Core i7-4960X "Ivy Bridge-E" Roughly 10% Faster than i7-3970X: Early Tests

[Tatty_Two]

You got to count in that the 3930K overclocks way more than a Nehalem chip.

My old i7 920 couldn't do more than 4,2Ghz.

My 3930K does 5,1-5,2Ghz.

Good point, but people are talking about advancement in architecture, higher overclocks could be argued as an advancement, but to be honest, seeing as 90+% of CPU owners don't overclock it's a moot point.

@ Aquinus..... a decent improvement yes when stock (higher) clocks are factored of course but if we talk about the architecture, run them at the same speed and that improvement is reduced vastly which is all my point is, if everyone is happy with each generation just stocking at higher clocks that's one thing but don't we want REAL architectural improvements that give us what our hard earned $$$ is really paying for (or not as the case may be), I mean, with the advances in silicon, die size etc, CPU's "should" cost less, especially if all manufacturers are doing is applying a few "tweaks", raising stock clocks by 200mhz..... but funnily enough they are not really any cheaper.

 

[Aquinus]

The voltage slope from 4,7/4,8 Ghz to 5,1/5,2Ghz is insane though, we are talking from a comfy 1,35v to 1,52-1,55v.

I wouldn't be surprised to see my motherboard VRM toast someday even though they are watercooled but the backside is not and you can't touch that backplate without getting almost burned.

Yeah, you see my board gives me about ~300mhz less for the same voltages, but even under heavy load conditions my VRMs stay relatively cool, warm to the touch but never scalding hot. Might have something to do with the 16+2+2 phase power. I also haven't gone too gung-ho with the digi+ settings as far as VRM frequency and such, I think CPU and VCCSA LLC is set to high for me. I've been a bit more lazy than normal to try to push it higher so I haven't. There hasn't been a need to either. I would rather not fry my CPU unless I can get something better without paying too much. An IVB-E could be fun. I would love to see some numbers though. I personally would like to see 166Mhz strap capable CPU and motherboards become more common for skt2011 or maybe even some cherry picked CPUs that can do 250Mhz strap, that could be pretty cool but I'm just dreaming at this point.

Good point, but people are talking about advancement in architecture, higher overclocks could be argued as an advancement, but to be honest, seeing as 90+% of CPU owners don't overclock it's a moot point.

@ Aquinus..... a decent improvement yes when stock (higher) clocks are factored of course but if we talk about the architecture, run them at the same speed and that improvement is reduced vastly which is all my point is, if everyone is happy with each generation just stocking at higher clocks that's one thing but don't we want REAL architectural improvements that give us what our hard earned $$$ is really paying for (or not as the case may be), I mean, with the advances in silicon, die size etc, CPU's "should" cost less, especially if all manufacturers are doing is applying a few "tweaks", raising stock clocks by 200mhz..... but funnily enough they are not really any cheaper.

I guess it could be argued that as technology progresses it gets increasingly difficult to design CPUs to run faster without dedicating more money and time in the development of new techniques to do it. I would imagine that intel is milking the current architecture as much as they can until there is really a reason to try and push forward. So they're in the power position and they're going to take advantage of it. I seriously doubt that they don't have a backup plan in case AMD or another company pulls a rabbit out of a hat, which I hate to say, doesn't look likely.

 

[HumanSmoke]

They appear to be graphics (and GPU dependant) benchmarks, so hardly surprising.
Of more interest would be 5GHz at 0.9v

Er didn't intel focus mostly on gpu improvements this time round and claimed a 50% improvement in that area though , I think given intels cpu ipc performance is bordering optimal already they are doing well but clearly they are as they should be, focused on power efficiency and gpu grunt.

The results posted aren't using integrated graphics. They were obviously posted with the graphics card listed in the screenshot - an MSI GTX 660 Hawk. A quick look at the HD 4000's actual 3DMark Fire Strike capabilities should be a pretty big red flag.

So, as far as I'm concerned, I still don't see a selection of GPU based benchmarks being overly relevant when a third-party GPU is being used to render the result.

EDIT: Digging around on the site where the graphics comparison cropped up (note to Ikaruga: a link with the graph you posted would've been good), also presents some CPU benchmarks which are probably more relevant- although I'm wondering how mature the board BIOS is given the memory bandwidth numbers:

 

[Fourstaff]

So they're in the power position and they're going to take advantage of it.

No they are more worried about the midgets chewing them from below (read: ARM). Our need for CPU advances has stalled a bit as of late (for the past 3 years or more really), and the real advances are made in efficiency (which makes sense since the bulk of the cost of datacenters is the power bill). The current climate dictates the direction Intel takes, not the other way round. Remember they have to keep running forward and release incrementally better products even when there is no competition: they have to compete against their past.

 

[ShockG]

For so called tech enthusiasts most of us have unreasonable expectations on INTEL, AMD or any other company in this business. More so than Joe average.
If there was a way for INTEL to magically deliver a 30% improvement over Sandy-Bridge-E, that's what we would have today. Sadly this is not possible to achieve for any outfit; ARM, AMD, NVIDIA, TI, SAMSUNG etc. Nobody could deliver these kinds of gains within the constraints that INTEL has. The advancements are incremental and at no point did INTEL ever promise anyone massive gains when moving from one generation to another. That assertion came from us and it has always been incorrect. When investing billions of dollars into R&D and thousands of man hours, lazy isn't the word I'd use to describe the efforts of INTEL, AMD or any outfit for that matter. That word would be better reserved for my own profound and limited understanding of the technology and it's evolution. I'm an enthusiast because of my appreciation for the technology not my expectations of it.

We also tend to forget that, as far as expertise at processors and process manufacturing is concerned, no other company on this planet has dedicated as many resources to this as INTEL. I doubt if any one of us can find a single company that has commercial products on a fin-fet process at this node let alone with such massive cores containing so many logic gates. Whatever system you may own that you find to be "good enough" for all your needs, it's precursors had similar miniscule advances between each generation, which culminated in your "good enough" system.

As I am no engineer I find it hard to be disappointed by Ivy-Bridge-E, because whatever disappointment there may be, it stems from my own ignorant expectations rather than INTEL's inability to produce a compelling CPU.
I will be buying the 4960X, with the relevant motherboards when it's released.

 

[NeoXF]

For so called tech enthusiasts most of us have unreasonable expectations on INTEL, AMD or any other company in this business. More so than Joe average.
If there was a way for INTEL to magically deliver a 30% improvement over Sandy-Bridge-E, that's what we would have today. Sadly this is not possible to achieve for any outfit; ARM, AMD, NVIDIA, TI, SAMSUNG etc. Nobody could deliver these kinds of gains within the constraints that INTEL has. The advancements are incremental and at no point did INTEL ever promise anyone massive gains when moving from one generation to another. That assertion came from us and it has always been incorrect. When investing billions of dollars into R&D and thousands of man hours, lazy isn't the word I'd use to describe the efforts of INTEL, AMD or any outfit for that matter. That word would be better reserved for my own profound and limited understanding of the technology and it's evolution. I'm an enthusiast because of my appreciation for the technology not my expectations of it.

We also tend to forget that, as far as expertise at processors and process manufacturing is concerned, no other company on this planet has dedicated as many resources to this as INTEL. I doubt if any one of us can find a single company that has commercial products on a fin-fet process at this node let alone with such massive cores containing so many logic gates. Whatever system you may own that you find to be "good enough" for all your needs, it's precursors had similar miniscule advances between each generation, which culminated in your "good enough" system.

As I am no engineer I find it hard to be disappointed by Ivy-Bridge-E, because whatever disappointment there may be, it stems from my own ignorant expectations rather than INTEL's inability to produce a compelling CPU.
I will be buying the 4960X, with the relevant motherboards when it's released.

Spoken like a true mindless consumer of this day and age... no offence.
Sorry, but that was a utter load of rubbish to me and I can't find any another way to say it (other than not saying it at all, but since everyone around me keeps saying I should speak out more, I'm starting to not hold back any more).

This kind of thinking borders on Stockholm syndrome... but in regards to consumers as opposed to a full-on assailant. And it's kind of sad if the trend will be shifting that way... As long as it's consumerism we're talking about, we, the customers, the paying customers, should have the first say in anything, not the other way around. I'm not buying into Intel's shitty performance increments, and I'm certainly not defending their name.

 

[HumanSmoke]

but since everyone around me keeps saying I should speak out more

As an appreciator of unintentional comedy, I fully support everyone around you.

 

[ShockG]

Spoken like a true mindless consumer of this day and age... no offence.
Sorry, but that was a utter load of rubbish to me and I can't find any another way to say it (other than not saying it at all, but since everyone around me keeps saying I should speak out more, I'm starting to not hold back any more).

This kind of thinking borders on Stockholm syndrome... but in regards to consumers as opposed to a full-on assailant. And it's kind of sad if the trend will be shifting that way... As long as it's consumerism we're talking about, we, the customers, the paying customers, should have the first say in anything, not the other way around. I'm not buying into Intel's shitty performance increments, and I'm certainly not defending their name.

You're entitled to your opinion for sure, doesn't mean it's a valid one though.
Intel's ***** performance increments? What has lead you to believe they could or were supposed to be better? What information do you have, that nobody else apparently has, leads you to make this statement with such zeal? In your expertise, what could INTEL have done from a technical POV to ensure the double digit percentage gains you so desire?
"You, the paying customers", aren't entitled to anything. INTEL above all else is a self serving business, they owe you nothing other than what they have provided to you when you purchased your most recent CPU form them. You are not entitled to anything past that, hence there's no discourse needed between INTEL and you on what they release and how they go about it.
I'm not an engineer or anything of the kind (and I'll certainly not attempt to come off as one from behind my keyboard), but from what I gather it is truly difficult to design a CPU given many of the limitations in TDP and such. Your annoyance stems from your ignorance, not from an understanding of what it is INTEL was trying to achieve here.
The question is where have you been done wrong by Ivy-Bridge-E for the CPU to warrant such disdain from you? I re-iterate, you're disappointed entirely because of your expectations. When did INTEL promise you or anyone else massive performance gains with Ivy-Bridge-E?

 

[NeoXF]

[snip]

I'm entitled to not paying a dime on anything they make, for starters, unless this so called "business" move in a direction I'm more inclined to accept paying for... And I don't know how you see businesses, but how I see it, if the customers aren't impressed, therefor, willing to spend on your products, neither will your so-called business stand for much longer.

But in a sense, I guess what you said is right, it's not Intel's fault, it's the consumer's fault for buying into nonsense every damn tick and tock they shelve out, and to an extent, to their competition. But I won't go into how wrong thinking (external) competition is the only thing pushing anything forward in this world. Very few people/organizations strive to better themselves because they can these days and for the most part, just stagnate slightly above the lowest common denominator.

As an appreciator of unintentional comedy, I fully support everyone around you.

I challenge you to find me a nVidia GPU-based laptop with a AMD processor. Even more so, specifically with the setup I listed.

There might be a batch of laptops with those GPU/GPUs w/ something like i7-3630QMs, but seeing as ix-4xxx will be priced pretty much the same, I see no point in paying for older hardware, no matter if there are any real improvements or not.

 

[Hilux SSRG]

We also tend to forget that, as far as expertise at processors and process manufacturing is concerned, no other company on this planet has dedicated as many resources to this as INTEL. released.

Intel is not pushing the boundry enough and it hasn't for years now. As an enthusiast I don't care about manufacturing concerns, I just would like to give money to a company [AMD, ARM, etc.] for a quality x86 chip that has improved *significantly*.

As it stands Intel is subpar and that is why myself and others haven't upgraded as often the last few years.

 

[Aquinus]

Intel is not pushing the boundry enough and it hasn't for years now. As an enthusiast I don't care about manufacturing concerns, I just would like to give money to a company [AMD, ARM, etc.] for a quality x86 chip that has improved *significantly*.

As it stands Intel is subpar and that is why myself and others haven't upgraded as often the last few years.

I don't know what planet you live on, but the 3820 is a pretty significant upgrade from a 920 or a 930. It clocks higher, supports more memory, runs faster memory, and not relying on QPI for PCI-E through the IOH is a nice perk. In general, the platform has gotten better, despite the performance, which is still better. So all in all, I think Intel achieved what they wanted to with skt2011 because it's just skt1155 on steroids.

More often than not if you're getting skt2011, you want either multi-threaded performance, support for more memory, the ability to have VT-d and overclock at the same time, or to have a lot of expansion opportunities with the 40 PCI-E lanes on the CPU, which is certainly no slouch. Clocks will only go so high but clocks alone is not a reason to go skt2011 and anyone who thinks that has no idea what they're doing.

 

[Tatty_Two]

I don't know what planet you live on, but the 3820 is a pretty significant upgrade from a 920 or a 930.

Your argument is flawed, only because the 3820 is effectively 2 generations ahead of Bloomfield, even then, once you do the research, you find clock for clock, across the board around an 18% - 20% increase in performance, in some things more.... yes, in a few things even less, that in my book spanning a further 2 generations is not too great personally, which is why I still have a 930........ See the thing is..... and this is exactly my earlier point, because 95% of CPU owners don't overclock, my CPU is faster than 95% of all later generation Intel CPU's, certainly the 4 core or 4 core/8 threadded ones anyways

 

[radrok]

To be honest the biggest upgrade Intel could gift to Enthusiast would be QPI enabled i7 X editions...

Dunno you guys but I'd drool over a dual 3960X/3930K setup.

 

[Aquinus]

Your argument is flawed, only because the 3820 is effectively 2 generations ahead of Bloomfield

Two? Okay, one for initial skt1366 release and one for a die shrink. A die shrink isn't going to yield amazing results compared to architecture changes.

See the thing is..... and this is exactly my earlier point, because 95% of CPU owners don't overclock, my CPU is faster than 95% of all later generation Intel CPU's, certainly the 4 core or 4 core/8 threadded ones anyways

...and my believe that this point is flawed is that most users investing in a skt1366 or skt2011 machine is highly unlikely going to be running it at stock clocks unless you're using a Xeon on skt2011. So you and I alike both like overclocking, which still leaves me 3820 faster than your 930. Not to say that your 930 isn't capable of doing everything my 3820 can do, but between the IPC gains and the higher overclocks, the performance improvement is significant for some applications.

All in all, most processors do everything it needs to now a days and more often than not overclocking is merely for fun, but the fact still stands that performance along is not a reason to invest in skt2011. Also the changes from skt1366 and skt2011 don't highlight performance. The big change was eliminating the IOH and putting PCI-E on the CPU (40 whole lanes of it,) and practically making QPI useless on most X79 boards.

Simplifying the motherboard design and adding more functionality to the CPU would be considered an improvement, despite not being directly performance related, wouldn't you say?

95% of CPU owners don't overclock

95% of CPU owners don't own a skt2011 or skt1366 rig either.

 

[Tatty_Two]

Sorry? You are talking platforms there, but if you want to..... what about S1155, S1156 prior to 2011? But lets look at CPU's....... 920/930/940/950/960 Bloomfield......i7 860/870 ........ 2500/2600 Sandybridge..... so two REAL generations I think 3 if you wanna include the 860/870 on S1156

Bloomfield was launched in Q4 2008, the 3820 was launched in Q1 2012, over 3 years later.

 

[Aquinus]

Sorry? You are talking platforms there, but if you want to..... what about S1155, S1156 prior to 2011? But lets look at CPU's....... 920/930/940/950/960 Bloomfield......i7 860/870 ........ 2500/2600 Sandybridge..... so two REAL generations I think 3 if you wanna include the 860/870 on S1156

Bloomfield was launched in Q4 2008, the 3820 was launched in Q1 2012, over 3 years later.

Tatty, what's your point? Any hardware that is released later and has more time for development is going to be better. The point is that you said that Intel has made very few changes, which is bullshit unless you're talking about strictly the compute cores.

Okay Tatty, let's forget performance and age of the CPU for a moment.

skt1366 has an IOH using QPI for PCI-E and DMI, skt2011 does not, it's all built into the CPU.
skt1366 has a triple channel memory controller, skt2011 has a quad.
skt1366 used to keep the uncore and core frequency segregated so the uncore can run slower than the core, skt2011 does not do this, the uncore is directly tied to the core frequency iirc.
skt1366 quad cores had 8Mb of L3, skt2011 so far has had at least 10Mb for a quad.

This all becomes moot though if you have something like a 970 or a 980, but as far as a quad-core is concerned, the 3820 and skt2011 is a contender and I'm not sure how you can say that it isn't. I'm not saying that every 930 and 920 owner should go out and invest in a 3820 or better though. I'm just saying that significant changes have been made to the platform since skt1366, regardless of weather or not they addressed performance or something else.

 

[Tatty_Two]

Tatty, what's your point? Any hardware that is released later and has more time for development is going to be better. The point is that you said that Intel has made very few changes, which is bullshit unless you're talking about strictly the compute cores.

I have never said Intel has made very few changes, I did say that there is little performace improvement over almost 3.5 years and spanning at least 3 generations of architecture, I said this in response to some people (not exclusively you but you included) who used terminology such as BIG or in some other instances HUGE (not you) improvement gains often relating to just one generation, this simply is NOT the case once you look at like for like, clock for clock performance which is specifically why I referred to "architectural improvements".

I am not suggesting anyone is getting ripped off or that Intel are very naughty boys, simply that some statements can be misleading, unless of course 8% across one generation, or 22% across 3 generations really is HUGE Big and huge are somewhat subjective but my interpretation is perhaps skewed, so I suppose my point is....... that additional time you refer to is not providing enough improvements IMO.

 

[Aquinus]

so I suppose my point is....... that additional time you refer to is not providing enough improvements IMO.

When you have a CPU with over a billion transistors crammed into such a small place, it's not exactly easy to make huge changes to it without investing a lot of time into testing and development. I think you're overstating the ability of Intel, despite the resources that they have available. You make it sound like they can completely redesign a CPU and get it right in 3 years. It's taken Intel years to get the Core architecture where it is now after years of revisions, changes, and optimizations. Right now everyone sees what AMD is going through with BD and PD, but as time goes on AMD will optimize it and get it right. I don't think it's reasonable to assume Intel is going to break a proven platform without any reason for doing it. There isn't the drive in the market and developers don't tend to need it unless it's in a server as cloud computing is really becoming the thing to do now.

So I think Intel has done a good amount in 3 years. Could they have done more? Absolutely, I won't deny that they could have done more, but would it be the same quality as revisions in the past if they used the same amount of time? I doubt it. Less care would be put into each change so I have a strange feeling that it will negatively impact QA.

 

[radrok]

I think you're overstating the ability of Intel, despite the resources that they have available.

While I tend to agree with this idea I have to add a bit.

While raw IPC is hard to improve I think they are just sandbagging on the core count, I mean bloody Westmere-EX (LGA 1567) had 10 cores.

What on earth is blocking them on making available a bloody 12core CPU for socket 2011 other than themselves?

 

[Aquinus]

What on earth is blocking them on making available a bloody 12core CPU for socket 2011 other than themselves?

They would have to put a 4k USD price tag on it or some data centers or rather starting busineses would just buy consumer products because they're cheaper instead of investing in a Xeon server. Also in most cases, a 10-core CPU at 2.4Ghz isn't going to do most people any good. There just isn't a market for it, it's so tiny that it isn't worth it to make yet another platform to accommodate a design that holds 10 cores.

Just because you can cram 10 or 12 cores on to a CPU doesn't mean you can get them to run fast and even if you can, power consumption and heat dissipation is a huge issue.

 

[Tatty_Two]

When you have a CPU with over a billion transistors crammed into such a small place, it's not exactly easy to make huge changes to it without investing a lot of time into testing and development. I think you're overstating the ability of Intel, despite the resources that they have available. You make it sound like they can completely redesign a CPU and get it right in 3 years. It's taken Intel years to get the Core architecture where it is now after years of revisions, changes, and optimizations. Right now everyone sees what AMD is going through with BD and PD, but as time goes on AMD will optimize it and get it right. I don't think it's reasonable to assume Intel is going to break a proven platform without any reason for doing it. There isn't the drive in the market and developers don't tend to need it unless it's in a server as cloud computing is really becoming the thing to do now.

So I think Intel has done a good amount in 3 years. Could they have done more? Absolutely, I won't deny that they could have done more, but would it be the same quality as revisions in the past if they used the same amount of time? I doubt it. Less care would be put into each change so I have a strange feeling that it will negatively impact QA.

You have hit the nail on the head and have summed up the last 3 or so years worth of architectural progression very accuratly and thats what dissapoints me just a little...... why? because the move from Yorkfield to Bloomfield realised around a 20% performance improvement across the board and to be honest at the time was a revelation, we have had few revelations since! Again personally i would have prefered Intel to have skipped one of the last 3 changes/generations/platforms and spent some additional development time in introducing something with greater gains, but as I said, thats just my opinion and may not have been cost effective or viable in the current climate.

 

[radrok]

thats just my opinion and may not have been cost effective or viable in the current climate.

I just think it wouldn't have been profitable for them.

 

[Aquinus]

I just think it wouldn't have been profitable for them.

In the end that's really what drives business, isn't it?