Apple's A5X Die (and Size?) Revealed
by Anand Lal Shimpi on March 15, 2012 5:15 PM ESTiFixit saved us all a whole lot of trouble and performed a teardown of the new iPad announced last week. The internals were mostly what we expected, down to the Qualcomm MDM9600 LTE baseband. Despite many of the new iPad's specs being a known quantity prior to launch, there were a few surprises in the teardown.
First and foremost, Apple has moved away from a PoP (Package-on-Package) stack with the A5X SoC and now uses two discrete DRAM devices. The iPad iFixit took apart featured two 512MB Elpida LP-DDR2 devices on the side of the PCB that doesn't feature the A5X (in yellow, below). The A5 SoC featured a dual-channel (2x32-bit) LP-DDR2 memory interface running at up to an 800MHz data rate.
Elpida, like most DRAM manufacturers, does a terrible job of keeping its part number decoders up to date publicly so these two devices (B4064B2MA-8D-F) aren't well documented. The first character in the part number ("B") tells us that we're looking at mobile/low-power DDR2 memory. The next two characters ("40") typically refer to the device density, the 4 in this case likely means 4Gbit while the 0 is a bit odd since it usually refers to DRAM page-size. It's the fourth and fifth characters that are a bit odd to me ("64"). Usually these tell us the width of the DRAM interface, the 64 would imply something that doesn't appear to be true (initial memory bandwidth numbers don't show any increase in memory bandwidth). It's quite possible that I'm reading the part number incorrectly, so if anyone out there has an updated source on Elpida (and other) DRAM part numbers please do share. Update: The 64 doesn't imply a 64-bit interface as we can see from this datasheet. The two devices are 32-bits wide each, unchanged from A5 implementations. Thanks ltcommanderdata!
As you might have guessed from the fact that Apple now adorns the A5X with a metal heatspreader, Apple has potentially made the shift from a wirebond package to flip-chip. What you're looking at in the shot above with the heatspreader removed is the bottom of the A5X die. If you were to drill down from above you'd see a layer of logic then several metal layers. Moving to a flip-chip BGA package allows for better removal of heat (the active logic is closer to the heatsink), as well as enabling more IO pins/balls on the package itself. Running gold wires from a die to the package quickly becomes a bottleneck as chip complexity increases.
Note that it is possible for Apple to have used flip-chip in the A5 and simply hidden it under the PoP memory stack. Intel's Medfield for example uses a FC-BGA package but will be covered by DRAM in a PoP configuration.
Update: Chipworks has actually measured the A5X die: 162.94mm^2. This means that our visual inspection was inaccurate and Apple is likely still on a 45nm process, which would explain the unchanged CPU clocks. This also helps explain the move away from a PoP stack. At 45nm the A5X's worst case thermals (heavy GPU load) probably demand much better cooling, hence the direct attach heatspreader + thermal paste.
Using the Toshiba eMMC NAND that resides next to the A5X as a reference, we can come up with a rough idea of die size. Based on Toshiba's public documentation, 24nm eMMC 16GB parts measure 12mm x 16mm. Using photoshop and the mystical power of ratios we come up with a rough estimate of 10.8mm x 10.8mm for the A5X die, or 117.5mm^2. If you remember back to our iPad analysis article, we guessed that conservative scaling on a 32nm process would give Apple a ~125mm^2 die for the A5X. While there's a lot of estimation in our methodology, it appears likely that the A5X's die is built on a 28/32nm process - or at least not a 45nm process. Note that this value is entirely dependent on the dimensions of Toshiba's NAND being accurate as well as the photo being as level and distortion-free as possible.
I'll chime in a little later to talk about A5X SoC performance.
Images courtesy iFixit
Facebook
Twitter
RSS
45 Comments
View All Comments
UpSpin - Friday, March 16, 2012 - link
' is to provide double resolution media.'that's the important thing: The resolution is four times bigger!
iPad 2: 0.7MP
iPad 3: 3.1MP
That's why people complain about the GPU. The GPU is fast, but it's only two times faster than the iPad2 GPU, while games on the iPad 3 have to process four times pixels. So a simple increase of resolution in high end games will render them useless. They can increase the resolution but aren't able to use the native resolution.
ufon68 - Friday, March 16, 2012 - link
"All other content will be scaled up from 1024x768 for two reasons: they will have to work on the older model(s) too and the lack of performance from cpu/gpu. It's like buying an 1080p notebook with an entry level (or any level by the way) GPU from NVIDIA or AMD and try to play the latest games at native resolution with every detail maxed out... And for 2048x1536 you need now a Core i7 / Radeon 7970 with a 500W PSU."You couldn't be more wrong about everything there.
The developers will make their apps to support both resolutions obviously, and you don't need those specs for that resolution. It's not the resolution itself which is demanding, it's what you're trying to display. I believe we can expect about the same amount of details in the new high res titles as in those for iPad2(or their iPad2 versions), but they'll be running at a higher res, so they will look better. I can guarantee you pretty much everyone will update their app to support the resolution, that goes for new titles, and for most old titles, at least those which are making money.
UpSpin - Friday, March 16, 2012 - link
if you quadruple the resolution but only double the GPU performance games which max out the iPad 2 GPU will not run on the iPad 3 in its 'retina' resolution without modifications. Either you have to upscale from maybe half the resolution or reduce GPU intensive effects to compensate the lack of missing GPU power.Things will look better on the iPad 3 than they do on the iPad 2, but they won't look four times better, which the retina marketing thing could imply, but only two times better, because the limiting factor is the GPU which is only, theoretically, two times faster but has to handle four times the amount of pixels.
Steelbom - Saturday, March 17, 2012 - link
Performance requirements don't necessarily scale linearly with resolution. So having four times as many pixels but only twice the GPU power as the iPad 2 doesn't mean it'll perform half as well in the same games.Look at Modern Combat 3, it's running at 2048x1536 smoothly on the iPad 3, and it's got fantastic graphics.
Raghu - Friday, March 16, 2012 - link
Dont think Apple would have ever used wire bonding for the A5. Its not used in any of the new age SoCs. Ancient technology for low density/speed signaling.