Octacore vs quadcore

lopri

Elite Member
Jul 27, 2002
13,211
597
126
In theory, people differ in opinions but many think octa-cores do make sense. Seamless switching between low-power cores high-power cores can ideally take you to the best of both worlds: Low power consumption and high performance, as needed.

In reality, the implementation leaves a lot to be desired. Neither hardware nor software (including, crucially, the OS) are anywhere close to optimal operation, so the current situation looks to be the octa-core devices are trying to match quad-core counterparts. They are close, but today, everything else being equal, I would go with a quad-core.
 

Eug

Lifer
Mar 11, 2000
23,754
1,312
126
Apple went tri-core with their latest iPad. More than 2, but not quad. I wonder how long it will take before the apps and OS utilize that well, and they decide to go quad.

Not that I know anything about chip design or programming, but nonetheless from a layperson's point of view, it seems like a common sense move, given that developers still have trouble truly using quad-core in mobile.

In fact, if I were buying an Android phone, I'd be perfectly happy with dual-core as well, as long as the performance was decent. I really don't give a chit how many cores there are, as long as it performs well, and doesn't use too much battery juice.
 
Last edited:

Mopetar

Diamond Member
Jan 31, 2011
8,024
6,481
136
Do any of them actually use all 8 cores at the same time? I thought the idea was to use the lower-power cores until there's something doing some heavy lifting, and then switch to the more powerful cores.

I suppose that if all of them were being used, it would help if there's a lot of multitasking going on, but I don't know if that necessarily means faster more than just not getting ground to a halt when heavily multitasking, which probably isn't desirable on a phone in most circumstances.

Otherwise there aren't going to be many applications that will use 8 cores. There aren't a lot of PC applications that take advantage of that many cores, and the type that do generally aren't the type of apps the a person is likely to run on a phone.

If there's a lot of crap/bloat-ware running on the device it would mean that the performance wouldn't suffer as much because of it, but that's still an undesirable situation to avoid. Single-threaded performance is going to be more important for most apps. Perhaps having 8-cores helps out in benchmarks to some degree, but I can't think of many real-world situations where it would improve performance, at least not for a typical user.
 

Rdmkr

Senior member
Aug 2, 2013
272
0
0
I imagine distributing heat evenly between active and inactive cores would help keep up longer term performance even if the cores aren't ever (or just aren't frequently) used simultaneously.

I've used mediatek quad-core and octa-core SoC phones and the difference in performance was quite substantial. It seems to be working out for them to up the core count, although that is not exactly the only thing they did between iterations.
 

Midwayman

Diamond Member
Jan 28, 2000
5,723
325
126
The nexus 9 is 'only' dual core and should blow almost everything away. More cores != better. Just look at the benches. Particularly for the type of work you do.
 

s44

Diamond Member
Oct 13, 2006
9,427
16
81
In reality, the implementation leaves a lot to be desired. Neither hardware nor software (including, crucially, the OS) are anywhere close to optimal operation, so the current situation looks to be the octa-core devices are trying to match quad-core counterparts.
No, I don't think so any more. Things have really improved over the generations since the original Exynos 5420. Even Qualcomm is giving up and going HMP next year.

The main thing to look for, though, is the speed of each big single core. Adding the little ones to the mix doesn't really help max thoroughput. And yes, it's possible for two *really* big cores (i.e. Denver) to beat four regular ones.
 

poofyhairguy

Lifer
Nov 20, 2005
14,612
318
126
Even Qualcomm is giving up and going HMP next year.

I wouldn't call it "giving up." More like Apple blindsided them by shipping 64 bit two years before anyone expected it which forced Qualcomm to purge its planned pipeline. This purge means Qualcomm is going to use standard 64bit ARM cores for a while, which happen to be HMP. Sometime down the road you have to assume they will bring back a 64bit Krait though.

Heck, I am looking at 2015 as a year of SoC bandaids. A53's aren't the most impressive thing ever (they are midrange chips), we might actually see some regressions next year in the Snapdragon lineup just to check the 64 bit box.

Nvidia has an interesting 64 Bit SoC right now, but if Qualcomm keeps getting all the design wins than 2015 is not something I am looking forward to in the mobile market.
 

s44

Diamond Member
Oct 13, 2006
9,427
16
81
we might actually see some regressions next year in the Snapdragon lineup just to check the 64 bit box.
Eh? We already know A57 beats the pants off the latest Krait core even in crippled 32 bit mode at 2/3 the clock. And replacing A7 with A53 is only for the good.

Nvidia has an interesting 64 Bit SoC right now, but if Qualcomm keeps getting all the design wins than 2015 is not something I am looking forward to in the mobile market.
Well that's definitely true. Qualcomm is good at tweaking, but they sit on their base platform for way too long. Even if Swift had never happened, we would *still* have had ARMv8 on A57 this year, and for Qualcomm not to have had a transition plan for that was ridiculous.
 

poofyhairguy

Lifer
Nov 20, 2005
14,612
318
126
Eh? We already know A57 beats the pants off the latest Krait core even in crippled 32 bit mode at 2/3 the clock. And replacing A7 with A53 is only for the good.

If they get the SoC right. Samsung proved even with generic ARM that is not a given.

Plus when I talk about regressions I am not talking about pure SoC power. If Qualcomm doesn't get it right we might see battery life that makes us miss a slower Krait. It was nice having that really improve this year.
 
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/    |