The Intel Ivy Bridge (Core i7 3770K) Review
by Anand Lal Shimpi & Ryan Smith on April 23, 2012 12:03 PM EST- Posted in
- CPUs
- Intel
- Ivy Bridge
Die Size and Transistor Count
At IDF last year we got word of Ivy Bridge's transistor count (1.4 billion), however today we know its die size: 160mm2. That's 75% the size of a quad-core Sandy Bridge, but with 20% more transistors.
This marks the first time since 2006 that Intel is offering a high-end desktop CPU with this small of a die size. I'm excluding the 6-core parts from the discussion since that line isn't really aimed at the same market anymore. The chart is even more insane when you consider the Ivy Bridge die size includes an integrated GPU alongside four of the highest performance x86 cores Intel has ever shipped. Remove the GPU and Ivy Bridge is even smaller than Conroe. A hypothetical GPU-less Ivy Bridge would measure in at roughly 113mm^2 chip on its 22nm process, making it smaller than any high-end Intel CPU since the days of the Pentium 3.
CPU Specification Comparison | ||||||||
CPU | Manufacturing Process | Cores | Transistor Count | Die Size | ||||
AMD Bulldozer 8C | 32nm | 8 | 1.2B | 315mm2 | ||||
Intel Ivy Bridge 4C | 22nm | 4 | 1.4B | 160mm2 | ||||
Intel Sandy Bridge E (6C) | 32nm | 6 | 2.27B | 435mm2 | ||||
Intel Sandy Bridge E (4C) | 32nm | 4 | 1.27B | 294mm2 | ||||
Intel Sandy Bridge 4C | 32nm | 4 | 1.16B | 216mm2 | ||||
Intel Lynnfield 4C | 45nm | 4 | 774M | 296mm2 | ||||
Intel Sandy Bridge 2C (GT1) | 32nm | 2 | 504M | 131mm2 | ||||
Intel Sandy Bridge 2C (GT2) | 32nm | 2 | 624M | 149mm2 |
Ivy Bridge is tiny—but what does this mean? For starters, it means the obvious—Intel has little competition in the desktop space. I'm always hard on AMD in my meetings with them because of this reason alone. A less than competitive AMD means we get a less aggressive Intel.
More importantly however, a tiny Ivy means that Intel could have given us a much bigger GPU without breaking the bank. I hinted at this possibility in our Ivy Bridge architecture article. Unfortunately at the time only Apple was interested in a hypothetical Ivy Bridge GT3 and rumor has it that Otellini wasn't willing to make a part that only one OEM would buy in large quantities. We will eventually get the GPU that Apple wanted, but it'll be next year, with Haswell GT3. And the GPU that Apple really really wanted? That'll be GT4, with Broadwell in 2014.
All of this being said however, we must keep in mind that Ivy Bridge is both faster than Sandy Bridge and no more expensive. If we look at the supply and pricing constraints that accompany TSMC's 28nm process, the fact that Intel is able to ramp up 22nm and ship the first products without any price increase is something we shouldn't take for granted.
173 Comments
View All Comments
DanNeely - Monday, April 23, 2012 - link
Isn't the net OC performance roughly a wash? You're losing ~10% off the top in clock speed, but getting it back by the CPU doing ~10% more per clock.I'm curious what the power gap for the OCed IB is vs SB. For a system kept running at full load, the stock power gap would give a decent amount of yearly savings on the utility bills. If the gap opens even more under OC it'd be a decent upgrade for anyone running CPU farms.
Shadow_k - Monday, April 23, 2012 - link
Very nice igp improvementsAn also when will anandtech do a review on the i5 3570k because igp is underclocked
Ram21 - Monday, April 23, 2012 - link
UltraoboksRam21 - Monday, April 23, 2012 - link
Page 11 has the incorrect title or chart of Starcraft II - GPU Bench on the Dirt 3 pageAnand Lal Shimpi - Monday, April 23, 2012 - link
Fixed both of these, thank you!ltcommanderdata - Monday, April 23, 2012 - link
I don't have a comment on this Ivy Bridge review itself since it's thorough as always from Anandtech and Ivy Bridge seems pretty much what was expected. I do want to suggest a new benchmark for the eventual OpenCL followup when Intel releases new GPU drivers. As AMD mentioned as part of heir HD7000 series launches, WinZip 16.5 has finally been released with OpenCL acceleration in collaboration with AMD. Since fluid simulations won't be a common use case for most consumers and video encoding seems better suited to fixed function hardware like QuickSync, this OpenCL accelerated file compression/decompression will probably be the first and most popular use of GPGPU by consumers. It'll be interesting to see how much of a benefit GPU acceleration brings and whether AMD's collaboration results in better performance from AMD GPUs compared to Intel and nVidia GPUs then raw hardware specs would suggest. Other interesting tests would be to see if the acceleration is more pronounced with 1x1GB compressed file versus many compressed files adding up to 1GB. How well acceleration scales with between different GPU performance classes and whether it'll be bottlenecked by PCIe bandwidth, CPU setup time, system memory transfers or more likely HDD I/O. Whether tightly coupled CPU/GPUs like Llano and Ivy Bridge gives a performance advantage compared to otherwise similar specced discrete GPUs. Whether GPU acceleration is worthwhile on older GPU generations like the AMD HD5000/6000 and nVidia 8000/9000/100/200 series which aren't as compute optimized as the latest AMD HD7000 and nVidia 400/500 series. Whether WinZip 16.5 supports the HD4000 series which is OpenCL 1.0 or whether it requires OpenCL 1.1. Does WinZip 16.5 use OpenCL to help improve performance scaling on high core count CPUs (such as 8 or more cores).If GPU accelerated file compression/decompression is effective hopefully Microsoft and Apple will consider adding it to their native OS .zip handler.
Ryan Smith - Monday, April 23, 2012 - link
Rest assured it's on our list of things to look at, though I haven't seen it yet.mgoldshteyn - Monday, April 23, 2012 - link
The graphics engine still cannot support 10-bit per color IPS displays, as can be found on quality modern laptops from Dell and HP. That means that one is forced to get an overpriced mobile video card from ATI or NVidia to compensate, lowering the laptops power on hours by requiring an external card to be used with these displays. On non-IPS displays, one can choose to use the Intel built in graphics engine to save battery life. No such choice on high quality IPS displays since they are incompatible with the graphics engine of even Ivy Bridge.zaccun - Monday, April 23, 2012 - link
The workstation class laptops you are referring to are only offered with discrete graphics cards. No other machine has a 10 bit IPS panel. There is zero sense in dell or HP offering a machine aimed at professionals doing 3d modeling/CAD/video editing/etc without also putting the graphics horsepower in the laptop to support it.While I personally would love the option of getting a machine with the awesome panels that those notebooks use, without also paying for the $$$$ quadro cards that pros need, neither Dell nor HP offer anything like that.
Arnulf - Tuesday, April 24, 2012 - link
Neither can you eyes distinguish 1 073 741 824 different colors so why would you care ?