Qualcomm Unveils Chip That Might Finally Make Wear OS Usable

Despite launching a year earlier, Google’s Wear OS platform has been unable to make even a tiny dent in the Apple Watch’s market share. Certainly, some of the blame rests squarely on Google’s proverbial shoulders as it struggles to design compelling experiences on such a small screen. However, the sluggish, power-hungry wearable chipsets in watches have been an even bigger problem. Qualcomm has announced a pair of new wearable chips that might finally fix that. The Snapdragon Wear 4100 and 4100 Plus improve on the old Wear 3100 in every way, but it’ll take more than new hardware to turn around Google’s smartwatch project. 

First, a little history. The first Android-powered smartwatches ran on low-power phone processors like the Snapdragon 400. Later, Qualcomm produced the Wear 2100 with a few modifications for wearables, but the Cortex A7 CPU cores were slow even by 2016’s standards. The Wear 3100 came in 2018 with a high-efficiency co-processor to improve always-on features, but the A7 CPU cores were even more out-of-date by then. The 4100 finally revamps the entire chip, which should make future wearable devices much more capable. We hope. 

The Wear 4100 and 4100 Plus share all the same core features. In place of the archaic 28nm A7 cores, the 4100s have four 12nm Cortex A53 cores clocked at 1.7GHz — Qualcomm says it’s about 85 percent faster than the 3100. Memory speed is also nearly doubled from 400MHz to 750Mhz. The GPU is about two and a half times faster, too. 

The Wear 3100 debuted the QCC1110 co-processor, and it’s still around in the new generation. However, it’s only part of the 4100 Plus chip — this is what makes it the “Plus.” The “Enhanced” QCC1110 has a Cortex M0 processor core along with its own dedicated memory and display controller. It supports more colors in always-on mode, number kerning, haptics, and more. Manufacturers that choose to go with the regular 4100 won’t have the enhanced always-on functionality. 

Qualcomm has started shipping chips to its partners, but there aren’t many companies still trying to make Wear OS devices. Fossil will probably get to the 4100 eventually, but Mobvoi says it’s already working on a 4100-based watch. Google itself might finally give wearables a shot with its pending acquisition of Fitbit. But after years of mediocre hardware and software, is anyone still waiting for a Google smartwatch?

Now read:

from ExtremeTechExtremeTech https://www.extremetech.com/mobile/312258-qualcomm-unveils-chip-that-might-finally-make-wear-os-usable

from Blogger http://componentplanet.blogspot.com/2020/06/qualcomm-unveils-chip-that-might.html

Shirley Oaks: Children ‘drugged, tortured and sexually assaulted’

Barristers representing victims accuse Lambeth Council of knowing about the abuse, but doing nothing.

from BBC News – London https://www.bbc.co.uk/news/uk-england-london-53237121

from Blogger http://componentplanet.blogspot.com/2020/06/shirley-oaks-children-drugged-tortured.html

Early Apple ARM Benchmarks Leak, Show Intriguing Picture vs. x86

Ever since Apple announced the A12Z and its shift away from x86, there’ve been questions about exactly how these ARM chips will perform and what we can expect from them. The first benchmark results are starting to appear from Apple dev kits, and as long as you take them with a mountain of salt, they’re pretty interesting.

What we have to work with here is Geekbench. Geekbench tends to be a very strong test for Apple CPUs, but in this case, we’re talking about Apple CPUs running the x86 version via emulation. Even if Geekbench does favor Apple CPUs more than x86, running the application through an emulator is going to hit performance.

Also, note that the application only reports four cores. The A12Z is nominally an eight-core chip, with four big, four little. It isn’t clear if these dev systems only use the “big” cores, or if the application simply doesn’t detect them properly, or if this is an emulator limitation. Regardless, it’s very early days and these are early results.

Here’s the data as it has come in to Geekbench 5.

We see single-threaded scores of 844 and a multi-threaded score of 2958, which yields a scaling factor of 3.5x. On the x86 side of the equation, there’s the 13-inch MacBook Pro, with scores of 1218 and 4233. This also works out to a scaling factor of approximately 3.5x. Similarly, the Macbook Pro 13-inch is roughly 1.44x faster than the A12Z in both single-threaded and multi-threaded mode.

One thing to keep in mind is that emulation performance can vary drastically depending on the application. Some programs might run with relatively small penalties, while others crater and die. Rosetta 2 is specifically designed to avoid those outcomes, but historically, there’s a nasty corner case or two lurking somewhere in any emulator. Some applications are harder to emulate than others. But the upshot of this effect is that we don’t really know if that 1.44x lead the 13-inch MacBook has is the product of emulator handicapping or if it’s a pretty good look at the CPU’s performance. Data from the iPad Pro suggests it might be the former.

If we assume that the A12X in the iPad Pro is a pretty good stand-in for the A12Z, we can check ARM-native Geekbench performance, albeit in iOS, not macOS. Here, we’re looking at 1120 single-core, 4650 multi-core, with a scaling factor of 4.16x. The MacBook Pro 13-inch is only about 8 percent faster than the iPad Pro in single-thread, and 10 percent slower in multi-thread.

Mac-Mini-Feature

Frankly, that should send a frisson of fear through Intel and AMD. The implication of these results is that the gap between the 13-inch Mac and the A12Z is largely the result of emulation. That’s not a guarantee, because OS differences matter in situations like this, but it certainly looks as though most of the penalty the A12Z is carrying is related to emulating x86 code.

That fact should send a frisson of fear down AMD and Intel’s collective spines. Apple’s year-on-year record of delivering new performance improvements is considerably better than Intel’s right now. AMD can make a much stronger argument for its own recent improvement, thanks to Ryzen, but the enormous 1.52x IPC improvement from Excavator to Ryzen tilts the comparison a bit. To put it bluntly, AMD’s improvements the last three years would be a little less impressive if Bulldozer hadn’t been such an awful chip to start with.

We’re in a weird situation at the moment. Intel has always been Apple’s chief supplier, but AMD is selling more performant mobile CPUs today, making them the more obvious point of comparison. The 4900HS appears to score a 1116 single-core and a 7013 multi-threaded score. x86 MT is, at least, in no immediate danger, in absolute terms. Keep in mind that the 4900HS also draws far more power than either the Intel or Apple chips.

What we see here isn’t proof that Apple will launch a MacBook ARM chip that rivals the best Intel and AMD can offer — but it certainly puts a floor under expected performance, barring unusual emulator quirks that Apple will spend the next few months quashing. The x86 companies may want to ask their mobile CPU designers to put an extra pot of coffee on.

Final note: These kits are not the CPUs Apple will ship to customers and do not represent final performance.

Feature image by Apple.

Now Read:

from ExtremeTechExtremeTech https://www.extremetech.com/computing/312234-apple-a12z-arm-performance-vs-x86

from Blogger http://componentplanet.blogspot.com/2020/06/early-apple-arm-benchmarks-leak-show.html