Watch out Intel, here comes Apple's A9X!

[DocSwag]

A recent review of the iPad Pro shows Apple's A9X Chip challenging Intel's Core M lineup.

As well, here is an article from ExtremeTech with a bit more information http://www.extremetech.com/mobile/221881-apples-a9x-goes-head-to-head-against-intels-core-m-in-arm-x86-grudge-match

Most of you have probably heard about the iPad Pro that Apple launched not too long ago (if you hadn't your cave must be quite cozy). As we all knew Apple's A9X Chip had incredible performance for a mobile CPU. Anandtech has gone ahead and reviewed the iPad Pro, and along with it checked out a comparison of the A9X vs. the Intel Core M lineup.

 

 

As this is a fairly dense lineup I’m not going to call out every figure, but let’s focus on a few key areas. First, on A9X versus the Core M-5Y31 (MacBook), the advantage flips between each device as each test hits upon different strengths and weaknesses of each CPU’s architecture. Overall each device wins half of the benchmarks, however the Core M powered MacBook wins by a larger average margin. In other words, the iPad Pro is competitive with the MacBook depending on the test, however on average it ends up trailing in performance.

The A9X can obviously fight against the Broadwell Core Ms, though it seems the Core M still beats the A9X by a small margin. However, this is still something of note. As well, the A9X seems to use less than 5 watts of power.

 

 

It’s evident from this test and some back of the envelope calculation that total device TDP excluding display power is roughly 5W, which is about right given the size of the device. This suggests that the A9X can be directly compared to Intel’s Core M in both performance and power, for better or for worse. 

The A9X seems to trail the Broadwell low-end Core Ms by a small amount, and trails higher end Core Ms as well as Skylake Core Ms by a greater amount, but this is definitely something we should notice. Apple has been improving IPC by quite a lot in recent years, while Intel has only been improving it by about 5-10% each year. A few years ago Apple SOCs were nowhere near Intel CPU IPC, but now this has changed considerably. The A9X is already coming quite close to Intel, and it is quite possible that the SOC going into the iPhone 7 and iPad Air 4 could be on par with Intel Core Ms. The generation after that, Apple could potentially start having their SOCs have higher IPC than Intel ones. If this happens, it is possible Apple could swap out their Macbook CPU for a A10X or A11X. It is not likely they will replace Macbook Air or Macbook Pro CPUs, but it is possible the Macbook could get an upgrade.

[DXMember]

good luck on running x86 on that thing

Intel has already secured it's position in the 80s

[Menzenski]

I could see future macbooks using an Apple design.  Apple is poised to become a low-wattage cpu competitor, which is exciting.

[Curufinwe_wins]

Sigh... Can people not keep doing this ARM vs x86 comparisons? They don't work.

 

Also Core M is super variable on manufacturer, Apple is known to do stupid ass shit resulting in really poopy load performance on their laptops.

 

Plus -U is a huge jump up from core M.

 

5W TDP isn't very impressive considering that's on the same configuration level as the i5 U series...

[DocSwag]

Sigh... Can people not keep doing this ARM vs x86 comparisons? They don't work.

 

Also Core M is super variable on manufacturer, Apple is known to do stupid ass shit resulting in really poopy load performance on their laptops.

 

Plus -U is a huge jump up from core M.

 

5W TDP isn't very impressive considering that's on the same configuration level as the i5 U series...

U is supposed to be the 15 watt chips. Core M is the 4.5 Watt ones.

[givingtnt]

"watch out intel"

lol that statement is as laughable as 

"source from WCCFTECH"

[DocSwag]

"watch out intel"

lol that statement is as laughable as 

"source from WCCFTECH"

It is possible that if Apple decided to use its own CPU in the Macbook Intel would pay them to not do that. Intel probably has too many resources to let Apple do that, though you never know.

[givingtnt]

It is possible that if Apple decided to use its own CPU in the Macbook Intel would pay them to not do that. Intel probably has too many resources to let Apple do that, though you never know.

if google is ready to pay 1b for a search engine

you bet intel will pay for that cpu

[Nineshadow]

 

With the iPad Pro, Apple has created a tablet with more power than ever before. But there's no magic or witchcraft to this feat; it just made a bigger tablet. The larger the object, the more room to dissipate heat, and the more space for a bigger battery. It's basic physics, and the iPad Pro takes full advantage. It contains a 38.5Wh battery. That's 40 percent larger than the battery inside the iPad Air 2, and about the same as the company's 11-inch MacBook Air and 12-inch MacBook, not to mention Microsoft's Surface Pro 4.

 

It's often vaunted that ARM-based chips are more power efficient than those based on Intel's x86. That's just not true. ARM and x86 are simply instruction sets (RISC and CISC, respectively). There's nothing about either set that makes one or the other more efficient. And despite ARM chips like Apple's typically being ultra-low power, the A9X is clearly not. Its performance on various sites' battery tests show comparable endurance to the 12-inch MacBook. Ars Technica's 200 nits WiFi browsing test, for example, shows the iPad Pro lasting three hours less than a MacBook. A WebGL test from the same site shows the iPad Pro outlasting the MacBook by two and a half hours. Of course, the iPad Pro's screen is slightly larger and denser than the MacBook's, and the two run completely different operating systems. The point isn't to discern which is more efficient, but merely to say they have similar battery sizes, similar endurance, and therefore similar efficiency.

 

But what of the benchmark tests that show the iPad Pro outperforming Intel's Core M processor, and even coming close to Intel's MacBook Pro range? Don't believe them. Patrick Moorhead, a highly respected analyst with a strong background in chips, urges caution, especially when it comes to comparing GeekBench numbers, as many have. "GeekBench is a synthetic, mobile benchmark," Moorhead tells Engadget. "The benchmark code is more like mobile application code than it is desktop code." Using GeekBench to test A9X versus Intel chips is "like comparing apples and oranges or an SUV with a sedan on the straight-away," he explains.

 

One area where the A9X has advanced massively over previous Apple chips is in graphics performance. "This has nothing to do with ARM and everything to do with PowerVR and Apple's implementation of PowerVR's IP," Moorhead clarifies. Imagination Technologies (that makes PowerVR) is a chip and graphics company that develops architectures and licenses its IP out to many manufacturers. It's not ARM; it's not x86. Intel licenses PowerVR tech, and straight-up features PowerVR designs in its Atom line.

 

What Apple has done, then, is create a powerful tablet chip, one with a processor that addresses the ARM instruction set and a graphics component that utilizes PowerVR technology. It's not a leap forward, and it's not out of nowhere; it behaves and performs exactly as a chip with as high a clock rate and as large a power draw as the A9X should do.

The idea that Macs could be running ARM chips has been around for a long time. Microsoft launched Windows RT, a version of its OS that works with ARM chips, because it wanted manufacturers to create devices that could compete with the iPad. It didn't work, mostly because of Window's reliance on legacy applications, but also because Intel started taking its low-power programs more seriously, and poured money into them. Its chips caught up fast. All the low-power Surfaces now use Intel x86 chips, rather than the Nvidia ARM chips they launched with.

Also , there were rumours that Intel almost managed to convince Apple to put an Intel CPU in their iPad Pro.

[Guest]

"watch out Intel"

so misleading

cause Intel can be taken down 

lmfao

[DXMember]

if google is ready to pay 1b for a search engine

you bet intel will pay for that cpu

you wot?

unless they run a spyware on the chip why would they muni to apple for them to use Intel chips

google on the otherhand get's their spyware running on ios, how would Intel benefit? unless marketing.... I guess I can imagine some add for a prebuilt going like - "With a Mac DNA" // "Intel inside, same chip that powers Mac" or smbllcrpp like that

[DaltonM]

Doesn't matter, they processors will still be in apple products, which always cost WAY more than something with a Core M equivalent should cost. 

[wpirobotbuilder]

Are the A series CPUs Unix compatable? That's what makes modern Mac processors so great.

[Menzenski]

"watch out Intel"

so misleading

cause Intel can be taken down 

lmfao

 

Lets say Apple develops an ARM compatible version of OSX.  Then they can use their own CPU designs.  Intel then loses business from Apple, who is kind of a big player in the computer world.

 

It's not that far fetched.

[Nineshadow]

if google is ready to pay 1b for a search engine

you bet intel will pay for that cpu

Except they will need to use an x86-64 CPU , and other than using a CPU from AMD , which at the current time makes no sense whatsoever , they will obviously need to get a license. Otherwise , using an ARM CPU on macbook pros , on actual productivity machines? It would be a disaster. Still , people would still buy them , since we're talking about Apple here . On just a Macbook? Maybe...? But then, the Macbook would be just an iPad Pro with a really nice keyboard so I don't see the point. Also, they would have to port OS X  to ARM , which would be a lot of hassle.

[Guest]

Lets say Apple develops an ARM compatible version of OSX.  Then they can use their own CPU designs.  Intel then loses business from Apple, who is kind of a big player in the computer world.

 

It's not that far fetched.

remember all the programs that would have to switch over from x86 

Its not reasonable to think that would happen.

[Nineshadow]

Lets say Apple develops an ARM compatible version of OSX.  Then they can use their own CPU designs.  Intel then loses business from Apple, who is kind of a big player in the computer world.

 

It's not that far fetched.

I think we'd rather see an iPad with an Intel SoC before a Macbook with an ARM SoC.

[Curufinwe_wins]

U is supposed to be the 15 watt chips. Core M is the 4.5 Watt ones.

That isn't actually true.

 

1. Only the i7 comes close to 15W in practice

http://ark.intel.com/products/88192/Intel-Core-i7-6600U-Processor-4M-Cache-up-to-3_40-GHz

 

2. Many -U processors ship with down-configured parts (all -U can be tuned as low as 7.5W or lower), and none ship with up-configured parts

 

3. While the entire lineup claims the "15W TDP", it should be brutally apparent that if a 3.4 GHz Turbo part resides within that TDP then a 2.3 Ghz i3-6100U comes NO WHERE CLOSE to that power consumption. This is the same issue as how all non-k i3/i5/i7 bskylakes are listed at 65W even though the actual power consumption for the parts vary wildly (with even a 6700 rarely touching the 65W envelop under "100% load").

 

http://ark.intel.com/products/88180/Intel-Core-i3-6100U-Processor-3M-Cache-2_30-GHz

[Menzenski]

remember all the programs that would have to switch over from x86 

Its not reasonable to think that would happen.

 

I don't disagree, but I would say that a potential low end macbook could get by using the App Store, with the higher end models retaining core m.  Pretty much just an iPad pro with a permanent keyboard and proper file explorer.

[AlexGoesHigh]

LOL -Intel

 

Either way, the A9X being almost equal to a Core M would be somewhat impressive if the Apple chips used less power, but since its the almost the same TDP as a Core M then is not impressive at all.

Except they will need to use an x86-64 CPU , and other than using a CPU from AMD , which at the current time makes no sense whatsoever , they will obviously need to get a license. Otherwise , using an ARM CPU on macbook pros , on actual productivity machines? It would be a disaster. Still , people would still buy them , since we're talking about Apple here . On just a Macbook? Maybe...? But then, the Macbook would be just an iPad Pro with a really nice keyboard so I don't see the point. Also, they would have to port OS X  to ARM , which would be a lot of hassle.

Well they went through the trouble of porting OS X to x86 from IBM's chip design (which i can't remember the name of) so they if they are very serious about switching to their own ARM designs, they will go through all that problem again.

[Mew]

Sigh... Can people not keep doing this ARM vs x86 comparisons? They don't work.

Also Core M is super variable on manufacturer, Apple is known to do stupid ass shit resulting in really poopy load performance on their laptops.

Plus -U is a huge jump up from core M.

5W TDP isn't very impressive considering that's on the same configuration level as the i5 U series...

If you even bothered to read the article, you'd know that they both ran the same test using the same instruction set.

Moving on, our other lower-level benchmark for this review is SPECint2006. Developed by the Standard Performance Evaluation Corporation, SPECint2006 is the integer component of their larger SPEC CPU 2006 benchmark. As was the case with SPEC CPU 2000 before it, SPEC CPU 2006 is designed by a committee of technology firms to offer a consistent and meaningful cross-platform benchmark that can compare systems of different performance levels and architectures. Among cross-platform benchmarks SPEC CPU is generally held in high regard, and while it is but one collection of benchmarks and like all benchmarks should not be taken as the be-all end-all of benchmarks on its own, it provides us with a very important look at CPU performance that we otherwise cannot get.

SPECint2006 is the successor to the SPECint2000 test we’ve been using periodically for the last couple of years now. Initially released in 2006, SPECint2006 is still SPEC’s current-generation CPU integer benchmark. We’ve wanted to switch to SPECint2006 for some time now, but have been held back by the overall low performance of tablet SoCs, which lacked the speed and memory to run SPECint2006 and to do so in a reasonable amount of time. However now thanks to the greater performance and greater memory of A9X, we’re finally able to run SPEC’s current-generation CPU benchmark on a tablet.

SPECint2006 is composed of 12 sub-benchmarks, testing a wide variety of scenarios from video compression to PERL execution to AI. This is a non-graphical benchmark and I believe it’s reasonable to argue that the benchmark set itself leans towards server high performance computing/workstation use cases, but with that said even if it’s not a perfect fit for tablet use cases it offers a lot of real-world tests that give us a good variety of different workloads to benchmark CPUs with. SPECint2006 scores are in turn reported as a ratio, measuring how many times faster a tested system is against the SPEC reference system, a 1997 Sun Ultrasparc Ultra Enterprise 2 server, which is based around a 296 MHz UltraSPARC II CPU.

They also compared A9x to 2 zenbooks, a broadwell and a skylake one. Core U is a 15w top chip and core m is a 4.5w "overclockable" to 6w.

Edit: I should also note that Turbo speeds are never meant to be sustained. IIRC intel once said that you should only see turbo speeds if the right conditions are met-available tdp and power for short periods of time.

[Mew]

LOL -Intel

Either way, the A9X being almost equal to a Core M would be somewhat impressive if the Apple chips used less power, but since its the almost the same TDP as a Core M then is not impressive at all.

Well they went through the trouble of porting OS X to x86 from IBM's chip design (which i can't remember the name of) so they if they are very serious about switching to their own ARM designs, they will go through all that problem again.

Tdp is a measurement of heat output.

[Curufinwe_wins]

Tdp is a measurement of heat output.

No it isn't...

 

Jesus

 

If you even bothered to read the article, you'd know that they both ran the same test using the same instruction set.

And hence all the cases where x86 optimized code was present it obliterated, and the other cases ARM squeaked wins... AKA still an flaws of x86 vs ARM article...

[Coaxialgamer]

Apple will not use ARM based SoC's in their next macbooks , simply because of how OSX runs on x86 , and making a custom ARM version would either require making a totally new OS for macbooks , or split the market in half and have windows RT all over again.

[Coaxialgamer]

Tdp is a measurement of heat output.

Yes , but TDP is often synonymous with power consumption