Nexus 5 With Android 4.4 and Snapdragon 800 Challenges Apple A7 In Benchmarks
MojoKid writes "One of the hallmark features of Google's Nexus 5 flagship smartphone by LG isn't its bodaciously big 5-inch HD display, its 8MP camera, or its "OK Google" voice commands. That has all been done before. What does stand out about the Nexus 5 is Google's new Android 4.4 Kit Kat OS and LG's SoC (System on Chip) processor of choice, namely Qualcomm's Snapdragon 800 quad-core. Qualcomm is known for licensing ARM core technology and making it their own; and Qualcomm's latest Krait 400 quad-core along with the Adreno 330 GPU that comprise the Snapdragon 800, is a powerful beast. Google also has taken the scalpel to Kit Kat in all the right places, whittling down the overall footprint of the OS, so it's more efficient on lower-end devices and also offers faster multitasking. Specifically memory usage has been optimized in a number of areas. Couple these OS tweaks with Qualcomm's Snapdragon 800 and you end up with a smartphone that hugs the corners and lights 'em up on the straights. Putting the Nexus 5 through its paces, it turns out preliminary figures are promising. In fact, the Nexus 5 actually was able to surpass the iPhone 5s with Apple's 64-bit A7 processor in a few tests and goes toe to toe with it in gaming and graphics." Ars Technica has a similarly positive view of the hardware aspects of the phone, dinging it slightly for its camera but otherwise finding little to fault.
This is not a fair comparison, the iPhone is twice the price.
Well it's actually worse than that. A phone that has a SoC with double the cores, cores that have a max clock rate 1 ghz higher and double the memory is only able to win in a couple of tests and just keep up with the A7 in every other test. Sounds like pretty fail.
They are both very nice phones. There. I said it.
Help stamp out iliturcy.
Qualcomm's latest Krait 400 quad-core along with the Adreno 330 GPU that comprise the Snapdragon 800, is a powerful beast.
If they had not focused much on the specs, but rather on battery life that can last a day of average use, I'd be happier. I ask my self: -
"Of what use is having the"latest and greatest if by mid-afternoon, I will be holding a brick in hand?
This is what I do to these good phones that are limited in the battery department. I underclock them with acceptable results.
By the way: Can one explain to me how Motorola was able to cram a 3000mAH into a phone smaller than this but Google and its LG partner cannot?
New phone almost as fast as month old phone.
Xperia Z1 was released same day as iPhone 5s. It is faster, waterproof, and has higher res 1080 screen. It also has a 20.7MP camera with a much larger 1/2.3" sensor.
The original iPhone caught on because it could play DRM iTunes.
You know, I don't think I've ever seen as horribly misguided a reason for the adoption of the iPhone as that one.
By your logic, the Motorola ROKR would have been a smash hit.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
the article doesn't touch on this, but I wonder how much untapped power is in that 64bit processor in iPhone. what's cool is, that's dormant in my phone right now, but will be unleashed next year so it will be like getting a new phone.
Please tell me you're being sarcastic... Even if all your apps get recompiled to 64-bit versions, you are not going to get a massive performance boost. Have you ever tried running a 32 vs. 64 bit install of Windows or Linux on the same hardware? Not too much difference for average use cases...
We ran Sunspider (1.0.2).
The iPhone 5S (and a Nokia Lumia 920) pasted my Nexus 5 on Sunspider. Both were about twice as fast as the Nexus 5.
I like the Nexus 5, it's very snappy. But when using it, it doesn't feel faster than a 5S.
The N5 is a heck of a value.
Now, about the awful pictures it takes... Is there any chance a better camera app (which also sucks) can improve them some?
http://lkml.org/lkml/2005/8/20/95
Yeah but that phone is half the price of the iPhone.
Pretty impressive to me.
Mod me down, my New Earth Global Warmingist friends!
yeah but if you use your iphone as a media transcoding server, the gains with be iMazing!
Mod me down, my New Earth Global Warmingist friends!
Yeah because when I am out and about, i much prefer to carrry a map, a compass, a walkman, a mobile phone, a laptop, a pager, a camera, a tape recorder and a gaming console. Fuck those integration guys in the neck.
I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
Sony could release a phone that claimed to cure cancer, solve world poverty and establish peace in the middle east. They're still not getting a cent of my disposable income.
I run: Windows, OS X, Linux, FreeBSD. Just because you have a hammer, doesn't mean everything is a nail.
The iPhone might not be any better (I don't know and don't care) but that's fucking pathetic.
iPhone 3GS shipped with iOS 3.0 in June 17, 2009.
Final iOS update was 6.1.3 in March 19, 2013.
http://en.wikipedia.org/wiki/IOS_version_history
That is 45 months. (Past performance does not guarantee future results.)
I am curious...
Before the 20th Century did the average person drive an automobile?
Before the Industrial Revolution did the average person have access to cheap, mass produced good?
Before the Agricultural Revolution, did the average person have access to plentiful grain?
Before the Paleolithic, did the average person have access to crafted stone tools?
Don't get me wrong, I'm just curious...
The main advantage of 64 bitness is access to a far larger memory address space. Yes there can be a few minor performance improvements with proper use of larger registers, but it's really not that big an advantage. Until smartphones and tablets start exceeding 4 gigabytes of RAM there is really not much point other than marketing to use 64 bit code on such devices.
That has been debunked again and again and again.
There has been iOS code that was measured to be 45% faster just by being recompiled to 64 bit. There are plenty of tricks in the Objective-C runtime and the C++ libraries that make it _significantly_ more efficient when running on a 64 bit processor. For example, a std::string up to 22 chars doesn't allocate any memory on the heap in 64 bit code but just uses three 64 bit words.
The main advantage of 64 bitness is access to a far larger memory address space. Yes there can be a few minor performance improvements with proper use of larger registers, but it's really not that big an advantage. Until smartphones and tablets start exceeding 4 gigabytes of RAM there is really not much point other than marketing to use 64 bit code on such devices.
Oh c'mon. Slashdot is supposed to be the smart nerds.
One advantage of a 64 bit architecture (such as x86_64 or the A7) is that in order to hold 64 bit data. But if you're still working with 32 bit data (and most of us are), you can simply load each register with two 32 bit chunks, basically doubling the amount of data you can hold on chip, and the processor has functions to support this.
And if you look at what Apple did with the A7, not only does their 64 bit chip do this, but the new ARM64 specifications double the number of registers in general:
"The ARMv8-A instruction set doubles the number of registers of the A7 compared to the ARMv7 used in A6.[13] It now has 31 general purpose registers that are each 64-bits wide and 32 floating-point/NEON registers that are each 128-bits wide."
http://en.wikipedia.org/wiki/Apple_A7
So basically you now have an crazy amount of registers, and an insane amount of registers if you are dealing with 32 bit data still. The NEON registers are 128-bits wide and there are 32 of them. If you have 32 bit data, you can process 128 chunks at a time! If you're working in float_16 with NEON, you can work through 256 chunks at a time. That's crazy good compared to ARM32. That would really speed up anything that works with media, images, video, animations, etc, most of which a modern window server does.
But that's not really the end of optimizations. If your registers are large enough, why bother using pointers? And that's what Apple did with the Objective-C runtime on ARM64.
http://www.mikeash.com/pyblog/friday-qa-2012-07-27-lets-build-tagged-pointers.html
Basically, if you've got a small enough object type, like an object that holds an 32 bit type, you can skip the allocation of extra memory to hold this data, and just store it in the pointer itself. A lot of the low level and frequently hit methods in Obj-C (like the entire memory allocation tracking system) have been optimized for this, so you should see a speedup in even basic applications.