Yea I'm sure that's why they are launching these devices in the winter for the northern hemisphere. Maybe the southern hemisphere will have to wait till July 2015 and along the equator the release is postponed indefinitely.
Because perf variability can be 50% according to Intel in fonction of the device temperature, i guess it was better to launch them on december, but anyway the TDP is temperature dependant, 4.5W is for a heated device that run will run close to 1-1.4GHz.
i use bluestacks now and its performance / implementation on my sp3 leaves a lot to be desired. although to be honest most of the apps i had on my ipad/nexus 7 i have on windows.
25% more TDP for 50% more perfs.??.
http://www.anandtech.com/show/8515/quick-look-at-core-m-5y70-and-llama-mountain
more stuff. i was hoping for something more indepth.
http://www.anandtech.com/show/8515/quick-look-at-core-m-5y70-and-llama-mountain
more stuff. i was hoping for something more indepth.
Yea I'm sure that's why they are launching these devices in the winter for the northern hemisphere. Maybe the southern hemisphere will have to wait till July 2015 and along the equator the release is postponed indefinitely.
You are mistaken if you think PL3 is a new thing. They've had it since Sandy Bridge, its just better on Broadwell.
Same with the 25%. All the figures were there since 2011. Now if you want to spin the data according to how you see it, you can pick and choose I guess.
I dont know who is spinning the facts since intel themselves are saying that perfs can be 50% higher when the device is cold, wich means at least 50% higher frequency is allowed when the system is cool, start counting the necessary increase of voltage and you ll end very far from your 25%.
Besides the power management is not the same, that s not all to talk about PL levels, one should also look at the thresholds between these and said threshold can be modded at will, nowhere it is said that it s totaly similar to SB, indeed the CB bench is run at 2.2-2.3Ghz for the full time given the score, that is 80-100% higher than base frequencies and at probably 250-300% of the base TDP, that s about 10-13W during the run.
Now sure, to run at a sustained ~2.2 GHz under a CPU only load the CPU cores may well be drawing 250-300% of the power that they would under their mixed workload 4.5W TDP allotment. That's the beauty of Intel's implementation. But that 250-300% figure may well only be something around the specified 4.5W TDP.
Actually, probably not at 250-300% of base SoC TDP. Remember that pesky GPU portion of Broadwell that takes up over half the die space? I know, it's convenient to forget about the portion of the 4.5W TDP that graphics takes up when you want to paint a biased picture of how much power the CPU cores are drawing.
Now sure, to run at a sustained ~2.2 GHz under a CPU only load the CPU cores may well be drawing 250-300% of the power that they would under their mixed workload 4.5W TDP allotment. That's the beauty of Intel's implementation. But that 250-300% figure may well only be something around the specified 4.5W TDP.
Before you get too excited, we should note that the scores may not be representative of what the chip can do in a typical device. Intel replaced the back of the reference design with a special piece of machined aluminum that could allow the CPU to maintain higher frequencies than in a conventional chassis.
Emm,have you watched the video??
All you can see is black screens and no actual test running(unless that little box with texture corruption is the test,but the test seems to not run anywhere as long as it needs to run too) and the tablet is mounted on a stand.
The video appears to have no editing as the chap doing the filming has his reflection in the bezel(unless he is very good at being a robot and standing very still with no movement for minutes at a time).
This is what one part of the Ice Storm sequence should look like when running:
https://www.youtube.com/watch?v=3gaL-RGRpz4
I think I am going to wait until an actual website does some proper tests on Core M based computers first.
The 5Y70's turbo is 2.6 Ghz, and to get 110 on Sunspider it pretty much has to be sustaining that. I guess we will have to wait and see how much it cheats to sustain the clock speed.
Edit: For a frame of reference, my Arrendale laptop (520M, turbos to 2.933) gets 160 for Sunspider on IE 11.
http://techreport.com/news/27039/preliminary-core-m-benchmarks-hint-at-broadwell-potentialIntel configured the system and ran the tests itself, so we weren't able to verify the results independently.
The Llama Mountain tablet is likely using a newer Chrome release than any of the other systems, which could give it an edge over the rest of the field.
The GPU perf. of this Core M variant seems to be within ~ 10% of the Core i5 variant in the Surface Pro 3. Naturally this is very impressive given the lower power consumption. But the GPU perf. difference between Core M and Tegra K1 may not be significant with a more GPU-intensive benchmark such as GFXBench 3.0:
Laws of physics are the same for anybody, including intel.
Increasing frequency by 50% will increase comsumption by 50% and we are talking of 50% better perfs so we re assuming perfect scaling , not that i m understimating the initial conditions, then on top of that you have to increase supply voltage to get this frequency being stable, that will yield 150-200% higher TDP, that is 250-300% of the assumed base TDP.
Numbers published by intel show Core M consuming 1.1W for a task where the previous equivalent offering did consume 1.4W, this point to about 30% better perf/watt at low frequencies, at high frequenciers we dont know but it s likely that it will be close to this number , it will consume about 10-11W where HW was consuming 15W, given that it s allowed to go to 15W it will subsequently perform much better by the virtue of the induced higher frequency.
What is convenient to forget is that when the GPU is not used the CPU will be allowed to use thoses spared watts.
Laws of physics are the same for anybody, including intel.
Increasing frequency by 50% will increase comsumption by 50% and we are talking of 50% better perfs so we re assuming perfect scaling , not that i m understimating the initial conditions, then on top of that you have to increase supply voltage to get this frequency being stable, that will yield 150-200% higher TDP, that is 250-300% of the assumed base TDP.
Numbers published by intel show Core M consuming 1.1W for a task where the previous equivalent offering did consume 1.4W, this point to about 30% better perf/watt at low frequencies, at high frequenciers we dont know but it s likely that it will be close to this number , it will consume about 10-11W where HW was consuming 15W, given that it s allowed to go to 15W it will subsequently perform much better by the virtue of the induced higher frequency.
http://techreport.com/news/27039/preliminary-core-m-benchmarks-hint-at-broadwell-potential
Which you seem to be doing.
You are really saying that at the clockspeeds these chips are running at (1-2.5 ghz) it takes 2.5-3x the amount of power to boost the frequency by 50%?
You wont get the said 50% better perfs with 50% better frequency, i used a best case of 50% higher clocks with perfs perfectly scaling.
http://www.hardware.fr/news/13880/intel-lance-core-m-1ers-broadwell-14nm.htmlWhere are you getting this from?
Is that at the same performance level?
I greatly think CPU power consumption has decreased more than you are thinking.
Stunning.
Broadwell must be the most impressive upgrade and silicon that I have ever seen.
Beats every other passive SoC by a factor of 2+: :thumbsup:
Beats Nvidia at its own game, the GPU: :thumbsup:
Because the 4.5W is exactly what is determined by the definition of TDP.
The 15W has nothing to do with TDP. It is turbo.
BTW, it' a bit disturbing that everyone believes a random review site with the 15W typo. Intel only released 3 SKUs, with at most a 4.5W TDP.
IntelUser2000 said:15W is PL3, and its only there for 10ms, which is nothing. PL2 is the Turbo that's most relevant with Cinebench, and can run for few minutes, and that's 25% above TDP. But running even longer than that it will bring it back to PL1, which is TDP.
Graphics performance impressed even more than the CPU numbers. 4.5W Broadwell-Y scores ~55-56k in Ice Storm Graphics, that's twice Surface Pro 3's 15W Haswell-U graphics score (~28k).