Intel's Broadwell Core M-5Y70: The First Benchmarks

[InvalidError]

ARM can either make individual instructions take a bit less time (not much room on that given how rudimentary the instruction set is in the first place) or they improve the pipelining and branch prediction.

Don't forget out-of-order.

A lot of ARM's original power-efficiency fame came from ditching all this single-threaded performance stuff but due to how little software can leverage multi-threading properly, pretty much all ARM designers are going back to focusing on single-threaded performance and putting all that stuff back in.

Considering how kludgy the x86 instruction set is, I used to believe there would never be a half-decent x86 chip under 10W but now Intel lowered the bar to 5W.

 

[krutou]

Now that Apple has lots of cash, maybe they will make an iPad premium that sells for $1000 and put this chip in it?

Whats the point of an x86 processor on iOS?

Might work if it was a touch optimized OSX tablet. Oh wait, Microsoft's been working on that for three years now.

 

[krutou]

So I'm not the only one who thinks that fan-less-ness is not so important for a productivity tablet.
Yes, it is impressive if you can do that, but I'd rather have a standard U series or even M series (the previous M) processor just to have that extra performance.

Read up on Surface Pro 3's mad throttling issues (with fan) and get back to me.

There is great value in reducing power consumption, fan-less-ness is only a small piece of the puzzle.

 

[krutou]

The problem is mullins out performed bay trail pretty badly yet gained zero traction because intel is giving away baytrail for free. Why should AMD or Qualcomm get off their backside and make a superior product if everytime they do it, intel just gives away the inferior product for free?

The following is from Anandtech's Beema/Mullins review:

AMD sees no value in supporting Microsoft's Connected Standby standard at this point, which makes sense given the limited success of Windows 8 tablets. Once again this seems to point to AMD eventually adopting Android for its tablet aspirations.

1. No connect standby means no Windows AMD tablets, end of story.

2. If AMD is competing in the Android space, they much achieve ARM's extremely low price and power consumption, not Intel's.

3. Intel had to drop Atom prices because they're competing with ARM, not AMD.

 

[sonofliberty08]

the quad core ARM chips was fast enough and serve me well for my mobile needs, i don't think i need any so call fast x86 mobile chips on the go at the moment, i only rely on my x64 desktop/workstation for the performance needs.

ARM chips do not run standard x86 applications and the Core-M is intended for premium convertibles/ultrabooks which will usually be purchased by people who do not want to be ball-and-chained to their desktop or do not want to bother with owning a desktop at all.

if u really need to run traditional x86 APPs on the go, the cheap E/A series APU or i3 ultrathin laptop was the better option, x86 for tablets and smartphones are useless, ARM APPs work better for smartphones and tablets, anyone who get the x86 tablets/smartphones are basically computer noobs who only run facebook and youtube most of the times, the pro will always want to hv an desktop/workstation.

Um, no.If Apple released a PROFESSIONAL Macbook pro with ECC memory and a mobile Quadro, I'd happily pay $6,000 for it rather than deal with a tower desktop. The downside would of course be only 2 USB ports (screw you apple) and the expense of thunderbolt for connecting to a drive cage or external GPUs for extra horsepower at the workplace or at home.

that's an bad investment, with that amount of money loaded, you can probably build your personal supercomputer which work hundred times better than that icrap pro!

 

[C0BRA]

I would like to see benchmarks against the latest Krait processors from Qualcom, and also the latest Tegra K1. Why are they comparing against Cortex A9's which are basically phased out?

 

[jimmysmitty]

the quad core ARM chips was fast enough and serve me well for my mobile needs, i don't think i need any so call fast x86 mobile chips on the go at the moment, i only rely on my x64 desktop/workstation for the performance needs.

ARM chips do not run standard x86 applications and the Core-M is intended for premium convertibles/ultrabooks which will usually be purchased by people who do not want to be ball-and-chained to their desktop or do not want to bother with owning a desktop at all.

if u really need to run traditional x86 APPs on the go, the cheap E/A series APU or i3 ultrathin laptop was the better option, x86 for tablets and smartphones are useless, ARM APPs work better for smartphones and tablets, anyone who get the x86 tablets/smartphones are basically computer noobs who only run facebook and youtube most of the times, the pro will always want to hv an desktop/workstation.

Because this will be useable in a smaller environment than those will and that is the point. Small tablets and maybe even bigger phones.

The problem is mullins out performed bay trail pretty badly yet gained zero traction because intel is giving away baytrail for free. Why should AMD or Qualcomm get off their backside and make a superior product if everytime they do it, intel just gives away the inferior product for free? Its the same as what happened 2003-2007, when intel gave away p4s for free to prevent athlon64 of athlon64 fx cpus from gaining market share.

Then of course instead of making money from Mullins no one uses it because baytrail is cheaper (as in free), and then intel comes out with what looks like x3 the performance of baytrail in this core m chip... and the opportunity vanishes for AMD in less then 4 months. sorta hard to play on an even field when chipzilla can break the rules at will to tilt the field in their favor whenever they need to, heck, chipzilla spends something stupid like x2 in R&D then AMD gross' in a year (note, gross, not net).

The numbers i see in this preview should freak AMD out. They no longer are remotely competitive with intel if this is the case; the only sector of the chip business that they made any money in the past 2 years has been in mobile. this part makes their whole mobile lineup irrelevant.

to against this unfair situation, the best way was to boycott all the manufacturer who take intel bribe and go full intel only, like boycott the asus zenfone and fonepad line, to warn them for not to be the puppets of intel giant.

There is no bribe going on. Right now Intel has a chip that can be used in phones, AMD doesn't quite have one. They are working on it but they also don't have as good of a process node as Intel.

I am sure if AMD does then Asus will load up a phone with it. They have Transformer pads with Intel, NVidia and ARM based chips currently.

ARM can either make individual instructions take a bit less time (not much room on that given how rudimentary the instruction set is in the first place) or they improve the pipelining and branch prediction.

Don't forget out-of-order.

A lot of ARM's original power-efficiency fame came from ditching all this single-threaded performance stuff but due to how little software can leverage multi-threading properly, pretty much all ARM designers are going back to focusing on single-threaded performance and putting all that stuff back in.

Considering how kludgy the x86 instruction set is, I used to believe there would never be a half-decent x86 chip under 10W but now Intel lowered the bar to 5W.

The thing people don't realize about Intel is that they have been doing this for a very long time (about 40 years) and are very familiar with the instruction set. As well they know more about OoO than ARM which benefits them heavily.

Add in the superior process nodes and they can probably push x86 into a much smaller TDP than people think.

I would like to see benchmarks against the latest Krait processors from Qualcom, and also the latest Tegra K1. Why are they comparing against Cortex A9's which are basically phased out?

The Tegra K1 that is available is based on the A15 which is very similar to the A9. Project Denver is still not out yet, nVidias first 64bit ARM based chip.

As well most current phones are using ARMv7 Cortex A9 based cores with a few using a mix of A9/A15. The next phone to use anything better will be whatever Samsung and HTC throw out in the S6/One M9 which will be ARMv8 64Bit Snapdragons, but both are not set for release until early 2015.

Mostly it is to show that this CP is in a good spot right now vs what is out.