[Coolaler] Core i7 3930K vs Core i7 3960X

[dma0991]

Core i7 3930K vs Core i7 3960X

Click the link above to see screenshots of benchmarks. Not going to post here because scrolling down a long post of images is PITA.

 

[Puppies04]

0.2ghz faster than my i5 2500k and it finishes 32m superpi a whole 9 seconds quicker. I love progress 😀

 

[tweakboy]

Were already having matches "VS" on CPU's that aren't even out and won't come out for months.

I think too many people here want their SuperPI to be 1 second faster so they get excited.

I bet these people in the post never used their CPU to 100 percent and they didnt do Video Editing with Premiere, or DAW Sonar X1c ... All they do is play games which takes about 60 percent CPU power and surf net watch video. Which your fine with a 4 year old processor let alone, keeping on upgrading processors for what ? its already fast enough Sandy is,, you wont see a difference.... Put the VS battle down until the CPU's exist in peoples hands.. Thanks gg and gl and always gb

 

[Rvenger]

We know single threaded performance will be comparable to SB-E but Multithreaded it will be better than entry level SB

 

[mrjoltcola]

0.2ghz faster than my i5 2500k and it finishes 32m superpi a whole 9 seconds quicker. I love progress 😀

Since the cores are nearly identical(still Sandy Bridge), I wouldn't expect much difference with SuperPi, since SuperPi is mostly a good measure of overall IPC. The significance is 6-cores of Sandy Bridge Excellence to finally displace the Nehalem 980/990X/995X for those wanting the most single socket grunt they can get, and the improved rendering, crunching and compiling power it will bring.

 

[mrjoltcola]

Were already having matches "VS" on CPU's that aren't even out and won't come out for months.

We are expecting SB-E within the next 30 days.

 

[dma0991]

Put the VS battle down until the CPU's exist in peoples hands.. Thanks gg and gl and always gb

We would be cleaning the cobwebs and wiping the dust off the AT server rack if everyone waits for the product to appear. Imagine a single thread for a product only after the product launches in 1-2 years time. It is not a big issue if it is not 100% legit, it is still news after all. Taking from what I've known about Bulldozer and its prerelease leaks, they are almost identical to the official reviews. This could probably be a similar case.

 

[Puppies04]

Since the cores are nearly identical(still Sandy Bridge), I wouldn't expect much difference with SuperPi, since SuperPi is mostly a good measure of overall IPC. The significance is 6-cores of Sandy Bridge Excellence to finally displace the Nehalem 980/990X/995X for those wanting the most single socket grunt they can get, and the improved rendering, crunching and compiling power it will bring.

Neither would I which is why i found it a bit of a weird benchmark to use.

 

[mrjoltcola]

Oh, good point. I guess SuperPi is just tradition. Myself, I usually scroll down to the Cinebench numbers right away.

 

[Arachnotronic]

I so incredibly want this. However, this tactical i7 875K I have inbound will have to do until Haswell-E.

 

[-Slacker-]

How can it score 13.3 points in cinebench 11.5 at stock speed? A 2600k manages like 7 points ... that's almost 2 times slower for 33% less cores...

edit: oh wait ... 4.5 ghz ... nevermind then.

 

[LOL_Wut_Axel]

Just as fast in what. Games? EE processors are definitely faster in rendering / encoding. Not everyone games. Whether thats worth the price premium, is up to the user.

I think less than 50% of the people here read the thread before commenting. You probably didn't, so again: both stock, the performance difference is 2-3% because of the 100MHz higher clock speed on the EE. Both at average overclocks, say at 4.5GHz, will be the same speed.

At the same clock speeds, they'll be the same speed, including in rendering/encoding/content creation.

If someone can't OC because it's for enterprise or the like, then it's up to them to see if the 2-3% higher stock performance is worth the extra 67% in cost.

There's a reason why Tom's themselves said the 3930K was the most interesting CPU of the bunch.

So what are we betting that you are wrong?

His arguement of saving money and going with the 3930 over the 3960 for most users is valid. No one is disputing that. But he also goes on to say that the 3930 and 3960 will have the exact same performance for every single application out there (clock or clock). Which is not true. Many applications love more cache. Just not games.

🙄

Differences are statistically insignificant and in margin of error at the same clocks, under 1%. That means they're the same speed.

So where's my prize? Do some people here actually think more cache than the already huge 12MB L3 the 3930K has will make a difference in desktop workloads? So there goes the cache argument. The difference in clock speed is only 100MHz, and looking at the 2500K and 2600K that means it's not better binned, but everything will depend on your luck. Can anyone pinpoint me as to why you'd buy the 3960X using objective reasons, meaning not something like "because I can"? Or is the Extreme Edition moniker and e-peen the only reason?

 

[tweakboy]

Wait is the 3960x ivy bridge ? If not, hold your horses everyone, let this pass. If you already have a Sandy, its a pointless upgrade you wont see a difference in real world usage. gl

 

[Arachnotronic]

3960X is 6 core of SNB with a quad channel memory controller.

 

[LOL_Wut_Axel]

Wait is the 3960x ivy bridge ? If not, hold your horses everyone, let this pass. If you already have a Sandy, its a pointless upgrade you wont see a difference in real world usage. gl

It's Sandy Bridge-E. And the six-core/twelve-thread CPUs (3930K, 3960X) will offer 30-45% higher performance than the quad-core/eight-thread (2600K, 2700K, 3820) CPUs in multi-threaded workloads, so there definitely is a big difference in real-world applications.

 

[rexinu]

It's Sandy Bridge-E. And the six-core/twelve-thread CPUs (3930K, 3960X) will offer 30-45% higher performance than the quad-core/eight-thread (2600K, 2700K, 3820) CPUs in multi-threaded workloads, so there definitely is a big difference in real-world applications.

How about gaming?

 

[LOL_Wut_Axel]

How about gaming?

Same speed unless you're directly trying to compare JUST CPU speeds at 1024x768 and the like.

 

[rexinu]

Thanks for that. I know this question has probably been done to death, but is it worth holding out for new gen tech 2011/ivy ? Was planning to finish my build in about 2 weeks and decided on the 2500k/Asrock extreme 4 to team up with my pair of 6970s. I know they aren't too far around the corner but considering I'm
In Aus it will probably even be a bit longer of a wait.

 

[LOL_Wut_Axel]

Thanks for that. I know this question has probably been done to death, but is it worth holding out for new gen tech 2011/ivy ? Was planning to finish my build in about 2 weeks and decided on the 2500k/Asrock extreme 4 to team up with my pair of 6970s. I know they aren't too far around the corner but considering I'm
In Aus it will probably even be a bit longer of a wait.

Not really. For gaming Ivy Bridge doesn't mean much, but for multi-threaded computing if going from something like an i5-2500K it could. Ivy Bridge will have 5% higher IPC, and overclocking headroom should increase by 5% too. That's 10%, so for MT computing someone with a 2500K would see a jump of ~30% in multi-threaded performance by going to the Ivy Bridge CPU that replaces the 2600K. Hyper-Threading gives a ~20% boost in multi-threaded programs on average, so that additional 10% yields 30%, which to many could be significant. Ivy Bridge will be launched in March or April next year, which is still a pretty long ways off.

Hyper-Threading gives you no performance gain in games, and that 10% additional performance from clocks and IPC translates to around 5% in CPU bound games and almost nothing in GPU bound games. If it's for gaming, build your 2500K rig now and don't look back.

 

[lamedude]

Quad channel fail? The AIDA64 memory speed is about the same as dual channel SNB.

 

[StrangerGuy]

Not real until official reviews. *snicker*

 

[bunnyfubbles]

unless they were just being lazy and/or were just cutting corners to ensure stability, I can't say I'm too enthused by their overclocking results. 4.6GHz @ 1.44+v isn't too encouraging, not terrible, but not exactly much of an improvement from Gulftown.

 

[BrightCandle]

Those AIDA64 memory scores have got to be wrong. Its hard to believe this processor isn't beating an original Nehalem given it has an additional channel and faster supported frequency.

I was expecting somewhere just under 40GB/s not just shy of 20GB/s. Not that it matters if the CPU can't actually utilize the bandwidth.

 

[AdamK47]

Same speed unless you're directly trying to compare JUST CPU speeds at 1024x768 and the like.

All of which are GPU limited.

The leaked benchmarks in the OP do use 3-way GTX 580s. Unfortunately, the only thing that was run was 3DMark Vantage/11. The GTX 580s are clocked very high at 950MHz for a 3-way setup. Mine are at 850MHz and I still manage this:

Vantage - P59093:
http://3dmark.com/3dmv/3559058

11 - P16408:
http://3dmark.com/3dm11/2001148

I'm really hoping my future SB-E system performs better than these leaked benchmarks show.

Edit: I see what's wrong with their Vantage results. It's not using PhysX. Either it's disabled, or the driver isn't installed.

 

[Edrick]

So where's my prize? Do some people here actually think more cache than the already huge 12MB L3 the 3930K has will make a difference in desktop workloads? So there goes the cache argument. The difference in clock speed is only 100MHz, and looking at the 2500K and 2600K that means it's not better binned, but everything will depend on your luck. Can anyone pinpoint me as to why you'd buy the 3960X using objective reasons, meaning not something like "because I can"? Or is the Extreme Edition moniker and e-peen the only reason?

For those benchmarks your arguement holds true. 15MB to 12MB makes very little, if any, difference. But as I did mention, there are some applications (workstation) which love more cache. Once these CPUs are launched, and I seem some results from the workstation camp, and if the results are the same, I will eat my words and say you were right. I am holding my opinion until then however. 🙂