Huawei’s Kirin 990 SoC Is the First Chip With an Integrated 5G Modem

This site may earn affiliate commissions from the links on this page. Terms of use.

Huawei’s year has been anything but good, but the company has pushed ahead with new technology introductions and smartphone designs. The Chinese firm has now announced its latest SoC, the Kirin 990. The new chip will ship in two flavors — the Kirin 990, and the Kirin 990 5G. These two chips are based on the same SoC design, but there are some significant differences between them.

First, the Kirin 990 5G is built on TSMC’s 7nm+ process node, which utilizes EUV. The Kirin 990, in contrast, is a standard 7nm design. It seems as though Huawei will be the first customer to ship a part that uses EUV for manufacturing. Huawei’s stated reason for using EUV for the 5G variant is that it allowed for a smaller die. Die size on the 5G part is larger than 100mm2, while the LTE chip is less than 90mm2. Transistor counts are also significantly different, with the LTE chip at 8B and the 5G chip at 10.3B.


One interesting fact that Anandtech mentions is that the Kirin 990 was originally expected to use ARM’s Cortex-A77 CPU, not the Cortex-A76. Apparently the Huawei team didn’t like how the Cortex-A77 clocked on TSMC’s 7nm process node. The A77 had higher peak performance, but overall power efficiency between the A76 and A77 was practically identical on 7nm and the A76 design was capable of hitting much higher clocks. Supposedly the A77 tops out around 2.2GHz on 7nm at the moment and the design may not be used widely until 5nm CPUs are available.

The new ARM Mali-G76 implementation is substantially wider than the 10-core implementation used on the previous generation Kirin 980. GPU power efficiency can often be improved by using a wider GPU clocked at lower frequencies, and Huawei believes the new GPU design will still be more power-efficient than the old Kirin 980, despite being substantially wider.

The NPU design is a homegrown Huawei effort. Where the company previously licensed an NPU from Cambricon, the new Kirin 990 uses Huawei’s Da Vinci architecture. Huawei intends to scale this AI processing block from servers to smartphones. It supports both INT8 and FP16 on both cores, whereas the older Cambricon design could only perform INT8 on one core. There’s also a new ‘Tiny Core’ NPU. It’s a smaller version of the Da Vinci architecture focused on power efficiency above all else, and it can be used for polling or other applications where performance isn’t particularly time critical. The 990 5G will have two “big” NPU cores and a single Tiny Core, while the Kirin 990 (LTE) has one big core and one tiny core.

Huawei’s Balong modem will support sub-6GHz 5G signals with a maximum of 2.3Gbps download and 1.25Gbps upload. Overall CPU performance improvements from the Kirin 980 to the Kirin 990 are modest — Huawei claims single-threaded gains of 9 percent and multi-threaded boosts of 10 percent. Power efficiency, however, has improved significantly. The top-end cores are supposedly 12 percent more efficient, the “middle” cores of Huawei’s Big.Little.littlest are supposedly 35 percent more efficient, and the low-end Cortex-A55 chips are 15 percent more efficient. Most workloads are supposed to run on the middle cores for maximum performance/watt.

It seems unlikely that these devices will come to the US market in any numbers, though you may be able to buy them from third-party resellers if the Trump Administration doesn’t take further action against the company. While devices are going to start carrying 5G modems from this point forward, I’ve yet to see a 5G phone I’d actually recommend. While it’s true that the first generation of LTE devices didn’t exactly cover themselves in glory, the first generation of LTE devices didn’t overheat and shutdown when summer temperatures rose above 85F / 29.4C. They didn’t require you to be literally standing underneath an LTE access point in order to see faster service, either. Verizon has already stated that outside city centers, its 5G network will closely resemble “good 4G,” which raises the question of what, exactly, consumers are paying all this money for.

The first LTE devices were the HTC Evo 4G, the Samsung Craft, and the HTC Thunderbolt. They sold for $200, $350, and $250, respectively, though this was in the era of two-year contracts. Apple’s first LTE device was the iPhone 5, which cost $649 if purchased without a contract. Assuming Apple and the other AndroidSEEAMAZON_ET_135 See Amazon ET commerce manufacturers continue to offer 5G as a luxury feature, we’ll likely only see it on devices at or above the $1000 price point for the next 12 months. I wouldn’t pay $1000 for a phone under any circumstances, but I definitely wouldn’t step up to a $1000+ device to buy a feature that I’ve got no chance of using at any point in the next few years.

Now Read:


10 minutes mail – Also known by names like : 10minemail, 10minutemail, 10mins email, mail 10 minutes, 10 minute e-mail, 10min mail, 10minute email or 10 minute temporary email. 10 minute email address is a disposable temporary email that self-destructed after a 10 minutes.– is most advanced throwaway email service that helps you avoid spam and stay safe. Try tempemail and you can view content, post comments or download something

Apple Could Switch to ARM, But Replacing Xeon Is No Simple Endeavor

This site may earn affiliate commissions from the links on this page. Terms of use.

The question of when Apple will switch to building its own custom ARM CPU cores for its software ecosystem rather than using Intel and x86 comes up on a regular basis. On ET, we first covered the topic in 2011, and I’ve hit it several times in the intervening years. My answer has typically been some flavor of “theoretically yes, but practically (and in terms of the near future), no.”

A recent AppleInsider article does a good job of rounding up the reasons why Apple really might be taking this step soon. We’ve previously heard rumors that the company could launch such a product in 2020, and while rumors are not the same thing as a definite launch date, the piece is solid. It makes a reasonable case for why Apple may indeed take this step and references various real-world events, including Intel’s difficulties moving on past 14nm, Apple’s design efforts around GPUsSEEAMAZON_ET_135 See Amazon ET commerce and CPUs, the increasing complexity and capability of its SoCs, and the fact that Apple has built its own secondary chips, like the T2 controller.

All of these points are true, and it’s why I think the 2020 rumor deserves to be taken more seriously than the dates and ideas that we used to hear. But there is still a major piece of this puzzle that doesn’t get talked about often enough. Apple can introduce an ARM core running full macOS, but if it wants to replace x86 in its highest-end iMac Pro and Mac Pro products, it’s going to have to take on some significant design challenges that it hasn’t faced before.

Intel’s Skylake mesh interconnect. This is anything but easy to build and design.

Apple has built CPUs, yes. But it’s never tried to build, say, a 28-32-core ARM processor in a multi-socket system. To the best of my knowledge, Apple has never built a server-class chipset or designed a CPU socket for its own product families. During E3, I attended an AMD session on the evolution of its AM4 socket, and how carefully AMD had to work in order to design a 7nm product with chiplets to fit into a socket that initially deployed four identical CPU cores in a 28nm process node. Even if Apple intends to create a platform without upgradable CPUs, it will need to design its own motherboards. The socket design decisions that it makes will impact how quickly it can iterate the platform and how much work has to be done at a later time. Achievable? Absolutely. But not something one does overnight.

The routing on AMD Ryzen 7 3000 PCB. That’s the connection between one chiplet and its I/O die. This isn’t easy to design, either.

Using chiplets makes some aspects of CPU design easier, especially on leading-edge nodes, but it doesn’t simplify everything. Chiplets require interconnects, like AMD’s Infinity Fabric. Apple would need to design its own solution (there are no formal chiplet interconnect standards yet). There’s a lot of custom IP work to be done here if Apple wants to bring a part to market to replace what Intel offers in the Mac Pro.

One simple solution is for Apple to launch new ARM chips in laptops but keep desktop systems on Intel for the time being. In theory, this works fine, provided the ecosystem is ready for it and Apple can deliver appropriate binaries for applications. Software application support and user expectations could be tricky to manage here, but it’s doable. The problems for Apple, in this case, are making sure that its consumers understand any compatibility issues that might exist and that the new ARM-based products are clearly differentiated from the old x86 ones.

Is There a Reason for Apple Not to Build Its Own Mac CPUs?

There is, in fact, a reason for Apple not to build its own CPU cores for Mac. There is a non-trivial amount of work that must be done to launch a laptop/desktop processor line. Doing all of the work of developing interconnects, chiplets, chipsets, and motherboards from the ground up is more difficult and expensive than working with someone else’s pre-defined product standard and manufacturing. There’s an awful lot of work that Intel does on Core that Apple doesn’t have to do.

The question of whether it makes sense for Apple to move away from Intel CPUsSEEAMAZON_ET_135 See Amazon ET commerce is therefore partially predicated on what kind of money Apple thinks it can make as a result of doing so. Obviously capturing the value of the microprocessor can sweeten the cost structure, but capturing the value also means capturing the cost. When Apple was a non-x86 shop, its market share was significantly smaller than it is today, and the company gained some market share immediately after switching to x86. It is impossible to tell if it gained that share because its software compatibility was now much improved or because many of its systems, especially laptops, were now far more competitive with their Windows counterparts.

Apple has to consider that it will lose at least some customers if it moves away from x86 compatibility again, either because of software compatibility or because its new chips may not offer a performance improvement in specific workloads relative to Intel. The most valuable CPUs — the ones powering the Mac Pro — are also the most expensive to design and build. If Apple doesn’t think it can command the price premiums that Xeon does, it might hold off on introducing CPUs in these segments until it believes it can. Unlike 2005, when IBM couldn’t produce a G5 that fit into a laptop, Apple isn’t quite that pinched as far as market segments.

I think Apple’s CPUs have evolved enough to make a jump towards ARM and away from x86 plausible in a way it wasn’t back in 2014, but there are still some significant questions to be answered about where Apple would sell the part and whether it would attempt to replace x86 in all products, or in specific mobile SKUs. And, honestly, I think there’s a version of this story where Apple ultimately continues to work with Intel or AMD long into the future, having decidedly to deploy its own ARM IP strategically across the Mac line, or in secondary positions similar to how the T2 chip is used.

Now Read:

10 minutes mail – Also known by names like : 10minemail, 10minutemail, 10mins email, mail 10 minutes, 10 minute e-mail, 10min mail, 10minute email or 10 minute temporary email. 10 minute email address is a disposable temporary email that self-destructed after a 10 minutes.– is most advanced throwaway email service that helps you avoid spam and stay safe. Try tempemail and you can view content, post comments or download something