Personal blog of Yzmir Ramirez

AWS today announced a number of IoT-related updates that, for the most part, aim to make getting started with its IoT services easier, especially for companies that are trying to deploy a large fleet of devices. The marquee announcement, however, is about the Alexa Voice Service, which makes Amazon’s Alex voice assistant available to hardware manufacturers who want to build it into their devices. These manufacturers can now create “Alexa built-in” devices with very low-powered chips and 1MB of RAM.

Until now, you needed at least 100MB of RAM and an ARM Cortex A-class processor. Now, the requirement for Alexa Voice Service integration for AWS IoT Core has come down 1MB and a cheaper Cortex-M processor. With that, chances are you’ll see even more lightbulbs, light switches and other simple, single-purpose devices with Alexa functionality. You obviously can’t run a complex voice-recognition model and decision engine on a device like this, so all of the media retrieval, audio decoding, etc. is done in the cloud. All it needs to be able to do is detect the wake word to start the Alexa functionality, which is a comparably simple model.

“We now offload the vast majority of all of this to the cloud,” AWS IoT VP Dirk Didascalou told me. “So the device can be ultra dumb. The only thing that the device still needs to do is wake word detection. That still needs to be covered on the device.” Didascalou noted that with new, lower-powered processors from NXP and Qualcomm, OEMs can reduce their engineering bill of materials by up to 50 percent, which will only make this capability more attractive to many companies.

Didascalou believes we’ll see manufacturers in all kinds of areas use this new functionality, but most of it will likely be in the consumer space. “It just opens up the what we call the real ambient intelligence and ambient computing space,” he said. “Because now you don’t need to identify where’s my hub — you just speak to your environment and your environment can interact with you. I think that’s a massive step towards this ambient intelligence via Alexa.”

No cloud computing announcement these days would be complete without talking about containers. Today’s container announcement for AWS’ IoT services is that IoT Greengrass, the company’s main platform for extending AWS to edge devices, now offers support for Docker containers. The reason for this is pretty straightforward. The early idea of Greengrass was to have developers write Lambda functions for it. But as Didascalou told me, a lot of companies also wanted to bring legacy and third-party applications to Greengrass devices, as well as those written in languages that are not currently supported by Greengrass. Didascalou noted that this also means you can bring any container from the Docker Hub or any other Docker container registry to Greengrass now, too.

“The idea of Greengrass was, you build an application once. And whether you deploy it to the cloud or at the edge or hybrid, it doesn’t matter, because it’s the same programming model,” he explained. “But very many older applications use containers. And then, of course, you saying, okay, as a company, I don’t necessarily want to rewrite something that works.”

Another notable new feature is Stream Manager for Greengrass. Until now, developers had to cobble together their own solutions for managing data streams from edge devices, using Lambda functions. Now, with this new feature, they don’t have to reinvent the wheel every time they want to build a new solution for connection management and data retention policies, etc., but can instead rely on this new functionality to do that for them. It’s pre-integrated with AWS Kinesis and IoT Analytics, too.

Also new for AWS IoT Greengrass are fleet provisioning, which makes it easier for businesses to quickly set up lots of new devices automatically, as well as secure tunneling for AWS IoT Device Management, which makes it easier for developers to remote access into a device and troubleshoot them. In addition, AWS IoT Core now features configurable endpoints.

At its annual TechCon event in San Jose, Arm today announced Custom Instructions, a new feature of its Armv8-M architecture for embedded CPUs that, as the name implies, enables its customers to write their own custom instructions to accelerate their specific use cases for embedded and IoT applications.

“We already have ways to add acceleration, but not as deep and down to the heart of the CPU. What we’re giving [our customers] here is the flexibility to program your own instructions, to define your own instructions — and have them executed by the CPU,” ARM senior director for its automotive and IoT business, Thomas Ensergueix, told me ahead of today’s announcement.

He noted that Arm always had a continuum of options for acceleration, starting with its memory-mapped architecture for connecting over a bus GPUs and today’s neural processor units. This allows the CPU and the accelerator to run in parallel, but with the bus being the bottleneck. Customers also can opt for a co-processor that’s directly connected to the CPU, but today’s news essentially allows Arm customers to create their own accelerated algorithms that then run directly on the CPU. That means the latency is low, but it’s not running in parallel, as with the memory-mapped solution.

As Arm argues, this setup allows for the lowest-cost (and risk) path for integrating customer workload acceleration, as there are no disruptions to the existing CPU features and it still allows its customers to use the existing standard tools with which they are already familiar.

For now, custom instructions will only be available to be implemented in the Arm Cortex-M33 CPUs, starting in the first half of 2020. By default, it’ll also be available for all future Cortex-M processors. There are no additional costs or new licenses to buy for Arm’s customers.

Ensergueix noted that as we’re moving to a world with more and more connected devices, more of Arm’s customers will want to optimize their processors for their often very specific use cases — and often they’ll want to do so because by creating custom instructions, they can get a bit more battery life out of these devices, for example.

Arm has already lined up a number of partners to support Custom Instructions, including IAR Systems, NXP, Silicon Labs and STMicroelectronics .

“Arm’s new Custom Instructions capabilities allow silicon suppliers like NXP to offer their customers a new degree of application-specific instruction optimizations to improve performance, power dissipation and static code size for new and emerging embedded applications,” writes NXP’s Geoff Lees, SVP and GM of Microcontrollers. “Additionally, all these improvements are enabled within the extensive Cortex-M ecosystem, so customers’ existing software investments are maximized.”

In related embedded news, Arm also today announced that it is setting up a governance model for Mbed OS, its open-source operating system for embedded devices that run an Arm Cortex-M chip. Mbed OS has always been open source, but the Mbed OS Partner Governance model will allow Arm’s Mbed silicon partners to have more of a say in how the OS is developed through tools like a monthly Product Working Group meeting. Partners like Analog Devices, Cypress, Nuvoton, NXP, Renesas, Realtek,
Samsung and u-blox are already participating in this group.

Qualcomm today said it wouldn’t extend its offer to buy NXP for $44 billion today as part of its release for its quarterly earnings, and instead be returning $30 billion to investors in the form of a share buy-back.

So, barring any last-second changes in the approval process in China or “other material developments”, the deal is basically dead after failing to clear China’s SAMR. As the tariff battle between the U.S. and China has heated up, it appears the Qualcomm/NXP deal — one of the largest in the semiconductor industry ever — may be one of its casualties. The White House announced it would impose tariffs on Chinese tech products in May earlier this year, kicking off an extended delay in the deal between Qualcomm and NXP even after Qualcomm tried to close the deal in an expedient fashion. Qualcomm issued the announcement this afternoon, and the company’s shares rose more than 5% when its earnings report came out.

“We reported results significantly above our prior expectations for our fiscal third quarter, driven by solid execution across the company, including very strong results in our licensing business,” Qualcomm CEO Steve Mollenkopf said in a statement with the report. “We intend to terminate our purchase agreement to acquire NXP when the agreement expires at the end of the day today, pending any new material developments. In addition, as previously indicated, upon termination of the agreement, we intend to pursue a stock repurchase program of up to $30 billion to deliver significant value to our stockholders.”

Today’s termination also marks the end of another chapter for a tumultuous couple of months for Qualcomm. The White House blocked Broadcom’s massive takeover attempt of Qualcomm in March earlier this year, and there’s the still-looming specter of its patent spat with Apple. Now Qualcomm will instead be returning an enormous amount of capital to investors instead of tacking on NXP in the largest ever consolidation deal in the semiconductor industry.