What's new

Broadwell Core-M first benchmarks and comparison with SP3

That's interesting. I'm surprised that the 5Y70 in this tablet performs so much better than the i5 or i7 (?) in Anandtech's Surface Pro 3.

Last week I've read that the 5Y70 is supposed to run approx. 10 % slower compared to the i5/i7 U-series while consuming only a third of the energy.

I would like to see if it is only better in these two benchmarks or if it faster in general.
 
Last edited:
That's interesting. I'm surprised that the 5Y70 in this tablet performs so much better than the i5 or i7 (?) in Anantech's Surface Pro 3.

Last week I've read that the 5Y70 is supposed to run approx. 10 % slower compared to the i5/i7 U-series while consuming only a third of the energy.

I would like to see if it is only better in these two benchmarks or if it faster in general.

Yes, I was surprised too, we should not have long too wait for confirmation of these numbers, first 5Y70 machines should be in retail by October. This could be a good news for the ones waiting for an updated Sp3 or Sp4 or even a competing Sp3 'inspired' machine.
 
it's an i5. MSFT did not sample any reviewers an i7.

i assumed core M would be a step down in performance. this is simply stunning and Surface Pro 4 will be a killer. maybe they will call it "Surface Pro Air" as it could probably get down to a pound or maybe 1.25...or bigger battery! the chassis for the chip is soooo much smaller, i'm amazed.
 
If Microsoft is smart they'll launch the next Surface along with Windows 9 based on these new processors.
 
Seems to be slightly better - a sunspider test is hardly a good representation of "performance" IMO (at least in the way I use the SP).

"Yes, it's unlikely it was 4.5W since most Intel CPUs can run at 125% or more of their official TDP for some time. Also as others noted it is way too fast to be true on SunSpider, so this is obviously due to the usual browser differences and tricks (unlike the other results the 5Y50 scores are provided by Intel). People will be quite disappointed when the actual CPUs become available as they of course won't be twice as fast as Surface Pro!"

The 3D mark test is a 10% difference. I would say that's underwhelming for a gfx upgrade that was supposedly 40% better.

To play devil's advocate the SP4 will definitely be better than the SP3 though.
 
I'm surprised the chip is up for release in the Lenovo Helix in October. I was also under the impression that the M Broadwell was not competitive in performance with the i5-4300U. It seems it is. Considering that it draws 1/3 the power, it is a big step forward, in size, heat production (no fan) and therefor also battery life.

The SP3 has been on sale in Australia for 13 days...not a lucky number maybe.

It surely can't be that long before Microsoft update the SP3?

That is the question.

It also means that there may be some amazing competition for the Surface coming our way very soon from other manufacturers.
 
Seems to be slightly better - a sunspider test is hardly a good representation of "performance" IMO (at least in the way I use the SP).

"Yes, it's unlikely it was 4.5W since most Intel CPUs can run at 125% or more of their official TDP for some time. Also as others noted it is way too fast to be true on SunSpider, so this is obviously due to the usual browser differences and tricks (unlike the other results the 5Y50 scores are provided by Intel). People will be quite disappointed when the actual CPUs become available as they of course won't be twice as fast as Surface Pro!"

The 3D mark test is a 10% difference. I would say that's underwhelming for a gfx upgrade that was supposedly 40% better.

To play devil's advocate the SP4 will definitely be better than the SP3 though.
I believe the 40% number is an in family figure meaning the Y series sees a 40% increase and the u series sees a 40% increase but there's not a direct correlation between Y & U thus you get a 10% increase over a Haswell U but also a drop in TDP from 15W to 4.5w. or 70% power reduction with 10% performance gain.
 
Back
Top