Slashdot Mirror
New G5 Power Macs "Fastest Desktop In The World"
Beyond the many numbers, the bottom line is that the new machines have a new architecture, and that the memory speed is now the bottleneck, not the processor or bandwidth speeds. So they can have up to 8GB of 128-bit DDR RAM, as it is efficient to keep data in memory. The memory bandwidth is one of the most talked-about features of the new architecture.
USB 2.0 is now included, as are FireWire 400 and 800, Bluetooth, AirPort Extreme, and digital audio in and out. The 4x SuperDrive is now standard, and it can house up to 500GB of internal storage.
For video, the GeForce FX5200 is standard on low-end models, Radeon 9600 Pro on high-end models.
The case of the new machines is redesigned too, from the ground up, focusing on decreasing noise and heat. It is an aluminum enclosure, with ports for FireWire and USB on the front, and a door on the side to get into the box. It has four distinct "thermal zones" with computer-controlled cooling with its nine (yes, nine) independent fans. And it is much quieter than its predecessor.
The G5 is 10 percent slower than the P4 and Xeon in SPEC int scores in single-proc units, but 20 percent faster in FPU scores, and the dual-proc G5 beats the dual-proc Xeon in all SPEC scores.
The models are a single 1.6 GHz ($1999), single 1.8GHz ($2399), and dual 2GHz ($2999). They will ship in August. A 3GHz processor will be available from IBM in 12 months.
Apple notes that recompiling apps for the 64-bit architecture is easy, and in some cases can be done in minutes.
There was no word about the heavily anticipated redesign of the 15" PowerBooks.
The difference in policy regarding announcements of future advances may be a result of the processors being made by IBM now. I think it is an IBM announcement more than an Apple one.
Karma: Can there be a void?
.. -. - . .-. .-. --- -...
As amazed as I would like to be by these claims I can't help but be a little aprehensive. Could Apple really have closed the over one year gap Intel has (or had) in technology? Going from Pentium 3 speeds to speeds surpassing the latest from Intel & AMD? I'm not going to swallow that claim until I see some independent benchmarks.
I think AMD tried to say the same too. AMD's site also claimed they were the fastest 64 bit processor even though Alpha is _still_ ahead and Itanium was still marginally ahead of Opteron. Nevermind the fact that you couldn't have bought the Opteron at the time they claimed that.
In fairness, I think they might claim that the Alpha and other processors were put in "workstations" not necessarily desktop class.
Not server, not workstation... desktop processor. First 64-bit for Joe and Jane Sixpack with some money.
"In God we trust, all others must bring data" - W. Edwards Deming
Doesn't that make some people want to wait for the extra year?
I suppose some people might wait, but don't underestimate the pent up demand for a high performance Mac. Apple's customers have already been waiting a looooong time for this machine. I don't think announcing that there will be a speed bump in a year will do much to the short term sales of the new boxes. Maybe in six months people will start holding off for the promised 3GHz boxes, but not now.
*ahem*
This geek has been waiting 'til he can buy a apple or apple clone motherboard down at the local computer shop, plus CPU. 'til then, there's very little chance I'll try out the mac platform.
The G5 is 10 percent slower than the P4 and Xeon in SPEC int scores in single-proc units, but 20 percent faster in FPU scores, and the dual-proc G5 beats the dual-proc Xeon in all SPEC scores.
Which Xeon? The 2 Ghz Xeon?
'Course the SPEC benchmarks arn't everything and this is just a very limited test, but damn, those G5 scores ain't nothing special. It's both slower and faster, it almost balances out. And on top of that, you know the regular 'ol Xeon is commonly available at 3+ Ghz. That's still hella faster than the Mac any way you look at it. Not to mention if you had two of them.
I do have to give Apple credit for getting the prices down. Still, a Dual 3 Ghz Xeon machine is cheaper and much faster.
Of course I'm ignoring the nice Apple designs and workable functionality (even if OS X has craploads of overhead and slowness).
The ratio of people to cake is too big
The new G5 machines, with the IBM 970 processor, use the "world's first 64-bit desktop processor" (and the "fastest 64-bit processor ever")
Wow, I'm sure people who had Alpha workstations back in the day will be surprised. Even the n64 had a 64 bit processor, the MIPS r4300. The chip was $35 dollars in bulk in 1996. Iâ(TM)m pretty sure this chip has been used in PDAs in the past few years.
The only reason that they havenâ(TM)t been used in desktops so far is that A) There is a huge legacy base to support and B) The speed increase isn't even that great. I mean, you don't need more then 32 bit ints for the vast majority of the calculations you need to do on a PC (whereas on a 16 bit computer, you need to use several instructions to calculate 'both halves' of the number anytime you needed to do math with numbers larger then 64k.). And anyway, all of the major CPUs available today have instructions that deal with huge amounts of data for floating point and SIMD multimedia stuff.
I'm suppressed apple isn't claming that their machines do 'twice as much work' because they have twice as many bits. This subversion of technical facts for marketing purposes is something apple is constantly guilty of, and it's really annoying. Because you know you're going to have some idiot mac zealot come back at you with something like "yeah, well this is the first 64-bit desktop EVAR" Just like how they claimed the g4 was the first "Desktop supercomputer" or something like that, because it met some obsolete government export restrictions, the same restrictions that the playstation two had surpassed months before.
autopr0n is like, down and stuff.
I think the keyword is "desktop" as opposed to "workstation".
I'm not saying I don't want to pay you guys when you upgrade the OS. You guys put a lot of features in every release, and your staff deserves to get paid for it. Panther looks pretty damn cool, for the most part. Just do me a favor. Reward me, even with a paltry amount, for being a customer who likes to keep his OS up-to-date.
Knock $40 off the price and call it a $89 upgrade fee. Hell, even $30, and $99, would be somewhat palatable. That's really not that much to ask, considering the discounts one can find elsewhere on the OS after a few months.
It's a bit more palatable than the pure psychological 'F--K YOU' of making me buy the operating system over and over and over again with every new release.
Longhorn users may be waiting until 2005 for their next release, but I doubt they'll have spent $460 or $690 by that point on keeping their OS up to date.
Sincerely,
Quite Unpleased Customer Who's About to Get His Ass Handed to Him By Fellow Mac Loyalists for Even Daring to Question the Wielder of the Reality Distortion Field
P.S. To all those who decide to flame instead of intelligently reply ... please use a flame more creative than
"whiner." Obliged.
For several years, Apple has lagged in the megahertz race. Motorola's G4 processors have only slowly improved in performance, while Intel and Advanced Micro Devices crank out ever-faster chips at a much swifter clip. Megahertz isn't everything when it comes to performance, but increasing the clock speed generally does boost chip and computer performance.
Yeah the writer eventually says megahertz isn't everything, but fails to grasp that megahertz isn't anything. The only scale that matters is how much work the system can do. Megahertz doesn't even have to enter into the discussion.
Btw, for the record, I'm a PC owner/user who probably won't switch, but still thinks these new Macs, along with the AMD Opteron chips, are the best news to come along in a good long while for all of us!
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Worse, even apple.slashdot.org is (almost) Slashdotted.
Never have I seen any of the Slashdot servers crawl as slowly as this one is now.
Oh yeah, and they can also run Mac OSX, OS9, and 64-bit UNIX scientific, math, and engineering applications at blazing speed and with unprecedented ease of use. So what's a Sun box good for again?
I'm no Sun evangelist (as a matter of fact, I hate their products lately), but let's at least stop displaying our abject ignorance. What's a Sun box good for? How about naming me a high-end manufacturing/engineering design package that runs on OS X first, then we can talk about what a Sun box is good for.
- A.P.
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
IIRC, Apple has contributed a lot to the PPC compiler backend in GCC. Wouldn't that make it a "special compiler" wrt Apple's chips?
GCC does not contain code that recognizes and special-cases certain SPEC fragments, e.g. by inserting hand-written machine code, as some vendor compilers do. Of course, Apple had plenty of opportunity to tune the PPC backend (maybe they did, to me Apple is mostly known for front-end work such as precompiled headers, which are generally useful), but they can't push code into GCC on the grounds of "it makes us look good on SPEC, but there's no other purpose".
Maybe, but it's nice to know. And besides, we all know that processors will be twice as fast in 18 months. But that doesn't stop you from buying a PC.
"Sometimes a woman is a kind of religion, she can save your soul & set you free from all your sins" - Bad Examples
Out of interest, how much is it for the 106-CPU version of the Mac, again?
For the workstation market, it doesn't matter very much.
I have been a Sun fan for some time, now, but I see the dual PowerPC 970 Mac and dual Opteron workstations coming down the line and wonder. These, feature-for-feature, make Sun Blade, IBM RS-6000, SGI Fuel, etc., much harder sells.
The G5 is gorgeous and powerful (like a Bond girl). The Opteron will be white-box and powerful (like the neighborhood geek-girl:). There's probably something for everyone, here. For completeness, I suppose Windows on Itanium would be like some sort of beast woman who still gets guys, because she is easy (blecch).
Sun and Apple are targeting completely different markets.
This was very true three years ago. However, what would happen if PTC released Pro/E for OS X? It's really a matter of the applications. Not only that, but I would bet getting Motif on OS X isn't too hard (suddenly lots of UNIX applications on OS X becomes plausible).
The workstation is going through serious evolution, right now. 64-bits is no longer the domain of the "big guys." The next two years will be very interesting.
Healthcare article at Kuro5hin
That's what Sun used to think about Intel. I'm not saying that Apple is going after Sun's market right now, but Sun's smug attitude hasn't hindered Intel's quest to bury them in the server market.
If you're on top of the market and you assume that nobody has plans to unseat you, sooner or later you'll get a rude wake up call to reality.
Read the EFF's Fair Use FAQ
If you don't care about your time or the quality of the software you use, you should stick with windows.
It's as easy as that.
There is a very important reason for announcing a 3Ghz processor for next year...
The G4 used to be very impressive compared to PCs of the time - but it's been around for far too long, with limited speed bumps...
Announcing a 3Ghz model is letting people know that there is a roadmap in place for ramping up the performance...
People want to know that there is a future... with many Mac owners and quite a few potential 'switchers' staying away from the dual G4s as they are past their sell by date, announcing a roadmap for G5 development - and not just new machines themselves - may well see an increase in current Mac sales...
First off, your English unfortunately is working against your making a point. I think you meant to say that Macs cost 30% more than PCs, which is simply ignorant to state. Second, you are dead wrong on price/performace. I work in a lab doing bioinformatic analysis of the bovine genome. The OLD G4 Xserves gets twice the performance per dollar as any linux-based workstations, built in-house or otherwise. In many ways they are faster to use for our jobs than shared-memory supercomputers to which we have access. Third, I also compose music, do some game development (including some 3D graphics work), and have done so on Macs and PCs. Even on an older Mac, I am far more productive, but back to the point: Configure a somewhat equivalent Dell and compare the price to a G5. Not only is the price competitive, the performance is superior with the Mac. Your attempted point on bang-for-buck is outright false. In any case, no one has suggested you buy a Mac in the first place, so why are you so defensive?
Um, 8GB of RAM?
PCI-X expansion?
Quiet?
I mean, name a PC where you can get more quiet for less money?
Or more PCI-X for less money?
Or more RAM expansion for less money?
Are those not all 'bang for the buck' metrics?
Or do you only count watts of heat generated as 'bang'?
You can re-arrange your original question this way:
Is the 30% price difference worth the lack of RAM capacity, PCI-X, extra noise, extra heat, dual 900MHz FSB, Firewire 800, BlueTooth, etc. You talk about value; value is not *only* raw HP, or you'd be buying and driving big rig trucks (500HP engines), and if you only valued HP/$, you'd be driving some really *ugly* and low *quality* cars.
Try it, all the really high HP/$ cars cheap, low quality vehicles. Producers know that if you add quality, people will buy more. It's nearly the definition of quality, in a way.
GPL Deconstructed
You cannot just take an enterprise machine and replace it with a desktop, because eventually the desktop will fail, usually unexpectedly and usually at the worst possible time.
Desktop PC's are meant to go on DESKTOPS, where if they fail, the most you've lost is a few man-hours of work. Enterprise machines go in server rooms where if they fail you might have just lost a few million in sales, and pissed off your customer base.
Jherico
What can the average user can do to ensure his security? "Nothing, you're screwed"
I want a reliable system, which more complexity always works against.
You're apparantly not familiar with the concept of "redundancy."
Of course, I'd be concerned about the replacement plan for these fans. When the warrant goes up in X years, how much will it be to replace a suddenly dead fan?
You know, I think that's one of the most ignorant comments I've heard on Slashdot-- and that's saying something!
I certainly don't consider myself braindead and I love using my Mac. I think the user interface of OS X is leaps and bounds beyond that of Windows or any of the latest Linux desktops.
I also know of plenty of very intelligent people who use Macs simply because they are easier to use and it allows them to focus on the task at hand. Not everyone takes the slop they're fed and feels that it's "good enough" (which is basically what you are saying). Some of us actually don't mind paying a little bit extra-- if even there is any extra to be paid. $3,000 for a dual 2GHz 64-bit machine is pretty damn low IMHO.
Of course, my guess is your needs are different than mine. My needs dictate that I have a fast and easy to use UNIX system. The cheapest computer meeting those needs is a PowerMac.
Perhaps instead you are interested in playing the latest whiz-bang gaming title-- in that case you want a Pee Cee.
i'm sorry, but where are you finding this dual P4 system? IIRC, P4s are single only - you need a Xeon for that.
go configure that dell with dual 3ghz xeons, which the g5 beats. you'll find it to be $3,934.
http://kered.org
The machine is fast and the OS is advanced. But what irks me to no end is that Apple seems hell-bent on keeping the Mac in its little niche market. It doesn't make much sense but Apple refused to capitalize on people's migration from traditional Unix to the more "user friendly" NT. As an example I'll use the situation I am most familiar with but keep in mind this sort of thing is probably similar across dozens of industries. Computer hardware and electronics design. The most popular tools today are probably those from Cadence and Synopsys. Both have powerful software suits available for 32-bit and 64-bit versions Solaris, Linux, HP-UX, and NT(32)/XP. For some reason people started migrating from Unix to NT. So now I'm stuck using design and verification tools on 2000. When I use Mentor Graphics ModelSim and Cadence's Layout and PSpice I have to install all this extra stuff like Cygwin, and Perl just to try to imitate the functionality avaialable in Unix. I'm sure many other people do this. Plus, these third party tools are so poorly integrated into the rest of the OS.
With Mac OS X, it's all there. The complete Unix toolset and environment comes standard, the Macs are good for graphics as it is (which is what all these new design tools focus on anyway), and the UI is a dream to use. It's simply a better platform in a lot of different ways. Check out Sun and SGI's third party applications pages, then look at Apples. There are whole industries missing.
Here's where Apple needs to come in and sell these people on their product. Users want better software, software companies want a larger use base and better product and Apple wants to ship more units. Why is this not being done?
The funny thing is that in-house ASIC design at Apple is probably done on Solairs, HP, or NT. I'm sending e-mail Cadence and gang. Everyone who doesn't want to see this whole industry to be swallowed by NT and wants to move to OS X should do the same.
> However, the most interesting part is that they
> used GCC to compile the SPEC suite,
Interesting, indeed. I wonder how they get
publishable SPECfp_rate numbers with GCC, as the
GNU Compiler Collection doesn't contain a
Fortran 90 compiler.
Toon Moene (current GNU Fortran maintainer).
oooooohhhhh
64-bit... wow!
Like, you can... ummm... support more than 2gb without swapping?
hrmmn...
like... you can support signed ints greater than 2.1 billion without some trickery?
ummmmm... that's about it.
64-bit != faster (necessarily). In fact, it could concievably be slower because of all the extra data that you are passing back and forth...
Step away from the pulpit... Whether the 970 ends up being faster in practice is yet to be seen. Whether OSX can take advantage of horsepower is a different question. We're talking about too many unknowns just yet.
Apple used GCC 3.3 to run the SPECmarks on the Intel processors too, so the results are indeed valid.
A comparison between ICC on the Intel and GCC on the G5 is interesting to determine how fast your code might run out-of-the-box on a P4 vs G5 but ultimately flawed for comparing CPU performance.
The new Apple PC is far more than just a PC. It is a workstation in its own right and outperforms the workstations built by Sun. The new Apple PC is both (much) faster and (much) cheaper than a Sun workstation.
Just look at the specs of the new Apple PC. 1.6 GHz and only $1999. It also does UNIX and Linux. Steve Jobs lucked out -- again. There will a surge of demand for this machine from engineers, moving beyond the traditional Apple core users (i. e. educational institutions, graphic artists, etc.). Apple will supplant both Sun and HP as the new workstation company of Silicon Valley.
By the way, the bell tolls. It tolls ominously for Sun.
Yeah, but did you buy it at compusa?
Why should I pay for something that is 10%-25% faster when it costs 30% as much as a PC? I care about value over absolute top performance.
:)
:) When I sit down at the computer, there's something I want to do, be it analytical or creative, and the last thing I want to think about is why some stupid driver won't load or why a program I need to run won't start because I installed something new.
I see lots of posts around here in the form of "Feature X of my PC is Y% {better,faster,shinier} than on the Mac, so why should I pay the Z% premium?", and rarely do I see good answers. It is a very hard thing to explain. But I will give it a shot. What follows is my (totally subjective) rant about why I prefer Macs:
I've used both Mac and PC (meaning Wintel) systems regularly and equally for almost twenty years now. I used to build PCs and sell them for extra cash years ago, and I've used every Mac from the 512K to the latest G4.
I have to use PCs at my job every day (I am a software engineer). But whenever I buy a system for myself, I always, ALWAYS, buy a Mac.
Why?
It's really hard to convey to someone else, because it's not based on anything specific or concrete but on years of experience using the two systems. There aren't a lot of specific details that I can give you that explain why I always go with the Mac. But after twenty years of using PCs and Macs, I can tell you this: Macs feel good to use in a way that PCs do not. I know this sounds silly, but it really is true. It's not that the operating system or the hardware have specific features that contribute to that effect. Instead, it's almost the opposite: when I'm doing something on my Mac, the operating system and the hardware never enter my mind. They are transparent and I can focus on the work, instead of the tool. There's something about the incredibly tight integration of the hardware with the OS that make it a joy to use, primarily because it never gets in my way.
Well, there's also the fact that everything I want to do with a computer I can do on my Mac. If that weren't true, it would be moot, of course.
Believe me, I understand how cheap and easy it is to build a PC from scratch, or how cheap it seems to just upgrade the one part of a PC that is lacking. But I also understand how frustrating it is to try and get everything to work together flawlessly. Personally, I have neither the time nor the inclination to deal with problems with the system itself. I get to do that all day at work.
The cost issue is irrelevant. As others have pointed out elsewhere, it evens out over time. I bought my current Mac almost 4 years ago, and it will last another year until I get a new one. I have friends who have sunk thousands of dollars into upgrades to their PC in the same amount of time. Certainly as much as I've spent on my system, including the minimal upgrades I've had to make (RAM and video card - total of $200). And I've been saving my pennies and next year I'll buy a new Mac with them, I'm sure.
For me, it just works, and that's all I need to know. The value of that is priceless. If what you have at the moment works for you, then by all means, stick with it. But if you're less interested in the machine than what you can do with it - and I mean creatively, not customizing the UI and such - try out a Mac. You may find it useful. Give it a few months, and if it works out, great. If not, sell it on eBay - they hold their value rather well.
Finally, yes, I've used XP (really, I should say I use XP) and it is indeed an improvement over previous versions of Windows, but I still don't like using it. And again, there's nothing terribly specific to complain about. Instead it is a death of a thousand cuts, and after extended bouts with XP, I tend to get rather irritable. It seems, for lack of a better term, condescending. It seems to treat me as if I am not of sufficient intelligence to be using a compuer, but out of some noblesse oblige it will allow me to do a
Free yourself. Everything else will follow.
Software can always be ported to meet the demand. I would be pretty scared right now if I were sun, honestly. If people realize that an apple could be used for the same sorts of purposes as those extremely expensive sun boxes, they may just be tempted to switch. Does that mean it's guaranteed to happen? definitely not, but the mere fact that it's getting more feasable should be enough to at least freak out sun.
Here's the deal: if you want to know how one computer compares to another, you have to use the same compiler.
not true at all. See below.
I mean, you just have to. Otherwise the test is meaningless. You can only test for one variable at a time if you want to get results that mean something.
Say you have compiler A which rocks for architecture A and sucks hard for architecture B. You run SPEC with this compiler, and A wins.
The next day you have compiler B which rocks for architecture B and sucks hard for architecture A. You run SPEC, and B wins.
How are these results meaningful? They say absolutely nothing about the two architectures independent of the compiler used. If you used completely different compiler brands for each architecture, you'd end up with the same thing: Results that are dependent on the compilers used.
The fact of the matter is, cross-architecture comparisons suck no matter what you do. GCC 3.3 for IA32 and GCC 3.3 for the G5 need to be treated as completely different compilers in any valid testing methodology. It doesn't matter that they have the same name and version number -- if they're compiling for different architectures, they're doing things differently. using "the same compiler" to try to feign fairness is simply a sneaky marketing trick.
So what is one to do? Well it depends on the result you want:
-- if you always use GCC 3.3 to compile your high speed apps and want to know which CPU GCC 3.3 works best for, then apple's (Veritest's) results are perfect for you. However, those results really say more about how good GCC is at optimizing for the separate architectures, rather than anything about the merits of the architectures themselves.
-- trying to compare the merits of the architectures themselves is the tricky part. Generally, modern processors need their code to be very well optimized to fully exploit the power of the processor. Therefore, a fair comparison would be between The Best Compiler for Architecture A vs The Best Compiler for Architecture B. This is the only way to even come close to comparing "What architecture A can do" vs "What architecture B can do". And this is what most people want out of a benchmark.
(Of course one has to make sure that the compilers used aren't cheating on the spec benchmarks to give huge results. This is where the base vs peak distinction is important.)
Finally, on a somewhat related note, if the speed of specific applications is most important to you, then of course you'd be looking at application benchmarks and not SPEC.
The following sentence is true. The preceding sentence was false.
That's not a desktop that's a workstation, and hardly commonplace. When was the last time you ran down to Walmart and picked up a DEC Alpha or SGI?
mo
Those results are interesting, but not incompatible with the results Apple used today. The closest results from that page compare a 3000 MHz P4 with a 1700 MHz Power4. 1200MHz Power4 != 1700MHz PowerPC 970. It still looks like the Power4 beats the Pentium4 Xeon on floating point, and the 1700MHz Power4 doesn't show up in all the tests on that page. When the page is updated to include official results from the PowerPC 970 (which the results Apple used seem to be) then I'll bite.
Comparing ICC on Intel to GCC on IBM is *not* a valid test of CPU capability
Neither is GCC on Intel vs GCC on IBM. That was his main point and you didn't address that.
In fact, the only valid test of CPU capability is to optimize the algorithm for the particular processor by hand
This is true. And using the best compiler available for each architecture (ICC for Intel for example) comes much closer to achieving hand-coded efficiency than simply using one compiler across the board, which may suck for particular architectures (GCC for Intel for example).
The following sentence is true. The preceding sentence was false.
I've always wanted the unmatched visual interface of Linux and the functionality of Gimp!
(as you can tell, I am being sarcastic). Linux is good for some things. Professional desktop publishing, graphics, motion video and 3d aren't them.
On the other hand, you could claim that Apple chose GCC on the Intel platforms to make them look bad in this comparison...
I don't expect much out of the Apple marketing department. These are the same people that claimed that a G4 was a supercomputer.
It's obvious that gcc was chosen to make x86 CPUs look bad. Gcc sucks compared to the Intel compiler for x86. Even AMD uses the Intel compiler to report SPEC scores. The discrepancy is huge. The Intel compiler has global whole program optimization as well as a ton of other features that gcc won't have for years.
IBM could have given Apple a decent compiler with these types of optimization features, but then the performance would look bad against Intel.
Even with this huge gcc-handicap, the 3GHz P4 still beats out the 2GHz machine by more than 10% on specint (889 vs. 800) - and by the way, did you notice that you can now buy 3.2GHz machines for less than the G5 machine which won't be available until August?
Then there's the bogus specrate comparison of 2 processor systems. Why didn't they turn on hyperthreading? Could it be that the dual Xeons would then stomp the dual G5s?
Sure the P4 is higher frequency, but it computes the answer faster than the G5, and that's all that should matter if you care about absolute performance.
Athlons are faster too.
So are Opeterons.
Athlon64 will no doubt be faster as well.
Now there is something to be said for Macs. They have a superior OS and wonderful apps and will give Microsoft some good competition, but to claim the "fastest desktop computer" crown is pure bullshit.
Actually, if you look at the benchmarks, the GCC scores are actually pretty close (for the FP benchmarks). Where the Intel side really fails is with the Fortran compiler, which is generally considered to be a pretty good Fortran compiler.
Given that if you are comparing Linux vs. OS X, the vast majority of your code will have been compiled with gcc, and the number of man years spent optimizing gcc's x86 performance, I think this is actually a pretty fair benchmark.
sigs are a waste of space
yeah you're right... but the problem is that now we have both: speed and a quality OS.
so now, i guess the only reason to buy windows is tradition.
Am I going crazy, or are all three systems using the same CPU?
Given that BusSpeed * ClockMultiplier = Processor Speed
Apple's three configurations:
1.6 Ghz - 800 Mhz bus
1.8 Ghz - 900 Mhz bus
2.0 Ghz - 1000 Mhz bus
Means that all three systems have the same multiplier on the chip. Which strongly implies to me that they're all the exact same chip. We'll have to wait and see how easy they are to overclock, but if you could just change the 800Mhz bus system to 1Ghz bus, you'd save yourself $1000 in the process.
Win XP 64-bit Edition is NOT a desktop OS, although MS claims otherwise. It's designed for Itanium which is a server CPU, and the chip alone costs over $3000 - more than the Dual 2 GHz G5 PowerMac.
But you (being a person that would assemble an entire system from stratch) would not pay Apple's prices for upgrades. You would order the base system with the minimum RAM, no DVD burner(?) and lowest capacity drive.
You would then simply visit pricewatch and purchase all your upgrades at street price, and you'd sell the FX5200 on eBay.
And the Mac still has lots of stuff that your self created system doesn't. Granted, much of it won't do much for your gaming experience. (gigabit ethernet, optical audio ports, PCI-X, FW800, 64bit system).
This is always going to be true: You can assemble a generic Wintel computer from commodity parts with fewer features than Apple's base machine, and spend less money of it.
This will always also be true: The Apple system will come with more hardware, software and design elegance than your generic machine. This value may be meaningless to you, but it is sill there.
If I loosely interpolate the performace of the dual CPU duel in the keynote down to the single processors we're talking about, the Mac in question would still be about 1.2 to 1.5 times as fast as the machine you would assemble.
Article X: The powers not delegated... by the Constitution...are reserved...to the people
I see the anouncement of the G5s as good because it should mean that a lot of G4 towers will hit eBay at a resonable (i.e. low) price. Unfortunately the UK Apple store says that they are not shipping until august :(
I am TheRaven on Soylent News
No other company can pull off so many cool things so quickly like Apple, not MS, not Sun, not HP, not even IBM, and certainly not Dell the box maker.
You have to watch Steve in QuickTime to fully appreciate how many amazing things Apple has done. Panther Developer Preview has already left Longhorn (Windows 2005) firmly in the dust bin: the new user-centric Finder, search-as-you-type, Expose, fast user switch, iChat AV, FileVault, Xcode, FontBook, and so on.
The PowerMac G5 is just amazing, 2 GHz 64-bit CPU with 2 independent FPUs and Velocity Engine, 1 GHz FSB, PCI-X, Serial ATA Drive, FireWire 800 & 400, USB2, Bluetooth, 802.11g, etc.
In terms of SPEC2000 floating point performance, the 2 GHz G4 is 21% faster than the 3.06 GHz P4, and the dual 2 GHz G5 PowerMac is 41% faster than a dual 3 GHz Xeon Dell which cost $1000 more. In real world tests (PhotoShop, Mathematica, 3D rendering, music), the PowerMac is more than 200% faster than the Dell.
It's clear that Apple has all the vital pieces nailed - harware, OS, applications, developers, Apple Retail Stores, iTune Music Store, iPod. It's time to buy some more Apple shares.
Small details in light of the mighty new G5... but I haven't seen any new accompanying mouse or keyboard with the new G5. Anyone else??
At specbench.org, I see for the P4, using Intel's compiler
specint_base2000: 1164
specfp_base2000: 1200
And if you ask IBM for their spec marks for the 970 they'll trot out much higher numbers as well:
specint_base: 937
specfp_base: 1050
Note: These are IBMs conservative specs at announcement @ 1.8
At 2.0GHz they should be closer to:
specint_base: ~1040
specfp_base: ~1170
*Gasp* Imagine my shock and awe! These work out to almost exactly what Apple said! *Gasp*
Admittedly, this just proves that gcc sucks, but that's all you get from Apple. Nothing has changed, Intel is still winning and Apple is still lying about it.
No, what it means is - on an level playing field Apple did very well and you seem to be having some problem with that. Apple could have just tweaked the 970 machines to get numbers just like the Intel one's quoted here, but instead chose to have an trusted third party run exactly equal tests. Intel's rigged results and IBM's rigged results work out almost exactly to Apple's unrigged results. The scale changes but the relationship doesn't.
Even if you think that Apple rigged the test - what about all the real world applications they ran during the keynote?
Real world app after app after app running more than 2x faster than the dual 3.06 Xenon box? Oh, Apple probably rigged those too.
And all this while the Xenon box was more expensive. Oh Apple rigging again. (Let me guess Dell's in on it?)
Intel's "still winning"? Because Intel's rigged spec is faster than the gcc results of a single processor 970? So I guess that dual P4 box that will kick the dual 970s ass is where?
=tkk
Bill Gates - Creationist?!?
But anyone paying a shred of attention to the computer industry for any frame of time over the past fifty years or so would know that computers always get both faster and cheaper. The market knows that whether or not the megalomaniacal CEO spells it out for the paying conference audience or not.
The capabilities of the machines announced today are such a significant jump over what was available until now that pointing out that further improvements are on the horizon should hardly be that damaging to the sales spike that Apple must be hoping for. The people that would be scared off by a 1 year forecast are not only the ones that wouldn't have bought a new Mac until the until-now-mythical G5 came out, they're the ones that wouldn't have bought a new Mac until that G5 computer put the equivalent of a Cray monster on your desk -- i.e. the ones willing to wait a long, long time, and so really can't count as customers.
For everyone else, this can't have been much of a shocker...
DO NOT LEAVE IT IS NOT REAL
Only on slashdot do I get moderated "Troll" for talking abou the technical sutff (hypertransport, the 1Ghz front side buss, etc)
But an guy who can only call me names and expresses his ignorance of MPEG4 (MPEG4 Video is a Video codec standard. MPEG4 includes many such standards) gets modded up "insightful"
I mean, you don't even know the difference between a 64 bit CPU and a 32 bit CPU, but here's a clue: the pentium is a 32 bit CPU.
When they start shipping itaniums in PCs, then you can talk. (And no, we all knwo you are lying when you say you can get an 8 way pentium desktop.... but then the difference between SMP and clustering is too technical for this forum, isn't it?)
Slashdot is a waste of time-- there are no engineers here.
Yeah, and you guys panned the ipod too: http://apple.slashdot.org/article.pl?sid=01/10/23
When's the last time you ran down to Wal-Mart and purchased a Mac? It's been a while hasn't it?
There's a HP rx2600 Itanium2 desktop machine upstairs. It's running Linux and GNOME, looks very nice, is damn fast and reasonably quiet and would make a studly Linux machine for somebody who needed a large VM space.
Obviously Apple are using a "words mean what I want them to mean" definition of "64-bit desktop". To me, it means "something small and quiet enough to put on a desk, and designed to be used from the console by a single user", and the rx2600 qualifies. There's no single line between workstation and pc anymore.
This is the machine that I have been waiting for (and have been putting off upgrading my G4/450).
:), but having that many slots allows you to upgrade at your desired rate. ie: you are less likely to have to pull out chips to make room for new ones. My G4's slots are all full right now, so if I wanted to add RAM, I'd have to ditch one chip.
Still, there are a few things I would like to have seen different, that I think are a step back from my Sawtooth:
1) Only one outward-facing drive. My Sawtooth can only have one optical and one 3.5" (A now-nearly-useless Zip drive for me), but the last generation of G4s had those dual optical drive bays. Given how cheap standard IDE CR burners etc are, it would be great to have that upgradeability option. In my quest to convert my friends, this has been a sticking point for many of them (most have at least two optical drives). Externals work, yes, but are much more expensive, and take up much more space.
2) Two hard drive bays. Even my Sawtooth has room for four internal hard drives. Again, IDE hard drives are cheap (Serial ATA not as much, but still....) and not everyone wants to pay a $100 premium for an external firewire box, just to do a drive upgrade. In many cases, that doubles the price of the bare drive. There are PC cases out there (ugly ones, natch) which give six front-facing bays and as many hard-drive bays.
3) The G4s were notoriously easy to access. The one side just flipped down and BAM! there was your whole motherboard. While the side of the G5 may be easy to remove, you still have to cram your hands into that tiny space to reach anything. Having everything fold out was a great innovation that I'm sad to see go.
4) The handles look OK in my opinion but are fairly thin metal. I can't imagine these things not hurting your hands if you're carrying a G5 around. I know you don't move a tower case that much, but if you're going to bother putting on handles, at least put on comfy ones.
5) As others have said, it would be nice to see a 128MB graphics card in the high end. But that's a minor quibble, really.
6) No reset button on the front. I know OS X crashes quite rarely, but sometimes this thing comes in handy. And it's a lot easier and more intuitive than holding the power button.
That said, I think these are fabulous machines, and will do Apple proud. Aside from the obvious blazing speed, a few other touches I liked:
1) front-mounted USB & firewire. Finally!
2) Optical digital audio ports. Also finally! Crossing my fingers that this means there's a 5.1-enabled DVD player app en route.
3) I think the cooling system is a stroke of genius. Nine fans sounds like a lot, but it gives much more custom air circulation patterns.
4) Eight RAM slots! I will likely never need 8 gigs of RAM (at least not before the Power Mac G7 in 2008
All my whining aside, this is a great machine! Now if only I had some money...
"Reality is merely an illusion, albeit a very persistent one " -Albert Einstein