The iPhone 5s Review
by Anand Lal Shimpi on September 17, 2013 9:01 PM EST- Posted in
- Smartphones
- Apple
- Mobile
- iPhone
- iPhone 5S
After Swift Comes Cyclone Oscar
I was fortunate enough to receive a tip last time that pointed me at some LLVM documentation calling out Apple’s Swift core by name. Scrubbing through those same docs, it seems like my leak has been plugged. Fortunately I came across a unique string looking at the iPhone 5s while it booted:
I can’t find any other references to Oscar online, in LLVM documentation or anywhere else of value. I also didn’t see Oscar references on prior iPhones, only on the 5s. I’d heard that this new core wasn’t called Swift, referencing just how different it was. Obviously Apple isn’t going to tell me what it’s called, so I’m going with Oscar unless someone tells me otherwise.
Oscar is a CPU core inside M7, Cyclone is the name of the Swift replacement.
Cyclone likely resembles a beefier Swift core (or at least Swift inspired) than a new design from the ground up. That means we’re likely talking about a 3-wide front end, and somewhere in the 5 - 7 range of execution ports. The design is likely also capable of out-of-order execution, given the performance levels we’ve been seeing.
Cyclone is a 64-bit ARMv8 core and not some Apple designed ISA. Cyclone manages to not only beat all other smartphone makers to ARMv8 but also key ARM server partners. I’ll talk about the whole 64-bit aspect of this next, but needless to say, this is a big deal.
The move to ARMv8 comes with some of its own performance enhancements. More registers, a cleaner ISA, improved SIMD extensions/performance as well as cryptographic acceleration are all on the menu for the new core.
Pipeline depth likely remains similar (maybe slightly longer) as frequencies haven’t gone up at all (1.3GHz). The A7 doesn’t feature support for any thermal driven CPU (or GPU) frequency boost.
The most visible change to Apple’s first ARMv8 core is a doubling of the L1 cache size: from 32KB/32KB (instruction/data) to 64KB/64KB. Along with this larger L1 cache comes an increase in access latency (from 2 clocks to 3 clocks from what I can tell), but the increase in hit rate likely makes up for the added latency. Such large L1 caches are quite common with AMD architectures, but unheard of in ultra mobile cores. A larger L1 cache will do a good job keeping the machine fed, implying a larger/more capable core.
The L2 cache remains unchanged in size at 1MB shared between both CPU cores. L2 access latency is improved tremendously with the new architecture. In some cases I measured L2 latency 1/2 that of what I saw with Swift.
The A7’s memory controller sees big improvements as well. I measured 20% lower main memory latency on the A7 compared to the A6. Branch prediction and memory prefetchers are both significantly better on the A7.
I noticed large increases in peak memory bandwidth on top of all of this. I used a combination of custom tools as well as publicly available benchmarks to confirm all of this. A quick look at Geekbench 3 (prior to the ARMv8 patch) gives a conservative estimate of memory bandwidth improvements:
| Geekbench 3.0.0 Memory Bandwidth Comparison (1 thread) | ||||||
| Stream Copy | Stream Scale | Stream Add | Stream Triad | |||
| Apple A7 1.3GHz | 5.24 GB/s | 5.21 GB/s | 5.74 GB/s | 5.71 GB/s | ||
| Apple A6 1.3GHz | 4.93 GB/s | 3.77 GB/s | 3.63 GB/s | 3.62 GB/s | ||
| A7 Advantage | 6% | 38% | 58% | 57% | ||
We see anywhere from a 6% improvement in memory bandwidth to nearly 60% running the same Stream code. I’m not entirely sure how Geekbench implemented Stream and whether or not we’re actually testing other execution paths in addition to (or instead of) memory bandwidth. One custom piece of code I used to measure memory bandwidth showed nearly a 2x increase in peak bandwidth. That may be overstating things a bit, but needless to say this new architecture has a vastly improved cache and memory interface.
Looking at low level Geekbench 3 results (again, prior to the ARMv8 patch), we get a good feel for just how much the CPU cores have improved.
| Geekbench 3.0.0 Compute Performance | ||||||
| Integer (ST) | Integer (MT) | FP (ST) | FP (MT) | |||
| Apple A7 1.3GHz | 1065 | 2095 | 983 | 1955 | ||
| Apple A6 1.3GHz | 750 | 1472 | 588 | 1165 | ||
| A7 Advantage | 42% | 42% | 67% | 67% | ||
Integer performance is up 44% on average, while floating point performance is up by 67%. Again this is without 64-bit or any other enhancements that go along with ARMv8. Memory bandwidth improves by 35% across all Geekbench tests. I confirmed with Apple that the A7 has a 64-bit wide memory interface, and we're likely talking about LPDDR3 memory this time around so there's probably some frequency uplift there as well.
The result is something Apple refers to as desktop-class CPU performance. I’ll get to evaluating those claims in a moment, but first, let’s talk about the other big part of the A7 story: the move to a 64-bit ISA.
Facebook
Twitter
RSS
464 Comments
View All Comments
helloworldv2 - Wednesday, September 18, 2013 - link
A good review would compare to the best in class, i.e. the Lumia 1020. Of course it would wipe the floor with the 5S, so that wouldn't be very good for Anandtech if they want to maintain good relations with Apple and all that..darkcrayon - Wednesday, September 18, 2013 - link
I think Apple is satisfied with their performance in the 5s form factor and understands it's a reasonable compromise vs sticking what looks like a section of an actual camera to the back of the phone, making an awkward 1/2 inch lump. And of course as an overall device the 5s it's much more advanced in other ways.Gridlock - Wednesday, September 18, 2013 - link
So Apple should have sent Anand a 1020?Or maybe Nokia PR should be slightly more awake.
120fps and 1024 available flash tones beats a Quasimodo Nokia for me.
Fleeb - Wednesday, September 18, 2013 - link
But in photography, in camera flash should only be used as a last resort.Petrodactyl - Monday, September 23, 2013 - link
if you're using remote flash with your phone camera, you're an idiot - and likely a bad photographer, to boot. Please try to stay within the realm of reality. Thanks.akdj - Wednesday, October 9, 2013 - link
It was an excellent review---and not just 'based' on photographic prowess. Is there a blog you've got going that provides 'good reviews'? I'm honestly interested because I found this one incredibly well written...and even responded, by the admin of the site---directly to you. He Didn't Have Your Beloved 1020. That said---plenty of comparison reviews if ALL you're interested in is the photographic abilities of the 5s. (There's a WHOLE lot more 'most' folks are seeking from their chosen phone). That said---Apple has always, for the time, provided top notch---maybe not always #1---but easily and consistently in the top 5 performers (including older models while a new one is released)...not to mention, the popularity to both developers and photo share sites speaks volumes to it's ubiquity. DPReview.com has an excellent and specific write up JUST for your helloworldv2 on the abilities (and downsides) to the iPhone 5s. Seems like an 8 or 10 page write up with plenty of comments for your to participate in as well. Seems like a better idea than coming in to a (possibly the most detailed on the net as well as insightful) site and bitching about one of the MANY functions of your 'pocket computer' review. Only so much time that can be set up to review each subject...and a finite amount of product---I'm sure in the lab hanging around, as well as the public choice...again ubiquitous---to choose Apple or Android en masse vs. Windows handsets at this point. If photography is your 'thing' (I shoot professionally, BTW)---grab a nice point and shoot. The Canon S110 or the new Sony RX100v2 are incredible performers....then you can own a decent phone too and not have to compromise!J
abrowne1993 - Wednesday, September 18, 2013 - link
Fair enough. I hope Brian gets the chance to do a comparison on here.bootareen - Tuesday, September 17, 2013 - link
There definitely is a display lottery. I've gone through around 7 iPhone 5's with different problems, but all had an interlace/scan line issue which is exactly what it sounds like. Even if you are further away from the screen and can't see the scan lines per se, the screen is noticeably less comfortable to look at and focus on with your eyes compared to a normal screen.Have you heard of this Anand, and are you aware of what would cause this issue?
fokka - Tuesday, September 17, 2013 - link
i can't really wrap my head around how the iphone can compete with high end android phones so well, even beating them by considerable margins in many benchmarks, although "only using a dual core" which is probably not even clocked as high as, say, a snapdragon 800?apple has put an emphasis on gpu-performance for a long time now, but seeing them on top so often and combining that with good battery life, all while using a miniscule battery (by android's standards) i have to say they are doing an astonishing job.
too bad i don't like apple software (and pricing).
Impulses - Tuesday, September 17, 2013 - link
The Moto X competes well with all the current quad cores too, it's not that big of a rarity... The fact that they can optimize for battery life better isn't that shocking either, it's the same deal as OS X... When you're only testing against a dozen models or so versus thousands you can do a lot more in this regard.