Banner Logo
Home
The Real Kato
About Me
Twitter
Facebook
Frozen Lunches
Links
Kottke
Daring Fireball
Amalah
Secret Agent Josephine
Dooce
Contact



Archives
Most Recent

2024 April
2004 May
2004 April
2004 March
2004 February
2004 January
2003 December
2003 November
2003 October
2003 September


Categories
All Categories 

bloggers 
books 
commentary 
dating 
food 
funnyhaha 
interesting 
life 
movies 
music 
politics 
reviews 
science 
site-business 
sports 
style 
techwatch 
television 
theater 
travel 


Recent Comments
On College Football 2022: Week 6 Recap and Week 7 Pre...
Ken said:
Yeah, we've both had our share of hope and disappointment in this game. Let's just hope for a good b...
On College Football 2022: Week 6 Recap and Week 7 Pre...
Dan* said:
I'm not sure how I feel about this game. On one hand, I feel pretty optimistic that we have the tale...
On College Football 2022: Week 1 Preview
Dan* said:
Glad to see you'll be back writing football again, Ken! Congrats on the easy win today. You didn't ...
On College Football 2021: Week 10 Recap and Week 11 P...
Ken said:
Yeah, sorry one of our teams had to lose. I've come to appreciate Penn State as a classy and sympath...
On College Football 2021: Week 10 Recap and Week 11 P...
Dan* said:
Hey Ken, congratulations on the win yesterday! Some really odd choices by our coaching staff in that...


<< Previous: Television: The "Fri... | Next: Computing: Intel Fig... >>

Apple Watch: Is PearPC Real, or a Novelty?
Wednesday, 2004 May 12 - 5:59 pm
Some enterprising folks have created a PPC emulator, called PearPC, ostensibly to run Mac OS X on x86 platforms. It's an amusing experiment, but it'll never work.

Right now, the creators of PearPC have a disclaimer that their emulator is only in its preliminary stages, and that the emulated processor currently runs 500 times slower than (or 0.2% the speed of) the x86 host. So a 3 GHz Pentium 4 would run like a 4 MHz PowerPC (taking into account processor pipeline depth and whatnot). I think their estimates are generous, so you're really talking about the speed of an Apple II here (you know, the computer that was discontinued twenty years ago).

I looked at their freely downloadable source. It is decidedly an elementary effort, as far as emulation projects go. PowerPC instruction execution is all done with a lookup table that maps a PPC instruction to a C function. So a one-cycle PowerPC instruction requires, oh, a few hundred bytes of program and data store lookup, as well as a hundred or more Pentium instructions. It's easy to see why this is so slow.

Here's the thing about emulating PowerPC on x86 (and why even Apple is unlikely to ever try this): even if you had hand-coded assembly and a dynamic recompiling emulator, the speed of emulation will be terribly slow. You'd probably get about 5% the speed of the host processor (i.e. maybe about the speed of the Macintosh SE), because x86 processors do not have enough registers to emulate the PowerPC registers. A lightning-fast register-based operation on the PowerPC would require main-memory access on the x86. There's just no comparison, speed-wise.

And there's the usual problem of emulating other hardware components, such as video, sound, disk, USB, etc.

By comparison, emulating x86 on PowerPC is simpler, since the PowerPC has registers to spare. In a lot of cases, x86 instructions can be mapped to a single PowerPC instruction. This is why Virtual PC for the Macintosh is still able to achieve about 25% the speed of the host, while fully emulating all I/O hardware as well as the CPU.

Macworld UK has a horrendously ignorant article which suggests that PearPC is a step towards giving PC users a way to run OS X. Hey guys: why don't you actually try it and see how "usable" it is? One screenshot of the Mac OS X boot screen isn't a road map to a working product.
Permalink   Bookmark and Share
Posted by Ken in: techwatch

Comments

There are no comments on this article.

Comments are closed for this post.
Login


Search This Site
Powered by FreeFind