could get a 4x speedup (typically outperforming the original Windows version) after re-organizing the application around OS/2's strengths and weaknesses, instead of around Windows' strengths and weaknesses.
Maybe yes, maybe no. Yes, there will be a lot of overhead due to any emulation/translation environment. On the other hand, we're talking about Intel chips in the 3-3.4GHz range, emulating PPC chips in the 1.33-2.5GHz range. A 20-150% increase in clock speed (depending on what two chips you compare) can mask a lot of overhead.
I have no idea if you're being sarcastic here or not. In actual practice, this may or may not be true, depending on what PPC chips you use as your baseline, what Intel chips you're benchmarking, and what apps you use for your tests.

I also develop for OS/2 from 1987 to 2000....
... and OS/2 was killed by the fact that Dos and Winos2 were not thrown from OS/2.

And the OS/2 spent its time to ask it self "Am I in 16bits adress mode or in 32 bits adress mode ?"

So for MacIntel, if MACOSX must support old world PPC code it will impact Macintel OS quality due to maintening Rosetta code and a lot of stuff added inside the kernel to insure compatibility of PPC code!

And what about ISV support for their PPC code running onto an Intel MAC...
Do you think they will provide support ?

No they will force customers to switch to Intel version with lot of $$$