AnandTech: Hardware News United Kingdom

This year’s September Apple event has been relatively unusual, not only because of the pandemic and online-only nature of the show, but also because amongst the new hardware releases there’s been an evident lack of a new iPhone at this point in time. Apple however didn’t disappoint, and managed to showcase brand-new iPads and Apple Watches. Amongst the new tablet line-up, we find the new 8th generation iPad which sees an upgrade in its computing capabilities with the new A12 chip, and the newest iPad Air which sees a total redesign, adopting the design queues of the iPad Pro siblings, and also for the first time introducing the new Apple A14 chipset – the industry’s first 5nm processor.

Apple iPad Comparison
	iPad (2019)	iPad (2020)NEW	iPad Air (2019)	iPad Air (2020)NEW
SoC	Apple A102x Hurricane4x Zephyr	Apple A122 × Vortex @ 2.5GHz4 × Tempest @ 1.59GHz	Apple A142 × Firestorm4 × Icestorm
Display	10.2" 2160x1620IPS LCD	10.5" 2224x1668IPS LCDDCI-P3, True Tone	10.9" 2360x1640"Liquid Retina"IPS LCDDCI-P3, True Tone
Dimensions	250 x 174.1x 7.5mm483g	250 x 174.1x 7.5mm490g / 495g	250.6 x 174.1x 6.1mm456g / 464g	247.6 x 178.5x 6.1mm458g / 460g
RAM	3GB LPDDR4	?	3GB LPDDR4X	?
NAND	32 / 128GB	64 / 256GB	64 / 256GB
Battery	32.9Wh	?	30.8Wh
Front Camera	1.2MP, F/2.2	7MP, F/2.2
Rear Camera	8MP, F/2.4, 1.12 µm	8MP, F/2.4	12MP, f/1.8
Cellular	2G / 3G / 4G LTE (Category 9)	UE Category 16 LTE (1Gbps) with 4x4 MIMO and LAA
SIM Size	NanoSIM	NanoSIM + eSIM
Wireless	802.11a/b/g/n/ac 2x2 MIMO,BT 4.2 LE, GPS/GLONASS	802.11a/b/g/n/ac 2x2 MIMO,BT 5.0 LE, GPS/GLONASS	802.11a/b/g/n/ac/ax 2x2 MIMO,BT 5.0 LE, GPS/GLONASS
Connectivity	Apple Lightning3.5mm headphone jack	Apple Lightning	USB-C
Launch OS	iOS 13.1	iOS 14	iOS 13.1	iOS 14
Launch Price	(Wi-Fi / Cellular)$329/$459 (32G)$429/$559 (128G)	(Wi-Fi / Cellular)$329/$459 (32G)$429/$559 (128G)	(Wifi / Cellular)$499/$629 (64G)$649/$779 (256G)	(Wifi / Cellular)$599/$729 (64G)$749/$879 (256G)

Starting off with the most exciting tablet today, which is the new iPad Air: At the heart of the new tablet we find Apple’s newest A14 chip, which is a keystone component of the new generation devices and will also likely power the next generation iPhone once it gets released later this year. Apple’s event disclosures this year were a bit confusing as the company was comparing the new A14 metrics against the A12, given that’s what the previous generation iPad Air had been using until now – we’ll need to add some proper context behind the figures to extrapolate what this means. On the CPU side of things, Apple is using new generation large performance cores as well as new small power efficient cores, but remains in a 2+4 configuration. Apple here claims a 40% performance boost on the part of the CPUs, although the company doesn’t specify exactly what this metric refers to – is it single-threaded performance? Is it multi-threaded performance? Is it for the large or the small cores? What we do know though is that it’s in reference to the A12 chipset, and the A13 already had claimed a 20% boost over that generation. Simple arithmetic thus dictates that the A14 would be roughly 16% faster than the A13 if Apple’s performance metric measurements are consistent between generations. On the GPU side, we also see a similar calculation as Apple claims a 30% performance boost compared to the A12 generation thanks to the new 4-core GPU in the A14. Normalising this against the A13 this would mean only an 8.3% performance boost which is actually quite meagre. In other areas, Apple is boasting more significant performance jumps such as the new 16-core neural engine which now sports up to 11TOPs inferencing throughput, which is over double the 5TOPs of the A12 and 83% more than the estimated 6TOPs of the A13 neural engine. Apple does advertise a new image signal processor amongst new features of the SoC, but otherwise the performance metrics (aside from the neural engine) seem rather conservative given the fact that the new chip is boasting 11.8 billion transistors, a 38% generational increase over the A13’s 8.5bn figures. The one explanation and theory I have is that Apple might have finally pulled back on their excessive peak power draw at the maximum performance states of the CPUs and GPUs, and thus peak performance wouldn’t have seen such a large jump this generation, but favour more sustainable thermal figures. What speaks against such a theory is that Apple made no mention at all of power or power efficiency this generation, which is rather very unusual given they’ve always made a remark in regards to this aspect of the new designs. We’ll have to see if this is indicative of the actual products, of it’s just a side-effect of the new more streamlined presentation style of the event. Whatever the performance and efficiency figures are, what Apple can boast about is having the industry’s first ever 5nm silicon design. The new TSMC-fabricated A14 thus represents the cutting-edge of semiconductor technology today, and Apple made sure to mention this during the presentation. Coming back to the iPad Air, the new tablet is a complete redesign for the mid-range device, and now adopts the new design language that had been introduced with the latest iPad Pro models over the last generations. This means a new thinner bezel design and the loss of the home button. Centre-stage we find a new 10.9” liquid retina IPS LCD panel with a 2360 x 1640 resolution. The panel comes with all bells and whistles you expect from Apple, such as a full lamination manufacturing process to enable better contrast and a “pop-out” feeling, True Tone and a Display P3 colour gamut. We’re seeing the adoption of the same 12MP 1.22µm pixel sensor as on the recent generation iPad Pro models, sporting a for a tablet relatively large f/1.8 aperture. Interestingly, because of the removal of the TouchID home button on the tablet, Apple has opted to not just solely rely on Face ID, but to introduce a new fingerprint scanner on the frame of the device. The new capacitive design isn’t exceptionally novel in the industry, however it’s the first time that we see Apple employ such a unit in their products. Another big noteworthy change in the new iPad Air is the fact that it’s now using a USB-C connector rather than Lightning. Apple here explains that the new connector allows for much faster transfer speeds between more devices. It’s a much welcome addition to the new generation, and we’re still crossing our fingers that Apple will make the same choice on the next-gen iPhone. 8th Generation iPad: A12 Brains Upgrade Also announced today was Apple’s new 8th generation iPad. The lower-entry tablet here largely retains the specifications of its predecessor when it comes to form-factor, display, cameras and connectivity. The big improvement for this generation is the move from the A10 chip to the newer A12 generation. Although it’s not the newest silicon, at this price range the upgrade represents a massive performance boost, and now it means that even the lowest-end iPad supports high-performance machine learning through the inclusion of the Neural Engine. $599+ for the iPad Air, $329 for the iPad The new iPad Air will commence at $599 which is an uptick in terms of price range compared to its predecessor. The upgrade from 64GB to 256GB storage costs an extra $130, whilst cellular LTE connectivity over the basic Wi-Fi models costs an extra $150 as well. Oddly enough, availability of the iPad Air will only start in October, which is unusual for an Apple launch. The 8th generation iPad starts at the same prices as the 7th gen, meaning $329 for the basic 32GB Wi-Fi model, with an extra $130 for the 128GB variant, and an extra $100 for cellular connectivity. Availability for the new iPad starts this Friday the 18th. Related Reading:

While NVIDIA’s usual presentation efforts for the year were dashed by the current coronavirus outbreak, the company’s march towards developing and releasing newer products has continued unabated. To that end, at today’s now digital GPU Technology Conference 2020 keynote, the company and its CEO Jensen Huang are taking to the virtual stage to announce NVIDIA’s next-generation GPU architecture, Ampere, and the first products that will be using it. Like the Volta reveal 3 years ago – and is now traditional for NVIDIA GTC reveals – today’s focus is on the very high end of the market. In 2017 NVIDIA launched the Volta-based GV100 GPU, and with it the V100 accelerator. V100 was a massive success for the company, greatly expanding their datacenter business on the back of the Volta architecture’s novel tensor cores and sheer brute force that can only be provided by a 800mm2+ GPU. Now in 2020, the company is looking to continue that growth with Volta’s successor, the Ampere architecture. Now a much more secretive company than they once were, NVIDIA has been holding its future GPU roadmap close to its chest. While the Ampere codename (among others) has been floating around for quite some time now, it’s only this morning that we’re finally getting confirmation that Ampere is in, as well as our first details on the architecture. Due to the nature of NVIDIA’s digital presentation – as well as the limited information given in NVIDIA’s press pre-briefings – we don’t have all of the details on Ampere quite yet. However for this morning at least, NVIDIA is touching upon the highlights of the architecture for its datacenter compute and AI customers, and what major innovations Ampere is bringing to help with their workloads. Kicking things off for the Ampere family is the A100. Officially, this is the name of both the GPU and the accelerator incorporating it; and at least for the moment they’re both one in the same, since there is only the single accelerator using the GPU.

NVIDIA Accelerator Specification Comparison
	A100	V100	P100
FP32 CUDA Cores	6912	5120	3584
Boost Clock	~1.41GHz	1530MHz	1480MHz
Memory Clock	2.4Gbps HBM2	1.75Gbps HBM2	1.4Gbps HBM2
Memory Bus Width	5120-bit	4096-bit	4096-bit
Memory Bandwidth	1.6TB/sec	900GB/sec	720GB/sec
VRAM	40GB	16GB/32GB	16GB
Single Precision	19.5 TFLOPs	15.7 TFLOPs	10.6 TFLOPs
Double Precision	9.7 TFLOPs(1/2 FP32 rate)	7.8 TFLOPs(1/2 FP32 rate)	5.3 TFLOPs(1/2 FP32 rate)
INT8 Tensor	624 TOPs	N/A	N/A
FP16 Tensor	312 TFLOPs	125 TFLOPs	N/A
TF32 Tensor	156 TFLOPs	N/A	N/A
Interconnect	NVLink 312 Links (600GB/sec)	NVLink 26 Links (300GB/sec)	NVLink 14 Links (160GB/sec)
GPU	A100(826mm2)	GV100(815mm2)	GP100(610mm2)
Transistor Count	54.2B	21.1B	15.3B
TDP	400W	300W/350W	300W
Manufacturing Process	TSMC 7N	TSMC 12nm FFN	TSMC 16nm FinFET
Interface	SXM4	SXM2/SXM3	SXM
Architecture	Ampere	Volta	Pascal

Designed to be the successor to the V100 accelerator, the A100 aims just as high, just as we’d expect from NVIDIA’s new flagship accelerator for compute.  The leading Ampere part is built on TSMC’s 7nm process and incorporates a whopping 54 billion transistors, 2.5x as many as the V100 before it. NVIDIA has put the full density improvements offered by the 7nm process in use, and then some, as the resulting GPU die is 826mm2 in size, even larger than the GV100. NVIDIA went big on the last generation, and in order to top themselves they’ve gone even bigger this generation. We’ll touch more on the individual specifications a bit later, but at a high level it’s clear that NVIDIA has invested more in some areas than others. FP32 performance is, on paper, only modestly improved from the V100. Meanwhile tensor performance is greatly improved – almost 2.5x for FP16 tensors – and NVIDIA has greatly expanded the formats that can be used with INT8/4 support, as well as a new FP32-ish format called TF32. Memory bandwidth is also significantly expanded, with multiple stacks of HBM2 memory delivering a total of 1.6TB/second of bandwidth to feed the beast that is Ampere. NVIDIA will be delivering the initial version of this accelerator in their now-common SXM form factor, which is a mezzanine-style card well-suited for installation in servers. On a generation-over-generation basis, power consumption has once again gone up, which is probably fitting for a generation called Ampere. Altogether the A100 is rated for 400W, as opposed to 300W and 350W for various versions of the V100. This makes the SXM form factor all the more important for NVIDIA’s efforts, as PCIe cards would not be suitable for that kind of power consumption. As for the Ampere architecture itself, NVIDIA is releasing limited details about it today. Expect we’ll hear more over the coming weeks, but for now NVIDIA is confirming that they are keeping their various product lines architecturally compatible, albeit in potentially vastly different configurations. So while the company is not talking about Ampere (or derivatives) for video cards today, they are making it clear that what they’ve been working on is not a pure compute architecture, and that Ampere’s technologies will be coming to graphics parts as well, presumably with some new features for them as well. Ultimately this is part of NVIDIA’s ongoing strategy to ensure that they have a single ecosystem, where, to quote Jensen, “Every single workload runs on every single GPU.” This is breaking news