The Wii would actually be better; the PS3 uses the Cell processor, of which one part is a PPC chip, and it's a very stripped down processor that doesn't even do out of order execution.
The Wii basicly has a high-end G3 like the ones used in the last iBooks, with some tweaks to make it better for gaming.
In fact, if you could install OS X on an external USB hard drive and hook it up, OS X would probably run perfectly after you hack the Wii to get it to boot. Although compared to a desktop the Wii has a pitiful amount of RAM (less than 128 MB IIRC).
sorry , i fail to see how you equate a machine with a slower CPU and without a harddrive as standard,(perhaps later?) as better, perhaps on price?.
it seems several readers are assuming a lot of things that are just plain wrong, for instance 'the PS3 uses the Cell processor, of which
one part is a PPC chip, and
it's a very stripped down processor' is wrong....
its a fully operational PPC CPU with
ALtiVec(running at 3.2), and 'that doesn't even do out of order execution' IS NOT the main CPU (as you imply) that feeds the other units, its they that are so called cut down units ( the so called SPE's)that dont do out of order calcs and thats by design for faster, simpler operation on Vectorising calcs etc.
lets NOT forget the PS3 main CPU is running at 3.2 so can do plenty of work even before the PPC linux maintainers (mostly Genesi/Peg2 Devs now) even look to include SPE's code , they are commiting this code right now by the way.
read this for an overview
http://arstechnica.com/articles/paedia/cpu/cell-1.ars
heres an extract
"As you can see, IBM has eliminated the instruction window and its attendant control logic, in favor of adding more storage space and more execution hardware. A Cell SPE doesn't do register renaming or instruction reording, so it needs neither a rename register file or a reorder buffer. The actual architecture of the Cell SPE is a dual-issue, statically scheduled SIMD processor with a large local storage (LS) area. In this respect,
the individual SPUs are like very simple, PowerPC 601-era processors.
The main differences between an individual SPE and an early RISC machine are twofold. First, and most obvious, is the fact that the Cell SPE is geared for single-precision SIMD computation.
Most of its arithmetic instructions operate on 128-bit vectors of four 32-bit elements. So the execution core is packed with vector ALUs, instead of the traditional fixed-point ALUs. The second difference, and this is perhaps the most important, is that the L1 cache has been replaced by 256K of locally addressable memory.
The SPE's ISA, which is not VMX/Altivec-derivative (more on this below), includes instructions for using the DMA controller to move data between main memory and local storage.
The end result is that each SPE is like a very small vector computer, with
its own "CPU" and RAM. "
"The SPE's very simple front end can take in two instructions at a time, check to see if they can operate in parallel, and then issue them either in parallel or in program order. These two instructions then travel down one of two pipes, "even" or "odd," to be executed. After execution, they're put back in sequence (if necessary) by the very simple commit unit and their results are written back to local memory. The individual SPUs can throw a lot overboard, because they rely on a regular,
general-purpose POWERPC processor core to do all the normal kinds of computation that it takes to run regular code. The Cell system features
eight of these SPUs all hanging off a central bus, with one 64-bit POWERPC core handling all of the regular computational chores. Thus all of the Cell 's "smarts" can reside either on the PPC core, while the SPUs just do the work that's assigned to them."
some PS3 SPE PPC maintainers/hackers
http://www.powerdeveloper.org/forums/viewtopic.php?t=927
you could always go and try
PPC Mac-On-Linux after you install any current PPC linux and report back here how it went, perhaps if you alrady have a PS3 and a web connection you might ask if people like Lu-Zero
http://cia.navi.cx/stats/author/lu_zero might like to access your netted linux ps3 to help him make his valued work more accessable etc...... or buy him a ps3 LOL.
i imagine that once someone makes available the better ps3 hardware gfx drivers then things will improve even more in a short time....
lets also not forget that you can net boot the current ps3 in otherOS mode so that also makes its value far greater for future turnkey projects.
Running OS X on the cell architecture is not trivial as one might think. The cell architecture emphasizes computational throughput over simplicity of program code and your OS must be coded to fully utilize the PPE and attached co-processors. btw, since March Linux 2.6.16 already (officially) supports the cell microprocessor .
as regards getting a current PPC Linux installed and running, (im not sure if anyones tryed running MOL there yet?)
Lu-Zero said here
http://www.powerdeveloper.org/forums/posting.php?mode=quote&p=5583
"Posted: Fri Nov 17, 2006 7:34 am Post subject:
--------------------------------------------------------------------------------
the quickest way to get it running is just fetch or produce a standard stage3 image, add a default kernel for ps3 (the latest cell-sources should do) and it should work. (if you have a powerpc or a ppc64 would be easy since you can chroot inside)
I'm not 100% sure since I don't have access to a system...
Currently I'm trying to update the toolchain snapshots to let people start using spus and ppu specific instruction scheduling since running generic or g5 tuned binaries could lead you to a delusion ^^ (it could be quite slow due misses, pipeline bubbles and other stuff you can avoid compiling for the cell target)
I'll try to prepare a quick recipe to let you play at the earliest, give me at least a day or two to be more sure.
ping me on irc in few ours (since I have to do something in this evening and I won't available now) or send me an email if you want to act as guinea pig (requirements: crossdev, time, patience) "
as you can see above (links)it is almost trivial
, unless your refering to the longer term goal of optimising for the specialist SPE's, then yes for now at least, but give it time and effort, as for now it runs or will run as soon as someone trys MOL and gives feedback to the devs if it didnt, fun factor fix 2 days+ estimated.
as a starting point anyone with a ps3 and wanting help with PPC based Mac-On-Linux should perhaps start asking here
http://www.powerdeveloper.org/forums/viewforum.php?f=27 as thats were many devs etc hang out....
see their IRC channels too to get and give access to hard working people that want this to grow....
where did you get that number from if may ask?
I was told the wii runs at like 1.1ghz or so and cnet said this just an upgrade version of what we saw in the Game Cube. What was the fastest G3 chip out?
the fastest G3 is 1 gig i seem to remember.
