STMicroelectronics combines a sensor and a digital signal processor (DSP) on the same silicon to enable the concept of an intelligent sensor processing unit, or ISPU. The company said it embeds brains into sensors to facilitate an “onlife era” enabled by smart sensors that can sense, process and take action.
Many companies talk about enabling localized and intelligent decision-making at the edge to overcome many issues such as latency, security, privacy, and bandwidth availability. But with the ISPU, STMicroelectronics takes the edge capability one step further to combine signal processing and artificial intelligence algorithms on MEMS sensors, injecting local decision-making and saving more space on storage devices. system-in-package, and reducing power by up to 80% – ST calculations show 5-6x savings over system-in-package approaches in sensor fusion applications; they also show a 2-3x saving in RUN mode.
In its announcement, ST said its ISPU offers substantial benefits in terms of power consumption, packaging, performance and price. The proprietary ultra-low-power DSP can be programmed in C, familiar to many engineers. It also enables quantized AI sensors to support one-bit full precision neural networks. This ensures good accuracy and efficiency in tasks such as activity recognition and anomaly detection by analyzing inertial data.
ST’s proprietary, C-programmable DSP is an enhanced 32-bit Reduced Instruction Set Computing (RISC) machine. It is extensible (in the chip design phase) for dedicated instructions and hardware components. The processor offers a full-precision floating-point unit, uses a fast four-stage pipeline, operates from 16-bit variable-length instructions, and includes a single-cycle 16-bit multiplier. The interrupt response is a spritely four cycles. ST’s sensors with ISPU will be packaged in standard 3mm x 2.5mm x 0.83mm packages and will be compatible with their predecessors (ST), allowing for quick upgrades.
Commenting on the importance of the ISPU, Andrea Onetti, Executive Vice President, MEMS Subgroup for STMicroelectronics, said, “Although technically challenging, integrating ST’s sensors on the same piece of silicon with our ISPU improves sensor-based systems from an online system. experience to life experience. It advances sensor functionality to accelerate decision-making by reducing data transfers, improving privacy by keeping data local, while reducing size and power consumption, which lowers costs. Moreover, the ISPU is easily programmable with commercial AI models and can ultimately work with all major AI tools. The company said that with more than 10 million C language developers, its new ISPU will allow many to deploy this intelligence capability at the edge.
In its launch material, ST talks about a shift in society towards an “onlife era” that requires this level of integration that its new ISPU offers. He says: “The onlife era recognizes living with the continuous assistance of connected technologies, enjoying natural and seamless interactions and seamless transitions, with no perceptible distinction between online and offline. With the ISPU, ST enables this era by helping to migrate intelligent processing to sensors that support the web of life: no longer at the periphery but in the periphery.
The first devices in the ISPU family are expected in the second quarter of 2022.