Slashdot Mirror
MacWorld's iMac Core Duo Benchmarks Debunked?
madgunde writes "Looks like MacWorld magazine was a little premature in reporting that the new Apple iMac Core Duo doesn't live up to Apple's speed claims. The folks over at MacSpeedZone have done some performance testing of their own that debunks MacWorld's results and shows that the new iMac Core Duo DOES live up to the hype. Not only did the new iMac wipe the floor with the old model in their tests, but using MacWorld's own test methodology would allow MacSpeedZone to conclude that the new Intel iMac is almost as fast as a PowerMac Quad G5. " I see only one way to solve this: Give me one. I'll run WoW on it, and decide.
That's the point of the article. The Macworld article never considered processor useage. They said the new Intel Mac is "10-20% faster" without considering whether their benchmarks used the full capacity of the processor. They claimed that Jobs' statement that the new Mac was "2x faster" was wrong because they got smaller speedups. What this article s howed is that if you used Macworld's methodology (showing benchmark results without showing processor usage) you could argue that the quad-core G5 is only 14% faster than the Intel iMac running Quicktime. They're not saying that such a conclusion is correct, they're using it as an example to show what conclusions you can arrive at if you use Macworld's logic.
The basic problem was that Macworld's benchmarks were not CPU benchmarks and didn't make full use of the second core in the Intel Mac. The '2x' number Apple said was for the CPU --- even SJ mentioned that it doesn't mean apps will be 2x faster since the disks and everything else are the same. This article shows that in cases where the benchmark is CPU bound, the new Intel Mac can be almost twice as fast.
A deep unwavering belief is a sure sign you're missing something...
He then doesn't see much of a performance increase when he uses it for whatever he does with it. Will he be satisfied by some Apple PR guy saying "But look! It's not using as much of the CPU as your old Mac! That means it's MUCH faster!"
The average Smoky McPotts Mac freak won't really care if it's using less of the CPU if it still takes as long to do the same stuff as before.
There's WAY too much flawed logic comparisons going on right now to make ANY sense of it. Benchmarks matter to a certain point, but what really matters is how long it takes to do stuff that you use it for. If it takes forever to do most of the tasks you want it to do, it doesn't matter what kind of benchmark scores it got by which review site.
Give me one. I'll run WoW on it, and decide.
One of my guildmates just got her one up and going last night, Running WoW under rosetta. It wasn't actually a comprehensive test, but here comment was "Wow I'm in orgrimar and not lagging". So I'm guessing at default settings it's OK.
Performance should improve when bliz relases 1.9.3 and she dosn't have to use rosetta anymore.
-Qyiet
I thought this was the best CPU technology?
It was. Then, Intel caught up.
-jcr
The only title of honor that a tyrant can grant is "Enemy of the State."
what i want to know - and what holds me back from moving to an iiMac from my DP g5 1.8 - is
In general there's no reason to do so, the iMac Core Duo should be roughly equivalent in speed to a dual G5 system right now. Having the cores on a single chip gives it a slight advantage but the power dissipation aside the G5 is a very efficient chip and matches up well with the new Intel offerings on a clock for clock basis.
The Intel iMacs are not a Power Mac replacement, and shouldn't be considered as such, they bring roughly Power Mac levels of performance to the iMac and Powerbook lines, but do not surpass it.
More specifically...
1. how they will perform when rendering with Compressor
Probably about the same or even in favor of the G5. Compressor's code is highly dependent on the SIMD (SSE or Altivec) unit and the G5's Altivec unit, or the G4's for that matter is generally considered a better SIMD implementation on a general purpose microprocessor than SSE.
2. how much faster is FCP when hooked up to similar disk packs (like cheap desktop FW400 raids)
Again there will probably be no significant difference between the two platforms, since a the Core Duo is roughly twice as fast as the G5 iMac, but so is a dual G5.
3. Will i still be able to run background processing tasks like Compressor and handbrake yet get good foreground performance so i can email, websurf and get on with life while waiting for those 30-1 hour long tasks, instead of walking away from the machine, lest i get tempted to use it and really slow down the renders.
Multitasking performance is as much a function of the operating system's scheduler as the hardware. Again you would see little difference between the two machines. The G5's ability to hold more memory actually gives it a higher level of potential performance when the memory is maxed out than the iMac.
4. Will Aperture stop sucking performance wise?
Short answer, no. Aperture's performance is largely a function of Core Image which depends on the graphics card and system bus moreso than the CPU.
In general if you need an immediate speed upgrade a quad core G5 with a lot of memory is what you should purchase, otherwise wait for the workstation class Intel machines (MacMac? Following the PowerBook -> MacBook convention)
You missed my point - perhaps I was too subtle.
I challenge your assertion: there are NOT a lot of apps that are cpu bound (or rather, the percentage of apps and users of those apps is a fraction of a fraction of the general population of users). I acknowledge that there are examples where CPU speed is king, but often, even these are limited by memory access and worse still disk access or even worse still network bandwidth... My point is that the legitimate examples of cpu-bound usage do not represent the mainstream usage of computers.
In the mainstream, most users click a button or hit a key and trigger some cpu event that completes long before they even recognize that it's done. Meanwhile, the cpu blazes away... waiting for the next request for a burst of useful activity. Real performance benefits come not from making the bursts faster and certainly not from making the waits faster, but rather from reducing the cycle time between the bursts. In other words, most users benefit more from smarter user interfaces than faster cpus.
Is there a market for faster cpus? Of course, just not the market that that is being pandered to by the standard benchmarks. If you have a cpu-bound application and your business depends on competitive performance, you're going to do your own benchmark and your performance assessment probably won't agree with everyone else's performance assessment.
The '2x' number Apple said was for the CPU
c 20060113.jpg/
Go to apple.com and there's a picture of an iMac, the tagline below is "2x faster. Twice as amazing."
That clearly gives the impression the machine is 2x faster. The machine isn't going to be twice as amazing if only one small part of it is 2x faster.
The tagline isn't "2x faster processor" ( of course the processor is 2x faster, there's two of them! )
And the picture isn't of the CPU.
here's a link to the pic incase the apple homepage changes
http://images.apple.com/home/2006/images/intelima