Mac Performance: From the G3 to the Xeon
Since we released Geekbench 2006 on July 10th, we’ve received over 4800 Geekbench results; over half of those results are from computers running Mac OS X. I took a look at the results, and found that we’ve received results for almost every computer model Apple’s shipped in the past six years, from the iMac G3 to the Mac Pro.
Since we love us some benchmarks here at Geek Patrol, I thought it’d be interesting to put together an overview of Mac performance over the past six years.
To make things easier, I’ve split the models into four categories: Pro Desktops, Pro Laptops, Consumer Desktops, and Consumer Laptops. I’ve then calculated and graphed the minimum overall score, average overall score, and maximum overall score for each model in each category.
There are a number of models I’ve not been able to include (like the PowerBook G3, the original 17-inch PowerBook G4, and the Xserves) due to a lack of results; any model included in this comparison has at least three results in our result browser.
Pro Desktop
What’s remarkable is that despite all the hubub about Apple failing to ship a Power Mac G5 with a 3GHz processor, Power Mac G5 performance has increased steadily (especially when compared to the Power Mac G4) with each new model.
The Mac Pro didn’t bring a huge performance jump over the Power Mac G5 (unlike like the jump in performance from the Power Mac G4 to the Power Mac G5), but the switch to Intel should ensure the Mac Pro keeps getting faster and faster with each new model.
Pro Laptop
Pro Laptop performance has been virtually stable (or stagnant, if you prefer) since the introduction of the aluminum PowerBooks, which shows just how out-dated the PowerPC G4 was then and now. Now with the switch to Intel, Macs are once again competitive when it comes to laptop performance; performance almost tripled with the switch from the PowerPC G4 to the Intel Core Duo.
Consumer Desktop
iMac performance (unlike PowerBook performace) has increased with each new model. The iMac has had four different processors, and performance has jumped each time the iMac has switched processors. The most impressive switch was the switch from the PowerPC G4 to the PowerPC G5, where performace almost doubled. The switch from the PowerPC G5 to the Intel Core Duo also seems impressive, but a large part of the performace gain came not from switvching architectures, but from switching from a single-core to a dual-core CPU.
Mac mini performance increased more dramatically with the switch to Intel chips, since previous Mac mini models used the G4, not the G5. Now, the Mac mini is an small and elegant machine with lots of performace, especially with the Core Duo as its CPU.
eMac performace, while somewhat lacklustre, did improve with each new model. The eMac is no longer available, though, having been replaced by the educational iMac.
Consumer Laptop
Like the Mac mini, iBook performance jumped dramatically with the switch from the PowerPC G4 to the Intel Core Duo; performance almost tripled (the switch from the PowerPC G3 to the PowerPC G4 was less impressive). MacBook performace is so impressive it’s possible that MacBook sales are cannibalizing MacBook Pro sales.
Final Thoughts
What struck me when looking at the graphs was how much the PowerPC G4 held back the Mac in terms of performance. Even though the G4 was introduced in 1999, Apple was still shipping computers that used the G4 until May 2006, almost seven years later.
Now, with the switch to Intel, Apple won’t be in a similar situation again (or if they are, they’ll be in it with the rest of the industry).
Trackbacks & Pingbacks
- The real problem at Levels of Detail pingbacked Posted August 31, 2006, 2:34 pm
- Chaotic Zee » Blog Archive » links for 2006-08-31 pingbacked Posted August 31, 2006, 5:21 pm
- Trevor’s Bike Shed » Blog Archive » My new computer: smokin’ fast pingbacked Posted October 11, 2006, 12:27 am
The great irony of the contest between Apple and Microsoft is this:
Microsoft is a software company that for almost 7 years could not squeeze out a substantially new operating system, Window XP.
Apple is a hardware company that for almost 7 years could not squeeze out a substantial improvement to their mainline processor, PowerPC G4.
Had either company not “stagnated”, they likely would have buried the other.
Very interesting! Hopefully now with the Intel chips we will never be in a similar situation as we were with the G4s. It’s amazing to see MacBook performance as I’m a last revision iBook user… perhaps i’ll swap
FYI, the PPC G4 was NOT Apple’s product, it was Motorola–Motorola (now Freescale) is the company that stagnated. Apple is a software AND hardware company, but NOT a processor company.
(And the G4 wasn’t Apple’s mainline processor anyway, that was IBM’s G5–which also stangnated, though not as badly as Motorola. IBM is more interested in game chips.)
The thing is, Intel stagnated too. The Pentium 4 was a bad design from the start, driven by marketers and not engineers. Only brute force and massive heat/power consumption kept driving speeds up–and not as far as Intel planned, either. The Pentium 4 would have been a terrible choice for Apple.
But Intel ended their stagnation on the laptop front (Pentium M) around the same time that Motorola stagnated badly with the laptop chip (G4) Apple relied on. And now, with Core and Core 2, Intel has ended their desktop (Pentium 4) stagnation and gone in a great new direction. Apple, happily, is on board!
It took some guts (and hours and cash!) for Apple to develop TWO versions of their OS, PPC and Intel, in secret for years–ever since the first OS X version. But it was a safety net that paid off brilliantly, allowing them to make a big CPU leap that would otherwise have been all but impossible without such foresight.
Great comparison! Very interesting to see. Now I can see on what kind of performance levels with my older Macs and which step will probably the next ; )
great graphs; BUT- the names are completely blurred out when enlarging in Preview to “see” the blasted things. Can you fix by better graph sizing & repost?
Am vision impaired due to glacouma.
THANK YOU…
Very interesing. I’m looking forward to my next upgrade!
What I have found interesting over the years is the perception of performance. I have been running a Powerbook G4 for almost 4 years. From your chart, it barely registers at the bottom. But I have been pretty happy with the performance when compared to the PC laptops I have from work.
While the hardware has been slower, the OS has been more consistent and performance has improved with each OS upgrade. On the PC’s, I still wait on Outlook to “phone home” peroiodically even on a high-speed Pentium-M class processor. The Windows “quirks” create an inconsistent level of performance and when compared to the Mac, seems slower to me.
Maryn said:
http://www.freescale.com/webapp/sps/site/homepage.jsp?nodeId=0162468rH3bTdG7249
Doesn’t look very stagnant to me, even before that there have been various other Freescale processors than were better than what Apple were using at the time. It’s not Freescales fault if Apple don’t use their products.
Apple also had the choice of going to one or two startups who were planning on fabricating Power based processors if Freescale weren’t up to much. (in fact they were in discussion with one of them).
Before anybody starts beating the Intel drum… I don’t think these tests show the weakness in the PowerPC arch (or rather, the PowerPC industry). But rather Apples inability to harness it. Which is probably why they moved to Intel, less work.
Just my opinion.
“Can you fix by better graph sizing & repost?
Am vision impaired due to glacouma.”
Get yourself a programable mouse, like the Logitech Laser MX, download their Mac software “Logitech Control Center” from their website and install.
Next program one of the mouse buttons to do a “command option 8″ to turn on/off “zoom”, first use “command option - or =” to set the zoom level.
See System Preferences “Universal Access” for zoom controls.
Now when you click your mouse button you can zoom in and out with ease.
What’s interesting is why the 15″ PowerBook edges out the 17″ PowerBook (G4) almost all the time in speed. I thought they were the same speeds all those times?
I guess I love my 15″ PB just that much better now. Seems to move along. Just think what the MacBook Pros will be like in a couple years!
I tend to try & wait for an order of magnitude performance change- that way the new box really blows me away. I just got the Macbook to replace our 300mhtz iBook- what a stunner leap that was!
I’ll try to get another 2 years out of our MDD 867, which is actually pretty snappy for our needs- I think they’ll be about 10X faster then. . . Although by the looks of the graph, maybe that’l happen this coming spring. If you can get 6 or 7 years out of a machine, it kind of justifies the extra cost of the pro box over the consumer models.
“Doesn’t look very stagnant to me, even before that there have been various other Freescale processors than were better than what Apple were using at the time. It’s not Freescales fault if Apple don’t use their products.”
Those other freescale processors can’t meet the needs of apple. As it was apple had a hard time with getting enough processors for their computer demand. Yes, there are 2ghz G4 chips, but not enough are manufactured which is why you only see them in G4 upgrades. Also who would you go with…a new powerpc start up company or intel who has an amazing roadmap? I praise apple for having the balls to change to intel….the G4 is too old and the G5 is waaaaaaay too hot.
Are the units comparable between graphs?
Ken,
Yes, the units are comparable between graphs.
“Doesn’t look very stagnant to me, even before that there have been various other Freescale processors than were better than what Apple were using at the time. It’s not Freescales fault if Apple don’t use their products.”
It’s Freescale’s fault if they can’t make enough of the CPUs, and if they don’t improve them enough, fast enough, to keep up with Intel.
Apple was not Freescale’s big customer. Most of their chips are sold for embedded electronics, in things like routers and automobiles. These applications have requirements very, very different from desktop PCs. And they don’t advance at the same pace as desktop PCs.
I don’t see why Apple would bother going with unproven startups. Maybe they have a chip that looks good today, but that may be all they have. They may hit a wall very quickly, as has happened before to startups promising faster PPC chips.
Another risk is that these startups may not be able to reliably produce chips in sufficient quantities. Even a comparable giant like AMD might have trouble providing enough CPUs for Apple.
The advantage of going with Intel is that Apple won’t be Intel’s only desktop computer customer. It won’t just be Apple asking Intel for faster CPUs, it’ll be all the myriad PC makers, as well as Microsoft. Freescale and IBM probably thought they could safely string Apple along while failing to deliver on promised performance, because (they thought) Apple needed them more than they needed Apple.
To be completely informative, this should have the dates of the releases as well. Plot the performance on one axis, time on the other; the product will have its name on the bar.
That would really tell us how things developed. As it stands, this distorts and doesn’t show where there was a lack of progress. For example the G4 Powerbook languished for ages. But that’s not obvious from the graphs - or at least not as obvious as it should be.
Shouldn’t be hard to find a site that’ll do this. You could then even plot different products in different colours - four or five should do it.
In many cases, the performance leap in the new Core Duos is the fact that there are two chips instead of one, and that these tow chips are able to offload work on one another, giving an additional speed boost.
The G4 is indeed an fossil in terms of age and architecture, however, it is not as obsolete as it seems.
Real world example. I am running off a Powerbook G4, 1.5GHz. I recently bought my girlfriend a Intel Mini, Core Solo, 1.5GHz.
All in all, same clock, and the Mini has a larger L2 cache and FSB.
In some tests, the Core Solo outdid the G4 by quite a margin, (i.e Cinebench) however, I decided to try some video encoding (which I do a lot of) using quicktime pro, as it is allegedly optimised and running native on both machines.
The results surprised me to say the least.
In 5 tests that I ran, ranging from convert to iPod, to specific codec setups, the Powerbook won 3 of the 5 speedtests! All in all, after average all the times out, the Powerbook came out on top, only by 5%, which is not much, but it surprised me as I expected much better performance from a much newer architecture.
In an interesting side note, when I used CHUD tools to shut down a processor on my friends Dual G5, the single processor was significantly slower in Cinebench than when 2 processors are active, but Cinebench is only rendering in single processor mode.
I am by no means a genius when it comes to processor architectures and the like, however, it seems the G4 still has some uses, and I believe a lot of the significant speed increases that the new Core Duos have are because they are dual processors, use newer system architecture and faster memory and hard disks (SATA vs IDE, not the RPM speed, but the data transfer speed)
In any case, after those tests, my Powerbook G4 does not look as slow as some tests may suggest.