p2pnet - rss feed: Intel Mac: 1st test results
p2pnet.net News:- Now Apple has officially confirmed that it’s going Intel comes further news that 3GHz Intel Pentium 4 Intel Macs are available to “selected developers for testing purposes” on a strictly enforced loaner basis.
And what will you find if you’re one of the chosen few?
Overall, nothing very exciting, says Think Secret.
Macs with Intel Inside are scoring between 65 and 70 with Xbench, “a far cry from the 200+ scores higher-end G5 systems reach,” says the report, going on:
“The CPU test is landing in the high teens compared with scores of 100 to 200 for G5 systems, but that appears to be primarily due to lackluster FPU scores. According to a recent Macworld story, Rosetta does not support AltiVec instructions, which substanti[at]es the results. The GCD Loop score for the Intel Mac, part of the CPU test, is a respectable 110, compared to dual-2.5GHz G5 Macs that score about 140.
“The Intel Mac performed substantially less well than the dual-2.5GHz G5 at Thread test, scoring an 82 compared to 225. In the Computation Thread test the Intel Mac scored a respectable 110 compared to 155 in the G5, but the G5 blew the doors of the Intel Mac in the Lock Contention test, scoring a 420 to the Intel Mac’s 66.
“The Memory Test tells a similar story: overall the Intel Mac scored a 214 to the G5’s 378, but the Intel Mac actually exceeded the G5’s Stream Memory Test: 351 to 319. The G5 trounces the Intel Mac at the system memory test, however, scoring a 464 while the Intel Mac musters a 154.
“The Intel Mac scored a 125 on the Interface Test, compared to a 380 for the G5.
“The Intel Mac scored well in both the Quartz graphics and OpenGL graphics tests—almost matching or exceeding dual-2.5GHz G5 score - although it’s unknown which video card is powering the system. There has been some speculation that Apple’s emracement of Intel processors will also allow the company to take advantage of off-the-shelf PC video cards.
“The Intel Macs are running Mac OS X 10.4.1 8B1025.”
Something you think we should know? tips[at]p2pnet.net
See:-
going Intel - Apple dumps IBM for Intel, p2pnet, June 7, 2005
Think Secret - New Mac OS X 10.4.2 build, Intel Mac benchmarks, June 8, 2005
June 8th, 2005 at 2:46 pm
Until Xbench is recompiled for the x86 version of OS X the numbers don’t mean much.
It is fairly impressive that the Xbench tests running under Rosetta would even perform this well though.
June 8th, 2005 at 2:59 pm
I don’t know why people are surprised the G5 blew the socks off the Pentium. I don’t think that is the point.
I think Jobs has decided to take the fight to Gates. In order to do that, OS X, hands down a better OS than Windows, has GOT to run on Intel. I was pissed at first, and I intend to buy a POWER PC Mac before they are all gone because I like the chip. But Steve Jobs has a different agenda and that is to stay in business, so good for him.
As for IBM, I have worked with IBM. they have some of the meanest, scariest chip engineers on the planet. Loyalty is not their strong suit, though.
All in all, I think getting into a situation where OS X runs head to head with Windows on the same equipment is a slick as s#!t move on Jobs’s part. A man that can wait 10 years for the proper time to engage his enemy is a man who will win.
June 8th, 2005 at 3:17 pm
Can you be more specific as to what version of 3GHz Pentium 4 the tests were done? Intel has 2 versions of that.
Since Intel and Apple kept this deal a secret for nearly 5 years, I don’t think we’ll get much detailed specs. any time soon. Until then, everything we read/hear is just speculation, and a lot of people have no idea what (they) are talking about.
I don’t bet much on Apple hardware, because they don’t make much. But the OS-X, Final Cut Pro and Shake software are just brilliant.
As for chips what can I say?
If you had a custom hot-rod and a Porsche (Intel & AMD) lined up to go on a straight line, then most likely the custom hot-rod would win. But if you want to go around curves, then I would personally choose a Porsche because the hot-rod would roll over. Macs use Power chips which are only good for speed (nothing else). There is a lot more going on with chip design than what most people think, and most Mac users have no idea what they are talking about.
I hope that Apple Intel move will encourage hardware manufacturers to make better video cards, sound cards… for Macs. At the moment if you want to upgrade your Mac with new hardare, you don’t have much choice. Product range is very limited. Either you settle with almost no upgrade, or just through your system in the bin (just like Dell and many other OEMs), or buy a new one.
I hope that by the end of the year we’ll see a more clear path for Apple.
June 8th, 2005 at 3:17 pm
Can you be more specific as to what version of 3GHz Pentium 4 the tests were done? Intel has 2 versions of that.
Since Intel and Apple kept this deal a secret for nearly 5 years, I don’t think we’ll get much detailed specs. any time soon. Until then, everything we read/hear is just speculation, and a lot of people have no idea what (they) are talking about.
I don’t bet much on Apple hardware, because they don’t make much. But the OS-X, Final Cut Pro and Shake software are just brilliant.
As for chips what can I say?
If you had a custom hot-rod and a Porsche (Intel & AMD) lined up to go on a straight line, then most likely the custom hot-rod would win. But if you want to go around curves, then I would personally choose a Porsche because the hot-rod would roll over. Macs use Power chips which are only good for speed (nothing else). There is a lot more going on with chip design than what most people think, and most Mac users have no idea what they are talking about.
I hope that Apple Intel move will encourage hardware manufacturers to make better video cards, sound cards… for Macs. At the moment if you want to upgrade your Mac with new hardare, you don’t have much choice. Product range is very limited. Either you settle with almost no upgrade, or just through your system in the bin (just like Dell and many other OEMs), or buy a new one.
I hope that by the end of the year we’ll see a more clear path for Apple.
June 8th, 2005 at 3:21 pm
Don’t know why Apple went for IBM on the first place. In the semiconductor industry IBM has a reputation for BS marketing and they don’t deliver what they promise.
Apple + Intel = let’s wait and see
June 8th, 2005 at 4:00 pm
Tough shit, huh? Guess they shoulda asked you first. Dipshits.
June 8th, 2005 at 4:03 pm
And by the way–did you even READ the story you quoted from? Have you ever used a computer?
“The benchmarks do not reflect native performance of the 3.6GHz systems, however, but rather provide an indication of how PowerPC-compiled applications will run under Rosetta on Intel-based systems.”
So you have even the slightest clue what that means, you yobs? Get an education. Don’t spread your ignorant stupidity around.
June 8th, 2005 at 4:06 pm
The G5 DID NOT blow the socks off of anything except itself!!! Read the original story (linked to in this moronic article). The person who wrote this story is an idiot who didn’t understand what was going on.
“I don’t know why people are surprised the G5 blew the socks off the Pentium.”
Yeah, right. Apple switched to Intel because the G5s were just too good, right? You’ve been buying the hype–now Jobs has pulled the rug out from under you. Whatcha gonna do now?
June 8th, 2005 at 4:17 pm
Well ’speed’ indeed may not be everything, but for some its the only thing. When you must process, edit and print large image files, speed always translates into dollars. Moreover, slow often translates into being beat by the competition.
I cannot imagine anyone editing images (scanned, still or video) who would choose ’slow’ over ‘fast’, that would be simply crazy.
Ditto for crunching numbers. What research scientist will opt to be slower than his commercial or institutional competition?
What’s needed is progress - G5X10! I want to make changes to my images in real time, without any delay for processing. I want to be able to load and edit 250 meg still-image files instantaneously. Porches don’t ‘race’ in reverse, that’s just plain silly!
June 8th, 2005 at 4:38 pm
I process, edit and print 250 meg still image files. I have a lot of competition. I need speed, because that is all that matters. If ‘anyone’ comes out with something faster than a G5, I’ll buy it. Not because I want to, but because my competition WILL buy it. In my business, slow MEANS no business.
I expect that the situation is the same for say, research scientists. I don’t think it likely that any would choose to be ’slower’ than their competition.
Speed is not merely an important thing, for many commercial and scientific applications, its the only thing.
June 8th, 2005 at 6:01 pm
Is it possible that the Power Pc performed so much better is because all the Apple software has been highly optimized for that architecture? I dont think they spent as much time making their software run that fast on Intel processors (yet).
June 9th, 2005 at 8:10 pm
Ok geniuses. The benchmarks that Think Secret posted are what you can expect using the Rosetta PowerPC *EMULATION* on a 3.6 GHz Pentium 4 (one processor with a single core). Think to the future — a year from now, we’ll have a fully-tweaked Rosetta running on dual-core dual-processor Intel systems (at the very least a dual-core single processor on PowerBooks), so let’s check back at that time to see how fast the Rosetta emulation is. And let’s see the ACTUAL benchmarks against comparable G5/Intel system when the systems come out. That should be proof that Apple made the right choice.
Comparing Rosetta PowerPC emulation to an actual G5 is like comparing the speed of Virtual PC (even on the fastest G5) vs. an actual PC box. Just STUPID.
Please report ALL of the story!
June 10th, 2005 at 1:18 am
It’s also worth noting that these tests were done on the first uild of Rosetta - one thats been superceeded in-house at Apple by a few versions.
They guy who compiled the test was very poorly informed.
June 10th, 2005 at 10:27 pm
In bothering to post this story in such a misleading manner, I have to assume that p2pnet has not idea what Rosetta is.
Although you can figure it out by clicking on the original Thinksecret story or noting the one passing reference to Rosetta, let me warn loud and clear to the casual reader:
THESE ARE NOT NATIVE BENCHMARKS. THESE ARE EMULATION-BASED BENCHMARKS THAT HAVE NOTHING TO DO WITH HOW MAC OS AND APPS WILL EVENTUALLY RUN NATIVELY ON INTEL.
June 14th, 2005 at 6:49 pm
The only time Apple expirienced a huge jump in speed is when they jumped from the 680×0 chips to the PPC chips. Classic apps ran slower in OSX when it first became available, so (surprise surprise) the intel macs are slower than the PPC macs. However, with this kind of slowdown, Apple may want to consider using dual-processors from here on out.
PS - Virtual PC on a G5 runs Windows about half of the speed of G4 and 2/3rds of the speed of a G5 processor on most Macs, and it took Connectix/Microsoft years to get it there. Apple has a much faster developement cycle, so they should get the emulation speed up to snuff much sooner (although if the 3+ghz G5 PowerMacs come out before 2006, they’ll end up shooting themselves in the foot for the first year after release).