A8’s CPU: What Comes After Cyclone?

Despite the importance of the CPU in Apple’s SoC designs, it continues to be surprising just how relatively little we know about their architectures even years after the fact. Even though the CPU was so important that Apple saw the need to create their own custom design, and then did two architectures in just the span of two years, they are not fond of talking about just what it is they have done with their architectures. This, unfortunately, is especially the case at the beginning of an SoC’s lifecycle, and for A8 it isn’t going to be any different.

Overall, from what we can tell the CPU in the A8 is not a significant departure from the CPU in A7, but that is not a bad thing. With Cyclone Apple hit on a very solid design: use a wide, high-IPC design with great latency in order to reach high performance levels at low clock speeds. By keeping the CPU wide and the clock speed low, Apple was able to hit their performance goals without having to push the envelope on power consumption, as lower clock speeds help keep CPU power use in check. It’s all very Intel Core-like, all things considered. Furthermore given the fact that Cyclone was a forward-looking design with ARMv8 AArch64 capabilities and already strong performance, Apple does not face the same pressure to overhaul their CPU architecture like other current ARMv7 CPU designers do.


Close Up: "Enhanced Cyclone"

As a result, from the information we have been able to dig up and the tests we have performed, the A8 CPU is not radically different from Cyclone. To be sure there are some differences that make it clear that this is not just a Cyclone running at slightly higher clock speeds, but we have not seen the same kind of immense overhaul that defined Swift and Cyclone.

Unfortunately Apple has tightened up on information leaks and unintentional publications more than ever with A8, so the amount of information coming out of Apple about this new core is very limited. In fact this time around we don’t even know the name of the CPU. For the time being we are calling it "Enhanced Cyclone" – it’s descriptive of the architecture – but we’re fairly certain that it does have a formal name within Apple to set it apart from Cyclone, a name we hope to discover sooner than later.

In any case one of the things we do know about Enhanced Cyclone is that unlike Apple’s GPU of choice for A8, Apple has seen a significant reduction in the die size of the CPU coming from the 28nm A7 to the 20nm A8. Chipworks’ estimates put the die size of Cyclone at 17.1mm2 versus 12.2mm2 for Enhanced Cyclone. On a relative basis this means that Enhanced Cyclone is 71% the size of Cyclone, which even after accounting for less-than-perfect area scaling still means that Enhanced Cyclone is a relatively bigger CPU composed of more transistors than Cyclone was. It is not dramatically bigger, but it’s bigger to such a degree that it’s clear that Apple has made further improvements over Cyclone.

The question of the moment is what Apple has put their additional transistors and die space to work on. Some of that is no doubt the memory interface, which as we’ve seen earlier L3 cache access times are nearly 20ns faster in our benchmarks. But if we dig deeper things start becoming very interesting.

Apple Custom CPU Core Comparison
  Apple A7 Apple A8
CPU Codename Cyclone "Enhanced Cyclone"
ARM ISA ARMv8-A (32/64-bit) ARMv8-A (32/64-bit)
Issue Width 6 micro-ops 6 micro-ops
Reorder Buffer Size 192 micro-ops 192 micro-ops?
Branch Mispredict Penalty 16 cycles (14 - 19) 16 (14 - 19)?
Integer ALUs 4 4
Load/Store Units 2 2
Addition (FP) Latency 5 cycles 4 cycles
Multiplication (INT) Latency 4 cycles 3 cycles
Branch Units 2 2
Indirect Branch Units 1 1
FP/NEON ALUs 3 3
L1 Cache 64KB I$ + 64KB D$ 64KB I$ + 64KB D$
L2 Cache 1MB 1MB
L3 Cache 4MB 4MB

First and foremost, in much of our testing Enhanced Cyclone performs very similarly to Cyclone. Accounting for the fact that A8 is clocked at 1.4GHz versus 1.3GHz for A7, in many low-level benchmarks the two perform as if they are the same processor. Based on this data it looks like the fundamentals of Cyclone have not been changed for Enhanced Cyclone. Enhanced Cyclone is still a very wide six micro-op architecture, and branch misprediction penalties are similar so that it’s likely we’re looking at the same pipeline length.

However from our low-level tests two specific features stand out: integer multiplication and floating point addition. When it comes to integer multiplication Cyclone had a single multiplication unit and it took four cycles to execute. However against Enhanced Cyclone those operations are now measuring in at three cycles to execute. But more surprising is the total Integer multiplication throughput rate; integer multiplication performance has now more than doubled. While this doesn’t give us enough data to completely draw out Enhanced Cyclone’s integer pathways, all of the data points to Enhanced Cyclone doubling up on its integer multiplication units, meaning Apple’s latest architecture now has two such units.

Meanwhile floating point addition shows similar benefits, though not as great as integer multiplication. Throughput is such that there appears to still be three FP ALUs, but like integer multiplication the instruction latency has been reduced. Apple has managed to shave off a cycle on FP addition, so it now completes in four cycles instead of five. Both of these improvements indicate that Enhanced Cyclone is not identical to Cyclone – the additional INT MUL unit in particular – making them very similar but still subtly different CPU architectures.


Apple iPhone Performance Estimates: Over The Years

Outside of these low-level operations, most other aspects of Enhanced Cyclone seem unchanged. L1 cache remains at 64KB I$ + 64KB D$ per CPU core, where it was most recently doubled for Cyclone. For L2 cache Chipworks believes that there may be separate L2 caches for each CPU core, and while L2 cache bandwidth is looking a little better on Enhanced Cyclone than on Cyclone, it’s not a “smoking gun” that would prove the presence of separate L2 caches. And of course, the L3 cache stands at 4MB, with the aforementioned improvements in latency that we’ve seen.

To borrow an Intel analogy once more, the layout and performance of Enhanced Cyclone relative to Cyclone is quite similar to Intel’s more recent ticks, where smaller feature improvements take place alongside a die shrink. In this case Apple has their die shrink to 20nm; meanwhile they have made some small tweaks to the architecture to improve performance across several scenarios. At the same time Apple has made a moderate bump in clock speed from 1.3GHz to 1.4GHz, but it’s nothing extreme. Ultimately while two CPU architectures does not constitute a pattern, if Apple were to implement tick-tock then this is roughly what it would look like.

Moving on, after completing our low-level tests we also wanted to spend some time comparing Enhanced Cyclone with its predecessor on some high level tests. The low-level tests can tell us if individual operations have been improved while high level tests can tell us something about what the performance impact will be in realistic workloads.

For our first high level benchmark we turn to SPECint2000. Developed by the Standard Performance Evaluation Corporation, SPECint2000 is the integer component of their larger SPEC CPU2000 benchmark. Designed around the turn of the century, officially SPEC CPU2000 has been retired for PC processors, but with mobile processors roughly a decade behind their PC counterparts in performance, SPEC CPU2000 is currently a very good fit for the capabilities of Cyclone and Enhanced Cyclone.

SPECint2000 is composed of 12 benchmarks which are then used to compute a final peak score. Though in our case we’re more interested in the individual results.

SPECint2000 - Estimated Scores
  A8 A7 % Advantage
164.gzip
842
757
11%
175.vpr
1228
1046
17%
176.gcc
1810
1466
23%
181.mcf
1420
915
55%
186.crafty
2021
1687
19%
197.parser
1129
947
19%
252.eon
1933
1641
17%
253.perlbmk
1666
1349
23%
254.gap
1821
1459
24%
255.vortex
1716
1431
19%
256.bzip2
1234
1034
19%
300.twolf
1633
1473
10%

Keeping in mind that A8 is clocked 100MHz (~7.7%) higher than A7, all of the SPECint2000 benchmarks show performance gains above and beyond the clock speed increase, indicating that every benchmark has benefited in some way. Of these benchmarks MCF, GCC, PerlBmk and GAP in particular show the greatest gains, at anywhere between 20% and 55%. Roughly speaking anything that is potentially branch-heavy sees some of the smallest gains while anything that plays into the multiplication changes benefits more.

MCF, a combinatorial optimization benchmark, ends up being the outlier here by far. Given that these are all integer benchmarks, it may very well be that MCF benefits from the integer multiplication improvements the most, as its performance comes very close to tracking the 2X increase in multiplication throughput. This also bodes well for any other kind of work that is similarly bounded by integer multiplication performance, though such workloads are not particularly common in the real world of smartphone use.

Our other set of comparison benchmarks comes from Geekbench 3. Unlike SPECint2000, Geekbench 3 is a mix of integer and floating point workloads, so it will give us a second set of eyes on the integer results along with a take on floating point improvements.

Geekbench 3 - Integer Performance
  A8 A7 % Advantage
AES ST
992.2 MB/s
846.8 MB/s
17%
AES MT
1.93 GB/s
1.64 GB/s
17%
Twofish ST
58.8 MB/s
55.6 MB/s
5%
Twofish MT
116.8 MB/s
110.0 MB/s
6%
SHA1 ST
495.1 MB/s
474.8 MB/s
4%
SHA1 MT
975.8 MB/s
937 MB/s
4%
SHA2 ST
109.9 MB/s
102.2 MB/s
7%
SHA2 MT
219.4 MB/
204.4 MB/s
7%
BZip2Comp ST
5.24 MB/s
4.53 MB/s
15%
BZip2Comp MT
10.3 MB/s
8.82 MB/s
16%
Bzip2Decomp ST
8.4 MB/
7.6 MB/s
10%
Bzip2Decomp MT
16.5 MB/s
15 MB/s
10%
JPG Comp ST
19 MP/s
16.8 MPs
13%
JPG Comp MT
37.6 MP/s
33.3 MP/s
12%
JPG Decomp ST
45.9 MP/s
39 MP/s
17%
JPG Decomp MT
89.3 MP/s
77.1 MP/s
15%
PNG Comp ST
1.26 MP/s
1.14 MP/s
10%
PNG Comp MT
2.51 MP/s
2.26 MP/s
11%
PNG Decomp ST
17.4 MP/s
15.1 MP/s
15%
PNG Decomp MT
34.3 MPs
29.6 MP/s
15%
Sobel ST
71.7 MP/s
58.1 MP/s
23%
Sobel MT
137.1 MP/s
112.4 MP/s
21%
Lua ST
1.64 MB/s
1.34 MB/s
22%
Lua MT
3.22 MB/s
2.64 MB/s
21%
Dijkstra ST
5.57 Mpairs/s
4.04 Mpairs/s
37%
Dijkstra MT
9.43 Mpairs/s
7.26 Mpairs/s
29%

Geekbench’s integer results are overall a bit more muted than SPECint2000’s, but there are still some definite high points and low points among these benchmarks. Crypto performance is among the lesser gains, while Sobel and Dijkstra are among the largest at 21% and 37% respectively. Interestingly in the case of Dijkstra, this does make up for the earlier performance loss Cyclone saw on this benchmark in the move to 64-bit.

Geekbench 3 - Floating Point Performance
  A8 A7 % Advantage
BlackScholes ST
7.85 Mnodes/s
5.89 Mnodes/s
33%
BlackScholes MT
15.5 Mnodes/s
11.8 Mnodes/s
31%
Mandelbrot ST
1.18 GFLOPS
929.4 MFLOPS
26%
Mandelbrot MT
2.34 GFLOPS
1.85 GFLOPS
26%
Sharpen Filter ST
981.7 MFLOPS
854 MFLOPS
14%
Sharpen Filter MT
1.94 MFLOPS
1.7 GFLOPS
14%
Blur Filter ST
1.41 GFLOPS
1.26 GFLOPS
11%
Blur Filter MT
2.78 GFLOPS
2.49 GFLOPS
11%
SGEMM ST
3.83 GFLOPS
3.44 GFLOPS
11%
SGEMM MT
7.48 GFLOPS
6.4 GFLOPS
16%
DGEMM ST
1.87 GFLOPS
1.68 GFLOPS
11%
DGEMM MT
3.61 GFLOPS
3.14 GFLOPS
14%
SFFT ST
1.77 GFLOPS
1.59 GFLOPS
11%
SFFT MT
3.47 GFLOPS
3.18 GFLOPS
9%
DFFT ST
1.68 GFLOPS
1.47 GFLOPS
14%
DFFT MT
3.29 GFLOPS
2.93 GFLOPS
12%
N-Body ST
735.8 Kpairs/s
587.8 Kpairs/s
25%
N-Body MT
1.46 Mpairs/s
1.17 Mpairs/s
24%
Ray Trace ST
2.76 MP/s
2.23 MP/s
23%
Ray Trace MT
5.45 MP/s
4.49 MP/s
21%

While the low-level floating point tests we ran earlier didn’t show as significant a change in the floating point performance of the architecture as it did the integer, our high level benchmarks show that floating point tests are actually faring rather well. Which goes to show that not everything can be captured in low level testing, especially less tangible aspects such as instruction windows. More importantly though this shows that Enhanced Cyclone’s performance gains aren’t just limited to integer workloads but cover floating point as well.

Overall, even without a radical change in architecture, thanks to a combination of clock speed increases, architectural optimizations, and memory latency improvements, Enhanced Cyclone as present in the A8 SoC is looking like a solid step up in performance from Cyclone and the A7. Over the next year Apple is going to face the first real competition in the ARMv8 64-bit space from Cortex-A57 and other high performance designs, and while it’s far too early to guess how those will compare, at the very least we can say that Apple will be going in with a strong hand. More excitingly, most of these performance improvements build upon Apple’s already strong single-threaded IPC, which means that in those stubborn workloads that don’t benefit from multi-core scaling Apple is looking very good.

A8: Apple’s First 20nm SoC A8’s GPU: Imagination Technologies’ PowerVR GX6450
Comments Locked

531 Comments

View All Comments

  • annah_souls - Tuesday, October 28, 2014 - link

    Yes, it's my money and I have a lot of them to buy as much as iPhone as I like. If you don't satisfy Apple product, you may not but $2000 handbag also. Pity you to yell Apple "The world is not fair!" LOL
  • Donkey2008 - Wednesday, October 29, 2014 - link

    People with intelligence don't buy purely on specs, which it seems 100% of Android owners do. I can just picture you like the many Android fanboys I have met....."Deeeerp, it has foure cores witch iz twice as mony as en iPhone so itz twice as fast, Deeeerrp".

    Enjoy your clunky, resource-hog, half-baked Google OS, your extremely inefficient hot-and-crispy quad-core space heater SOC (which has to be throttled by Android so the phone doesn't melt LULZ) and premium plastic-wrapped junk.
  • leonhk1 - Wednesday, October 29, 2014 - link

    Hi,
    I have stock of Brand New Apple iPhone 6 - 64GB Unlocked phones for sale at $650 only, sealed in box with 1 year warranty. Available in Gold , silver and space grey colors

    Interested buyer should E-mail me at: megas83@yahoo.co.uk
  • iphone 3 - Friday, October 31, 2014 - link

    I am wondering if you guys have similar analysis for ipad air 2 A8x
  • odedia - Tuesday, November 4, 2014 - link

    Please check the NAND differences between the 64gb model and the 128gb model. It appears the 128gb model uses TLC and not MLC.
  • curiosity - Thursday, November 6, 2014 - link

    output power / voltage: per channel or combined?
  • sellcheapli - Monday, November 24, 2014 - link

    Apple iPhone 6 - Plus 4G 16GB , 64GB , 128GB (Grey,Silver,Gold) ... $600
  • sellcheapli - Monday, November 24, 2014 - link

    Apple iPhone 6 - Plus 4G 16GB , 64GB , 128GB (Grey,Silver,Gold) ... $600

    Apple iPhone 6 - 16GB , 64GB , 128GB (Grey,Silver,Gold) ... $500

    Message : sellcheaplimited@gmail.com
  • Apple_iPhone_Service - Thursday, April 30, 2015 - link

    http://www.iphoneservicecenterchennai.co

    Find the best Iphone Service center in your area in Chennai & Bangalore

    iphone service center in Anna Nagar | iphone service center in Mogappair | iphone service center in Thirumangalam | iphone service center in Perambur | iphone service center in Egmore | iphone service center in Kilpauk | iphone service center in Aminjikarai | iphone service center in Koyambedu | iphone service center in Kodambakkam | iphone service center in Nungambakkam | iphone service center in TNagar | iphone service center in Royepettah | iphone service center in Mylapore | iphone service center in Teynampet | iphone service center in Saidapet | iphone service center in Guindy | iphone service center in Ashok Nagar | iphone service center in KK Nagar | iphone service center in Saligramam | iphone service center in Virugambakkam | iphone service center in Chrompet | iphone service center in Pallavaram | iphone service center in Tambaram | iphone service center in Velachery | iphone service center in Thiruvanmiyur | iphone service center in Adyar | iphone service center in OMR | iphone service center in ECR | iphone service center in Medavakkam | iphone service center in Madipakkam | iphone service center in Perumbakkam | iphone service center in Pallikaranai | iphone service center in Sholinganallur | iphone service center in Gopalapuram | iphone service center in Besant Nagar | iphone service center in Washermenpet | iphone service center in Broadway | iphone service center in Purusawalkam
    iphone service center in koramangala | iphone service center in jayanagar | iphone service center in jp nagar|iphone service center in btm | iphone service center in ulsoor | iphone service center in kammanahali | iphone service center in cox town \ iphone service center in frazer town | iphone service center in mathikere | iPhone Service Center in kempapura | iphone service center in marathalli | iphone service center in hsr | iphone service center in electronic city | iphone service center in sg playa | iphone service center in Bellandur | iphone service center in Domlur | iphone service center in Malleswaram | iphone service center in Rajajinagar | iphone service center in majestic | iphone service center in forum mall | iphone service center in Sony world signal | iphone service center in echo space | iphone service center in forum mall | iphone service center in Whitefield

    We provide wide-range of Hardware & Software services for all branded smartphones and tablets including brands like APPLE, SAMSUNG, HTC, SONY, LG, MOTOROLA, MICROMAX, LENOVO etc. can recover the smartphone devices from any sort of problems like physical damage, Water lock and replacing the core components like Display , IC's, Front and Rear Camera components and other hardware/software issues.
    Training
    Topics Discus under Training Program:
    Soldering, De-soldering of components, Check of voltages in a battery of a mobile phone, Use of SMD reworks station, Triggering of batteries, Assembling & disassembling of mobile phones, Chip level servicing of components: Power amplifiers (pf), audio IC (Cobba), CPU (Mad), Power supply IC (Cont), Charging Control IC (Chaps). Rf Signal Processor IC (Hagar). Also well versed with SMD components replacement (Capacitors, Diodes Resistors, and LED’s). Rebelling & repair of ball grade array ICs (BGA).
    Hardware Complaint Service Training:
    Mobile Complaints: Dead, network, display problem, keypad problem, display light problem, keypad light problem, touchpad problem, sensor problem, head phone jack problem, speaker problem, mic problem, ringer problem, charging problem, Bluetooth problem, wifi problem, camera problem, volume button problem, camera button problem, on off switch problem, strip problem, fm problem, network problem, dead, water lock, hanging problem, handset off problem, restart issue
    Software Complaint Service Training:
    Phone unlock, pattern lock, vibrator problem, navigation key problem, Contact service, hanging, partial dead, network, unlocking, Flashing various software like USR, twister, tornado, griffin, UFS, Uni Box for color, camera, blue tooth, infrared enabled mobile phones of Nokia, Samsung, Panasonic, Ericson, Sony, Siemens, LG, Motorola and many more
    Motherboard Complaint Service Training:
    Ic (integrated circuit), Smd ic (leg type), bga ic (ball type)capacitor, Resister ,transistor, filter, fuse, diode, power crystal, clock crystal connector, battery connector ,usb jack, charging jack, head phone chack, inner key pad, vibrator ,speaker, mic, ringer

    Koramangala 5th block
    no 75/8,kristal prestige 4th floor, idea show room upstairs,opp to bhima jewellers,
    koramangala industrial layout, 5th block, 7026604420/ 7026604423

    Koramangala 7th block
    no 340, maruthi plaza,1st b cross,koramangala 7th block
    opp to forum road,behind A2B, 08041521112

    Koramangala 1st Block
    no 16,vijith plaza,80ft road,koramangala 1st block
    opp to reliance fresh, 08041521115

    jayanagar 4th block
    Diamond Arcade,no 21,east 11th main,32nd d cross,jayanagar 4th block
    opp to kalamandir & mom and me,near cool joint signal
    08041521113

    jayanagar 9th block
    no 1339,41st cross,25th main,jayanagar 9th block
    opp to central mall road,behind jain college,next to himalaya store
    08041521110/

    Banashankari 1st stage
    no 5,Sln complex,80 ft road,srinivasa nagar circle,banashankari 1st stage
    near bata showroom
    08041521119

    Banashankari 2nd stage
    no31, 21st main road, near bda complex,banashankari 2nd stage
    near goli vada pav
    08049570768 / 9980090798

    Rajajinagar 6th block
    no 246,Dr.Rajkumar Road,Rajajinagar 6th block
    next to nea albek hotel & sangeetha mobile showroom
    08041521116

    Malleswaram
    no 10,2nd main,sampige main road.near mantri mall,
    opp to albek hotel,below to samsung show room
    malleswaram, 08041474313

    Mathikere
    28/3, Sai Shekar complex,H.M.T Main Road, Beside Subbaiah Hospital
    08041573366 / 9611269682

    Kempapura
    Door no-3, 21st main road, sri Rajeshwari New Colony, Hebbal,
    Kempapura Main Road, Bangalore
    08042103355 / 9611269682

    ulsoor
    no 49&50, guru gowtham complex,SV road,next to metro station,
    below to manak jewellers , ulsoor, 08041520642

    Domlur
    no 11,service road,old airport road,next to hyundai showroom,befor sony show room
    domlur in towards mg road, 08041103602

    Frazer town
    no 64/1, concord plaza, coles road, frazer town, near shanthi sagar hotel
    08041105150

    Kammanahalli
    no 17,mathu mansion,kammanahalli circle near,opp to ganesha temple
    below to liberty showroom, 08041103592

    BTM
    no 746,Tayapa towers,13th main,7th cross,near udupi garden,opp to dominas,icici,peter england
    below to mumbai kitchen , 08041500208

    HSR
    no 2580, 27th main, 13th cross,next to PHD
    08049530063

    Bellandur
    No 71/1a,opp to swarnamukhi hospital,univercell upster,sarjapura main road
    next to bellandur total mall, 08042060460

    Jp Nagar 7th Phase
    no 243, Brigate Apartment signal opposite, jp nagar 7th phase
    08040958575

    Marathahalli
    No: 35/1B, CRM SOWBHAGYA ANNEXE, Shop No.2,Varthur Main Road,
    marathahalli bridge next,Munnekolala,
    08065304422,09043888404

    VV puram

    Anna nagar
    no 18, TNSCB shopping complex,near jsp honda showroom,
    thirumangalam junction water tank,anna nagar west,
    04430069841

    Velachery
    no 25,sambantham garden,100ft road tharamani link road,opp to karaikudi hotel near TCS
    velachery, 04442139797

    OMR(thoraipakkam)
    no 64/4, sri vidhya avenue,omr ptc main road,opp to kfc restaurant
    04465668880

    Anna nagar-2
    Muva’s arcade,C52/4,anna nagar east,near chinthamani roundana circle, opp to girias
    chennai-600102
    04449539191

    T-Nagar

    No 2 ,North usman Road,Kodambakkam Road Junction ,Near Motherhood T-nagar,
    below Mallika mansion Chennai-17
    04443527474

    apple iphone service center in abu dhabi
    apple iphone service center in abu dhabi
    iphone service center in abu dhabi
    apple iphone service center in dubai
    apple iphone authorized service center in dubai
    apple iphone authorised service centre in dubai
    apple iphone service center in dubai
    apple iphone authorized service center in dubai
    apple iphone authorised service centre in dubai
    apple iphone authorized service center in dubai
    apple iphone authorised service centre in dubai
    iphone service center in bur dubai
    iphone service center in deira dubai
    iphone service dubai
    iphone service dubai
    iphone service center dubai
    iphone service in dubai
    apple iphone service center uae
    apple iphone service centre uae
    apple iphone service center uae
    apple iphone service centre uae
    apple iphone service center dubai
    apple iphone service center in uae
    apple iphone service centre in uae
  • raj parihar - Tuesday, November 3, 2015 - link

    mcf doesn't have any Multiply operations. In A8, its benefiting from a better (tuned) prefetcher possibly with negative (-3 or -1) stride.

Log in

Don't have an account? Sign up now