NASA recently benchmarked Apple’s dual 2GHz Power Mac G5 at its Langley Research Center in Virginia. The main purpose of the tests was to compare the G5 to the G4 for “computational fluid dynamics applications” however they also compare it to the Pentium 4.The test was well documented and concludes that “the G5 has about 22% better scalar floating point performance per clock cycle than the G4 systems tested and 32% better floating point performance per clock cycle than the P4 systems tested.”
IBM intends to use the PowerPC 970 (termed the “G5” by Apple) with its AIX operating system in workstation units soon, and Apple plans to begin shipping the Power Mac G5 with MacOS X 10.3 this fall.
Apple released today a 94-page PDF document detailing on the G5 architecture.
More about the G5 and an analysis can be found at DigitMagazine, while The Age has an article titled “Massive Mac“.
Insanely Great Mac informs us that the final release of Panther definitely won’t support beige G3 or earlier PowerMacs, nor will it support PowerBook G3s that lack built-in USB ports.
JH:”I don’t know about you, but 5177 MFLOPS compared to 288 MFLOPS is a extraordinary huge performance difference to me.”
Did you read this part of the article:
“Note that the higher level of optimization (-O2) and SSE/SSE2 options in the Portland compiler degraded Jet3D performance on the P4 system, and were therefore not used.“
Either NASA is reaaaaaly stuuuupid or if SSE2 degrades vector performance someone should take the entire intel engineering team and shoot them in the back of the head.
Sagres: the test didn’t say SSE2 degrades vector performance, it said that code created using the Portland compiler with SSE/SSE2 option on produced worse results than non-vector code. Presumably, coding for SSE/SSE2 is not trivial and since the compiler flags failed to automatically produce better code, the NASA researcher didn’t bother testing it.
Someone on Slashdot posted a message from Craig Hunter from January which explains the work he did in writing the vector version of Jet3D for the G4 (not the G5 tested in this latest report).
The info I’ve heard thrown around seems to agree that the hand-tuned SSE/SSE2 optimizations will give you a 3-4X boost, whereas the NASA guy is saying 10-13X is typical for the G4/G5.
I say bring on more real world test, and we’ll see more and more how the G5s really smoke the competition.
Date: Mon, 13 Jan 2003 23:29:38 -0500
From: Craig Hunter
Subject: G4 vs. P4 performance
I have been following the discussion of Rob Galbraith’s benchmarks with much interest, as I have spent a good deal of time testing, optimizing, and benchmarking software for the G4 (OS X) and P4 (Linux).
The first thing to realize is that there are numerous benchmarks that show the P4 is faster, and there are numerous benchmarks that show the G4 is faster. What matters? Well, probably the benchmarks that apply to the kind of work you do. For people doing photo processing with the software Rob tested, his results are extremely relevant. But, someone working with a program optimized for AltiVec and dual processors might have a completely opposite experience.
Just to give an example of a benchmark that goes the other way, see this chart.
(You’re welcome to mirror this benchmark image, since my web site may not handle a lot of traffic). These real-world results come from the Jet3D computational fluid dynamics noise prediction software, which I developed for my doctoral thesis and currently use in my work at NASA. Jet3D is written in a combination of FORTRAN 77, FORTRAN 90, and C, and is optimized for AltiVec and dual processors on G4 hardware. When compiled on Linux using Intel’s ifc compiler tools, Jet3D also becomes optimized for the P4 (using the various SIMD extensions available on the P4).
As you can see, the G4 does quite well here. A dual processor 1.25GHz G4 system is more than 3.5X faster than a single processor 2GHz P4 system. Though it’s not shown on the chart, a single 1.25GHz G4 processor benchmarks at about 1589 MFLOPS, 1.9X faster than the P4. If you look at MFLOPS per MHz for a single processor, the G4 comes in at 1.27 MFLOPS/MHz, while the P4 comes in at 0.42 MFLOPS/MHz. If you want a good example of the MHz myth, look at the Cray, which comes in at 1.78 MFLOPS/MHz with only a 500MHz processor, beating both the G4 and P4.
Without AltiVec, the Jet3D benchmark would be about 794 MFLOPS on the dual-1.25GHz G4, which erases the performance lead over the P4. And then, using only a single processor, the 1.25GHz G4 benchmarks at about 418 MFLOPS, which is about half as fast as the P4. And all of a sudden, the G4 doesn’t look very compelling. For the Jet3D benchmark, AltiVec and dual processors are key (AltiVec more so than dual procs). This is true for most benchmarks I have looked at; thus numerically intensive applications that can’t use AltiVec and/or dual processors are likely to suffer on the G4.
In the case of Jet3D, it was easy to optimize for AltiVec. I was able to hand-vectorize about 10 lines of code within the guts of the FORTRAN algorithm and convert the computations to C for easy access to AltiVec hardware instructions. It had a huge effect for not a lot of work. For other more complicated cases, it may be possible to use the VAST compiler tools to automatically vectorize and tie in with AltiVec (VAST has parallel tools also). But in some cases, vectorization is not possible or feasible. In those instances, you’re stuck with the processor’s scalar performance, and the P4 generally has better scalar performance than the G4 in my experience. One final note: these are my personal views, and do not represent the views of NASA Langley Research Center, NASA, or the United States Government, nor do they constitute an endorsement by NASA Langley Research Center, NASA, or the United States Government
Evrybody said before the G5 came out that Apple has slow expensive hardware. Cool, I agree…why not? Now a cool CPU (the G5) came out and it powers their machines. Mega-Cool, only that most of the trolls wont accept that. Intel always had more Mhz than the competition. Who cares? They where not the first to overcome the 1 Ghz barrier, AMD was with its K7. Mhz is not everything. The G5 is a powerfull 64 bit CPU, and I’m sure that Apple’s software will take advantage of it. Intels architecture goes way way back…itys still x86, don’t tell me IA32 is not x86. G5 is cool, and at the end of the year I’m gonna get a Dual G5 from Apple.
To Anonymous, the platform is nice, I’ve toyed with one in the last couple of days. It was a dual G4. Apple is cool.
Why the hell did they use an old version of the Portland Group compiler when is very well known that Intel optimizing F90 compiler is almost unbeateble and further more freely available for Research institutions??
Typically this is because the build environment for the program has been designed around that particular compiler toolchain. This is happening more and more frequently. I experience it on a daily basis trying to build software designed around the GNU toolchain on my sparcv9 systems with Forte 7.
Our mesoscale atmospheric modelling program, RAMS (soon to be released under the GPL) is designed to use pgf90 on x86.
I have tried to move the build environment to Intel f90 on x86, but unfortunately the model produces different numbers with Intel’s compiler versus the Portland Group compiler.
So, there are numerous technical reasons which could be responsible.
The SPEC benchmarks made it look like it was only slightly faster bet every real world test showed that it was WAY faster. It only confirms what I’ve been saying all along, “SPEC BENCHMARKS ARE NOT A TRUE GAUGE FOR SPEED.
Real world tests of selected applications that mostly are traditionally have been Mac applications as oppose to Windows applications (e.g. Photoshop was not built primarily on Windows, rather Macintoshes). And the configuration of the SPEC benchmarks used isn’t fair, if Apple used Windows and ICC on the PC – which is heavily promoted by both Intel and Windows, as oppose to GCC (which Apple promotes) on Linux, the benchmark would be more in favour of Wintel.
And in addition to the fact that gulf of difference between PCs and Macs in Apple’s own benchmark is far smaller than back then between G4s and P4s before G5 was released – yet Macheads back then would like us to believe the difference is barely noticible.
Besides, if you see my point, I’m saying that PCs will catch up. Why?
IBM have far less incentive to spend as much effort and money on 970 as Intel and AMD. Why? How many 970s they can sell anyway? Certainly far less than Intel with Pentiums. And IBM’s business isn’t dependant on 970s.
Comparing the speed at which x86 was able to close the gap is not a fair comparison. Apple announced the G4 but could ship for (if I remember correctly) 4-6 months! That had NOTHING to do with the scalability of the G4 but had EVERYTHING with the INABILITY of Motorola to ship and ramp up.
What about G3? Same problem then. The problem is that neither IBM nor Motorola have any incentive to follow Moore’s law.
make no mistake, this situation will not be another Motorola-like induced catastrophe. The ramp up room for these chips is HUGE.
And why is that? With about the same prices as G4s when it was first released in relative to PCs, with what can you say G5s be much more better in relative to PCs then G4s in the same sales benchmark? You can’t. And most likely, it won’t. In other words, I see no reason why G5s would be more successful than G4s.
Besides, G4s scalability was very high too back then. Where is it now?
What makes you think the situation would be completely different this time? Unless you know some internal business plan I (and the rest of us) don’t know, you are just deluding yourself.
That argument assumes that price it the only way to compete.
Sorry fact, heh? From Apple’s sales record in relative to other PC makers, it doesn’t seem consumers are all that crazy for other variables.
No need for a miracle. The roadmap for these chips is so strong it should have no problem keeping a significant leap ahead of x86.
The roadmap of G4s was also great. Did Motorola kept to it? G3’s roadmap wasn’t too shabby either. Did IBM kept to it?
But buying a Mac does NOT cost a whole lot of money. Rather, it costs either a little more, is at the same price, is slightly less, or significantly less when you match both computer’s hardware and software inclusions as close as possibe.
Good thing you mentioned software (although in a different sense altogether). I’m a PC user. I have Office with Access and Frontpage, Photoshop, PageMaker, and Illustrator. My brother uses a couple of sound editing programs I don’t use. Now buying a Mac means buying new licenses for all this before making the Mac useful – which means Office, Photoshop, PageMaker, Illustrator, File Maker Pro (Access altenative) and Dreamweaver (to replace Frontpage). But buying a PC, I can transfer the licenses to the new PC while slowly replacing them on my old machine. Or if I like going against the law, I can make copies of those software on my new PC. Or if I’m even more nasty, I can shop around for pirated good over here (something you can’t do for Macs.
Which is more expensive now?
That comment assumes that the Mac equivilent is not a better solution as is often the case.
The fact is that PC have more niche software than the Mac, especially when it comes to business applications. And in many cases, there is no Mac equivilent.
And what does Paint Shop Pro offer me that I couldn’t get elsewhere on the Mac?
From the time I used Paint Shop Pro years ago, I can say it is easier to use than Photoshop and have a few features (I find useless) that till today can’t be found properly implemented on Photoshop.
It is like comparing PageMaker and QuarkXpress – neither are comparable. Both does roughly the same thing, but both aren’t after the same market.
And what does WordPerfect Office offer me that I couldn;t get elsewhere on the Mac?
How the hell would I know? All I know is that my lawyer uncle would rather eat faeces than move to Office. It does have features than Office doesn’t have, but since I never used them, I have no idea what it does. But as the second biggest word processor in the market (in terms of market share, of course), it is hardly one you ignore.
You do have a point there. While there ARE alternative CAD software solutions on the Mac, AutoCAD has them all beat.
Precisely. I’m going into AutoCAD for product design (hehe, pirated version, couldn’t afford the original just of yet), while now my feature requirements can be filled by just about any market player, but I doubt it is for long.
I simply cannot justify the price difference between a new G5 and and equivalent x86 system which despite some people saying otherwise is Huge for me as I build my own systems for Much much less than I could buy an Apple. I will never do those things the G5 seems to excel at. I use my PC to play games and surf the web mostly with some word processing, photo editing and video encoding. While if the benchmarks we have seen are true, I would probably be able to encode a little faster on the G5 I cannot even get most of the games I play on it and the G5 simply cannot compete Price/Performance wise in games which are very very rarely MP aware and will never use the specific optimisations which would make them run really well. Even my favorite game UT2003 which has been ported to the MAC is missing some features because it has to use OpenGL and is definatly slower than on my pc. Maybe if Apple can continue to be competitive with the PC for more than a few months and gain some market share then game developers will make ports for Mac available at the same time as the PC but even now you are more likely to get a port to Linux before OSX.
Hippocrates is the father of modern medicine is from Ancient Greece. He was the leader of a medical school of Cos andthe author (as well as co-author) of most of its books. He had a great impact on succeeding generations of practitioners of medicine and some general rules still apply. His work and writings rejected the superstition and magic of primitive “medicine” and laid the foundations of medicine as a branch of science. The Hippocrates oath is the oath taken by all medical doctors before practising.
Perhaps you meant hypocrite which means “a person who puts on a false appearance of virtue or religion”
“Without AltiVec, the Jet3D benchmark would be about 794 MFLOPS on the dual-1.25GHz G4,which erases the performance lead over the P4.And then, using only a single processor, the 1.25GHz G4 benchmarks at about 418 MFLOPS, which is about half as fast as the P4. And all of a sudden, the G4 doesn’t look very compelling. For the Jet3D benchmark, AltiVec and dual processors are key (AltiVec more so than dual procs). This is true for most benchmarks I have looked at; thus numerically intensive applications that can’t use AltiVec and/or dual processors are likely to suffer on the G4.”
Straight from the horses mouth – only dual processor Macs using Altivec optimised operations are faster than the P4 – in other situations the P4 is much faster. In other words most apps are slower on the Mac.
@rajan:
Thanks for the webster lesson :-). However, do you have an opinion on the rest of my post, the title non-withstanding?
If I largely disagree, I would say something right? 🙂
How many 2 GHz PPC 970 chips does it take to “beat” a P4 3 GHz? Just one on most FPU apps with vectorization. How man CPUs? Two. A single PPC 970 chip has 2 CPU cores inside of it.
Accuracy? Depending on the calculations required, a 64 bit data pipe could be more desireable on really big or really small fractions than 32 bit data paths. About half the number of calculations to a 64 bit “word” as opposed to running a 64 bit word in 2 pieces through a 32 bit CPU.
Power consumption? A PPC 970 chip only uses 10 watts of power. A P4 uses over 10 times that amount and generates copious amounts of heat. Multiply that by your cluster size and you would end up with either a very big cooling bill for a P4 cluster, or a quite a bit smaller one for a PPC 970 cluster. Long time Intel and AMD users (I’m one) joke that you don’t need a heater in the room if you have your P4 or Athlon running SETI@home.
How about price? Xeon 3.0 Ghz systems cost about as much as the prices Apple is quoting for the G5 when it appears. IBM systems with PPC 970, I’ve yet to see a price on.
Software support? Lot’s of software for the Pentium class CPUs, but how many are actually taking advantage of the advanced features in the P4? Not as many as you’d think. When you code software for the platform at hand, instead of buying off the shelf, then this is a moot point. Most R&D software suites are coded and optimized as much as possible for the target platform. The average consumer (business or personal) is generally the only ones buying off-the-shelf.
How fast would it take for off-the-shelf to catch up? You will see PPC 970 optimized software packages as soon as Apple (and IBM?) start shipping to the mass market. That’s simply the way the software market works.
Will I personally buy a PPC 970? Only if I can find a good system that I can afford. Which will be very unlikely. It’s a shame that the average computer user can’t afford good equipment. :/ (And before you say that an IA32 system is good, try learning about all the patched up architectural nonsense that goes into the current IA32 that has kept the platform “modern” and still backwards compatible. It’s a nightmare compared to most other systems.)
“How many 2 GHz PPC 970 chips does it take to “beat” a P4 3 GHz? Just one on most FPU apps with vectorization. How man CPUs? Two.”
The test was completed with one processor turned off.
Here are some interesting numbers:
Program use 1024 KB of memory — that’s unusally low.
G5 data cache:
hw.l1dcachesize = 32 KB
hw.l2cachesize = 512 KB
G4 cache:
hw.l1dcachesize = 32 KB
hw.l2cachesize = 256 KB
hw.l3cachesize = 2048 KB
P4:
cache size: 512 KB
It looks like the G4 should walk all over these other processors- the whole dataset fits in cache. One really interesting thing about the dual G5 is that each processor can access data in the other’s cache… Since the 2nd processor was still installed, I wonder if its cache was still operating! If so, then this might boost the G5’s cache to roughly the size of the data set.
I don’t think it’s fair to compare the system performance of the Mac with one of its processors off to the P4. The highest end Mac has two processors for a reason.
“No!” you cry. “That’s not a fair comparison! The P4 only has one processor, so to make the benchmark equal, we have to make sure the systems are on equal footing!”
Well, too bad. It’s a system limitation that Intel put in. If I buy a TOP END system, I want to see top end performance. The fact that the P4 was so (badly) designed isn’t my problem, or Apple’s. Their top end machine spanks ANY P4 system you can put to the test because they decided that a good way to make the system faster would be to make sure it supported dual processors.
Now, if you’re stricly comparing PPC970s to P4s, and you want strict PROCESSOR benchmarks, then fine, just test the processor. However, even results like this benefit from the architecture of the system. A fast, data starved processor is useless.
I’m uninterested in raw CPU results. I can’t do anything with JUST a CPU on my desk. I need a whole system.
This is the highest performing, lowest cost Dell that anyone posted to this discussion:
Dell Dimension 8300: (same as XPS except not blue)
3.2GHz Pentium 4
200GB Ultra ATA – 7200rpm
DVD+RW/DVD+R/CD-RW
512MB DDR400 SDRAM
Microsoft® Windows® XP Professional
Wordperfect
ATI Radeon 9800 pro
No Monitor
$2239
This is the base 2GHz Apple. So, the cheapest, highest performing Apple.
$2,999.00
Dual 2GHz PowerPC G5
1GHz frontside bus
512K L2 cache/processor
512MB DDR400 128-bit SDRAM
Expandable to 8GB SDRAM
160GB Serial ATA
SuperDrive
Three PCI-X Slots
ATI Radeon 9600 Pro
64MB DDR video memory
56K internal modem
And that doesn’t list the computer controlled cooling or expensive case, the fact that the Apple is quiet, the gigabit ethernet, the optical digital audio and analogue audio in and out, or any of the engineering that went into making all of those things fit together. For only $700 more, you get an extra processor, superior performance, and an operating system that’s actually worth using.
Remember, you get what you pay for…even with Apple. Dell puts togher fine PCs, and they’re certainly cheaper. However, (for the first time in a while) the Mac is BETTER.
price cimparison between similarly configured high-end single-processor systems:
Apple PowerMac G5:
1.8GHz PowerPC G5
250GB Serial ATA – 7200rpm
SuperDrive (DVD-R/CD-RW)
512MB DDR400 SDRAM (PC3200)
Mac OS X
AppleWorks
ATI Radeon 9800 Pro
56k V.92 internal modem
No Monitor
$2874
Dell Dimension XPS:
3.2GHz Pentium 4
200GB Ultra ATA – 7200rpm
DVD+RW/DVD+R/CD-RW
512MB DDR400 SDRAM
Microsoft® Windows® XP Professional w/ Microsoft® Plus!
Microsoft® Works Suite 2003
ATI Radeon 9800 pro
No Monitor
$3062
Apple is selling the faster system for a lesser price than a similarly configured Dell (and yet this doesn’t even factor in bundled software!)
G5s and other chips that can do SMP achieve that capability through a trade-off. The Intel developers who did the P4 accepted the other side of the bargain, better single chip performance in exchange for not being able to dual chip. That’s a valid design choice but don’t expect a similarly priced single CPU system to be chosen over a better performing dual CPU setup merely because ‘chip for chip’ the single chip is better. The dual system will be better overall and will get bought.
Pardon me, though, if I believe Intel’s docs over your assertion that P4 speeds are rising rapidly. They’re supposed to get a .2Ghz in the next six months and another .2Ghz speed bump the six months after. That’s a .4Ghz bump in a year. IBM says they’ll do 2.5x that and bump a full 1Ghz in the next 12 months. You have to come to the conclusion that IBM is lying and overstating their progress or Intel is lying and understating it to maintain your position.
I’ll believe Intel at their word because they’ve been generaly good about hitting their roadmap targets and not going ahead or behind them but IBM’s progress statements have been a bit off on the PPC 970. They promised us a 1.8Ghz chip at this time and delivered a 2Ghz chip. At that rate, in 12 months we’re not going to get 3.6Ghz P4 v 3.0Ghz PPC970 but 3.6Ghz P4 v. 3.3Ghz PPC970. What a calamity… for Intel.
As for 10.3, I’m pretty comfortable with 10.2 right now and am likely to stick. If I didn’t need 10.2 for one application I desired, I would have stuck with 10.1 and hopped to 10.3. You know, my corporate Windows clients do the exact same thing, upgrading every other MS OS upgrade cycle. Apple chose an early release strategy and those of us who wanted to go along for the ride paid the $ price for it. But a lot of mac users are still on OS 8-9 and haven’t jumped into the OS X pool. I expect that the G5 introduction with G4s becoming very cheap will lead a lot of people to come into the 10.3 cycle and they’ll upgrade again around 10.5 or 10.6. It’s the nature of the beast. As long as they can run their apps, they’re happy and OS X is getting to the point where you don’t have to get every upgrade to have a very good computing experience right where you are.
But what’s keeping MS from shipping *its* next OS? They’ve been on a new OS every two years cycle since forever. Now they’re taking longer. If Apple’s to be criticized for innovating too frequently (wow, what a slam) isn’t MS vulnerable to the opposite charge, leaving its users stuck in the mud? You can’t get their new technologies at any price. They’re all being saved up for Longhorn.
Microsoft Windows XP Pro: Full price: $299
Microsoft Windows XP Pro Upgrapde: $199
http://shop.microsoft.com/Referral/Productinfo.asp ?siteID=10798
MacOS X 10.3/2/1 Full price: $129
http://www.apple.com/macosx/
Microsoft Windows XP Pro (5 Users): $1315.60
MacOS X 10.3/2/1 (5 Users): $199
If you bought Windows XP ($299), and then can upgrapde to Longhorn for $199, you paid $498. If you bought MacOS X 10.1, 10.2, 10.3, and 10.4, you paid $516. Pretty similar, and that’s assuming you only have to pay $199 for Longhorn. In the meantime, Apple users enjoy continued advance, while Windows stagnates for 4+ years.
Do the same with a family licence of 5. Buy Windows XP for $1315.60, then upgrade for $875.60: $2191.20 (over 4 years, for 5 people: $109.56/user/year).
Buy MacOS 10.1, 10.2, 10.3, 10.4 (5 User Licence): $796 (over 4 years, for 5 people: $39.80/user/year).
Using http://shopper.cnet.com I found a copy of Windows XP Pro for $207, and an upgrade for Windows XP Pro for $177. I found a copy of MacOS X 10.2 for $98.
If these prices hold over to the newer Operating Systems these companies release, then Windows would cost $384 (23% savings), and MacOS X would cost $196 (24% savings). If you bought every point upgrade Apple released it would cost $392.
How is a dual Athlon going to “trounce” a G5 when the 970’s beat a dual Xeon, which will trounce a dual Athalon?
Hmmm… I think this is a bit more fair comparison:
Dell Dimension 8300:
Pentium 4 3.2GHz w 800MHz FSB
512MB Dual Channel DDR400 RAM
ATI Radeon 9800 Pro w 128MB RAM
200GB Ultra100 7200RPM HDD
16X DVD-ROM
4x DVD+RW/+R Drive w/CD-RW
56K PCI Data/Fax Modem
XP Home
WordPerfect Productivity Pack
15″ LCD (free with system)
Total: $2,587
Apple PowerMac G5:
1.8GHz PowerPC G5
250GB Serial ATA – 7200rpm
SuperDrive (DVD-R/CD-RW)
512MB Dual Channel DDR400 RAM
Mac OS X
AppleWorks
ATI Radeon 9800 Pro
56k V.92 internal modem
No Monitor
Total: $2874
Then there’s this for Dell on the low end:
Dimension 2350
Pentium 4 2.2GHz
128MB DDR RAM
40GB HD
48x CD-ROM
48x CD-RW
56k Modem
Altec Lansing Speakers
XP Home
WordPerfect Productivity Pack
15″ LCD
Total: $498 (see slickdeals.net)
Athlon is clock per clock faster than P4…
What is the great buzz about that?
I remember to have used G3 when Mac people told me that G3 was 2 times faster then a Pentium III using the same clock. Then, I’ve compared MPW (in a G3 400MHz) with G77 (in a Celeron 300MHz(!)) and the permormance in all the tests I’ve made were similar.
Propaganda… It makes this world such a mess!
You realy can’t compare Dell vs. Apple. They are two vastly different system. Dell specializes in economy systems while Apple certainly does not.
Its like comparing Hyundai vs. Mercedes, of course you can get a pretty nice hyundai with all the features of an entry-level Mercedes for much much less, but the difference is in the quality, aesthetics, and target market.
As an owner of 2 Dells, a Dimension desktop and a Lattitude Laptop, which we refer to here as the “mistakes,” I can once again reaffirm that you get what you pay for. Dells are cheaper, and they are junk, I would never buy one again.
Bascule,
The two machines you compared aren’t even closely matched…
You realy can’t compare Dell vs. Apple. They are two vastly different system. Dell specializes in economy systems while Apple certainly does not.
“You realy can’t compare Dell vs. Apple. They are two vastly different system. Dell specializes in economy systems while Apple certainly does not.”
Sure you can compare the two. Dell sells economy systems as does Apple. Apple is sometimes slightly more, sometimes the same, sometimes slightly less, sometimes significantly less when the two companies hardware and software are compared the exact same or as close as possible. The comparison that Bascule made just wasn’t compared with equal hardware.
“I remember to have used G3 when Mac people told me that G3 was 2 times faster then a Pentium III using the same clock.”
At the time of their introduction that was correct.
price cimparison between similarly configured high-end single-processor systems:
Apple PowerMac G5:
1.8GHz PowerPC G5
250GB Serial ATA – 7200rpm
SuperDrive (DVD-R/CD-RW)
512MB DDR400 SDRAM (PC3200)
Mac OS X
AppleWorks
ATI Radeon 9800 Pro
56k V.92 internal modem
No Monitor
$2874
Dell Dimension XPS:
3.2GHz Pentium 4
200GB Ultra ATA – 7200rpm
DVD+RW/DVD+R/CD-RW
512MB DDR400 SDRAM
Microsoft® Windows® XP Professional w/ Microsoft® Plus!
Microsoft® Works Suite 2003
ATI Radeon 9800 pro
No Monitor
$3062
Apple is selling the faster system for a lesser price than a similarly configured Dell (and yet this doesn’t even factor in bundled software!)
Apple claims 15.7 for the Dual 2GHz G5, and the 3GHz P4 getting an 8.07. NASA gives the Dual 2GHz G5 498MFLOPS and the 2.66GHz P4 255MFLOPS.
If you use your math skills: 15.7 / 8.07 about equals 498 / 255. So therefore we can draw the conclusion that they have similar results.
Now, NASA only used a 2.66MHz P4 while Apple used a 3GHz P4. Although remember NASA’s figure that the P4 had 0.096 MFLOPS/MHz? Give the P4 333 more MHz, and you find it has about 286.968 MFLOPS. NASA also suggests a 20% performance increase can be expected with compilers that take advantage of the G5.
Although, even without this increase Apple’s benchmark and NASA’s benchmarks are very close. Which would lead one to draw the conclusion that Apple’s benchmarks were in fact valid.
And how is that a more fair comparison than the one I pasted?
Apple is not selling comparable systems cheaper than Dell is
“The thing that everyone else seems to have overlooked (the PC freeks or so concerned about loosing the pissing contest) is the fact that Nasa is looking at using G5s. That says a lot in my book.”
You clearly have not worked in a research government research facility. That decision says nothing. NASA also uses many other architectures. So there happens to be some people in NASA who want to use G5’s. There are also many people in NASA that want to use XEONs, Athlons, Itaniums, etc.
More importantly, the benchmarks didn’t look into clustering tests which is what most government research facilities are interested in. I think this whole NASA document is not as relevant as some Apple fans think.
Also, what give NASA? You can’t afford to buy a new Intel chip for your benchmarks?
And yes, this post was written from my 17 in. Powerbook which I believe is the best laptop in the world. I hope to see a G5 in the next Powerbook!!! Or maybe a G6
Perhaps the G5 is a bit faster, perhaps it’s the Intel or a comparable AMD. What really matters is that OSX is spiffy and I feel it would behoove the general population, ubergeek or not, to support alternatives to the Wintel juggernaut.
“The thing that everyone else seems to have overlooked (the PC freeks or so concerned about loosing the pissing contest) is the fact that Nasa is looking at using G5s. That says a lot in my book.”
This basically suggests that you misunderstand research institutions. Researchers are basically independent agents not employees. They usually have great discretion in purchasing decisions. In any large university you will see a wide array of architectures and OSes deepnding on individual preferences.
MFLOPS = (million floating point operations) / second
MHz = (million cycles) / second
MFLOPS / MHz = (million floating point operations) / (million cycles)
=> (floating point operations) / cycle
So this unit is deliberately chosen to disfavor the P4 since it measures only number of operations per cycle and and is not a measure of speed or how fast. To measure speed it has to be per second .
We all know that the P4 has more cycles per second than the G5, this benchmark is the other extreme of the MHz myth. More floating point operations per cycle does not mean much without considering the number of cycles per second.
A computer that does 10 ops per cycle, and 1 cycle in 10 seconds only does 1 op per second.
Another computer that does 1 op per cycle and does 10 cycles in 1 second, would do 10 ops per second.
Which is faster? I’m sure you don’t need a research institution to tell you that.
Nasa claims that you should compare them only on the ops/cycle metric. And some G5 zealots here tend to agree. What a disgrace to common sense.
“At the time of their introduction that was correct.”
How can this lead be eroded so fast???
I repeat: I’ve compared a 400MHz G3 with a 300MHz Celeron (should be slower than PIII) and there was practically no difference.
How can somebody justify a two-fold advantage if it turns to be a 25% disadvantage (to a lower end version of the processor that should be losing the match)?
It is another planet.
That’s why I don’t believe an inch about what Aple says when they make propaganda for their processors.
I live in Brazil, a country in which each coin you spend for the operations you need are measured because we simply do not have money to waste. We would love to have Macs really competing price/performance with Intel and AMD because we also would win in the process.
Now, in the real world…Try to guess the market share of Macs here. It is even less then in US or Europe… It is too expensive.