Early Benchmarks Show Significant Performance Gains for Core i7 MacBook Pro

[jragosta]

From the PrimateLab benchmarks and relative to the 3.06 GHz Core 2 Duo, we would get the following.

Overall Performance:
Core I7 @ 2.66 GHz: 29% faster
Core I5 @ 2.53 GHz: 18% faster
Core I5 @ 2.40 GHz: 14% faster

Integer Performance:
Core I7 @ 2.66 GHz: 18% faster
Core I5 @ 2.53 GHz: 7% faster
Core I5 @ 2.40 GHz: 3% faster

FP Performance:
Core I7 @ 2.66 GHz: 34% faster
Core I5 @ 2.53 GHz: 23% faster
Core I5 @ 2.40 GHz: 17% faster

Keep in mind the limitations of any benchmarks. They only measure what they're designed to measure. For example, in evaluating the above figures, consider:

1. I don't believe that benchmark is multithreaded, so if your app or OS is multithreaded, there will be some additional benefit because of hyperthreading.

2. I assume that that benchmark would take advantage of TurboBoost. If it doesn't, then the actual results would be a little better.

3. That benchmark is mostly CPU performance. Keep in mind the differences in the other parts of the system. With OSX, for example, some things that were typically considered CPU dependent will benefit from the faster GPU in the new systems.

For those reasons, I rarely consider synthetic benchmarks (Geekbench, for example, shows single digit percentage increases on systems that are massively faster in real life). The BEST benchmark is to find the applications you use and compare them. Apple almost exclusively uses application benchmarks. They're not perfect, but IMHO, they're better than a synthetic CPU-only benchmark.

 

[barefeats]

GeekBench 32-bit scores
8107 = iMac Core i7 2.8GHz
5417 = MacBook Pro Core i7 2.66GHz
4974 = MacBook Pro Core i5 2.53GHz
4182 = MacBook Pro Core 2 Duo 3.06GHz

GeekBench 64-bit scores
9243 = iMac Core i7 2.8GHz
6325 = MacBook Pro Core i7 2.66GHz
5827 = MacBook Pro Core i5 2.53GHz
4619 = MacBook Pro Core 2 Duo 3.06GHz

CineBench 11.5 -- OpenGL Test
32.4 fps = iMac Core i7 2.8GHz
15.8 fps = MacBook Pro Core i7 2.66GHz
15.7 fps = MacBook Pro Core i5 2.53GHz
13.01 = MacBook Pro Core 2 Duo 3.06GHz using 9600M GT
5.9 fps = MacBook Pro Core 2 Duo 3.06GHz using 9400M

CineBench 11.5 -- CPU test
5.1 pts = iMac Core i7 2.8GHz
2.5 pts = MacBook Pro Core i7 2.66GHz
2.3 pts = MacBook Pro Core i5 2.53GHz
1.8 pts = MacBook Pro Core 2 Duo 3.06GHz

Special thanks to Mark Booth, a member of this forum, for benchmarking the MBP Core i7 for me while I wait for mine (which left Shanghai yesterday).

 

[barefeats]

OpenGL benchmark to try

Smalllux 1.5.5 OpenCL "Mid-Range" Benchmark
10.9 sec = iMac Core i7 2.8GHz
53.8 sec = MacBook Pro Core i7 2.66GHz
56.9 sec = MacBook Pro Core i5 2.53GHz
83.5 sec = MacBook Pro Core 2 Duo 3.06GHz

If you want to see your results and/or post them there, go here to download the latest version of the benchmark posted by Andreas Michalak:

http://www.macupdate.com/info.php/id/33632/smallluxgpu

Then run the "Benchmark Midrange GPU" (top right button).

 

[HyperX13]

GeekBench 32-bit scores
8107 = iMac Core i7 2.8GHz
5417 = MacBook Pro Core i7 2.66GHz
4974 = MacBook Pro Core i5 2.53GHz
4182 = MacBook Pro Core 2 Duo 3.06GHz

GeekBench 64-bit scores
9243 = iMac Core i7 2.8GHz
6325 = MacBook Pro Core i7 2.66GHz
5827 = MacBook Pro Core i5 2.53GHz
4619 = MacBook Pro Core 2 Duo 3.06GHz

CineBench 11.5 -- OpenGL Test
32.4 fps = iMac Core i7 2.8GHz
15.8 fps = MacBook Pro Core i7 2.66GHz
15.7 fps = MacBook Pro Core i5 2.53GHz
13.01 = MacBook Pro Core 2 Duo 3.06GHz using 9600M GT
5.9 fps = MacBook Pro Core 2 Duo 3.06GHz using 9400M

CineBench 11.5 -- CPU test
5.1 pts = iMac Core i7 2.8GHz
2.5 pts = MacBook Pro Core i7 2.66GHz
2.3 pts = MacBook Pro Core i5 2.53GHz
1.8 pts = MacBook Pro Core 2 Duo 3.06GHz

Special thanks to Mark Booth, a member of this forum, for benchmarking the MBP Core i7 for me while I wait for mine (which left Shanghai yesterday).

But but but 64 bit doesnt make any difference on speed, only if you want to access more memory... LOL where are those dudes now? haha...

 

[stodge]

Wow, huge jump from i7 mobile to i7 desktop. Thanks for this eye-opening. Especially regarding i5 vs i7.

GeekBench 32-bit scores
8107 = iMac Core i7 2.8GHz
5417 = MacBook Pro Core i7 2.66GHz
4974 = MacBook Pro Core i5 2.53GHz
4182 = MacBook Pro Core 2 Duo 3.06GHz

GeekBench 64-bit scores
9243 = iMac Core i7 2.8GHz
6325 = MacBook Pro Core i7 2.66GHz
5827 = MacBook Pro Core i5 2.53GHz
4619 = MacBook Pro Core 2 Duo 3.06GHz

CineBench 11.5 -- OpenGL Test
32.4 fps = iMac Core i7 2.8GHz
15.8 fps = MacBook Pro Core i7 2.66GHz
15.7 fps = MacBook Pro Core i5 2.53GHz
13.01 = MacBook Pro Core 2 Duo 3.06GHz using 9600M GT
5.9 fps = MacBook Pro Core 2 Duo 3.06GHz using 9400M

CineBench 11.5 -- CPU test
5.1 pts = iMac Core i7 2.8GHz
2.5 pts = MacBook Pro Core i7 2.66GHz
2.3 pts = MacBook Pro Core i5 2.53GHz
1.8 pts = MacBook Pro Core 2 Duo 3.06GHz

Special thanks to Mark Booth, a member of this forum, for benchmarking the MBP Core i7 for me while I wait for mine (which left Shanghai yesterday).

 

[AidenShaw]

But but but 64 bit doesnt make any difference on speed, only if you want to access more memory... LOL where are those dudes now? haha...

Extended addressing per se doesn't give a speedup, and can sometimes hurt slightly.

The x64 architecture, however, has improvements beyond the wider address bus, and can be faster when in 64-bit mode. The main improvement is that x64 has twice as many of each type of register - which helps compilers. (The x86 has 5 usable integer registers (3 of the 8 have predefined uses) - but x64 has 13 usable.)

In our testing, when an app isn't using a large data set (one that would otherwise require memory swapping), the speedup due to running in 64-bit mode is around 8-12%.

http://blogs.adobe.com/jnack/2008/04/photoshop_lr_64.html

In other words, the $1800 MBP 2.4 running 64-bit is about as fast as the $2200 MBP 2.66 running 32-bit. Your savings: $400

 

[Eidorian]

Wow, huge jump from i7 mobile to i7 desktop. Thanks for this eye-opening. Especially regarding i5 vs i7.

You're only going to notice it in these benchmarks to be honest.

 

[dsprimal]

I know macs aren't the best "gaming" rigs around...but i was just curious on if there would be a big difference from gaming on a Core i5 2.4Ghz / 215MB GPU. and a Core i7 2.66Ghz / 512MB GPU? I've seen a video of the core i5 2.4Ghz running Modern Warfare 2 and it ran smooth and the graphics looked amazing. Just want to know if the gaming experience would be even BETTER on the Core i7 15" MBP? Thanks!

and also, would Hyperthreading in the core i7 at all give an extra boost for gaming?

 

[roxnadz]

Which Core i7 does the iMac have? I'm presuming either the i7-860 or -930?

Most of the barefeats tests appear to lean toward heavy graphics use. I know that 4 cores in the iMac has a lot to do with it, but it appears - to me at least - that NVidia GT330M is getting positively spanked by the desktop Radeon (which is expected, obviously - I just didn't think by that much).

I think Apple could have put a mobility Radeon (like the HD 5730 for example) in there and gotten better graphics performance. I would gladly give up an hour of battery life for that, personally.

I was thinking about picking up a fully loaded i7 since it will be my last laptop purchase for quite a while, but I think I'm gonna just chill. I await further real-world testing, but I think I'm gonna sit on my 3.06 GHz Core 2 Duo for the short term, at least.

 

[Eidorian]

Which Core i7 does the iMac have? I'm presuming either the i7-860 or -930?

The iMac uses a LGA1156 socket. It's the Core i5 750 and Core i7 860.

 

[macinside]

So far for me, autoswitching is a dream come true! The previous mbp I had (exchanged it since I was within 30 days for the new i7 17" 2.66GHz model) to log out to use the integrated gpu all the time and I had to relaunch all my apps on 4 spaces. Now I dont have to log in and log out anymore while getting 10 hours of battery life.

Yes you heard me right, I'm getting 10 hours of battery life!

Yours is one of the first posts I've seen about the battery life of the 17 i7. 10 hours for a 17" is actually amazing, That's a lot longer than the 1st gen 17" 2.66 C2D unibody I have which runs 4.5hrs at load to 7hrs max.

I was curious to see if the new i7 got lower battery life than i5s, but from the (admittedly minimal) info I've seen so far, it sounds like you might even be getting more battery life than people have reporeted so far with the the i5 15". Impressive!

What sort of load are you running in those 4 spaces, jjahshik32?

Anybody else have any battery experiences with the new processors yet?

 

[corvus32]

Wow, huge jump from i7 mobile to i7 desktop. Thanks for this eye-opening. Especially regarding i5 vs i7.

The desktop i7 processor in the iMac has twice as many cores, twice as much L3 cache, and a higher turbo boost (3.46GHz vs 3.33GHz) than the mobile i7 in the MBP. It also consumes roughly three times as much energy (95W vs 35W).

Think about that last point for a moment. The iMac's i7 consumes nearly 300% more energy in return for a 46% higher Geekbench score. That's not to mention all the power being consumed by the rest of the system. Having the same 95W TDP as the i7, the iMac's i5 processor is an even worse offender, as are the C2D iMac's, and every other mac released prior to April 13.

iMac Core i7 2.8GHz = 97 Geekbench units per watt (9350 / 95W)
iMac Core i5 2.66GHz = 79 Geekbench units per watt (7500 / 95W)
MacBook Pro Core i7 2.66GHz = 181 Geekbench units per watt (6350 / 35W)