The Intel Atom Thread

Page 32 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Khato

Golden Member
Jul 15, 2001
1,248
321
136
TR says that a single core can pump 1W according
to their JS number , wich is a single threaded task ,
hence 4 cores can use 4W on peaks , far from
Anand s number wich should be of equal amplitude
given that CB is FP heavy and FP ops are power hungry
tasks.

Quite true. But it's also the case that we don't have benchmark results for Baytrail-T running a multi-core workload while drawing 4+ watts. We only have benchmark results of multi-core workloads while consuming roughly 2.6 watts. Heh, and this is one of the reasons why TDP is a difficult figure to specify - sure it might be possible to hit a certain value, eg 4 watts, but if the power control logic doesn't let the SoC run in any state that goes beyond 3 watts then what's the correct TDP number to report?

Which pretty much mirrors what we see in the benchmark results - the multi-threaded cinebench results for Baytrail appear to be about 90% of what we'd expect to see if frequency remained constant. Of course that's assuming that the single-threaded result was running at a frequency that's near the maximum and requires an extra 0.1-0.15 volts (if the design had more frequency headroom then we'd likely see some of the many higher power parts take advantage of it.) Since yeah, running at 90% frequency and dropping from 1.1V to 1V would already bring 4W down to 3W.
 

blackened23

Diamond Member
Jul 26, 2011
8,548
2
0
Only uninformed sheep (i.e standard consumers) still buy shiny shiny fruit products or Android, not realizing that Windows tablets give them vastly more versatility. And of course, sheep want toaster appliances. Now that ARM has woken Intel up, things will be vastly different within a year or two.

You're ridiculous. As a preface, I think the BT-T is a great product and Intel needs that to compete - a compelling product. It isn't perfect, qualcomm is the one to beat, but BT-T is a great step forward and has the best CPU performance and has given ARM SOC makers legitimate reason to worry about the future (especially with Airmont having integrated LTE and better graphics). BT-T isn't perfect but it's a compelling product, just what intel needed.

In that respect I agree with you. Windows is also highly desirable to me, but I can also see the like for android and iOS. They're great for basic use. iOS is even better than android, IMO.

That being said, you're being ridiculous with the "sheep" comment. The iPad sells well because it's a great product. Many Android tablets are also great products. I agree that Windows is also desirable, as I find myself wanting more out of my tablet and Windows can give that to me. But to relegate everything else to "sheep" is the stupidest thing i've read here in some time. Whether you want to admit it or not, there are compelling products in both of those spaces (iOS and Android).

If you want to argue in favor of Windows, do it with better substance than "sheep". Christ. And i'm saying this as someone who agrees with many of your points - I can see the clear differentiation between iOS/android and Windows. I also like the Windows platform - That doesn't mean iOS / android are bad - fact of the matter is, they get the job done for most folks who aren't power users.
 
Last edited:

Imouto

Golden Member
Jul 6, 2011
1,241
2
81
What, when tablets barely existed and the whole mobile thing was only nascent? That is your best response?

Yeah, the very same time when Windows was more versatile than mobile OSes. Not the case anymore since Windows is painfully awkward in a touch screen device.
 

Enigmoid

Platinum Member
Sep 27, 2012
2,907
31
91
Yeah that 75W peak of the A4-4000 is pretty high. No disagreements here. And folks were saying the 5000 could fit in a tablet, guess not. Maybe that's what the OEMs knew that we didn't.



Keep moving them goalposts, son! Comparing the desktop part which is intended to use more power (celeron J1750) to the tablet part which isn't tested (Bay Trail-T).

What I think is amazing is look at how small the delta is between load and idle (last part of graph). Then factor out the RAM and SSD to see how much power the CPU is using. Baytrail is SIPPING power there (though again the PSU introduces inaccuracies), really the CPU is only using a couple watts. The ~20w figure is complete garbage though. My whole laptop, including a 15.6" 1080p display uses less power browsing these forums measured before BEFORE the power brick (18-19w).

Quite true. But it's also the case that we don't have benchmark results for Baytrail-T running a multi-core workload while drawing 4+ watts. We only have benchmark results of multi-core workloads while consuming roughly 2.6 watts. Heh, and this is one of the reasons why TDP is a difficult figure to specify - sure it might be possible to hit a certain value, eg 4 watts, but if the power control logic doesn't let the SoC run in any state that goes beyond 3 watts then what's the correct TDP number to report?

Which pretty much mirrors what we see in the benchmark results - the multi-threaded cinebench results for Baytrail appear to be about 90% of what we'd expect to see if frequency remained constant. Of course that's assuming that the single-threaded result was running at a frequency that's near the maximum and requires an extra 0.1-0.15 volts (if the design had more frequency headroom then we'd likely see some of the many higher power parts take advantage of it.) Since yeah, running at 90% frequency and dropping from 1.1V to 1V would already bring 4W down to 3W.


I don't think baytrail is dropping any frequency. I just think the scaling is bad.





To within margin of error, scaling is similar. And kabini runs at the same speed in that single and multi test.

TR says that a single core can pump 1W according
to their JS number , wich is a single threaded task ,
hence 4 cores can use 4W on peaks , far from
Anand s number wich should be of equal amplitude
given that CB is FP heavy and FP ops are power hungry
tasks.



Looking at AMD's slide there Intel has a clear advantage. If intel can run a 2.4 ghz silvermont core on 1w and amd can run a 1 ghz jaguar core on 1 w and a 1.4 ghz jaguar core on 2w then amd's efficiency is so bad that silvermont will utterly dominate in tablets.
 

mikk

Diamond Member
May 15, 2012
4,245
2,299
136
I dont think so, the celeron j1750 is a desktop sku with 792Mhz gpu...

http://liliputing.com/2013/07/leake...eron-and-pentium-chips-use-less-than-10w.html


J1750 GPU can boost its GPU up to 750 Mhz. Your link is wrong. Only the J1850 and J2850 can boost up to 792 Mhz.

Comsumption is high , yet some people by there think
that the same chip with double the cores and as high
frequency will consume three time less...


These are system power results. It doesn't say much about the SoC power requirements. At least we would need an idle load delta but they failed doing it.
 

escrow4

Diamond Member
Feb 4, 2013
3,339
122
106
Yeah, the very same time when Windows was more versatile than mobile OSes. Not the case anymore since Windows is painfully awkward in a touch screen device.

Says one who has never used a Windows 8 tablet.
 

escrow4

Diamond Member
Feb 4, 2013
3,339
122
106
You're ridiculous. <snip>
That being said, you're being ridiculous with the "sheep" comment. The iPad sells well because it's a great product. Many Android tablets are also great products. I agree that Windows is also desirable, as I find myself wanting more out of my tablet and Windows can give that to me. But to relegate everything else to "sheep" is the stupidest thing i've read here in some time. Whether you want to admit it or not, there are compelling products in both of those spaces (iOS and Android).

They are sheep. New Apple product, big line around the block. BAAA BAAA BAAA.
 

Imouto

Golden Member
Jul 6, 2011
1,241
2
81
Dude, Bay Trail benchmark reign lasted barely 1 week and lost to an ARM custom SoC like the A7. A damn 2 core SoC and the one for the next iPad remains to be seen.

What was all this fuss about, seriously?
 

USER8000

Golden Member
Jun 23, 2012
1,542
780
136
The thing is that both Android and iOS are evolving too,and I personally think MS really needs to think about reducing licensing costs to drive lower cost laptops and tablets. The lower down you go the greater the percentage of the entire device is the OS cost. History does have a tendency to repeat itself. MS managed to knock the wind out of Apple in the PC market decades ago,by selling Windows for a relatively low cost and saturating the market.

The problem is that the newer OSes might end starting to do the same thing and start making inroads into basically productivity applications like word processing,spreadsheets,etc as software support gets better.

I can see even more and more general PC users,using things like Google Docs,etc.
 

Sweepr

Diamond Member
May 12, 2006
5,148
1,143
131
Seriously, what is all the fuss about Intel delivering best in class x86 CPU performance at high (Core line) and now low (tablet oriented Atom) power levels?
 
Last edited:

Sweepr

Diamond Member
May 12, 2006
5,148
1,143
131

Bay Trail was faster in 2 tests, A7 in 1 (Javascript/HTML5 benchies only). Still, impressive for a phone chip. A6X was only slightly faster than the A6 on the CPU side, so dont expect a significant boost on the new iPad (vs the iPhone 5S, except on the GPU side).

Surprisingly Bay Trail's criticized GPU compares favourably to the mighty PowerVR Rogue GPU inside the 5S:





The new iPad should beat both and S800/Tegra 4-based tablets though.
 
Last edited:

liahos1

Senior member
Aug 28, 2013
573
45
91
this is good for intel. they are going to be competitive against a53/a57 cores next year with silvermonth wwhile smoking the a15s and s800s that are only starting to trickle to market. they'll be iterating on airmont at 14nm and should pull ahead yet again.
 
Last edited:

mavere

Member
Mar 2, 2005
188
4
81
Surprisingly Bay Trail's criticized GPU compares favourably to the mighty PowerVR Rogue GPU inside the 5S:

You linked to the overall score, not the GPU scores.

Anand suggested that there could have been a bug within 3DMark's CPU tests on A7 or iOS7. The individual 3DMark tests demonstrated CPU performance that is suspiciously equal to the last generation, which contradicts every single other test as well as even the roughest analysis of the A7.

It'd be nice if a 3DMark developer could assess Anand's thoughts.
 

Enigmoid

Platinum Member
Sep 27, 2012
2,907
31
91
Lukewarm.

Screen is still to small. 1 GB RAM.

CPU performance gains are nice but generally competitive with S800. Used to be that apple was a year ahead of everyone in regards to gpu, now they are barely playing catchup.
 

Sweepr

Diamond Member
May 12, 2006
5,148
1,143
131
You linked to the overall score, not the GPU scores.

Anand suggested that there could have been a bug within 3DMark's CPU tests on A7 or iOS7. The individual 3DMark tests demonstrated CPU performance equal to the last generation, which contradicts every single other test as well as even the roughest analysis of the A7.

It'd be nice if a 3DMark developer could assess Anand's thoughts.

Just saw it. Slightly better GPU performance than the S800, nice. I'm expecting slightly better CPU performance with A7X (maybe 1.4 vs A7's 1.3GHz just like A6X/A6) and a ~50% faster GPU, possibly matching X360/PS3's graphics performance.
Airmont should be safe with a typical ~5% ''Intel tick'' IPC bump + higher base-clock/turbo clock but it definitely has a lot to improve on the GPU side. Hopefully Intel's new gfx architecture (Gen 8) and a lot more EUs than Bay Trail puts Airmont in a better position here next year.
 
Last edited:

USER8000

Golden Member
Jun 23, 2012
1,542
780
136
The A7 is better than I expected,especially considering it is a phone chip(and not a tablet one). With Apple now using TSMC,I do wonder if it means the A8(or whatever it is called) will be on 20NM at the end of next year??

All these battles between the big players,are no doubt going to be a win-win situation for the consumer(hopefully).
 

sequoia464

Senior member
Feb 12, 2003
870
0
71
Yeah, the very same time when Windows was more versatile than mobile OSes. Not the case anymore since Windows is painfully awkward in a touch screen device.

Not awkward at all. Writing this using a W8 tablet. Also have a couple of android tablets and an iPad.

Prefer the W8 tablet to the others, wouldn't object to a higher resolution screen though.

Suppose it boils down to user preference.
 

raghu78

Diamond Member
Aug 23, 2012
4,093
1,475
136
Apple's ARM v8 Cyclone core is really a mobile powerhouse. huge improvements to the CPU core - execution units, caches, memory controller, branch prediction, full 128 bit FPU, AES and SHA1 support. btw Silvermont is still on a 64 bit FPU. the A7 chip is shipping in high volume 6 months before Merrifield is available for Android smartphones. Even at 1.3 Ghz this chip is kicking some serious ass. I am waiting to see the ipad version A7X.

http://anandtech.com/show/7335/the-iphone-5s-review

Apple has beaten Intel at its own game. Apple is shipping products in high volume with the A7 chip with an optimized 64 bit iOS and 64 bit apps. This is the advantage of a completely vertically integrated design company. Nobody including Intel can match that. Apple's OS and apps are ready for 64 bit mobile computing while the competition is atleast 6 - 12 months away. so much for Intel's unassailable lead. gone within a week. :whiste:
 

SPBHM

Diamond Member
Sep 12, 2012
5,059
413
126
A7 looks overpowered for a phone imo, but should be great for the ipad.

it's really good, and makes Bay Trail looks far less impressive for sure...

still, you can't run Windows with it.
 

tempestglen

Member
Dec 5, 2012
88
17
71
The A7 is better than I expected,especially considering it is a phone chip(and not a tablet one). With Apple now using TSMC,I do wonder if it means the A8(or whatever it is called) will be on 20NM at the end of next year??

All these battles between the big players,are no doubt going to be a win-win situation for the consumer(hopefully).

 

raghu78

Diamond Member
Aug 23, 2012
4,093
1,475
136
A7 looks overpowered for a phone imo, but should be great for the ipad. it's really good, and makes Bay Trail looks far less impressive for sure...

still, you can't run Windows with it.

For the mobile market (tablets and phones) Windows is a distant third to Android and iOS.

http://bgr.com/2013/08/05/ios-android-tablet-market-share-2/

I think Apple wants to reverse their market share losses to Samsung and other Android tablets manufacturers. The fact that A7 is the first 64 bit ARMv8 chip with 64 bit iOS and apps and shipping now is a clear indication of how seriously Apple views the threat. With A7 Apple is atleast a year ahead of other ARM SOC companies like Samsung, Qualcomm and Nvidia.

As anandtech says smartphones with 2 stronger cores than 4 weaker cores are the better option. Its just like the desktop - a 4 core, 4 thread core i5 Haswell is better than a 8 thread FX.

2 stronger cores mean OS and app responsiveness will be better for the majority of cases.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |