Slashdot Mirror
IBM Releases Compiler for Power4 and G5
davids-world.com writes "IBM offers its optimized XLC compiler not just for Intel CPUs, but also for its own G5 processor (article in German at Heise). Unlike gcc, it is optimized for the G5 and achieves a major boost in speed, as first results show. I guess we will have to compare the new benchmark data (once available) with the data we get with the optimized Intel compiler for Xeon. The compiler is available for download now."
So will this new compiler speed up the process of porting Duke Nukem Forever to the Mac?
Slashdotter are stupid and biased.
Lest anyone forget, Apple beat Intel in real world benchmarks... so the PC fanboys cried that SPEC benchmarks are the real measurement to gague speed... (probably because the comparisons were much closer when conducted this way). When SPEC benchmarks were displayed, these same fanboys cried that Intel's compiler wasn't used (instead the same compiler between platforms). Apple replied that its fairer to normalize the compiler between platforms and that while Intel could have achieved higher results when their compiler was used, Apple could do the same. So, here is that compiler. When/if the G5 outperforms Intel's best, what will the fanboys rally cry be next?
This is a preview beta. What will the final product be released under?
>So will this new compiler speed up the process of porting Duke Nukem Forever to the Mac?
Sorry to burst your bobble, but there's a reason why the game name's Duke Nukem *Forever*. That's the amount of time it will take to make it.
And is there a particular reason why IBM couldn't apply their work towards gcc? So much for the whole open-source, contribute-to-the-community philosophy.
I'm personally rather tired of companies which consider "contributing to the open-source community" to be "lets send in drivers for our proprietary hardware which only we will ever need." That's NOT contributing to the community, that's getting your foot into the kernel.
I know Watson labs has made many contributions to GCC over the years..and I'm not naive enough to think Big Evil Corporations aren't out for their own interests...but it's still a shame they couldn't have used gcc as a base.
Please help metamoderate.
They optimized XLC for intel at all. I knew they did for the PPC but not intel.
Is there some good reason why IBM doesn't just improve gcc? I mean, apple uses gcc; free software users use gcc.. Gcc is a complete compiler suite.
Why didn't they just submit some patches? : )
Liberty.
located here says that people are seeing nearly a twofold increase in both G4's and G5's. I lifted this next spec directly from their discussion: (XL improvement over Absoft and GCC 3.3): Type of Code G4 G5 Scalar +70% +210% Vector +40% +70% _If this holds that places his _2.0GHz G5 (single)_=254 at _787__ Note also that the _P4 2.66_ is _255_. This is a big deal. Let's just hope they use this to compile the OS.
I, for one, welcome our new IBM overlords.
Ok, now that's out of the way, let's get back to real comments.
Believe it or not, people DO sometimes run singular tasks on hardware which they want highly optimized...and believe it or not, you can actually install more than one compiler on your system at a time(yes, I know, amazing!)
Please help metamoderate.
I guess we will have to compare the new benchmark data (once available) with the data we get with the optimized Intel compiler for Xeon
Yeah we need fuel for lame ass my mac is better than your pc flamewars.
I'd imagine one could cook up code to make whichever machine they want look "faster".
Who gives a rats ass anymore.
I don't need no instructions to know how to rock!!!!
The new IBM compiler should rectify the situation. Apple will not need to manipulate the SPEC scores by hiding behind the GCC compiler. In the past, Apple stuck with the GCC compiler because it causes the Pentium to perform much worse than it would perform on code compiled with an Intel-provided compiler.
Of course, both the Power4 (and derivatives like the PowerPC 970) and the Pentium IV crush the UltraSPARC in performance. The new IBM compiler is yet in another nail in the coffin of the UltraSPARC.
Xcode, the new compiler/IDE, which is based on gcc, is also optimized for the G5.
For more information, see Apple's Xcode site.
-- Fighting mediocrity one bad post at a time.
BUT he was saying it is worthless to compile the kernel if it wasn't GCC compatible...not worthless in general because of GCC or something.
GCC's whole purpose is to be the most portable compiler possible, not the best performing on any particular architecture.
XLC has a different set of design goals, and the internal architecture of the the compiler is different enough from GCC that there wouldn't be much point in trying to graft them together.
-jcr
The only title of honor that a tyrant can grant is "Enemy of the State."
Having used the xLC compiler (on AIX 4 and 5), I can say that it is a very nice compiler. It's probably one of the most strict ANSI-compliant compilers I've used. It also has some nice architecture tuning optimizations. If this new version speeds up the G5, then you can count on future versions giving even better increases.
This is very good news for Apple-people.
It is good to see IBM ending the habit of charging extra for the C compiler. AIX hasn't bundled the compiler since 3.2.5.
The top 5 questions/posts from slashdotters:
1) Is it open source, I didn't RtFA?
2) Why isn't it open source?
3) Will they release it for Linux on the ppc?
4) What does this have to do with SCO?
5) Apple is dead and these are flawed stats flamewar.
I'm too lazy to come up with a sig that is good enough to be the same everytime, so you can just read this instead. You can try and rid your braincells of this text, but it's pretty much stuck there now.
I know everyone wants to know why they did not just contribute to GCC, but seriously people, I imagine they have their reasons.
Perhaps they wanted something done in a timly manner without waiting for the GCC people to accept their patches. Perhaps they felt a more elegant solution could be achieved by building their own compiler from scratch. Maybe they think GCC is a piece of crap (which for high performance computing, it is).
Just because IBM support open source does not mean they are obligated to do everything for the sole purpose of advancing the movement.
Finkployd
What's a "real-world" benchmark? Comparing the function of photoshop on mac vs. pc, when it's developed natively for the mac? That's not really fair. It's simply not the same code. We could take any of the many programs made natively on PC (which are then ported to mac) and do the same trick.
so the PC fanboys cried that SPEC benchmarks are the real measurement to gague speed... (probably because the comparisons were much closer when conducted this way).
And I'm sure that the macheads don't favor the "photoshop test" for the same reason? We need some objectivity here. Nothing wrong with a fair benchmark, and I'll go on record as always preferring a benchmark, regardless of who it favors.
Apple replied that its fairer to normalize the compiler between platforms and that while Intel could have achieved higher results when their compiler was used
Why fairer? Shouldn't tests use whatever compiler will *actually be used*? If apple/IBM made a chip without a decent compiler to support it, that's their problem. I'd say it was fair to use Intel's compiler for intel's chip. Now it will be fair to use IBM's compiler for IBM's chip. Also interesting was how you suspect the "fanboys" of being biased when they wanted benchmarks instead of "real-world" tests, but Apple just "realized that it's fairer" to do something that benefited them. It works both ways.
Apple could do the same. So, here is that compiler. When/if the G5 outperforms Intel's best, what will the fanboys rally cry be next?
That's perfectly fair. Let's use the best compiler for each machine. I've no problem with it.
Now, to ensure a completely fair test, let's make sure Apple uses both machines as they ship, and everything will be fine. But the pc "fanboys" as you call them were right to criticize a test in which Apple modified the machines, both their own and Dell's, fom the way they shipped. The changes it made to the Apple were beneficial, the ones to the Dell were all detrimental. That's not science.
I honestly like Apples, this is just a matter of scientific method to me. I really could give a shit who wins.
-Looking for a job as a materials chemist or multivariat
I wonder how the AltiVec support in XLC for OSX compares to that in GCC?
This is actually really important. One of the big reasons that the Intel C compiler spanks every other available x86 compiler is that its SSE/SIMD support is, in the words of one of my assembly-programmer friends, "awe-inspiring." Like, unrolling entire program loops and replacing them with single SIMD instructions.
As far as I know, pretty much all of the AltiVec/VMX support in GCC was contributed by Apple and Motorola, and prior to the ppc970, IBM has never produced a PPC CPU with AltiVec instructions, so prior versions of XLC have never had to support it. So I'll be really curious to hear how it stacks up against GCC's Altivec.
News for Nerds. Stuff that Matters? Like hell.
I mean, if they have other tools within the compiler, which are covered by restrictive licenses like SCO's trying to foist, they might be barred from releasing that technology. Some of the optimizations may be covered under patent, which they don't own outright.
Second, the people involved in that compiler are not exactly "clean-room" when it comes to submitting patches to gcc without intimate knowledge of those other methods/IP....
Last thing IBM needs now is a REAL case of leaking information which is covered under patent/IP or whatever protection.....I expect them to release all the details, just expect that they will only provide factual information rather than "how-to".....
I am not a software dveloper...so maybe I don't know how it works. I was thinking that perhaps they just wanted to build their compiler, without waiting for their patches to be approved (or not) and having to deal with the time it takes. With their own compiler they can work on it right there, in house and in full control of how it is done.
But I guess they could of just released a fork of gcc how they wanted it though. Who knows.
It looks really good.
Does it support Obj C though?
Can it compile Cocoa code?
Is there some good reason why IBM doesn't just improve gcc? I mean, apple uses gcc; free software users use gcc.
This is IBM's product. IBM doesn't sell MacG5's, they sell AIX based workstations based on their POWER and PPC chips. XLC is the compiler for AIX, so it makes sense for them to optimize the compiler for their products. If Apple gets a side benefit, than good for Apple, but it's not like IBM did this for the primary benefit of Apple.
I couldn't care less about the kernel. Just how much performance do you think you could potentially gain in improving the kernel? Kernel is irrelevant.
You need to optimize the applications and, if you are dealing with serious mathematically heavy programs, you need a compiler to really bang the hardware bits.
To put it bluntly, GCC is a worthless piece of shite on anything else than a ix86 architecture. Furthermore, on ix86 arch the Intel compiler beats the shit out of GCC and a Linux version is available at an affordable price.
BOO! TERRO
When SPEC benchmarks were displayed, these same fanboys cried that Intel's compiler wasn't used (instead the same compiler between platforms) ...
Pot - Kettle - Black. You got the whole fanboy thing reversed.
You have to be an Apple fanboy, a gcc fanboy, an Apple PR/Marketing person, or a non-technical person to believe GCC normalizes results. GCC is not a constant, the quality of it's generated code varies from one architecture to the next. On some architectures it is great, on others it is so-so. Intel's compiler is available for Linux and some apps show dramatic improvements.
Apple's current comparison is fair in a marketting context, it only fails in an engineering context. When we compare Intel compiled SPEC on a Pentium 4 800 MHz FSB with dual DDR-400 against an IBM compiled SPEC on a G5 we'll finally have a truly fair comparison. No cherry picking compilers or CPUs (another problem with the current Apple claim, but fair in the marketing world), just the best available all around.
How are you sooooo cool that you have a dual-2ghz G5 before it's even shipping? Funny, funny bullshit!
Is the word "fanboy" used by anyone but fanboys?
Eh, I wouldn't say that GCC is "worthless", it's just that its worth lies in an area that has nothing to do with high-performance computing. Or even mid-performance computing. :)
GCC's primary virtue is that it exists. For practically every computing platform on the planet, there's a famliar, stable toolchain that produces repeatable results. You can't optimize a program that doesn't exist in the first place, and GCC is the tool that's allowed many if not most of the programs we use on a daily basis to exist. There's value in that.
News for Nerds. Stuff that Matters? Like hell.
The IBM compiler dis some wild instruction reordering which made the optimized compiled code really hard to understand, but somehow better fitted to the processor's pipeline structure. Fortunately the only thing that broke when I turned on the optimizer was the "marching ants" used for selection, and that was the result of some way-too-fancy-casting of Pattern pointers that fooled the optimizer. I suspect the IBM compilers will continue to reign if performance is the goal.
this new variant of the Troll.Mac virus actually had me chuckling to myself at work, give it a funny.
Live EVERY week... Like it's Shark Week
And when you buy these computing platforms you speak of, you can you not afford a native compiler?
BOO! TERRO
No, I don't mean scientific computing. I mean high performance computing. SP clusters, Linux clusters, weather modeling, the stuff that large universities do. No offense but where I am we run significantly larger clusters than SARA has ever seen.
GCC is a great compiler, I use it daily. Better than Intel and IBM for performance (expecially FORTRAN) it is NOT. It was designed as a cross compiler and in that it shines. But it is not all things to all people.
I certainly did not flame GCC and all the people who work on it, come back down off your high horse. All I did was list some reasons why IBM may not have used GCC, one of which is that most of the HPC people I know and work with have tested it and found it to be unacceptable for what they do.
That said, I certainly can see a day when GCC IS the best performing compiler, hands down. I believe open source will eventually overtake most commercial applications due to the momentium it currently has. However it would be silly of me to say that MySQL is better than Oracle, when it clearly is not (yet).
Finkployd
A 486 with 8Mb of ram that has the blaster virus must have either Win 2k or XP on there (perhaps Nt4 as well?) which is impressive by any stretch of the imagination.
Anyway, grandparent post is an interesting change to the regular Mac troll that appears in every thread.
Has anyone determined whether Taco has written this troll post into slashcode or if it's an actual human person positing them?
Anyways, back to your problem. If you copy with the shell or with any other file manager on the Mac it will be considerably faster.
As for Adobe Acrobat, I don't know what is wrong there. I installed it in just a few minutes without any problems.
However I must ask if you are for real. Sorry but just today have reports of dual G5's come out. That you "recently upgraded" sounds a bit doubtful. I don't know anyone with a dual G5. That you say your iPod stopped working and Safari isn't working during a copy makes me think either you have a flawed pre-release machine or are just blowing air. My apologies if you are legit. Just doesn't sound right.
Very often, that "native" compiler either doesn't exist (because even the vendor is using gcc), or is prohibitively expensive for a startup company.
It's best to approach GCC like Java: use it to prove the correctness of your app, then profile profile profile and insert inlined assembly into your bottleneck points. Remember your Brooks: 90% of all optimization is premature.
News for Nerds. Stuff that Matters? Like hell.
Check this post out if you need an answer to your question.
The speed could be infinite. IBMs new complier is powered by rainbows, dreams, wishes, magic gumdrop sprinkles, and imagination. Theoretically speaking, you could bypass the rainbows, dreams, and wishes; while using a wrapper to off-load the burden of the magic gumdrop sprinkles to the flux capacitor. Then you could primarily focus your development on imagination... which would allow you to compile and run applications at a speed predetermined by your imagination.
I've also heard that the wishes and dreams can be fairly powerful tools as well. However, results may vary due to unfulfilled wishes and crushed dreams.
"Things are more moderner than before- bigger, and yet smaller- it's computers-- San Dimas High School football RULES!"
Why would you install an expensive, licensed compiler on all 1000 nodes of a cluster???
A Good Intro to NetBS
I'm interested - *are* there winzealots who don't live in Redmond? I've never known anyone who gave half a shit about their windows. I've known PC-zealots who happen to run windows, but they're usually graphics-card zealots, or case-mod guys.
But I have yet to meet a true fan of the windows way of life.
-Looking for a job as a materials chemist or multivariat
The problem is that the increase in execution speed is matched by a corresponding inflation of Steve Job's ego.
Huh? I can't speak for any "pc fanboys," if such a thing exists, but I would be simply interested, from a scientific standpoint, if Apple's made up all that ground after a long period of Motorola being pretty bad. I don't know about anyone else, but I don't really care which one wins.
Just for the record, and in the interest of full disclosure, are you a mac "fanboy?" I myself use both platforms (apple and intel) regularly, counting Linux, BSD, and Windows on the PC.
-Looking for a job as a materials chemist or multivariat
people who run their compiler from the command line or through make.. I bet tons of people will start using this to get solid performance increases on the mac if not i86 architectures
Of those to whom much is given, much is required.
amen on the SIMD comment. not being a HPC guy, i hadn't realized until recently that intel had absorbed the kuck & associates team (the folks who used to do vectorizing compilers for supers, back when people cared about supers). it is just too cool to see this just pop up when you type "make":
Sound_to_Pitch.c(211) : (col. 7) remark: LOOP WAS VECTORIZED.
IBM's benchmarks comparing gcc and xlc on SPECint2000 and SPECfp2000 seem not very meaningful to me. First of all, note that both -O2 and -O3 are semantics preserving in gcc, while -O4 and -O5 in xlc are not. That is, in particular on the SPECint2000 benchmarks, the xlc compiler is faster simply because it changes the behavior of your program. The same may even be true for xlc compiling SPECfp2000 at lower optimization settings; the Intel compiler on P4, for example, achieves large gains in performance on some benchmarks by inlining math functions that gcc uses a library for--because the P4 instructions aren't quite right.
In my experience, you can usually match the performance of those other "fast" compilers with gcc by using the "-f" and "-m" flags. The main difference is that gcc forces you to be explicit about which semantic changes the compiler is allowed to make, rather than lumping things together under some generic "-O5" setting. That's a good thing.
(Note that my comments apply to gcc; g77 may well be a much worse performer than commercial Fortran compilers even though it shares the same back-end with gcc. That affects the SPECfp2000 scores. Fortran just doesn't seem to be a high priority for gcc.)
Or roll it into their Xcode (does Apple even use Xcode for work on OSX)? I don't know much about compilers so I'd be curious to know if Apple and Mac developers could make use of this new compiler from IBM?
Umm, yes, IBM does contribute to GCC, but that doesn't mean that they'll stop the development of their high performance, highly competitive compiler that has several years of development and optimizations behind it. Think about it, would they really just abandon all the manhours, resources and intellectual property that have sunken into it and migrate, just like that, to some compiler that is just now becoming competitive with other, propertiary compilers ?
In the past, Apple stuck with the GCC compiler because that's what they're using on their machine. I don't see why (some) people have been so tremendously uptight about this; it's not like their benchmarks showed the G5 dunking the P4's head in the toilet and mopping the floor with it, they just showed it being competitive. GCC may be mediocre, but it's mediocre on all platforms. This may not be the most spiffy way to try to eliminate compiler effects from a test and it may not even be the Official SPEC Way, but it's still probably a better way to do it than to say "go ahead, compare our scores with GCC against Intel's special compiler with the '-optimize-for-spec-test' flag" like the loudest critics seem to think they should have.
And why is Intel struggling to make even incremental performance boosts to the their Pentium lines? Why are they throwing back their delivery schedules for Prescott, etc.? The Pentium is near its EOL, the G5 is only starting. Intel gambled on the new Itanium architecture and it is not working out for them either. MSFT doesn't plan to put in 64-bit extensions into XP till its SP2 later in 2004, so AMD is screwed as well. The Wintel world is carrying the x86 and Win32 monkey on its back and it is crwling under the weight. Longhorn the solution? We will have to wait till 2006. In the meantime, IBM and Apple are moving like a race car.
Interesting, as I heard it they did some things to make floating point calculations slower. Makes me wonder why they didn't even try a stock Dell? A perfectly fair comparison, yet I haven't heard it resported at all.
from using the same compiler
That was to benefit apple, at the time the intel compiler was much faster. This changes now, with parent story, obviously.
Get over it. x86 hasn't always been the reigning speed champ.
And I would say the same to you. Is it possible to actually discuss this story without accusing people of being in denial? I *don't care* who wins, it's about experimental methodology for me.
And this is how all the apple posts go:
PC user: I don't know - isn't it possible that the apple isn't the fastest machine on the planet?
Apple user: Shutup you PC-fanboy zealot! You need to get out of denial and face the fact that the apple is faster. x86 sucks!
I mean, why is it impossible to rationally discuss this story with mac users?
-Looking for a job as a materials chemist or multivariat
Most convicted internet pedophiles run Windows. No Joke.
“Common sense is not so common.” — Voltaire
Anyone else find it ironic that all the recent g5 stories are labeled with the picture of the g4 chip? =)
Interesting to note that Objective C is much closer to raw C than C++, and as such yes. You can do some stuff with it that's worthwhile.
Also note that David Stes released his POC, which is an Objective-C->C compiler with a runtime he uses (actually it's a bit more than Objective-C) to run ObjC code today.
Apple will probably use this new compiler to recompile their CoreFoundation stuff, which is all C stuff that Carbon and Cocoa tap into. So, a simple recompile of CoreFoundation should net good speed improvements on G4s and MUCH better results on a G5.
So even if IBM chooses not to directly support Objective-C, Apple can still benefit in the short term while they rustle up their very own ObjC->C system (which is NOT a very challenging feat, considering the ObjC runtime is a relatively simple-to-use C library).
Slashdot. It's Not For Common Sense
Because little or no commercial software will ever be compiled for Intel chips using gcc, rather Intel's compiler. It would be like saying apple should force their system to emulate 32 bits since that's all the PC has. I see the availablity of a completely superior compiler to be a fair advantage. Even now that IBM's made a kick-ass compiler for Apple.
And it seems to me that you can't get over the fact that maybe, just maybe, Intel isn't the top of heap (again).
I have no idea where you get this from. Did you miss what I said last post? Can people actually just discuss this? I've said it twelve times - I don't care who "wins." I'm a scientist, and as such, I considered Apple's methodology deceptive. It doesn't affect me as a computer user. Put it this way - I've never been the guy with the fastest computer anyway. In fact, I don't own an Intel. I run an AMD-900, so that should tell you something about how much of a speed freak I am.
I'm one of the few Mac fanboys who will admit that for the last two years or so, the G4 (#@!#$! Motorola) and corresponding architecture has lagged behind the Intel world in terms of raw speed.
Hey, that's great. But you indeed are a fanboy, as evidenced by the fact that you overly criticize those who aren't apple fans.
-Looking for a job as a materials chemist or multivariat
IIRC, Apple compiles OS X on gcc 3. Would it take a lot of work for them to use the new IBM compiler and therefore take better advantage of the G5? Are there too many differences are between gcc and XLC to allow the open source community to continue to work on Darwin, while Apple uses XLC for performance?
"Anyone that has ever gotten an idea based on any of my work and done something better with it-good for you."--J.Carmack
(Disclaimer: speculation)
If IBM were to work with Apple and include Objective-C (as a C superset) and Apple were to market this as an alternative compiler on the Mac platform, would that be a good or a bad thing?
If I go from Mac to Intel, or vice versa, and I'm not the type to pirate everything from friends, warez sources, or p2p, then I have to buy (prices from Amazon.com, rounded to nearest dollar)...
So the cost to switch is:
To Mac from Win: hardware + 1883 software
To Win from Mac: hardware + 1857 software
And that's just the basics for a good multimedia development set-up. If you code, create Flash/Shockwave, etc., then you can add on another $500-1000 for other tools... or more.
Bundles and other incentives can bring it down, but this is not an inconsequential cost. Even if you could get a 10% faster PC for the same price as a Mac, or a 10% faster Mac for the same price as a PC, you have to ask yourself how much that 10% is really worth to you.
How often will you utilize all the capabilities of the machine and stretch the system past the capabilities of the alternative? How many hours of labor will the system save you over time?
And when all is said and done, you can scream over benchmarks and which is the better OS all you like. But they're totally meaningless.
(Mac fans can claim Windows has an inherently higher TCO, but let's face it, that's if the user is someone who thinks GNU is a Milton Bradley game that succeeded Gnip-Gnop. The rest of us know that a well-educated Windows user can avoid many of its pitfalls.)
Each time I've upgraded my hardware, there's one question I ask when I consider whether to switch platforms... What's the bottom line? How much more would this cost or save?
When I worked it out in 1993, a 486 DX2/50 by mail-order beat an education priced Quadra 40 from the university. Since then, I've invested much more in software that I had as a student... Even though the hardware costs are becoming less of a factor, the software costs have become more of a factor to compensate.
If I won the lottery, I'd buy a Mac and all the cool software I wanted. But barring that, I'll be looking carefully at Prescott versus Athlon 64 in the coming months, and making my choice in the Wintel world because that's where my software is.
So, though this compiler news is cool if you're a Mac User, because it makes your platform better *for you*, the arguments about whether Mac beats WinTel are a lot of sound and fury, signifying nothing.
Start a happiness pandemic
Shitty nvidida geforce fx 5200 for the pc(64 mb version)... $60...for the mac... $120...
Hmmm... Pie...
The Pentium scores you listed are from Pentium CPU's (not the xeons which did slightly higher) which are incapable of dual cpu operation. This was against a dual cpu system that was probably optimized well for dual use.
Whats interesting to note that the single pentium machine scored 836 in int performance and the xeons (dual machines) scored 840... Almost no performance increase from going dual here.
Hmmm... Pie...
It's taco that's doing this. Everyone knows that if they want to laugh, they read at -1. If everyone wants be mis-informed, they read at +5. If everyone wants to learn, they are told by Theo Teh Ratd to RTFM.
Further, it didn't originate from the Mac world OR the PC, but from SGI-space. It's had time to be optimised for x86, and Apple have also had a crack at it (at least for V3).
I, for one, would welcome new ove^H^H^Hbenchmarks I could relate to.
Why would anyone engrave "Elbereth"?
What I wonder is whether this compiler will be used in future versions of xCode. If it is, in fact, significantly faster than GCC, it seems logical that Apple would wants it as part of their own developer tools.
In addition, I wonder what this will do for Metroworks' CodeWarrior compiler?
"Reality is merely an illusion, albeit a very persistent one " -Albert Einstein
Event: Somebody actually does something realted to some Apple product.
Slashdot reaction: Unless it comes in GCC today and fixes me a martini and picks my nose and sings the Hallelujah chorus and comes with a big check, what damn good is it, anyway?
Event: Somebody at Microsoft says that they might do something in a couple of years if they feel like it.
Slashdot reaction: Hah! Luser! See, Microsoft already did it.
Event: Somebody decides that it might be possible to do something cool if they could only get cheap enough buckytubes to wire the brains of ants to the FPU in Python emulated in Perl emulated in ELisp. And it will run on Linux. Except nobody is going to do it, really, but it would be cool.
Slashdot reaction: Linux is ready for the desktop! Linux is ready for the desktop!
This is because both Motorola and IBM codeveloped the PowerPC architecture. For example, did you know that the G3 chips used in the iBooks are actually manufactured by IBM? The 970 (aka G5) has native 32-bit PPC instructions. Basically, to make software for the G5, it requires taking your code, putting it on a G5, and recompiling. Done. No code changes necessary.
If you're going to rebut about VPC not working, that's because it made some specific little-endian calls that the G4 has but the G5 is big-endian only. This was done for speed, but oh well. It'll have to be updated.
- Sherman
Xcode is just an IDE for GCC; it's not a separate compiler.
Actually, over 70% of Adobe's Photoshop, Illustrator and InDesign sales are for the Mac.
I've read this same statistic too, however that figure (70%) is for the three applications as a whole. The majority of Photoshop sales are for Windows, while the majority of Illustrator and InDesign sales are for Mac. All together, 70% of those sales are for Mac.
yes but believe it or not, the most critical single items to improving the performance of EVERYTHING on the system is the kernel and those single applications you speed of have a good chance of gaining a boost if the kernel is compiled with this.
This isn't just another compiler, it's a compiler made by the chipmaker to be highly optimized beyond what anyone else can for their G5 chip.
Somehow I suspect mac users and the users of any other operating system will be concerned with whether the macosx and other kernels that run on this chip can be compiled with it as well... optimizing an app is great and all, but it can't possibly affect the performance of as many apps as the kernel.
no it simply depends on certain features in the compiler. They exist in other compilers. Last I checked EVERY operating system requires fairly advanced features in it's compiler.
Every APP depends on the kernel and it's response to system calls. A small gain in the kernel means overall system performance speeds up.
Last I checked the intel compiler cannot compile the kernel, including the linux version.
BTW, rename the files to vacpp.60.macos.beta.dmg (C/C++ toolkit) and xlf.81.macos.beta.dmg (fortran) if your browser does not handle the ftp redirect well. If LaunchServices opens the file with the wrong application when you double click on the disk image, drag the file onto the Disk Copy icon in Applications:Utilities instead.
Let me guess. You work for Microsoft.
Every time a company (just like IBM) comes up with some new code to help out the Linux kernel, OSS, whatever - it helps their competition as well. So where's your fuzzy logic now?
The new world is open source, open ideas, and open specifications. Every single day it becomes more and more apparent. Get with the times.
- It's not the Macs I hate. It's Digg users. -
If anyone would like to take the initiative and has access to a G5, IBM offers these instructions for running SPEC2000 on a G5 using the optimized Fortran compiler.
-You may license this sig for only $6.99.
This makes me think of those leaflets some whino'll push in your hand trying to prove They DIDN'T Land on the MOON.
I think, therefore I am...I think.
Can't we talk about Macs on Slashdot without having to talk about whether they're overpriced or slow or whatever? I have a Mac, I like it, I use it for lots of things. I'd like to be able to discuss it, rather than just read x86 users' posts about how much better their platform is & why. This article is about a complier, not comparison shopping. Could we stick to that please??
It seems to me that this special super-duper compiler wouldn't benefit any other CPU's since it's designed to make code that the processor executes the most effeciently.
Open sourcing a compiler for a CPU wouldn't automatically make the Xeon compiler any better. It would make gcc compile for that processor better.
Either way.. where's my super-duper Athlon and Athlon64 compilers!!
- It's not the Macs I hate. It's Digg users. -
Looking at all these pretty graphs, and knowing that in most cases sane people will restrict their optimization to -O2 (-O3 and above are usually unsafe: not as well tested, may change the program behaviour, cut corners with IEEE math, etc), GCC is still looking pretty good.
In most cases in both FP and Integer, GCC matches XLC up to -O3, sometimes a bit slower, sometimes a bit faster.
I applaud the work of the GCC people. GCC is the most versatile and portable C compiler, and it's not half bad at optimizing either.
Thanks too to IBM. Their compiler will surely prove useful in a lot of cases, and a new compiler to try and benchmark is always good news!
Back when the P4 was somewhat new, Toms Hardware did a test on MPEG-4 video encoding. Well the results were that Athlons beat, rather badly, P3s and P4s. Well Intel thought something was screwy here and found that the MS VC complier had been used. Since theirs plugs into VC, they got the source for the MPEG-4 program and recopiled it. Simply recompiling it produced amazing results. The P4's speed jumpes 3.7x, the P3 2x. Even the Athlons doubled their speed. Now this was just using the code written for the x87. Intel then wrote some SSE optimised code that increased it further. However the impressive part was just the recomplie not only increased the speed on their processors, but on their competitors too.
. ht ml
Now this code was written for the Intel compiler, it wasn't written by Intel (they wrote their own optimizations, which ran even faster), they just ran it through their compiler.
The Apple/Dell SPEC results also jive with this. The big difference between the two is the use of the Intel compiler. It really DOES do a better job, loath though some peopel are to admit it. I don't understand why, one would expect a company's own compiler to do the best job, but some peopel seem to hate the Intel compiler based on principle or something.
At any rate it really is a good compiler, regardless of if you acknowledge that or not.
http://www6.tomshardware.com/cpu/20001125/index
The G5 is both big and little endian. It is part of the PPC architecture. MSFT needs to clear up their statement.
All the PowerPC processors are binary compatible. Even the Power series from the Power2 forward to the Power5. The beauty of the PPC architecture, is that the physical implementation can be radically different, but the instruction set remains the same. (For the most part, the PowerPC ISA is still revised to it keep modern.)
What is different is the performance you may get when targeting a processor. The compiler can optimize your code to a particular processors physical implementation. For example, code compiled for the G5 will be structured to work better knowing how the G5 processes instructions down its pipeline, how it makes its decisions, caching, etc. But the 32-bit code will still work on a G4 albeit at a slower rate.
IBM is in the best position to understand the physical design of the G5 and thus they can make sure that when compiling code, the compiler chooses and structures the instructions that will run optimally for it. In addition, IBM is pretty advanced in developing optimization techniques and they bring a lot of intellectual property to the table. All this makes for some pretty serious optimizations that rival anything a more generalized compiler may be able to do.
What this means is that the Mac developer has another weapon in his arsenal for conquering performance issues. Consider it a free upgrade for your processor, the results are showing significant improvements that will work there way into OS X and performance sensitive Apps.
Holy shit, I just fell out of my chair laughing. Someday in 2030.... I've just recently upgraded from a Mac G12 AI to help me at my freelance gig where I copy a 40 Terrabyte file from one folder on the holographic drive to another. On my Pentium 5 this operation takes only 5 days. I won't bore you with the laundry list of other problmes I've encountered while working on various macs, but suffice it to say that I have absolutely nothing better to do than continously post this stupid comment everytime I get a chance.
Anyone who whines about being modded down should be.
Does it integrate with ProjectBuilder, XCode or CodeWarrior? I don't know, you tell me. If not, who will use it? A better question would be: is it compatible with objc (cocoa)?
May not be perfect, but it's still the best government we have. For now.
[notices "HAIL IBM" sign taped up, tears it down]
Oh, yes, by the way, the spacecraft still in extreme danger, may not make it back, attempting risky reentry, bla bla bla bla bla bla. We'll see you after the movie.
Mmmm... If I wanted to improve the performance of my Linux PC by recompiling a single package, I'd rather go with glibc than with kernel.
> Eh, I wouldn't say that GCC is "worthless", it's just that its worth lies in an :)
2 000-20030728-02428.html
and2 000-20030728-02417.html
> area that has nothing to do with high-performance computing. Or even > mid-performance computing.
GCC is really fast.
Look at some SPEC_FP numbers:
(1) http://www.spec.org/cpu2000/results/res2003q3/cpu
(2) http://www.spec.org/cpu2000/results/res2003q3/cpu
The c++ benchmarks (177.mesa,179.art,183.equake,188.ammp) were compiled with ICC (1) and gcc (2).
At two out of those four benchmarks (50%), GCC 3.3 is FASTER than the best Intel Compiler.
At least for Opteron (and Athlon) GCC is really good. Opteron with GCC and PGI Fortran compiler is excellent suited for High-Performance-Computing.
A big Thanks to the SuSE team for porting GCC to AMD64 and doing some usefull optimizations. http://www.x86-64.org/contributors/gcc
they're doing the OSS community some good by flicking SCO off their suit like an annoying little fly.
ibm does not offer its xlc compiler for intel chips -- that's simply wrong in the story, sorry for that!
From the GCC home page :
Major decisions about GCC are made by the steering committee, guided by the mission statement.
The mission statement (below) suggests that the main aim of GCC is to attract developers in order to forward the aims of the FSF. Thus choosing use or develop GCC is an overtly political act promoting the agenda of a lobby group.
Portability, well, multiple architectures is mentioned in the overture but not in the Design and Development Goals.
http://www.gnu.org/software/gcc/gccmission.html
The GCC development effort uses an open development environment and supports many other platforms in order to foster a world-class optimizing compiler, to attract a larger team of developers, to ensure that GCC and the GNU system work on multiple architectures and diverse environments, and to more thoroughly test and extend the features of GCC.
Free Software Project
* Supporting the goals of the GNU project, as defined by the FSF.
* Compilers are available under the terms of the GPL.
* Copyrights for the compilers are to be held by the FSF.
* Other components (runtime libraries, testsuites, etc) will be available under various free licenses with copyrights being held by individual authors or the FSF.
* All legal relationships with contributors and users are the responsibility of the FSF.
* Patches must be legally acceptable for inclusion into the GNU project.
Design and Development Goals.
* New languages
* New optimizations
* New targets
* Improved runtime libraries
* Faster debug cycle
* Various other infrastructure improvements
There are places where the networks are not touching,and there are places where they are-Boeing's Lori Gunter
Is it just me, or is testing an optimized compiler on processors it isn't optimized for a little silly? It's the Intel compiler. It's not going to take advantage of things like 3dnow that the AMD chips use.
And the muscular cyborg German dudes dance with sexy French Canadians
...to get the Opteron to run OS X? One or two-hundred bucks?
;)
I'll have to look into that
We apologise for the fault in this post. Those responsible have been sacked. -- Signed RICHARD M. NIXON
I remember some Apple fans praising Apple for, more or less, "inventing USB 2.0".
They weren't happy either when I mentioned Intel invented it.
However, Apple does a better job at integrating technology and, periodically, pushes the envelope much further than the PC companies. The interconnects on the G5 are amazing.
MOST is, MOST isn't good enough though, and not ALL of the kernel can be portable, and some parts can't and maintain any semblence of performance.
> Is it just me, or is testing an optimized compiler on
> processors it isn't optimized for a little silly?
No, it's not. That compiler is (in many cases) the best compiler for Opteron. The Intel Compiler is able to optimize for P3-like CPUs and Athlon and Opteron CPUs have many P3 characteristics.
> It's the Intel compiler.
Yes, it is Intel's compiler. But an Opteron with this Intel compiler is faster than an comparable Intel CPU. That's what matters for High Performance Computing.
> It's not going to take advantage of things like 3dnow that the AMD chips use.
It's going to take advantage of things like SSE and SSE2 that the AMD Chip uses. 3Dnow has no real advantage over SSE/SSE2 even on an Opteron.
But if you want, search www.spec.org for some P4 gcc Spec numers and compare them with ICC numbers. ICC is faster, no question, but even there GCC manages to achieve some comparable results. At some sub-benchmarks it is even faster.
They wanted to keep it fully x87 compatible. They had other options they addedd that had vector code in them. that's what's truly amazing. Without using any new instruciton it gained that speed increase.
The G5 could also run Linux
Sorry, but all of those fans require software to run them... software built into OS X. Porting Linux to a G5 is not going to be easy.... unless you want to build your own cooling system.
There are 10 types of people in this world, those who can count in binary and those who can't.
According to the readme:
/opt/ibmcmp/vac/6.0/samples/macide.pdf
This beta includes files that can help you integrate the IBM compiler with
the Project Builder and Xcode integrated development environments (IDEs).
For more information, see:
"Leave the strategizing to those of us with planet-sized brains." -Tycho
>> You assign to IBM all right, title, and interest (including ownership of copyright) in any data, suggestions, and
>> written materials that 1) is related to Your use of the Program and 2) You provide to IBM.
>Doesn't that mean that they can demand that you transfer the copyrights of code that you compile with it?
What it says is, if
1) You provide data, suggestions, and/or written materials to IBM, and,
2) They are related to your use of the program, then
3) They become the property of IBM.
So if you send IBM a note saying 'This compiler would be MUCH better with a green splash screen,' and then they implement it with a green splash screen, you can't then sue them for stealing your idea.
-Fred
Sign #11 of Slashdot overdose: You see the phrase 'moderate Republican' and you wonder if that would be a +1 or a -1.
I've admitted that Apple hasn't held the speed record. But yet you seem unwilling to believe/accept that they may hold it now.
Are you a troll or do you actually possess the world's worst reading comprehension? I've granted that Apple might win since my first freaking post. Do you have selective reading issues or something?
-Looking for a job as a materials chemist or multivariat
The beta comes with instructions to integrate with both XCode and Project Builder. Just check in: /opt/ibmcmp/vac/6.0/samples/macide.pdf