While AI was once a buzzword to describe new levels of machine or device automation, there is no longer any doubt that true AI-based machine learning and intelligence are making an impact. significant on more and more consumer, commercial and industrial devices. However, the AI edge (or endpoints) has a unique set of requirements compared to AI in the data center or cloud. At the edge, robust, low-latency (5G) connectivity is essential, along with low power consumption and the ability to deliver high-performance AI processing on-device, with minimal leaning. on cloud data centers, to achieve target latency and performance.
Qualcomm is one of the key players driving the advancement of the AI-powered connected smart edge. The company has been innovating in this area for years and multiple generations of products now, so it has shipped more than 1.8 billion AI-enabled chips to date, when you consider the number of products it has. it comes with an AI engine on board.
Measure AI performance – Enter MLPerf
After recently submitting MLPerf results for its Snapdragon 8+ Gen 1 mobile platform SoC – demonstrating a notable performance lead in AI workloads such as natural language processing, images and object detection – Qualcomm continues to execute in the space enabling more capable and intelligent mobile and peripheral devices, from smartphones to IoT, automotive and industrial automation.
MLPerf is a widely respected machine learning benchmark offered by MLCommons, which is a consortium of founding members that established a set of industry standard metrics for measuring machine learning performance in 2018. Since then, MLCommons and MLPerf have been adopted and contributed to by virtually every major heavyweight, from Intel, AMD, NVIDIA and Arm, to Facebook, Google, Mediatek and many more, like Qualcomm.
As you can see above, except for the offline image classification, even Qualcomm’s previous generation Snapdragon 8 Gen 1 platform was ahead of the pack when it comes to different workloads. of smartphone AI, and its Snapdragon 8+ Gen 1 platform is currently unmatched on every level. .
Where does Qualcomm AI live
Beyond benchmarks, Snapdragon AI engines power a slew of devices and platforms, scaling from less than a compute TOP to low-power functionality, like noise-cancelling wireless headphones. noise, to more powerful devices like AR glasses, where AI helps with hand and eye tracking 6 DoF (6 degrees of freedom) prediction and spatial awareness.
Boosting its power, Qualcomm’s Hexagon AI engine can also be found in Snapdragon 8cx Gen 3 powered laptops like Lenovo’s ThinkPad X13, where it’s harnessed for video conferencing with background blurring, image beautification ‘AI, as well as noise and echo cancellation for audio streams.
Robotics and industrial automation and monitoring are also big market opportunities for Qualcomm AI, where machine vision and real-time safety monitoring are key to keeping factories running smoothly and maintaining safe working environments. for employees. However, perhaps one of the biggest opportunities that Qualcomm Snapdragon AI is currently focusing on is the connected, software-defined smart car.
Here, Snapdragon Digital Chassis solutions with on-board AI engines power everything from infotainment systems to climate control, driver monitoring for safety, ADAS (Advanced Driver Assistance Systems) for self-driving functionality, lane detection, navigation and more.
You might say that Qualcomm’s AI engines are one of the tech industry’s best-kept secrets, as they’re built into many of the company’s chips and offer a kind of unsung hero capability that allows more intelligence, adaptation and control of the machine. .
As many others have noted, AI and machine learning permeate everything in electronics, and in fact are now even helping to design new chips. With Qualcomm’s long heritage in AI development, performance-per-watt leadership, and a rich set of development tools and frameworks like Qualcomm AI Stack, AI engines and Qualcomm’s silicon solutions are powering more and more connected and smart devices. edge.