The iPhone XS & XS Max Review: Unveiling the Silicon Secrets
by Andrei Frumusanu on October 5, 2018 8:00 AM EST- Posted in
- Mobile
- Apple
- Smartphones
- iPhone XS
- iPhone XS Max
The A12 Vortex CPU µarch
When talking about the Vortex microarchitecture, we first need to talk about exactly what kind of frequencies we’re seeing on Apple’s new SoC. Over the last few generations Apple has been steadily raising frequencies of its big cores, all while also raising the microarchitecture’s IPC. I did a quick test of the frequency behaviour of the A12 versus the A11, and came up with the following table:
Maximum Frequency vs Loaded Threads Per-Core Maximum MHz |
||||||
Apple A11 | 1 | 2 | 3 | 4 | 5 | 6 |
Big 1 | 2380 | 2325 | 2083 | 2083 | 2083 | 2083 |
Big 2 | 2325 | 2083 | 2083 | 2083 | 2083 | |
Little 1 | 1694 | 1587 | 1587 | 1587 | ||
Little 2 | 1587 | 1587 | 1587 | |||
Little 3 | 1587 | 1587 | ||||
Little 4 | 1587 | |||||
Apple A12 | 1 | 2 | 3 | 4 | 5 | 6 |
Big 1 | 2500 | 2380 | 2380 | 2380 | 2380 | 2380 |
Big 2 | 2380 | 2380 | 2380 | 2380 | 2380 | |
Little 1 | 1587 | 1562 | 1562 | 1538 | ||
Little 2 | 1562 | 1562 | 1538 | |||
Little 3 | 1562 | 1538 | ||||
Little 4 | 1538 |
Both the A11 and A12’s maximum frequency is actually a single-thread boost clock – 2380MHz for the A11’s Monsoon cores and 2500MHz for the new Vortex cores in the A12. This is just a 5% boost in frequency in ST applications. When adding a second big thread, both the A11 and A12 clock down to respectively 2325 and 2380MHz. It’s when we are also concurrently running threads onto the small cores that things between the two SoCs diverge: while the A11 further clocks down to 2083MHz, the A12 retains the same 2380 until it hits thermal limits and eventually throttles down.
On the small core side of things, the new Tempest cores are actually clocked more conservatively compared to the Mistral predecessors. When the system just had one small core running on the A11, this would boost up to 1694MHz. This behaviour is now gone on the A12, and the clock maximum clock is 1587MHz. The frequency further slightly reduces to down to 1538MHz when there’s four small cores fully loaded.
Much improved memory latency
As mentioned in the previous page, it’s evident that Apple has put a significant amount of work into the cache hierarchy as well as memory subsystem of the A12. Going back to a linear latency graph, we see the following behaviours for full random latencies, for both big and small cores:
The Vortex cores have only a 5% boost in frequency over the Monsoon cores, yet the absolute L2 memory latency has improved by 29% from ~11.5ns down to ~8.8ns. Meaning the new Vortex cores’ L2 cache now completes its operations in a significantly fewer number of cycles. On the Tempest side, the L2 cycle latency seems to have remained the same, but again there’s been a large change in terms of the L2 partitioning and power management, allowing access to a larger chunk of the physical L2.
I only had the test depth test up until 64MB and it’s evident that the latency curves don’t flatten out yet in this data set, but it’s visible that latency to DRAM has seen some improvements. The larger difference of the DRAM access of the Tempest cores could be explained by a raising of the maximum memory controller DVFS frequency when just small cores are active – their performance will look better when there’s also a big thread on the big cores running.
The system cache of the A12 has seen some dramatic changes in its behaviour. While bandwidth is this part of the cache hierarchy has seen a reduction compared to the A11, the latency has been much improved. One significant effect here which can be either attributed to the L2 prefetcher, or what I also see a possibility, prefetchers on the system cache side: The latency performance as well as the amount of streaming prefetchers has gone up.
Instruction throughput and latency
Backend Execution Throughput and Latency | ||||||||
Cortex-A75 | Cortex-A76 | Exynos-M3 | Monsoon | Vortex | |||||
Exec | Lat | Exec | Lat | Exec | Lat | Exec | Lat | |
Integer Arithmetic ADD |
2 | 1 | 3 | 1 | 4 | 1 | 6 | 1 |
Integer Multiply 32b MUL |
1 | 3 | 1 | 2 | 2 | 3 | 2 | 4 |
Integer Multiply 64b MUL |
1 | 3 | 1 | 2 | 1 (2x 0.5) |
4 | 2 | 4 |
Integer Division 32b SDIV |
0.25 | 12 | 0.2 | < 12 | 1/12 - 1 | < 12 | 0.2 | 10 | 8 |
Integer Division 64b SDIV |
0.25 | 12 | 0.2 | < 12 | 1/21 - 1 | < 21 | 0.2 | 10 | 8 |
Move MOV |
2 | 1 | 3 | 1 | 3 | 1 | 3 | 1 |
Shift ops LSL |
2 | 1 | 3 | 1 | 3 | 1 | 6 | 1 |
Load instructions | 2 | 4 | 2 | 4 | 2 | 4 | 2 | |
Store instructions | 2 | 1 | 2 | 1 | 1 | 1 | 2 | |
FP Arithmetic FADD |
2 | 3 | 2 | 2 | 3 | 2 | 3 | 3 |
FP Multiply FMUL |
2 | 3 | 2 | 3 | 3 | 4 | 3 | 4 |
Multiply Accumulate MLA |
2 | 5 | 2 | 4 | 3 | 4 | 3 | 4 |
FP Division (S-form) | 0.2-0.33 | 6-10 | 0.66 | 7 | >0.16 | 12 | 0.5 | 1 | 10 | 8 |
FP Load | 2 | 5 | 2 | 5 | 2 | 5 | ||
FP Store | 2 | 1-N | 2 | 2 | 2 | 1 | ||
Vector Arithmetic | 2 | 3 | 2 | 2 | 3 | 1 | 3 | 2 |
Vector Multiply | 1 | 4 | 1 | 4 | 1 | 3 | 3 | 3 |
Vector Multiply Accumulate | 1 | 4 | 1 | 4 | 1 | 3 | 3 | 3 |
Vector FP Arithmetic | 2 | 3 | 2 | 2 | 3 | 2 | 3 | 3 |
Vector FP Multiply | 2 | 3 | 2 | 3 | 1 | 3 | 3 | 4 |
Vector Chained MAC (VMLA) |
2 | 6 | 2 | 5 | 3 | 5 | 3 | 3 |
Vector FP Fused MAC (VFMA) |
2 | 5 | 2 | 4 | 3 | 4 | 3 | 3 |
To compare the backend characteristics of Vortex, we’ve tested the instruction throughput. The backend performance is determined by the amount of execution units and the latency is dictated by the quality of their design.
The Vortex core looks pretty much the same as the predecessor Monsoon (A11) – with the exception that we’re seemingly looking at new division units, as the execution latency has seen a shaving of 2 cycles both on the integer and FP side. On the FP side the division throughput has seen a doubling.
Monsoon (A11) was a major microarchitectural update in terms of the mid-core and backend. It’s there that Apple had shifted the microarchitecture in Hurricane (A10) from a 6-wide decode from to a 7-wide decode. The most significant change in the backend here was the addition of two integer ALU units, upping them from 4 to 6 units.
Monsoon (A11) and Vortex (A12) are extremely wide machines – with 6 integer execution pipelines among which two are complex units, two load/store units, two branch ports, and three FP/vector pipelines this gives an estimated 13 execution ports, far wider than Arm’s upcoming Cortex A76 and also wider than Samsung’s M3. In fact, assuming we're not looking at an atypical shared port situation, Apple’s microarchitecture seems to far surpass anything else in terms of width, including desktop CPUs.
253 Comments
View All Comments
willis936 - Friday, October 5, 2018 - link
Great review. I loved the SoC analysis. There's definitely something spooky going on in an SoC with three caches that are scattered throughout the die. You do mention that there are two more fixed point ALUs but when analyzing a SPEC test result that relies on execution units you said that the A12 didn't have any execution improvements. Aren't the extra ALUs more execute?It's clearly a nice device and there are areas that saw massive improvements and other areas that are more of the same. I really appreciate that your conclusion isn't "it's a great device so buy it" but "it's a great device but really expensive".
Andrei Frumusanu - Friday, October 5, 2018 - link
The A11 had two more ALUs over the A10, the A12 doesn't improve in this regard.3DoubleD - Friday, October 5, 2018 - link
More than half the die shot was unlabeled. I found it strange that over 50% of the die wasn't worth discussing... what does it do? Are these fixed function units, modems, ISPs, ect.?It's really amazing how the CPU and GPU are taking less and less space on a SoC.
shabby - Friday, October 5, 2018 - link
It's not like Apple gives out these die shots with everything labeled, we're basically guessing what everything is.melgross - Saturday, October 6, 2018 - link
Nobody knows what the entire chip does. Since Apple doesn’t sell their chips they’re not obligated to tell us all of the secret sauce that’s in there.Ironchef3500 - Friday, October 5, 2018 - link
Thanks for the review!bull2760 - Friday, October 5, 2018 - link
I returned my MAX because of antenna signal issues. I upgraded from the 8 plus and while it was super fast it definitely has issues. I drive the same route to work everyday and in the few days I had the phone I had 4 dropped calls in the middle of conversations and when I looked at the screen is said call failed. One call to my wife I had 2 calls failed within 5 minutes. From my research the dropped calls are related to the new antenna system that Apple is using. Unless you are in a strong signal area you will receive a lot of dropped calls. From what I'm reading this has nothing to do with switching to Intel from 3Com it is directly related to the choice of antennas. Had 3Com had a chip ready to go with the same specs it too who have similar signal issues because of the antennas. The other issue I was having was network connectivity. I would be connected to my wireless at home or at work and often get page cannot be displayed errors and I need to check my network. I was clearly connected to my wireless network. I would turn the wireless on and off and it would start working. Speeds were crazy too. One minute you'd get really fat throughput and the next it would be crazy slow. I'd hold off on purchasing the new phones until Apple sorts out the bugs.FunBunny2 - Friday, October 5, 2018 - link
ehh?? everybody knows that if you want to use a telephone, you get a landline. mobile phones ceased being about phone calls at least a decade ago. what?? for a Grand$ you want to talk to someone??? how Neanderthal.PeachNCream - Friday, October 5, 2018 - link
Hah! I love the sarcasm!On a serious note though, I do wonder how long we'll even have a phone network or carriers that treat voice, text, and data as individual entities. We can and have already been able to do VoIP for what feels like ever and calling over WiFi is a thing. It'd make sense to just buy data and wrap up voice and text inside 4G or whatever.
FunBunny2 - Friday, October 5, 2018 - link
"It'd make sense to just buy data and wrap up voice and text inside 4G or whatever."I suspect that some scientists/engineers have run the numbers to see what that does to data capacity. which may be why it hasn't happened. or, it could also be that the data scientists at the carriers (and phone vendors) have found that smartphone users really don't make enough phone calls to warrant supporting decent quality.