Slashdot Mirror

You need a dynamic binary translator: http://www.transitive.com/

You're mixing up Mono and Rosetta.

Mono has ports to many different CPU architectures, and these ports don't involve translating code into x86.

Rosetta's the name Apple uses for the commercial CPU emulator code from Transitive, so that OS X on x86 can run OS X programs built for PPC.

Transitive has a news article ... it's them again, same tech provider as Apple uses for their Rosetta product (obviously, reverse of the technology, Intel -> PPC, instead of PPC -> Intel).

http://transitive.com/news/news_20070423.htm

With Just-in-Time compilation, legacy x86 programs could be painlessly run on ARM/PPC by translating them dynamically at run time, similar to how CIL and Java work.

Yeah, and run 20x slower.

Given Transitive's technology, "20x" might be an exaggeration, unless either the ARM/PPC/whatever processor isn't fast enough or translating from x86 to ARM/PPC/whatever is significantly harder than translating from PPC to x86 - Rosetta isn't, as far as I know, 20x slower than native.

I see no mention of virtualisation techiques that virtualise a different architecture - such as Transitive's QuickTransit software, of Rosetta fame. They announced a version of their software the other day which virtualises a SPARC Solaris machine on x86-64 Linux, which sounds more interesting than simply pretending to be yourself :)

Yes, it's the The brains behind Apple's Rosetta.

There are some other links on the Transitive Home Page about Apple using it for Rosetta.

Apple isn't doing it because they are working with Transitive to build Rosetta for the Mac.

At this stage, I imagine it would be politically incorrect to switch sides and start supporting VMWare. It might be the easy thing to do, but it may also jeopardize ongoing agreements with another vendor.

The company's name is Tranitive, but I don't believe they have a trade name for their software.

Rosetta is just what Apple is calling the version they're providing with OS X-86.

Just think about the consequences of Microsoft switching to PPC just as Apple switched to Intel. They could claim "superior performance" while maintaining x86 compatibility via our friends at transitive http://www.transitive.com/, and if PC users flocked to this new platform, it would bury Apple's attempts at x86 by claiming that Apple is using an inefficient and outdated architecture.

Ok,
this is unlikely, but we've all seen stranger things recently.

http://appleintelfaq.com/

What did Apple announce at the Apple Worldwide Developers Conference (WWDC) on June 6, 2005?

Apple announced that it is transitioning from PowerPC processors provided by IBM and Freescale (formerly Motorola) to x86 architecture processors from Intel. The first Intel-based Macs will ship before mid-2006, and the transition will be complete by the end of 2007.

Where can I find out more official information about this announcement?

Apple press release

Intel press release

WWDC keynote address (Transcript)

Why did Apple make this change?

The following scenario likely contributed to this decision:

IBM has been unable to meet its performance commitments for the PowerPC 970 family (G5) processors. In mid-2003, IBM promised 3 GHz G5s to Apple by mid-2004. As of mid-2005, 3 GHz G5s are still not available, over two years after the initial announcement, and over one year after the promised delivery.[1]

Meanwhile, Microsoft has announced that IBM will make 3.2 GHz triple-core G5 derivatives available to Microsoft for Xbox 360.[2] IBM is also concentrating efforts on chips for Nintendo Revolution and Sony PlayStation 3.[3, 3.1] With IBM concentrating on expensive high-end server class processors and the console and embedded markets, and with Apple at less than 2%[4] of IBM's PowerPC business, it was clear IBM's priorities were focused elsewhere.

Apple is also less than 3%[4] of Freescale's PowerPC business, with Freescale focusing on embedded, communications, and automotive markets. The priorities of IBM and Freescale do not coincide with performance and other needs of the traditional desktop and portable computing marketplace.

What has Apple done to prepare for this transition?

Apple has been publicly maintaining the core OS of Mac OS X, Darwin, for both PowerPC and x86 platforms since the release of Mac OS X. Internally, Apple has been secretly maintaining Mac OS X in its entirety and all Apple applications for both PowerPC and x86 for over 5 years, since before Mac OS X's public release.[5] Mac OS X's predecessors also ran on x86.

Apple has made available Xcode 2.1, which adds the capability of creating PowerPC/x86 universal binaries. Xcode 2.1 can be used on either PowerPC or x86 systems to create universal binaries. Application developers already using Xcode in most cases need only recompile their application with an additional checkbox adding x86 architecture support.

Apple has also licensed[6] QuickTransit from Transitive Corporation for Rosetta, a realtime binary translation system to support PowerPC binaries seamlessly on x86 hardware. The current performance of Rosetta

http://appleintelfaq.com/

What did Apple announce at the Apple Worldwide Developers Conference (WWDC) on June 6, 2005?

Apple announced that it is transitioning from PowerPC processors provided by IBM and Freescale (formerly Motorola) to x86 architecture processors from Intel. The first Intel-based Macs will ship before mid-2006, and the transition will be complete by the end of 2007.

Where can I find out more official information about this announcement?

Apple press release

Intel press release

WWDC keynote address (Transcript)

Why did Apple make this change?

The following scenario likely contributed to this decision:

IBM has been unable to meet its performance commitments for the PowerPC 970 family (G5) processors. In mid-2003, IBM promised 3 GHz G5s to Apple by mid-2004. As of mid-2005, 3 GHz G5s are still not available, over two years after the initial announcement, and over one year after the promised delivery.[1]

Meanwhile, Microsoft has announced that IBM will make 3.2 GHz triple-core G5 derivatives available to Microsoft for Xbox 360.[2] IBM is also concentrating efforts on chips for Nintendo Revolution and Sony PlayStation 3.[3, 3.1] With IBM concentrating on expensive high-end server class processors and the console and embedded markets, and with Apple at less than 2%[4] of IBM's PowerPC business, it was clear IBM's priorities were focused elsewhere.

Apple is also less than 3%[4] of Freescale's PowerPC business, with Freescale focusing on embedded, communications, and automotive markets. The priorities of IBM and Freescale do not coincide with performance and other needs of the traditional desktop and portable computing marketplace.

What has Apple done to prepare for this transition?

Apple has been publicly maintaining the core OS of Mac OS X, Darwin, for both PowerPC and x86 platforms since the release of Mac OS X. Internally, Apple has been secretly maintaining Mac OS X in its entirety and all Apple applications for both PowerPC and x86 for over 5 years, since before Mac OS X's public release.[5] Mac OS X's predecessors also ran on x86.

Apple has made available Xcode 2.1, which adds the capability of creating PowerPC/x86 universal binaries. Xcode 2.1 can be used on either PowerPC or x86 systems to create universal binaries. Application developers already using Xcode in most cases need only recompile their application with an additional checkbox adding x86 architecture support.

Apple has also licensed[6] QuickTransit from Transitive Corporation for Rosetta, a realtime binary translation system to support PowerPC binaries seamlessly on x86 hardware. The current performance of Rosetta

Any Apple PPC software you have today won't run on a new Mac in two years.

Unless they offer a reverse-Rosetta; if Rosetta's based on Transitive's QuickTransit, it could do x86-on-PowerPC just as it does PowerPC-on-x86.

Any Apple PPC software you have today won't run on a new Mac in two years.

Unless they offer a reverse-Rosetta; if Rosetta's based on Transitive's QuickTransit, it could do x86-on-PowerPC just as it does PowerPC-on-x86.

the Rosetta emulation will allow for PPC software to run on Intel

The original poster seemed to be talking about new (x86) software not running on current or near-future machines, not old (PPC) software not running on the new x86 machines.

However, Rosetta - at least if it's Transitive's QuickTransit works both ways - their product family includes both QuickTransit for x86, to allow non-x86 programs, including POWER, to run on x86, and QuickTransit for Power/PowerPC, to allow non-Power/PowerPC programs, including x86, to run on PowerPC-based Macs.

the Rosetta emulation will allow for PPC software to run on Intel

The original poster seemed to be talking about new (x86) software not running on current or near-future machines, not old (PPC) software not running on the new x86 machines.

However, Rosetta - at least if it's Transitive's QuickTransit works both ways - their product family includes both QuickTransit for x86, to allow non-x86 programs, including POWER, to run on x86, and QuickTransit for Power/PowerPC, to allow non-Power/PowerPC programs, including x86, to run on PowerPC-based Macs.

"Rosetta" = transitive.

4)no need for developers to worry for the change right now http://www.transitive.com/

Apple supposedly licensed software from Transitive that would let them run existing binaries on x86.

Can you say binary incompatability?

Industry sources also say Apple is a licensee of Transitive's QuickTransit virtual processor technology, which allows anything to run on Intel x86 (and vice versa) via dynamic instruction translation.

I have heard rumors that Apple has been talking to Transitive Technologies about Quick Transit), then we should actually see a performance increase for PPC applications (not recompiled) running on OS X x86.

If you were Steve and your apps (as well as everyone elses) ran unmodified on intel hardware faster than it ran on your own, you would probably build some boxes based on intel as well.

There may actually be no need for developers to recompile anything. With Quick Transit built into the OS (let's assume it becomes part of OS X), it would be possible to target x86, PPC or even other architectures and yet run at essentially full speed on any deployment architecture. I know this sounds a bit wicked. It did to me as well. I am sure there will be a bit of a performance and memory hit when your applications are not native, but those hits may be completely overwhelmed by silicon horsepower.

If done properly, this could be a very good move for Apple.

It also occurs to me - another point that I'm sure others have already thought of - that this may be why they are forced to switch to Intel. They can't get chips small enough for a Powerbook G5 line.

These may just be Apple negotiations tactics - rumors originating with Apple to light the fire under IBM's ass.

Or, as I pointed out in a previous post, Apple may have a real ace up it's sleeve.

I have heard rumors that Apple has been talking to Transitive Technologies about Quick Transit which is a code translation system that can re-map system calls on the fly as well as do very fast optimized recompilation of native code. Think of it as a JIT for processor emulation.

If the claims about Quick Transit are true, and there is no reason to believe that they are false as evidenced by the product's success runix MIPS code on Itaniums (see here), then we should actually see a performance increase for PPC applications (not recompiled) running on OS X x86.

If you were Steve and your apps (as well as everyone elses) ran unmodified on intel hardware faster than it ran on your own, you would probably build some boxes based on intel as well.

There may actually be no need for developers to recompile anything. With Quick Transit built into the OS (let's assume it becomes part of OS X), it would be possible to target x86, PPC or even other architectures and yet run at essentially full speed on any deployment architecture. I know this sounds a bit wicked. It did to me as well. I am sure there will be a bit of a performance and memory hit when your applications are not native, but those hits may be completely overwhelmed by silicon horsepower.

If done properly, this could be a very good move for Apple.

But in reality, i believe this is so apple can release "big iron" type systems (servers), the VM would allow Multiple versions of the server OS to run for maximum uptime, protection etc...

I completely agree. To get a true integrated environment that you can cut, copy, paste, and have overlaying windows between OSes then there must be one OS in charge. This architecture would make it very complicated to do that when running two OSes at the chip level. Both OSes would have to be modified to talk to each other like that.

Most people are going to take it as "Cool i can run windows and OSX at the same time at full speed" But in reality its closer to what i described above.

Yes, I think that products like QuickTransit from Transitive will make the emulation (or "hardware virtualization" as they call it) of other OSes much more useable, and this product still runs on top of the OS. This technology doesn't sound like it would be all that practical for the average user.

Plus....at least Windows won't be able to crash my machine (only itself) if it's running on top of OSX. If they're running side by side then who knows....

Well, there is always the posibility that one processor could concentrate on dynamic binary translation, which can improve performance Transitive anyway, and another run the translated code.

I totally agree that VPC is dead-dog slow on OS X.

However, it may be that VPC has seen its last days anyway if this stuff has any merit. Let's hope.

From the press release:

"Los Gatos, Calif. - September 13, 2004 - Transitive Corporation, the leading provider of software that enables transportability of applications across multiple processor and operating system pairs, today launched its QuickTransit(TM) product line, a family of products that allows software applications compiled for one processor and operating system to run on another processor and operating system without any source code or binary changes. The company's breakthrough hardware virtualization technology is unique because it provides 100% functionality, transparent interactive and graphics performance, near-native computational performance, and allows virtually any processor/operating system pair to be supported.

The first products available in the QuickTransit(TM) product line are:

QuickTransit for Itanium®: with support for MIPS®, POWER(TM)/PowerPC®, x86, and mainframe binaries
QuickTransit for Opteron®: with support for MIPS, POWER/PowerPC, and mainframe binaries
QuickTransit for x86: with support for MIPS, POWER/PowerPC and mainframe binaries
QuickTransit for POWER/PowerPC: with support for MIPS, x86, and mainframe binaries"

It's also interesting to note that they are saying:

"Transitive has signed agreements with six of the world's largest computer OEMs to date."

Find out more at:

http://www.transitive.com/index.htm

http://www.transitive.com/gameing_oem.htm the games section of their site shows a model with games from an old system (x86 in the example) to a new game system (ppc in the example). x86 to ppc could only be for xbox, the gamecube is ppc already and the ps2 (im pretty sure) is not x86.

We could all be doooooooomed!

The graphic on Transitive's website shows only Unix/Linux operating systems. One of their steps, Operating System Mapping, says "QuickTransit supports operating system mapping between any two Unix/Linux-like operating systems, as well as mapping between mainframe and any Unix/Linux-like operating systems." Doesn't sound like Windows to me.

All of this is supposedly done on the fly, and not beforehand.

Quake and The Gimp wouldn't be my choices to show off flexibility. Quake is OpenGL on Linux and OSX, so there isn't any graphics magic going on. And the ability of BSD-based systems to run Linux binaries is old hat. The Gimp isn't exactly taxing on a CPU as far as user responsiveness goes.

Extraordinary claims require extraordinary proof. Press conferences for journalists aren't a conducive forum for proving anything. They are a good place to baffle 'em with bullshit, though.

-Charles

After reading this, the term Universal Emulator doesn't seem to apply. Here is the text from Transitive's Website:

Operating System Mapper. Dynamite supports operating system mapping between any two Unix/Linux-like operating systems, as well as mapping between mainframe and any Unix/Linux-like operating systems. Where similar operating system calls exist between the source and destination operating system, Dynamite maps calls between the two. Where an equivalent operating system call doesn't exist in the target environment, Dynamite maps to similar calls per the customer's guidance. Dynamite also monitors certain system calls, for example thread scheduling and memory mapping calls, to ensure that it can reproduce the complete behaviour of the program it is executing.

It's not that clear from Transitive's home page, but if you read their Datasheet, you'll see that Dynamite actually translates and optimises the binary as it runs, so no PowerPC binary "pops" out at the end, as such.