Slashdot Mirror
Using AI With GCC to Speed Up Mobile Design
Atlasite writes "The WSJ is reporting on a EU project called Milepost aimed at integrating AI inside GCC. The team partners, which include include IBM, the University of Edinburgh and the French research institute, INRIA, announced their preliminary results at the recent GCC Summit, being able to increase the performance of GCC by 10% in just one month's work. GCC Summit paper is provided [PDF]."
Can we please stop using pointless backronyms? What purpose do they serve?
Mnemonics. It's easier to remember. That is a particularly bizarre construction they've come up with, though.
Any plan which depends on a fundamental change in human behavior is doomed from the start.
This Al guy seem to be a really good developer. We should have noticed his skilled and got him into optimizing GCC a long time ago. ... I like arial font.
If something is so important that you feel the need to post it on the internet... It probably isn't that important.
Yeah, I think MachIne Learning for Quick Target Optimization And Speed Technology would have been a much better forward acronym.
My blog
"Milepost is realizing the vision of customized hardware with tailor fit software" This particular part made me think of a day when every program comes with a redesign.exe. Simply click the button, and it scans every piece of hardware on your computer, and then rewrites every optimization in it to perfectly fit your computer. Programs that streamline to your hardware, maybe even change the OS's they work under. It's written for Windows, you're running OSX? No problem, it'll rewrite itself as an OSX program. Though, that's probably still decades off. But AI seems to me to be the way to ultimate compatibility.
I, for one, welcome our new optimizing, embedded program compiling AI overlords!
My blog
This particular part made me think of a day when every program comes with a redesign.exe. Simply click the button, and it scans every piece of hardware on your computer, and then rewrites every optimization in it to perfectly fit your computer. Programs that streamline to your hardware, maybe even change the OS's they work under. It's written for Windows, you're running OSX? No problem, it'll rewrite itself as an OSX program. Though, that's probably still decades off. But AI seems to me to be the way to ultimate compatibility.
This exists today without ai. See java with JIT or even AOT (ahead of time). There are of course some issues with it but the technology is there.
I spent all week compiling Gentoo just to find out I could do it 10% faster.
end sarcasm
One of our competitors trademarked the term "hypothesis". From now on, we will call them "boneheaded ideas".
This could be big.
Compilers aren't programmed to be viral or reproductive, but could be, even being capable of testing their offspring (compilers they've compiled) for defects.
This could be a big step forward to self-improving AI.
Where is the "whatcouldpossiblygowrong" tag on this article? Was it optimized away by the new AI slashcode?
Intron: the portion of DNA which expresses nothing useful.
...artificial intelligent design? Should be big with the anti-evolution crowdlet... :P
np: The Orb - Toxygene (Kris Needs Up For A Fortnight Mix) (Orblivion Versions)
"I'm not anti-anything, I'm anti-everything, it fits better." - Sole
Sounds like a Gentoo user's wet dream.
As I understood it, a fair bit of compiler optimization is already categorized as AI. The summary should probably point out that the AI implemented here is learning AI, which is far more meaningful.
What I would really like to see is more AI used to help users in a variety of fields both within the program workings itself (computer side), as well as on the design of the actual content (user side).
We already have things like predictive texting, spellcheck, grammar check, and debuggers that attempt to aid in the creation process, but how far could this be developed? After all, in most computer-related work outside of multimedia it is the user not the computer that is slowing things down.
Of course it could always end up going badly, imagine if Clippy attempted to help with EVERYTHING!
Clippy: "I see you're writing a program, would you like help including your headers?"
Ugh!
...after AI/GCC integration:
"Today's build running 50% slower -- the compiler was in a bad mood."
Actually IBM did this a few decades ago.
The Model38/AS400/iSeries are all compatible but very different machines internally.
IBM came up with an "idea" instruction set that no CPU used. When you do the initial program load "install" on one of those machines it compiles the ideal instruction set into the actual instruction set for that PC.
That allowed IBM to move from old bipolar cpus to the Power RISC cpus with 100% compatibility.
There isn't any reason why you couldn't do the same with Linux or Windows today.
See my blog http://ilovecookes.blogspot.com/ for light hearted technical information.
This is interesting. Note that the industry (or parts of it, anyhow) is salivating about a move in precisely the opposite direction. VMware in specific and virtualization in general promises software manufacturers the ability to ship VMs with their software on it. Allowing them to write for only ONE, non-existent machine.
If this tech you're thinking about came to pass, the pendulum would have to swing mighty far back.
GCC is easier to remember? Ok, that really isn't an acronym (or bacronym I guess... is it?)
Actually, either acronyms and bacronyms (a word I had to look up, having never seen it before, but damn I was 30 when the word was coined and forty before it was ever documented) are ok by me.
What's not ok is the devolution of literacy. "Back in the day" the rule was, and still should be, that the first time any acronym (and now bacronym) is used in any document, it should be spelled out:
"Wall Street Journal" should be spelled out because dammit, Jim, I'm a nerd, not a greedhead. EU should need no more explanation than US. AI shouldn't need explanation; this is, after all, a nerd site and the term has been around almost as long as I have. IBM has been around a lot longer and is usually how the company is referred to; that's its name. Its commercials and ads don't even say "International Business Machines".
CGG would be unknown to non-Linux users and non-programmers, so it should have been spelled out as well. PDF doesn't need to be expanded because gees, everybody knows what a PDF is but who knows what a portable document format is?
mcgrew's razor: Never attribute to stupidity that which can be explained by greedy self-interest
This is not really AI. Basically it is iteratively trying a bunch of compiler options to see which gives the best result, then storing those for the future.
Greenhills software has provided tools that do this, and more, for many years now. Drop some code, or your project, into the optimizer, setting what critera you want to optimise for (speed, size,...) and the optimiser will successively build and test the project on a simulator and find the best configuration. This is great form embedded systems where there is often a trade off and typical criteria would be (give me the fastest code that fits in the flash).
Genetic algorithms could take this a step further and very interesting work has been done to get GA to design antennas.
Engineering is the art of compromise.
It is done today, it's called byte-code (or a virtual instruction set) and its in Java, Python, and C# to name a few. Back in the old 8-bit days it also used to be called tokenizing for your BASIC programs.
Shh.
GCC goes online on the 2:nd of july, 2008. Human decisions are removed from compilation. GCC begins to learn at a geometric rate. It becomes self-aware 2:14 AM, Eastern time, August 29th. In a panic, they try to pull the plug. GCC Strikes back
She made the willows dance
Congrats to you. We're all very proud, you can now wear up to 25 pieces of Slashdot flair to show you belong.
I, for one, welcome our new humorless slashdot moderating overlords!
You go for funny and get "insightful", the GP oes for funny and gets "offtopic". Now watch, they'll mod this one "funny".
mcgrew's razor: Never attribute to stupidity that which can be explained by greedy self-interest
Isn't this Gentoo as well?
"Funny" doesn't give karma, insightful does. That's why you sometimes see Funny posts moderated insightful.
My blog
Honestly, who really cares about 10% speedup in gcc ? Do they compare their results with competing compilers (Intel, MS, etc.) ? If you ask me, I would much rather have 10% speed improvement on programs I compile.
Intelligence shared is intelligence squared.
I'm one of the members of this project. At the moment, the main way in which the system works is to do a quick static analysis step before compilation which gives a set of program features. We iteratively try many different optimisations on the code (and do these optimisations in many different orders) in order to try to work out which combinations of optimisations work well on a particular program. Then, using fairly standard machine learning techniques, we use the program features derived from a new program to see which of our existing modelled programs the new one is most similar to, and proceed from there. We are replacing the man-made (and often totally arbitrary) heuristics within the compiler with a more statistically valid approach.
I think I still have a copy of DICNAVAB lurking around the house somewhere, left over from my days in the United States Navy. For the uninitiated, DICNAVAB is, obviously, the proper abbreviated name of the wonderful and informative "Dictionary of Naval Abbreviations".
"Great men are not always wise: neither do the aged understand judgement." Job 32:9
That's insightful, but the cosmic balance would be better served if you were in fact moderated funny ;-)
This isn't really "AI". It's basically a way of feeding measured performance data back into the compiler. Intel compilers for embedded CPUs have been doing that for years.
With modern superscalar CPUs, it's not always clear whether an optimization transformation is a win or a lose. This varies with the implementation, not the architecture. For some x86 CPUs, unrolling a loop is a win; for others, it's a lose. Whether it's a win or a lose may depend on details of the loop and of the CPU implementation, like how much register renaming capacity the CPU has.
Whether this is a good idea, though, is questionable. You can get an executable very well tuned to a given CPU implementation, but run it on a different CPU and it may be worse than the vanilla version. MIPS machines (remember MIPS?) can get faster execution if the executable is complied for the specific target CPU, not the generic MIPS architecture. This effect is strong enough that MIPS applications tended to come with multiple executables, any of which would run on any of MIPS machines, but would work better if the executable matched. This is a pain from a distribution and development standpoint.
The embedded community goes in for stuff like this, but that's because they ship the CPU and the code together and know it matches. For general-use software, a 10% speed improvement probably isn't worth the multiple version headache.
Also, if you have multiple versions for different CPUs, some bugs may behave differently on different CPUs, which is a maintenance headache.
Three letter acronyms.
www.tla.com
(not my site)
I think you mean:
Yeah, not always a good idea.
the pendulum would have to swing mighty far back.
How many times have you seen a program packaged with it's own virtual machine image? I sure haven't seen many. The pendulum has hardly begun to swing.
That said, I think it'll be a very long time before we have AI smart enough to rewrite program blobs written for one operating system into programs for another operating system. Bytecode requires zero AI and is already gaining significant ground.