Heh. I'm still on Penryn, for my main laptop, and running OS X Yosemite 10.10 too. Core 2 Duo 2.26 GHz P8400.It's fast, probably comparable to a 2C/2T SB at the same frequency.
I'm not going to be the guinea pig. I won't open the box until I know it's 2 GB.Good luck - and please let us know how much RAM there is (if we don't get the news b/4 you get your iPad).
I don't like Apple,
short bursts because Cyclone can't operate at max speeds for long so it's as fast as 8 years old desktop CPU for a second or 2 maybe 4 and back to being 2x slower due to throttling.
Yep, thats it.
Can you be more informed before spouting nonsense. Under a really heavy load, after 10min, A8 in the iphone6 went from 1.4ghz to approx 1.15ghz and maintained 1.4ghz for approx 40 sec.
http://arstechnica.com/apple/2014/09/iphone-6-and-6-plus-in-deep-with-apples-thinnest-phones/3/
My P8400 supposedly gets around 3300-3400 or so.
I had tests done on A7 in mind. I don't feel like looking for those, but AFAIR there were done on AT. And it throttled VERY quickly.
I think you are confusing Geekbench 2 and 3. P8400 scores in the vicinity of 2450 in Geekbench 3
http://browser.primatelabs.com/geekbench3/101778
Ok thx. The Geekbench browser just listed the scores without specifying the Geekbench version. I made the mistake of assuming all the recent entries were Geekbench 3. I guess that explains why there is such a big ranges of scores.
http://browser.primatelabs.com/geekbench2/search?q=P8400&commit=Search
Ok thx. The Geekbench browser just listed the scores without specifying the Geekbench version. I made the mistake of assuming all the recent entries were Geekbench 3. I guess that explains why there is such a big ranges of scores.
http://browser.primatelabs.com/geekbench2/search?q=P8400&commit=Search
Yep, thats it.
Can you be more informed before spouting nonsense. Under a really heavy load, after 10min, A8 in the iphone6 went from 1.4ghz to approx 1.15ghz and maintained 1.4ghz for approx 40 sec.
http://arstechnica.com/apple/2014/09/iphone-6-and-6-plus-in-deep-with-apples-thinnest-phones/3/
Do note I personally consider Geekbench to be garbage and useless, it may be one of the better multiplatform benches, but these benchmarks are still bad. It may be better than javascript, it may be better than a dozen other things, but it is nowhere near good.
Do understand it is very easy to throw stones at things such as Geekbench and I realize I have not personally created anything better and I respect the development that is put into it but to me it is diagnostic noise and to think it means anything is to think knowing someone's knuckle size will tell you anything useful about their dna or their life outcomes.
Test platform- Haswell 4C/8T iris pro 2.0 -2.5 ghz
Enigmoid said:Lots of stuff
...
...
Geekbench plays up all these little tricks, to the effect of favouring mobile with bursts and outdated instructions on the desktop. This kind of stuff is why its not intensive at all on the desktop.
And don't get me wrong there is a point to have benchmark that tests all these bursts and stuff for certain usage models this makes sense. All those fancy instructions with vectors and such is not important if you are not doing anything that takes advantage of vectors and things. "Normal people" (I am using this as a pejorative) may have no need whatsoever for those instruction sets, but those instruction sets provide an order of magnitude improvement.
But then again you use a can use a mobile cellphone differently than a tablet differently than a light and portable laptop different than a desktop / workstation. I would not wanting to be doing lots of data entry on any cellphone and if I did I would want a blackberry with an actual keyboard. Same thing when we start moving to more complicated stuff such as engineering, graphics, video rendering, scientific/math calculations, program compiling etc.
Like I said earlier Geekbench is useless to me. It is just not good, it may be better than other mobile benchmarks but it is still not good or useful.
Also your a8 about throttling is also useless for me for unless you are playing a video game 1.2 ghz vs 1.4 is plenty of speed for a cellphone (with apples a7 and a8 ipc). I want burst speed and dynamic range for a cell phone usage model, you know race to sleep and quick to ramp when I want it. 4 minutes before throttling is plenty of enough time. And if you are playing a video game setting the cpu goal to something like 1 ghz instead of 1.4 makes sense to keep thermals down, maximize battery life, allow n-1 or n-2 generations to play the game etc. That said throttling to 50% cpu speed instead of 75% cpu speed looks really bad (5s numbers, 6+ is good in my opinion)
That A8 throttle test doesn't stress the GPU at ALL.
Interesting to note that using GFXBench 3.0, the iphone 6 doesn't throttle at all.
http://www.anandtech.com/show/8554/the-iphone-6-review/7
(look at previous page for peak performance)
While the Galaxy S5 (LTE-A model) goes from 27.2 down to 14.0fps by the end of the test.
LG G3 goes from 20.5 down to 10.7
Even Nvidia Shield tablet goes from 57.1 to 49.7
You are 100% right. I did not think of encryption when I respond with my earlier post. Mainly because I do not care about this stuff on an instinctual level, it does not motivate me if that makes sense. But my rational brain, understand this is of profound importance with businesses and keeping the internet secure. You know encryption is the man behind the curtain kind of thing, you are not supposed to see him. You are supposed to be in disneyworld not see all the things behind the curtain to make it possible. Encryption is damn important and if avx and other things can help that is great and should be implemented in a true benchmark.Encryption stuff
Yes, this is true.
However, there is not a lot of CPU load during GFX bench. My point was that under heavy load it is possible for throttling to occur (CPU + GPU).
Other phones don't throttle nearly as much.
You are 100% right. I did not think of encryption when I respond with my earlier post. Mainly because I do not care about this stuff on an instinctual level, it does not motivate me if that makes sense. But my rational brain, understand this is of profound importance with businesses and keeping the internet secure. You know encryption is the man behind the curtain kind of thing, you are not supposed to see him. You are supposed to be in disneyworld not see all the things behind the curtain to make it possible. Encryption is damn important and if avx and other things can help that is great and should be implemented in a true benchmark.
I was thinking of all the awesome stuff avx helps like medical imaging, scientific calculation, probability calculation etc. I did not even think of encryption, you are not going to run these awesome tasks on mobile silicon.
You made a very good point!
Not sure what you are implying. by "Other phones don't throttle nearly as much."
Do you mean other phone don't throttle as much as the iPhone 6 since that is absurd as in GFXBench (with little CPU load), the flagship models from Samsung and LG already halved their frame rates.
Are you assuming the +40% CPU perf claim Apple made is single-thread increase alone then?A forum member at B3D has dug up an iOS CPU PassMark chart which indicates that A8X will have three CPU cores! So in comparison to A7, the A8X SoC appears to have 50% more CPU cores and 50% more GPU cores, which would help to explain the 50% difference in transistor count (1 billion extra transistors!).
So I would estimate the Geekbench 3 AArch64 results to be ~ 2000 for single-core and ~ 5400 for multi-core!
iPad 5,4
Memory Mark 2 GB: http://www.iphonebenchmark.net/memmark_chart.html
CPU Mark triplecore: http://www.iphonebenchmark.net/cpumark_chart.html
Click on performance bar on graph to see specs.
I'm skeptical. CPU boost is 100% over A7 and 75% over A8.