Analyzing Intel Core M Performance: How 5Y10 can beat 5Y71 & the OEMs' Dilemma
by Brett Howse & Ian Cutress on April 8, 2015 8:00 AM EST3DMark Cloud Gate Results
3DMark Cloud Gate is a benchmark aimed at notebooks and home PCs, and is quite a bit less demanding. It has a DirectX 11 engine but is limited to Direct3D feature level 10, and is compatible with DirectX 10 hardware. The overall run is about three minutes.
There is not much more to be said about the Core i5 at this point. It does an admirable job keeping the GPU frequency almost flat during this benchmark. You can clearly see the Dell Venue 11 Pro ramping up frequencies on the CPU, which cause temperature spikes when this happens. When it throttles the CPU on this workload, it does free up enough thermal room to allow the GPU frequency to be fairly strong. We see a lot of throttling on the ASUS as well, but not quite as pronounced. Once again, on the physics test the GPU is pushed down in frequency to give the CPU more room. The Yoga 3 Pro tries its best but is once again limited by a much lower SoC temperature set point.
On the CPU side, we have a very similar situation to the Sky Diver benchmark. The ASUS once again keeps a higher average CPU frequency than all of the other Core M devices in this test. The Venue 11 is close though.
On the GPU side, the Zenbook and Venue 11 Pro are basically tied. The shorter and less demanding workload lets the Dell keep up despite not having as good of a cooling solution. But, averages are just averages. Clearly the ASUS keeps a substantially higher GPU frequency for much of this test, as is seen in the graph.
The SoC temperatures are actually quite high on the Zenbook in this test, with it coming close to the Venue 11 Pro, but the cooling system clearly is more efficient since the change in temperature on the ASUS is much more gradual than the spikes seen in the Venue 11 Pro. The Yoga 3 Pro tries to stay around 65°C but near the end the temperature does go above their target.
The overall benchmark results for this test are very similar to the previous 3DMark test. The ASUS comes in very close to the Dell Latitude with its Core i5, and the other devices fall back quite a ways. Long sustained GPU workloads are very difficult for both of the 5Y71 devices to handle.
Facebook
Twitter
RSS
110 Comments
View All Comments
zepi - Wednesday, April 8, 2015 - link
Surface pro 3 is ~50% thicker than iPad Air 2, weights ~50% more, has active cooling and still has poorer performance than Surface Pro 2.From my point of view Surface pro 3 proves that Haswell-U can't power ultra-thin x86 tablets.
lilmoe - Wednesday, April 8, 2015 - link
Didn't know the iPad was an ultra-thin x86 tablet that replace your laptop. Good to know, thanks.I get that the iPad has a huge fan base, I really do. But would you guys please stop comparing it to real PCs in tablet form already??
zepi - Thursday, April 9, 2015 - link
Central argument proposed was that SP3 somehow proves that Haswell-U can power ultra-thin X86 tablets. There were no mentions about Windows or OSX compatibility in original statement.Keyword is Tablet. x86, ultra-thin etc. are describe terms. You don't need to go far and see that the statement is clearly false. Ultra-thin in context of tablets means these days that thickness of the device should to be somewhere around 6-7mm. SP3 is 9mm. I picked iPad Air 2, because it is the most well known of competitors. We could just as well use Dell Venue 8. Ipad thickness is 6.1 and Dell is 6mm thick. Later is even x86 and runs windows
Weight was another thing. Naturally comparing weight to Venue 8 makes very little sense since SP3 has over twice the total screen area of Venue 8 so I compare it with iPad air 2, which has the biggest screen area of the most well known tablets in the market. Most certainly, there are some less well known 12" models, but they are not widely spread and have hardly any market penetration.
I cannot see how SP3 would prove that 15w TDP allows for compact tablet designs. SP3 is already thermally limited and mostly proves to me that in order to reach smaller and thinner designs, lower power SOC's are necessary. From my point of view SP3 is full computer which offers decent (though arguably best in class) tablet usability in addition of being dockable general purpose PC-computer.
digiguy - Wednesday, April 8, 2015 - link
come on, you change the comparison in the same sentence, SP3 is thinner and lighter than SP2, and has has higher res screen. As for ipad air, try to run Windows on it....Jaybus - Wednesday, April 8, 2015 - link
Or even if it ran OSX. The iPad is a giant iPhone. If it ran OSX, then we could compare it to SP3. For now, iPad can only be compared to Android tablets.xthetenth - Wednesday, April 8, 2015 - link
Being thicker than slower devices and slower than thicker devices only proves that it fits between them on a size/performance scale and does nothing to show that it's not a good device.ppi - Wednesday, April 8, 2015 - link
My desktop is also thicker than iPaid Air2, weighs more, has active cooling and certainly eats more power. So ... ?You have to realize, that this 4.5W chip actually has performance that is in league with 15W chip. For many ultrabook/2-in-1 use cases ideal chip. And read the Yoga3 review, where on CPU-bound benchmarks, Core-M runs circles around A8X.
frozentundra123456 - Wednesday, April 8, 2015 - link
I agree with some of the other posters. The problem is the price of these devices for the performance. I can see them for say business use, where the company is paying, use is light, and mobility is important (say for a sales rep who travels a lot), but otherwise, I cant see Joe Average Consumer paying north of 1000 for these when you can get similar perrformance for less in a 350.00 conventional laptop or less performance, but still decent in a 100 to 300 dollar atom device.xthetenth - Wednesday, April 8, 2015 - link
The ASUS is in the 700 dollar range and avoids a great many other compromises cheaper devices would make. It fits into the price/quality scale very nicely.zepi - Wednesday, April 8, 2015 - link
From gaming / usability perspective the average-results do not necessarily tell enough.Ie. does the usage experience of certain devices suffer because GPU / CPU throttles too much under certain loads?
Are the bottom 10% frametimes so horrendous on throttling devices that DOTA-gaming is practically out of question despite relatively small difference in average frame rates?