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.
Facebook
Twitter
RSS
173 Comments
View All Comments
cjb110 - Tuesday, April 24, 2012 - link
Considering that on most games both the Xbox and PS 3tend to be sub 720p, the iGPU in Ivy Bridge is impressive. Has anybody compared the 3?tipoo - Tuesday, April 24, 2012 - link
You have a unified shader GPU with similar performance to the x1900 series but more flexible, and something like a Geforce 7800 with some parts of the 7600 like lower ROPs and memory bandwidth...7 years later, if even an IGP didn't beat those, it would be pretty sad. Those were ~200gflop cards, todays top end is over 3000, a lower-mid range chip like this I would expect to be in the upper hundreds.gammaray - Tuesday, April 24, 2012 - link
Why do Intel and AMD even started building IGPs in the first place?Why can't they just put a video card in every desktop and laptop?
And if they continue making IGPs, whats their goal?
Do they eventually wanna get rid of video card makers?
versesuvius - Tuesday, April 24, 2012 - link
Better yet, why not just put the graphics on a chip like the CPU? That way the "upgrade path" is a lot clearer, not to mention "possible". It will also offer the possibility of having those chips in different flavors, for example good video transcoder or good gamer. There is room for that on the motherboard now that the north bridge is gone. Or they can review the IBM boards from 286 days and learn from their clean, and very efficient design.Unfortunately the financial model of the IT industry from a collective viewpoint entails throwing a lot of good hardware away just for a small advantage. Just the way many will throw away their HD3000 IGPs without having ever used it. The comparison is cruel but that should not be what distinguishes them from the toilet paper industry.
As of late, Anand has taken to reminding us that technology has taken leaps ahead of our wishes and that we need time to absorb it. That is not the case. No wish is ever materialized. We only have to take whatever is offered and marvel at the only parameter that can be measured: speed. Less energy consumption is fine, but I suppose that comes with the territory (i.e. can Intel or AMD produce 22 nm chips that consume the same watts as 65 nm chips with the same number of transistors?).
tipoo - Wednesday, April 25, 2012 - link
Cost, size, power draw. All reduced by putting everything on one chip. I'm not sure if AMD wants to get rid of discreet graphics cards considering that's their one profitable division, but Intel sure does :)klmccaughey - Tuesday, April 24, 2012 - link
I've tried every setup possible and have never got quicksync to work at all. It won't even work with discrete graphics enabled and my monitor hooked up to the intel chip on my Z68 board.I have tried mediacoder (error 14), media converter 7, MEdia Espresso. I have downloaded the media SDK, I have tried the new FFmthingy from the intel engineer. Nothing, nada. It has never ever worked. AMD media converter will convert a few limited formats that went out of fashion 5 years ago (of all my 1.5TB of video the only thing it would touch was old episodes of Becker).
All in all I have got nothing whatsoever from any video accelerated encoding and I have always had to go back to my tried and trusted handbrake.
I don't think it actually works - I've never heard of anyone getting it working and the forums on mediacoder are full of people who have given up.
klmccaughey - Tuesday, April 24, 2012 - link
*disabled (for discrete graphics)JarredWalton - Tuesday, April 24, 2012 - link
What input format are you using? I've only tried it on laptops, and I've done MOV input from my Nikon D3100 camera with no issues whatsoever. I've also done a WMV input file (the sample Wildlife.WMV file from Windows 7) and it didn't have any trouble. If you're trying to do a larger video, that might be an issue, or it might just be a problem with the codec used on the original video.dealcorn - Tuesday, April 24, 2012 - link
Intel has big eyes for the workstation graphics market and has had some success at the bottom of this market. Will IB's IGD advances enhance Intel's access to this market?chizow - Tuesday, April 24, 2012 - link
Hope you're not counting yourself, you've proven long ago your opinion isn't worth paying attention to.