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
CyberAngel - Thursday, September 19, 2013 - link
Hurray!name99 - Wednesday, September 18, 2013 - link
I imagine he would say "I heard exactly the same shit about the A6 and how it couldn't possibly be as good as I claimed. Come back when you have NUMBERS to back up your complaints."monaarts - Wednesday, September 18, 2013 - link
You are mistaking a more natural transition to a 64-bit mobile world with a "PR stunt." Yes, Android will probably make a huge jump and switch to 64-bit and include 8GB of memory, or something crazy like that, but will only add to fragmentation they are already burdened with. However, Apple is trying to avoid that by building steps that lead to where they eventually want the iPhone to go.ddriver - Wednesday, September 18, 2013 - link
The PC market is fragmented as well, but is still goes, doesn't it? Surely, as a bigger ecosystem, android will be slower to adopt changes. But HPC doesn't really make sense in a phone, that is why most ARM chip vendors are focusing on server v8 chips and infrastructure, which will be more lucrative than consumer electronics. v8 is the future, no doubt about it, but apple has no other winning hand besides offering v8 a little too early, knowing they can make up for the cost of the premature transition with profit margins other manufacturers cannot dream of asking for the same hardware. Surely, other brands have their fanboys too, but nowhere nearly as fanatically devoted and eager to "just take my money".tbrizzlevb - Wednesday, September 18, 2013 - link
I've never had any problem with this "fragmentation" that you cut and pasted from somewhere. How exactly has that kept you from buying Android? Do you normally keep your phone for 5 years or more? I'd be willing to bet you aren't using an iPhone 3 right now.. If you upgrade your phone every few years anyways, what do you care if the first generation Droid doesn't run the latest OS update?AaronJ68 - Wednesday, September 18, 2013 - link
The fact that there was never an iPhone 3 might have something to do with that.CyberAngel - Thursday, September 19, 2013 - link
As a programmer I say there is a HUGE fragmentation problem with all the Androids.I code for Jelly Beans only and I do have an "old" 4.0 mono CPU device for testing the lag.
Focher - Wednesday, September 18, 2013 - link
You lost me when you used the phrase "apple fanboys" and "declining sales". You don't seem to understand the difference between market share versus unit sales.ddriver - Wednesday, September 18, 2013 - link
So you must have taken "apple fanboys" personally, and understandably "declining sales" in a context regarding apples conflicts you. Like all other vendors, apple sales drop, thus the periodic refreshes, which do need their selling points, this time around it is v8. In the past, apple resorted to similar strategies, like making exclusive deals, purchasing the entire initial batches of new generation parts, and again making up for the cost of this "innovation" with their profit margins.I don't recall any other brand which pushed kids to selling their organs, do you? If that is not fanatical fanboyism, I don't know what it is...
akdj - Thursday, September 19, 2013 - link
Weird---seems to me EVERY time an iPhone is released, it sells MORE than the previous version FASTER! In fact, it's never been surpassed by another electronic item in history...and it's sales continue to climb. News Flash! Android (High end; S4/Note/HTC 1/XPeria) also sell @ a premium and almost @ the exact price of Apple's handsets. The rest of your post is nonsense. It's not just Anand's site and review praising the performance of the A7---it's ubiquitous. Is Apple paying Ars? TechCrunch? MacRumors? WSJ? Engadget? CNet?Dude---this is one HELL of an SoC. It's so much MORE than a 64bit chess match. A company licensing and building from the ground up a CPU/GPU/IPU that matches their OS and allows the tools to developers (For Free!) in XCode so the transition is seamless! The speed of this chip is awesome. Setting themselves up early is smart---the iPad release is imminent and has competition from both sides...Microsoft and Android. With a significantly larger 'body' and area to allow for more RAM...and future releases of other ARM based products, Apple is making in-roads within the mobile sector that ONLY bozos that cherish other brands, OEMs, or otherwise have some weird bone to pick with Apple can't realize. Mind blowing. I'm brand agnostic---use OSx, Windows and even own a couple of Android devices....but to me as dismissive as you are about the A7s build and putting it in a product the size of a pack of smokes is about as silly and should I say 'ignorant' a stance as I've seen in a long LONG time.
This move by Apple is HUGE. Moore's law now attributed to mobile. Still a dual core. Still 1GB of RAM (albeit DDR3 vs DDR2)---yet doubling, tripling, sometimes quadrupling performance of the other 'off the shelf' SoCs on the market that other OEMs are using. It's no secret---Apple has been hiring and head hunting chip designers from Intel and AMD for some time now. These guys and gals are some of the brightest minds on earth....but you've got it all figured out and somehow Anand's been blinded by the conspiracy---as has EVERY other reviewer on the 'net.
Un-Believable.
J