Slashdot Mirror
Ivy Bridge Running Hotter Than Intel's Last-gen CPU
crookedvulture writes "The launch of Intel's Ivy Bridge CPUs made headlines earlier this week, but the next-gen processor's story is still being told. When overclocked, Ivy Bridge runs as much as 20C hotter than its Sandy Bridge predecessor at the same speed, despite the fact that the two chips have comparable power consumption. There are several reasons for these toasty tendencies. The new 22-nm process used to fabricate the CPU produces a smaller die with less surface area to dissipate heat. Intel has changed the thermal interface material between the CPU die and its heat spreader. Ivy also requires a much bigger step up in voltage to hit the same speeds as Sandy Bridge."
Post
... a processor without a on die gpu, if I'm going to have more heat I want more performance.
After switching all my lights to LED bulbs, its a bit cold in my office. A new, hotter CPU could be just what I need.
"Have you ever thought about just turning off the TV, sitting down with your kids, and hitting them?"
Obama ate a dog.
It's clear in the article, but the headline here sort of implies that the chips run hotter in general, whereas this test is only saying the new chips run hotter when overclocked. From what I can find, when run at the rated voltages/speeds, Ivy Bridge CPUs run at about the same temperature as last gen's CPUs.
10 PRINT CHR$(205.5+RND(1)); : GOTO 10
I'm not going to be overclocking my CPUs, so does it run hotter in spec?
Ivy also requires a much bigger step up in voltage to hit the same speeds as Sandy Bridge.
I get the feeling that they have very weird notions about what constitutes CPU Speed...
Go back in time to the introduction of 32nm and you'll see stories about how the 32nm chips don't overclock as well as chips the mature 45 nm process.
Intel's 22nm process is currently tuned for the lower-clocks used in mobile devices where the early reviews are very favorable to IB. It will take some time for the process to mature and for us to see more overclocking headroom.
Even in its current state, Ivy bridge does overclock fine up to about 4.5Ghz. Where you see issues are at the very highest ends of the OC spectrum where the power density of the 160 mm^2 die becomes an issue compared to the larger 216 mm^2 die of Sandy Bridge. Ivy Bridge does use less power than Sandy... the problem is with sucking the heat out of an increasingly tiny area. Especially for overclockers who usually use discrete graphics and disable the GPU, the activated die area on Ivy Bridge is likely only about 100 - 120 mm^2, which is very hard to keep cool.
Remember a year ago Intel was bragging about their new 3d tri-gate process would be 50% more power efficient: http://www.intel.com/content/www/us/en/silicon-innovations/standards-22nm-3d-tri-gate-transistors-presentation.html.
Comparing the i7 3770K against the 2600K, which is clocked at the same frequency it's only 17% more power efficient: http://www.anandtech.com/show/5771/the-intel-ivy-bridge-core-i7-3770k-review/20
Also you have to bare in mind some of the power saving is due to the DDR controller power gating
Not all of us do overclocking. Subject is misleading.
TFAs don't make this clear. I read around mid-March that the same problem showed up in the engineering samples. I'm curious: with over a month between the discovery and now, wouldn't have it been possible for the engineers to figure out some sort of solution? Or, is that just not possible, with the potential of chip production occurring at the same time as the engineering sample testing?
Certainly, I understand that the problem appears to appear only during overclocking. It's still interesting.
So lemme see here...Intel's new CPU dies are now smaller (good), which makes them less dissipative of heat (bad), so they decide to use worse thermal paste stuff?
Seems legit.
You can hold down the "B" button for continuous firing.
Emphasis on sample
If the retail releases also have this issue, then its newsworthy
So, the "new" processor burns more electricity, runs hotter, and most reviews have it doing marginally better than Sandy Bridge...all for what will be a higher price. Never buy a new framework when it first comes out.
The majority of people do not overclock their CPUs so this is not an issue for the majority.
Jesus was a compassionate social conservative who called individuals to sin no more.
There's only so many tricks that Intel can pull off to keep the power dissipation down. Intelligent power gating, process improvements, optimized circuits, etc... and still, we have WAY more transistors on die that we can actually switch due to power constraints. Think about that for a second. Even ignoring the fact that 90% of the chip is very low activity cache, we cannot utilize all our transistors and get under 100 W/cm^2 (the limit of conventional fan + heatsink cooling). A lot of your chip is going to waste because of power constraints.
And it's just going to get worse. Imagine what the power density will be like when 3D monolithically stacked ICs go into serious production? Multiply your power density times the number of vertical layers!
There's only so much you can do when you're cooling your chip by essentially blowing on it. One of the big innovations is going to have to be improved cooling. Microfluidic channels, which were developed almost THIRTY YEARS ago, might be a good option.
Traditional scaling has been over for a couple generations now (ask any Intel process engineer). Power and process variation are what matter now. And both of them are very, very difficult problems to solve that will get much worse with each generation.
The CPU is 20C hotter, but does the upper limit it can reach safely is also 20C hotter or stay the same?
I too run a little hot when overclocked.
With Sandy Bridge Intel basically said it was normal and wanted to overclock the K series. I have a Corei5 3.3ghz and increased it to 4.4ghz with a single BIOS parameter change with no additional tweaking and no disadvantage at all. Paying for this CPU and not doing it would be stupid.
I think that something that people need to keep in mind is this chip is ~31% smaller. Even with that it's using the same amount of power. I'm not surprised that a byproduct of compressing an area like that is more heat. Also, the chip uses Turbo Boost 2.0. This is automatic overclocking.
Power consumption varies with the square of the voltage (p=v^2/r) while the power consumption varies linearly with the frequency, if it takes signicantly more voltage to over clock then it's no wonder the power usage is so high.
Ivy Bridge is smaller in area than Sandy Bridge. Assuming I got the right numbers from Wikipedia, 160 mm^2 vs 216. That's 74% the area for heat transfer.
uses less power, and is comparable fast. That way, i can save literally hundreds of euro's each year. My PC is fast enough. I'm not even remotely interested in overclocking. All i want is a gaming-PC that uses only 25W power. Ty.
After switching all my lights to LED bulbs, its a bit cold in my office. A new, hotter CPU could be just what I need.
You're confusing temperature and heat. A candle burns hotter than a person, but a person puts out more heat (100W) than a candle (80W). Likewise, Ivy Bridge puts out less heat than Sandy Bridge, even though it's hotter.
(T>t && O(n)--) == sqrt(666)
Looking at the pictures in the Overclockers.com link, you'd probably get better thermal dissipation if had Intel left the heat spreader off, with nothing expect the protective overcoat on the back of the chip.
Actually, I bet modders are going to start cracking the IHS off for that very purpose, in order to directly contact their heatsinks.
so let me get that right. The summary states that they have the same power consumption and a smaller area?
i am a physicist. If you have the same heat flow trough a smaller area then i expect that the higher thermal resistance causes a higher temperature difference.
\Delta T \lambda A t = P
where \Delta T is the temperature difference to ambience, \lambda the thermal conductivity A the are an t the thickness of whatever coupled you to outside, and P the power dissipated.
I am still looking for the mystery. The most interesting question is if the performance is higher.
It's hotter when overclocked. Overclockers love having to run pipes and submerge things. How are you going to justify hauling out the liquid nitrogen if it's running cool?
Meanwhile everyone else is happier that it runs cooler, takes less power, is faster, and even costs less than Sandy Bridge.
This is Win Win, people.
Seriously. What kind of quantum chromodynamics calculations are you simply not getting done today?
I think these days technically ALL of us do overclocking thanks to Turbo Boost and similar such technologies which up the frequency of the processor when only some cores are loaded.
I partially heat my home office with my Pentium 4.
Really. Sometimes I boot my old box just because the room is chilly.
"No fear. No envy. No meanness." Liam Clancy
This brings new meaning to the term "burning bridges". ;-)
The majority of people do not run a Athlon XP without a heatsink. So bursting into flame is not an issue.
Perhaps I'll flip the fan around on the side of the case to blow outwards. Then I'll have the breeze.
I've been trying to fry that P4 for nearly a decade. But. It. Just. Won't. Die.
"No fear. No envy. No meanness." Liam Clancy