Core i5 3.6 GHz vs Core i5 Quad 2.8 GHz

[gonzo84]

I am sorry if such a thread exists already, i didn't find anything, so......

Im just configuring the iMac I'd like to buy and am wondering about the difference between the Quad Core i5 and the dual Core i5 with 3.6 GHz.

I'm not much of a video or sound editor, not even photos really,, some occasional gaming. I've noticed the 3.6 GHz is Clarkdale in 32 nm while the 2.8 Quad is Lynnfield with 45 nm.

I tend to the Quad, simply because I don't really like something to be maxed out, which i assume is the case in a 3.6 GHz chip.

I am confused and hope u guys can help me make a decision.

Thanks a lot

[Hellhammer]

Quad is faster in games

http://www.anandtech.com/show/2901/12

[hleewell]

Quad is faster in games

http://www.anandtech.com/show/2901/12

Well, it also depends on whether the game is written for dual core or quad core system. A Quad Core will always be faster than a Dual Core, technically speaking. But a dual 3.6 i5 can be faster in certain applications than a quad 2.8 i5.

[Hellhammer]

Well, it also depends on whether the game is written for dual core or quad core system. A Quad Core will always be faster than a Dual Core, technically speaking. But a dual 3.6 i5 can be faster in certain applications than a quad 2.8 i5.

Quad i5 goes up to 3.33GHz with Turbo. The CPU is not the bottleneck here, it's the GPU so there won't be huge difference between the games plus all upcoming games support quad core so future wise quad is better investment.

[Eidorian]

Lynnfield any day of the week over a 2 core, 4 thread Clarkdale.

[alent1234]

the dual has 4MB cache and the quad has 8MB cache. game performance will be so small you won't notice it.

the sweet spot for this refresh seems to be the higher end 21.5" model. last time it was the lower end 27" which is over priced this time

[dolphin842]

If you're not going to be encoding video or running multiple virtual machines on a regular basis, the dual-core i5 should be fine.

But Eidorian's right... the quad-core will certainly be faster... depends if you want to put out the extra cash though.

[gonzo84]

Thanks guys, you have been a huge help.

21,5'' core i5 would be nice, but i am concerned if the gpu will serve my future needs. 5750 seems to be noticably faster then 5670 i think.

So to sum up, the concensus seems to be Lynnfield Core i5 Quad is better if you want to spend the extra cash. Even though Lynnfield is manufactured in 45 nm? I guess I am overthinking it, anything will be better then my Merom, right? :)

Thanks

[stroedel]

another question:

i3 anno 2010 vs i5 anno 2009

will there be a big difference ?

[Hellhammer]

Thanks guys, you have been a huge help.

21,5'' core i5 would be nice, but i am concerned if the gpu will serve my future needs. 5750 seems to be noticably faster then 5670 i think.

So to sum up, the concensus seems to be Lynnfield Core i5 Quad is better if you want to spend the extra cash. Even though Lynnfield is manufactured in 45 nm? I guess I am overthinking it, anything will be better then my Merom, right? :)

Thanks

The manufacturing process doesn't really speed it up. Lynnfield iMac gets you the better GPU as well

[Eidorian]

another question:

i3 anno 2010 vs i5 anno 2009

will there be a big difference ?The Core i5 750 wins. There will never be a Core i3 (Clarkdale) that's faster than the Core i5 750.

[Hellhammer]

another question:

i3 anno 2010 vs i5 anno 2009

will there be a big difference ?

Yes, i5 is a lot faster as it's quad core

[stroedel]

tnx for replys...
and what about the i3 versus the "old" Intel Core 2 Duo E7600
cause difference here is 1729 € vs 1499€

[Hellhammer]

tnx for replys...
and what about the i3 versus the "old" Intel Core 2 Duo E7600
cause difference here is 1729 € vs 1499€

Depends on what you do. You won't notice much, if any difference if you just browse on the net but if you do something CPU intensive like video encoding, the i3 is better

[stroedel]

Depends on what you do. You won't notice much, if any difference if you just browse on the net but if you do something CPU intensive like video encoding, the i3 is better

if im not a gamer, and if i only do video encoding once a month..
im thinking on getting dual core + 4 GB extra ram !
pff, they didnt make it easy ...

[dolphin842]

tnx for replys...
and what about the i3 versus the "old" Intel Core 2 Duo E7600
cause difference here is 1729 € vs 1499€

I'll be running some more Handbrake encoding benchmarks once I get to the Apple Store, but here are some results from running it on the last-gen iMacs and current-gen MBP:

[EDIT: scroll down the page for updated benchmarks]
i5 750 (2.6 GHz x 4): 62fps [EDIT: disregard this, I had inferred it from a quad-core i7 reading]
Core 2 Duo (3 GHz x 2): 31fps
i7 (from MBP, 2.6 GHz x 2): 37fps

[Eidorian]

I'll be running some more Handbrake encoding benchmarks once I get to the Apple Store, but here are some results from running it on the last-gen iMacs and current-gen MBP:

i5 750 (2.6 GHz x 4): 62fps
Core 2 Duo (3 GHz x 2): 31fps
i7 (from MBP, 2.6 GHz x 2): 37fpsIt doesn't sound like Turbo Boost is in action on that Core i5 750.

[dolphin842]

Hmm... I was running Handbrake in the same way on each machine (High Profile x264, RF 28). The quad-core i7 got ~67fps. Are the other figures in line with what you'd expect?

[Eidorian]

Hmm... I was running Handbrake in the same way on each machine (High Profile x264, RF 28). The quad-core i7 got ~67fps. Are the other figures in line with what you'd expect?It appears that I was incorrect. You were perfectly in line.

[freiheit]

I'll be running some more Handbrake encoding benchmarks once I get to the Apple Store, but here are some results from running it on the last-gen iMacs and current-gen MBP:

i5 750 (2.6 GHz x 4): 62fps
Core 2 Duo (3 GHz x 2): 31fps
i7 (from MBP, 2.6 GHz x 2): 37fps

It's a shame for them to call that overpriced dual-core an i7. It's a crying shame and gives the i7 a bad name. Looking forward to your reports on the new iMacs, especially the dual-core i5 versus the quad-core i5 since both technically provide 4 threads. I suspect real cores will always beat virtual ones, but over time virtualization/hyperthreading should become more refined and maybe the line will blur.

[RAM3Zero]

As a direct result of this thread, I finally placed my order for a 27" quad i5 (with trackpad, I couldn't resist). Was considering going low-end but knew in the end I wouldn't be satisfied. I've been itching to switch over to mac for a really long time now and finally placing the order is quite freeing.

Thanks to Hellhammer, TMRaven and Eidorian (plus others) for their solid input over the past 6 months. I've been following your posts regularly and you've answered my unasked questions and provided great data. Should arrive between August 3rd-10th in Canada, will keep you posted.

R.

[dolphin842]

Alright, just got back from the Apple Store. There weren't any i5 3.6GHz (dual-core) or quad-core i7's on display, but I got stats on the rest. Here they are along with all my other data:

Handbrake x264 test (High Profile, 28 RF, 720x480 DV source file @ 60fps, anamorphic loose w/ 40px auto-cropping on left and right):

13fps: 1.83 Core Duo (original intel iMac, my current machine:rolleyes:)
25fps: 2.6 Core 2 Duo (Mac Mini Server)
31fps: 3.06 Core 2 Duo
37fps: 2.66 i7 (dual-core, MacBook Pro)
41fps: 3.06 Core i3 (dual-core)
43fps: 3.2 Core i3 (dual-core)
65fps: 2.8 Core i5 (quad-core)
67fps: 2.8 Core i7 (quad-core, 2009 model)

A few notes for this particular workflow:
- The move from Core 2 --> i3 yields about a 32% performance increase at identical speeds for the dual-cores. What a difference an architecture can make:cool:.
- The flip side of the previous point: Whereas moving from to 2 to 4 cores yielded an essentially linear performance increase in last year's models (~100% when the jump was from a core 2 to a core i5), this year the extra cores only get you a ~50% increase in performance.
- The speed bump from 3.06 i3 --> 3.2 i3 is rather minimal; in this case, you'll only want to pick the faster model if you want the newer ATI graphics and/or the extra 500GB of internal storage. For single-threaded applications, I believe the 3.2 i3 has turbo boost, which may make a bigger difference.
- Hyperthreading (quad-core i5 vs. i7) yields only a 3% speed increase, likely because x264 is multithreaded and maxing out all physical cores, leaving little downtime for hyperthreading to be of use.

[freiheit]

Alright, just got back from the Apple Store. There weren't any i5 3.6GHz (dual-core) or quad-core i7's on display, but I got stats on the rest. Here they are along with all my other data:

You are wonderful! Thank you so much for posting this. Does the Apple store seriously let you go in and put your own data on their systems to try stuff out? I mean, you had to have installed Handbrake and attached a drive with your data and stuff. What DON'T they let you do?

It's too bad you didn't get to benchmark the dual-core i5. I'd love to see how it compares to the quad-core and how much you really get over the i3 running 400MHz slower. I would prefer to buy a quad-core, but the 27" screen is far too big and high resolution for me, so the top 21.5" is where I'd be buying unless the 27" with i5 shows a significant performance boost.

[dolphin842]

You are wonderful! Thank you so much for posting this.

No problem... I'm in the market for a new Mac myself so I figured I'd share what research I've done so far :).

Does the Apple store seriously let you go in and put your own data on their systems to try stuff out? I mean, you had to have installed Handbrake and attached a drive with your data and stuff. What DON'T they let you do?

Yeah, the retail stores let you mess around with the Macs quite a bit. I've not had any employees ask what I was doing, though one time they did quickly reboot the machine after I left :rolleyes: (I assume it has a default disk image that it reverts to). As for file transport, Handbrake.app and my test file fit on a 1GB flash drive, so it's easy to just hook up and drag both to the desktop.

It's too bad you didn't get to benchmark the dual-core i5. I'd love to see how it compares to the quad-core and how much you really get over the i3 running 400MHz slower. I would prefer to buy a quad-core, but the 27" screen is far too big and high resolution for me, so the top 21.5" is where I'd be buying unless the 27" with i5 shows a significant performance boost.

My guess is that the performance increase going to the 3.6 i5 will be pretty linear. Both cores are taxed with x264 encoding, so even if the turbo boost is more substantial on the i5, there won't be much opportunity to use it (similar to hyperthreading's limited usefulness in this scenario).

So for the 3.6 i5 you'd probably be in the 48fps range or thereabouts. If that's the case, then the move to quad-core would give a performance increase in the neighborhood of 35%. As I mentioned above, the speed bump going from dual-core-->quad-core is less pronounced this time around due to the lower-end iMacs finally getting the new i-series architecture. So unless you plan on encoding videos fairly regularly, the extra cost of the 27" might not be worth it.

[Will : Hi !]

Hyperthreading (quad-core i5 vs. i7) yields only a 3% speed increase, likely because x264 is multithreaded and maxing out all physical cores, leaving little downtime for hyperthreading to be of use.

HandBrake's High Profile preset enables 2 poorly-threaded filters (decomb, and more importantly detelecine) by default.

Edit: Also, DV at 60 fps? Are you sure it's not 480i60 (60 fields per second)? That's likely causing some more time spent in the filters vs. actually encoding in x264.

[dolphin842]

HandBrake's High Profile preset enables 2 poorly-threaded filters (decomb, and more importantly detelecine) by default.

Ah, I didn't realize that. So if the filters in play are poorly-threaded, does that mean hyperthreading is having more of an effect vs. if they were turned off and the main encoding process occupied more of the cycles? I was under the impression that if there were no decombing or detelcining needed, the filters would detect this and turn off. That said, if I find myself in an Apple Store with an i7 machine, I'll turn off the decomb and detelecine and see if it makes any difference.

Edit: Also, DV at 60 fps? Are you sure it's not 480i60 (60 fields per second)? That's likely causing some more time spent in the filters vs. actually encoding in x264.

It's 480p60. The original source was indeed 480i60, but I deinterlaced it beforehand with JES Deinterlacer to make it 60 full frames per second. For the source footage I'm working with (video games with a lot of rapid movement), it makes a big difference in quality.

[Will : Hi !]

Ah, I didn't realize that. So if the filters in play are poorly-threaded, does that mean hyperthreading is having more of an effect vs. if they were turned off and the main encoding process occupied more of the cycles?

The opposite - the filters could be a bottleneck of sorts. Other HandBrake benchmarks I've seen show a 30% advantage to the 2.8 i7 compared to a 2.66 i5. I would still expect a 20-25% advantage for the i7 vs. the new i5.

Note that I asked the developer who integrated the filter to HB and it turns out the detelecine filter is not threaded at all.

Edit: well, I can't find the benchmark where the i7 is 30% faster than the i5, but I found two PC-based benchmarks:

http://www.bit-tech.net/hardware/cpus/2009/09/08/intel-core-i5-and-i7-lynnfield-cpu-review/5

http://www.guru3d.com/article/core-i5-750-core-i7-860-870-processor-review-test/14

Both using HandBrake for Windows, i7-860 is 20% and 26% faster than i5-750. Even adjusting for the 2010 imac i5's 5% higher clock and faster 1333 MHz memory (let's say it's 10% faster), the 2009 i7 should still be 9-14% faster.

All the non-GUI code is the same on both platforms, so relative speed should be the same under OS X.

I was under the impression that if there were no decombing or detelcining needed, the filters would detect this and turn off.

The only reliable way to detect interlacing and hard telecine is to analyze the source - the filters can't just "turn off". Of course, encoding a progressive source will still be much faster (than encoding interlaced or telecined content) since the filters don't need to perform any actual filtering.

It's 480p60. The original source was indeed 480i60, but I deinterlaced it beforehand with JES Deinterlacer to make it 60 full frames per second. For the source footage I'm working with (video games with a lot of rapid movement), it makes a big difference in quality.

I see. I'm not familiar with capturing video games, but it sounds like you should switch to something that captures progressive content. BTW, the HandBrake nightly builds can now re-encode Fraps (there was a bug in 0.9.4 and earlier that prevented this).

[dolphin842]

Thanks Will for this info :)

The opposite - the filters could be a bottleneck of sorts.

I agree that the filters here are likely posing a bottleneck, though I'm still a bit confused as to why this would make the benchmark I ran seem less impressive than the stats you referenced. Isn't it this type of bottleneck where hyperthreading is supposed to excel? I'm envisioning the detelecine filter sitting in one core, but not maxing it out... wouldn't it be an advantage in this case for the i7 to have another thread (something related to the actual x264 encoding perhaps?) right there in the core ready to utilize what the detelecine thread doesn't? I'm probably just conceptualizing it improperly, so if you're able to explain it better, that would help alleviate this confusion.

I don't doubt the benchmarks you posted; it certainly seems like hyperthreading can offer some tangible benefits in some situations. I'm just not sure what those situations are specifically. That said, if the decomb/telecine filters are indeed causing a bottleneck that reduces the i7 performance gains, wouldn't it be safe to say though that people will be running these filters more often than not (encoding DVDs of film/animation)? I'm not sure what the source files were for those other benchmarks (I did notice they were HD, though I'm not sure if that matters).

The only reliable way to detect interlacing and hard telecine is to analyze the source - the filters can't just "turn off". Of course, encoding a progressive source will still be much faster (than encoding interlaced or telecined content) since the filters don't need to perform any actual filtering.

Good to know. I must have misread something from the HB devs a while ago... I thought they had said to just leave it at the default setting, but from now on I will explicitly turn them off when not required and see what happens.

I see. I'm not familiar with capturing video games, but it sounds like you should switch to something that captures progressive content. BTW, the HandBrake nightly builds can now re-encode Fraps (there was a bug in 0.9.4 and earlier that prevented this).

Ideally I should be capturing in progressive, but it would require getting more expensive equipment. I'm capturing SD footage from consoles (Wii/Gamecube mostly), so at the moment it's easy to just use a 15-year old VCR to split the composite stream into a firewire DV bridge :cool:.

[tipman2000]

hey if someone gets a hold of a dual 3.6 i5 then can they please gets some benchs up on here cuz i lust for extremely high clocks.

[tipman2000]

hey if someone gets a hold of a dual 3.6 i5 then can they please gets some benchs up on here cuz i lust for extremely high clocks against the dual 3.2 i3

[cherry su]

hey if someone gets a hold of a dual 3.6 i5 then can they please gets some benchs up on here cuz i lust for extremely high clocks against the dual 3.2 i3

Here's a benchmark from MacWorld: http://www.macworld.com/article/153385/2010/08/36ghzcorei5_imac.html?t=

[SiMBa37]

hey if someone gets a hold of a dual 3.6 i5 then can they please gets some benchs up on here cuz i lust for extremely high clocks against the dual 3.2 i3

There's a whole GeekBench thread on this:

http://forums.macrumors.com/showthread.php?t=980698

[The-Pro]

Bit late to bring this thrad to life again, but the 3.6 ghz i5 has hyper threading and NO turbo boost. the 2.8ghz quad core i5 has NO hyper threading but has turbo boost to 3.33 ghz. So the 3.6 ghz has 4 virtual cores while the 2.8 has 4 physical cores. these 4 physical cores when all 4 are used run at 2.8 ghz. In comparison the 3.6ghz i5 when all 4 virtual cores are being used still is running at 3.6 ghz. wouldnt it make sense if the 3.6ghz is techincally as quick or quicker for day to day use?. i mean come on, its clocked 800 mhz higher. Can 2 more physical cores at 800mhz less really be that much more powerful than 2 more virtual cores???

[Eidorian]

Bit late to bring this thrad to life again, but the 3.6 ghz i5 has hyper threading and NO turbo boost. the 2.8ghz quad core i5 has NO hyper threading but has turbo boost to 3.33 ghz. So the 3.6 ghz has 4 virtual cores while the 2.8 has 4 physical cores. these 4 physical cores when all 4 are used run at 2.8 ghz. In comparison the 3.6ghz i5 when all 4 virtual cores are being used still is running at 3.6 ghz. wouldnt it make sense if the 3.6ghz is techincally as quick or quicker for day to day use?. i mean come on, its clocked 800 mhz higher. Can 2 more physical cores at 800mhz less really be that much more powerful than 2 more virtual cores???All Core i5 processors have Turbo Boost. ;)

[The-Pro]

ah ok, my bad, true, apple website is misleading :P

still its a 800mhz difference at base clocks if system is used 100%. for the standard user woudlnt the 3.6 be of much greater performance than the 2.8. tasks where all 4 virtual cores are used, woudlnt hey be completed faster with 3.6ghz incomparison to 2.8 ghz with 4 physical cores

Also single threaded tasks would definetly be completed much quicker on the 3.6 right?? (3.86ghz turbo vs 3.33ghz turbo = 530mhz quicker)