PowerPC Architecture Emulator Unleashed 124
Sebastian Biallas writes "We have finally released version 0.1 of our PowerPC architecture emulator: PearPC. The emulator itself is (prepared to be) architecture independent but only tested on x86s (here you go porters...). It also features a must faster just-in-time compilation unit for x86 hosts. This means that you can now run your favourite PowerPC-OS on x86: Mandrake Linux (9.1), Darwin (6 + 7) and Mac OS X (10.3)! And the best things is: it's GPL'd.
But be warned: it's experimental.."
Why not use it natively? (Score:4, Insightful)
This means that you can now run your favourite PowerPC-OS on x86: Mandrake Linux (9.1),
Why not just run it natively on the x86 architecture?
Re:Why not use it natively? (Score:2)
But, what I want to know is how well and how fast does Mac OS X run on it. I would download it and test it out myself, but I'm in the middle of moving and don't have the time-- maybe in a week or two.
Re:Why not use it natively? (Score:4, Informative)
From the PearPC site:
Not too quick then!
Re:Why not use it natively? (Score:1)
Good thing you dony have time for piracy!
Re:Why not use it natively? (Score:1)
I believe he meant downloading PearPC, not Mac OS X.
Re:Why not use it natively? (Score:4, Funny)
Re:Why not use it natively? (Score:5, Funny)
You've got to have:
Mandrake running
on PowerPC
on PearPC simulator
on Virtual PC
on VMWare
on XBox
on
To get be reported on
The trick then, is to withstand the
And take a screenshot of the smoking machine.
Then you get the "Immortal" rating.
Then, just may be, you can get rooted.
Re:Why not use it natively? (Score:5, Funny)
You must be new here.
Re:Why not use it natively? (Score:1)
Re:I call total and complete bullshit on OSX... (Score:2, Insightful)
Must hurt to be wrong. (Score:4, Informative)
Re:Must hurt to be wrong. (Score:2)
Re:Must hurt to be wrong. (Score:2)
Re:I call total and complete bullshit on OSX... (Score:5, Informative)
Re:I call total and complete bullshit on OSX... (Score:2)
Re:I call total and complete bullshit on OSX... (Score:1)
Re:I call total and complete bullshit on OSX... (Score:2)
um, that's just the ical icon. when ical is running it'll change that icon to reflect the current date.
Panther on x86? (Score:2, Insightful)
I never thought this day would finally come... a PowerPC emulator that
is stable and mature enough to actually run MacOS X on an x86!
Oh well, i've already bought 2 macs now (Titanium Powerbook G4) and a G4
Cube (which got majorly upgraded; 1.2ghz G4, GeForce3 64mb, 1.5gb ram,
etc).
But still, I wonder... will apple try to kill this project?
D.
Re:Panther on x86? (Score:5, Insightful)
The x86 is just really poorly suited to emulate PPC, the PPC has more registers and they're all general purpose, as opposed to x86's small groups of purpose specific registers. You can try to minimize the drawbacks from this with a JITC, but it's still going to crawl compared to the real thing.
Re:Panther on x86? (Score:2)
Re:Panther on x86? (Score:1)
Of course, RISC mimicking CISC is easier than CISC mimicking RISC. The latter is pretty forced to use RAM for all registers, and forced to use RMW for every RISC operation despite the fact that the RISC code has already had to do everything itself as RMW. That's _twice_ the overhead. RMW = read/modify/write, 3 ops typically, where CISCs could often to the same operation
Re:Panther on x86? (Score:1)
Re:Panther on x86? (Score:4, Informative)
It's running at 10 MHz.
Re:Panther on x86? (Score:1)
I wouldn't even run OS X on a Mac with that little RAM
Re:Panther on x86? (Score:2)
A bit of swapping at times, but otherwise fine.
Re:Panther on x86? (Score:3, Insightful)
Re:Panther on x86? (Score:5, Interesting)
The x86 is just really poorly suited to emulate PPC, the PPC has more registers and they're all general purpose, as opposed to x86's small groups of purpose specific registers.
While that may be true, modern emulation techniques take this into account with things like JIT compilation. While an instruction-for-instruction emulation scheme will have performance problems, the same program compiled in C on respective platforms will run with equivalent speed. The program just needs some time to mature for speed.
Me, I plan to try and get onto the list of developers to port to x86-64. Simple emulation should be much easier thanks to the larger register file on AMD's chips...
Re:Panther on x86? (Score:2)
Re:Panther on x86? (Score:1)
So you get some speedup from not having to read ppc bytes, lookup translation, perform emulation, etc for each cycle, but it's not a miracle method of 1000x performance gain
That said, X86-64 should really help speed this up, as you said..
Didn't AM64 have more general purpose registers? (Score:2)
Or did I disregard something?
Re:Didn't AM64 have more general purpose registers (Score:3, Insightful)
Bottom line is that the number of registers makes it more difficult than it would seem.
Disclaimer: I don't
Re:Didn't AM64 have more general purpose registers (Score:2)
Read my comment again. I stated that having 2x as many registers will *not* make that much of a difference.
"The P4 has atleast 128 registers. They are just hidden behind a little thing called register renaming"
The P4 does NOT have 128 seperate general-purpose registers. Register renaming does not allow you to use any more general-purpose registers per program than if you only had one set. It's simply a
Re:Didn't AM64 have more general purpose registers (Score:2)
Yeah, you should. You're ruining the image of ACs by posting intelligent comments
Re:Didn't AM64 have more general purpose registers (Score:2)
That's pretty much what I was trying to say. I guess it depends on how them implement it. Even with only having to emulate half the registers, it's still going to be a very significant slowdown. Unless you can keep them in cache, your emulated registers are going to be in RAM, which is painfully slow compared to hardware registers. I hope they have a competent team, cause I really want to see this work in the near future at decent speeds.
Re:Didn't AM64 have more general purpose registers (Score:2)
Significant slowdown.
What does that mean?
1/3 of native? 1/10 ?
In my mind that would be okay.
1/50? Too slow.
1/10 speed of native code executed, on the latest Athlon FX-52?
That would be just dandy.
Re:Panther on x86? (Score:2, Insightful)
I'm very excited though. It will be a great day when I see a dual 3ghz+ x86 machine running OS X
Re:Panther on x86? (Score:5, Interesting)
But i just read the website. Its 500 times slower than the real thing
Oh well. Guess the previous posters are correct. Apple won't go after this project as
its next to useless. Infact, it might be a good thing. It lets people try out and play
with MacOS X before they commit to buying all that expensive hardware. (Nevermind the
legal issues of course.)
When I was first trying to make the decision to buy a mac, spending 5 minutes or 30
minutes "playing" with it at the store wasn't enough. I wanted to spend several days
on it, using it to do all the things i do now, but in a different enviornment. You
can't do that in the shop.
So i ended up borrowing a friends crappy old imac (which only ran OS9) and chucked a
priated copy of OSX 10.1 i downloaded of the net.
Loved it to bits, and promptly bought my PowerBook G4. (And then that cube of ebay
So, i spose, this emulator will give people the ability to try out MacOSX and run it
to do day to day stuff, albiet very very slowly. Its a well known fact Microsoft never
went after software pirates in the old days so that their software become so
widespread it became the standard. Perhaps this might work for Apple, too.
D.
Re:Panther on x86? (Score:2)
It should get better. Especially when a couple more developers jump into it
Re:Panther on x86? (Score:4, Interesting)
Re:Panther on x86? (Score:4, Funny)
When I was first trying to make the decision to buy a mac, spending 5 minutes or 30
minutes "playing" with it at the store wasn't enough. I wanted to spend several days
on it, using it to do all the things i do now, but in a different enviornment. You
can't do that in the shop.
Hmm - But you could play a total of 45 hours of "testing" in this emulator - and still havent done as much as 3½ minut on the real deal?
Re:Panther on x86? (Score:1)
I believe Apple actually includes that with the computer.
Re:Panther on x86? (Score:1)
(I wonder if they even could...)
Re:Panther on x86? (Score:2)
I'm going go install it my gaming machine.
Athlonx XP 3200+, nforce 2 Ultra, 1024 meg DDR400.
Perhaps it will scream?
I wonder if the emulator translates OpenGL? Because that would explain a lot of the slowdown. Remeber Quartz Extreme uses OpenGL a lot.
Re:Panther on x86? (Score:2)
Why? Any speed advantage of the x86 would be utterly destroyed by the emulation.
Re:Panther on x86? (Score:1)
Re:Panther on x86? (Score:1)
Based on what? It's not emulating the OS, it's emulating the processor.
Re:Whoa. This is huge. (Score:2)
Opteron is "cheapo hardware"?!
Re:Whoa. This is huge. (Score:2)
Re:Whoa. This is huge. (Score:2)
By the time this thing is optimized, it will be.
That's not intended as sarcasm, either, just a simple observation.
Re:Whoa. This is huge. (Score:1)
Apparently it is now [theregister.co.uk].
Re:Whoa. This is huge. (Score:2)
Re:Whoa. This is huge. (Score:1)
What makes you think that it's better to emulate a 32-bit CPU using a 64-bit CPU rather than another 32-bit CPU?
What benefit do you think the 64-bit nature of the Opteron family gives you?
As someone who's worked with 68K-on-PPC emulators, I can assure you that having only a 32-bit host made it _easier_ to emulate a 32-bit target.
YAW.
Re:Whoa. This is huge. (Score:1)
Won't be simpler of cource!
Work with OS X? (Score:1, Redundant)
If OS X even installs, how much of it works? Networking? Sound? Video acceleration?
Re:Work with OS X? (Score:1)
as for your other questions... you haven't used any virtualization/emulation software before, have you?
Re:Work with OS X? (Score:2, Informative)
Re:Work with OS X? (Score:4, Insightful)
But the fact that the darwin kernel boots, and Aqua can start up (no quartz extreme in the installer i am guessing) and the installer runs, he's doing _very_ well.
Infact, if he concentrates on just getting darwin working reliably (he said theres a few quirks) you can bet that OSX will run just as reliably. Its just the Aqua GUI (and carbon, cocao, apps, and all that other crap) running on Darwin. Darwin is the OS though, and as long as Darwin runs, and runs well, OSX should be a no brainer.
Getting some good hardware support in OSX for video, sound, and what not might be another story tho.
Some speed would also be nice. OSX isn't gonna run if it takes 3 weeks to install on a 10mhz emulated PowerPC chip
D.
Re:Work with OS X? (Score:1)
screenshots (Score:5, Informative)
Re:screenshots (Score:2)
Not the first (Score:5, Informative)
Hopefully, the two projects will collaborate and help improve the performance of the emulator until it is usable. 1/20th of actual CPU speed would be acceptable.
Re:Not the first (Score:1, Redundant)
As you can probably tell, the Mac emulation scene is pretty much dead.
Re:Not the first (Score:2)
I would think that that was made clear by the following quote in my post:
"only up to Mac OS 8.6, not OS X"
"As you can probably tell, the Mac emulation scene is pretty much dead."
SheepShaver + This new project would seem to imply that this is not the case.
Re:Not the first (Score:2, Informative)
Emulating a Mac on x86 isn't the same beast as emulating the x86 on a Mac. For one the markets aren't the same.
Everyone who needs to run Mac programs, has a Mac. Something like this would only be useful for someone who wants to experiment. High speed isn't as critical as it was for someone who needed to run a Win98 App under Mac OS 8.x.
LK
Re:Not the first (Score:2, Funny)
Re:Not the first (Score:2, Insightful)
Something like this would only be useful for someone who wants to experiment.
It could be fairly useful for web developers/designers in Windows-only shops who want to be able to test out Safari compatability for their site. It wouldn't have to be fast just to check that their markup renders correctly on a Mac.
Still, it would have to be at least a bit faster than 1/500th the host system, it would probably take OS X an hour just to boot at that rate! :)
Basilisk II, ShapeShifter is ILLEGAL (Score:2)
http://www.emaculation.com/fusion.php [emaculation.com]
Microcode solutions were extremely pissed with Christian Bauer. I read somewhere, that to prove he was copying their code for their own competing product, "fusion-pc", Microcode Solutions put dummy code in one of their releases. That dummy code appeared later in ShapeShifter. Can't find a ref at the moment.
When (as Drew alleges) EMPLANT code was ille
In other news (Score:2)
Last week, IBM announced industry's first POWER5-based server [ibm.com], based on - advanced 64-bit IBM POWER5 (PowerPC) microprocessor technology
QEmu? (Score:5, Informative)
"QEMU is a FAST! processor emulator using dynamic translation to achieve good emulation speed. "
"News
(May 8, 2004) QEMU version 0.5.5 is out. (Changelog). Much improved Windows 98 support. VGA support in PowerPC PREP target.
(Apr 26, 2004) QEMU version 0.5.4 is out. (Changelog). This is the first version which is able to install and run Windows XP (experimental). This is also the first version which is able to boot a PowerPC PREP Linux kernel on a PC."
Comment removed (Score:5, Funny)
Not everyone is behind the times (Score:3, Interesting)
Mac OS X supports the use of 2nd button for pulling up "context menus", similar to right clicking in Windows. Of course, it's the same as control-clicking with the single button mouse, but it is supported. OS X also supports the scrollwheel to some extent (behaving mostly as you'd expect), which PearPC doesn't yet.
I once asked an Apple engineer why you couldn't GET a two-button mouse when buying a new Apple. It was implied that someone "with a huge amount of control over the design process" was still ad
Re:major bug (Score:2, Interesting)
heh. (Score:2)
Why not run Darwin native and emulate apps (Score:4, Insightful)
Would it be possible to get this thing to run on Darwin in such a way that the system calls run natively but the apps run in the emulator?
So only the non-kernel pats of a program are emulated? That might bring down that 500x a bit.
It would involve having some translation at the boundary between the apps and the kernel but is this not the way Apple emulated old 68000 programs when they did their transition to PowerPC?
Re:Why not run Darwin native and emulate apps (Score:2)
Re:Why not run Darwin native and emulate apps (Score:1)
Re:Why not run Darwin native and emulate apps (Score:1)
Neat and all, but useful? (Score:3, Insightful)
Re:Neat and all, but useful? (Score:1)
Thanks, but no thanks (Score:3, Interesting)
For $450USD I can buy a very good low end PC Clone using an AMD processor at 2.0 Ghz, and an 80G hard drive, and 512M of RAM, DVD+RW drive, GeForce FX video chipset, onboard LAN, USB 2.0, Firewire, etc sans an OS and for $50USD I can buy a copy of Lindows, and use F/OSS software for the rest of it. So $500 total, and what do I have to spend to get all that with a Macintosh? $1799 for the low end G5 model.
yeah! (Score:1, Funny)
Performance information (Score:4, Interesting)
Open SSL benchmark [comcast.net]
And a screen shot of the PCI information:
PCI info [comcast.net]
These tests were run on a Pentium III 500 under XP Pro. You can recrate the test on your system by running openssl speed rsa dsa md5 and compare the results to a real pc or mac running linux.
Re:Performance information (Score:1)
$ openssl speed rsa dsa md5
To get the most accurate results, try to run this
program when this computer is idle
...
OpenSSL 0.9.7b 10 Apr 2003
built on: Fri Mar 26 15:00:34 PST 2004
options:bn(64,32) md2(int) rc4(ptr,char) des(idx,cisc,16,long) aes(partial) blowfish(ptr)
compiler: cc -arch i386 -arch ppc -g -Os -pipe -Wno-precomp -arch i386 -arch ppc -pipe -DOPENSSL_NO_IDEA -DFAR=
available timing options: TIMEB USE_TOD HZ=100 [sysconf value]
timing function us
Re:Performance information (Score:2)
Re:Performance information (Score:2)
% openssl speed rsa dsa md5
To get the most accurate results, try to run this
program when this computer is idle.
Doing md5 for 3s on 16 size blocks: 1104593 md5's in 3.00s
Doing md5 for 3s on 64 size blocks: 940257 md5's in 3.04s
Doing md5 for 3s on 256 size blocks: 660215 md5's in 3.00s
Doing md5 for 3s on 1024 size blocks: 301285 md5's in 2.98s
Doing md5 for 3s on 8192 size blocks: 49740 md5's in 3.04s
Doing 512 bit private rsa's for 10s: 6927 512 bit private RSA's in 9.89s
Doing
OK, so it's slow, but look how CHEAP it is. (Score:3, Funny)
With just a little bit of work and a decent motherboard you can put together a smokin' Wintel box for $400, tops and, well, sure, the eMac includes a monitor but you probably already have one.
So what if it runs at 1/200 the speed of a Mac? Hey, put a cooler on the chip and overclock it, then it will run at 1/100 the speed of the Mac!
And for less than half the price!
Well, OK, for $0.50 more than half price.
How difficult would this be? (Score:2, Interesting)
What about taking a x86 "lower half" of the OS (i.e. Darwin) and plugging and emulated "upper half" (i.e. Cocoa, Charcoal, etc.) of OS X above it.
Would that be feasible?
Re:How difficult would this be? (Score:2)
http://softpear.sourceforge.net/index.php
I got into some trouble... (Score:1)
so should i even dare... (Score:2)
The install could take DAYS! But i might be eligable for added geek points, aye?