Due to its unique charge-domain processing architecture, AIStorm can outperform digital GPU-based solutions, delivering edge-ready solutions at 5x to 10x lower cost; available today are market-ready solutions optimized for mobile handsets, IoT, and ADAS
BARCELONA, Spain -- February 25, 2019 -- AIStorm, an innovator of high-performance AI-in-sensor processors, has introduced a family of semi-custom solutions for mobile handsets, IoT, and advanced driver-assistance systems (ADAS).
AIStorm CEO David Schie sees a huge opportunity to outperform approaches that need to digitize sensor data, a step that introduces latency and the potential to miss important information.
“Many industry players are focused on deep submicron GPU/NPU-based solutions to accelerate AI at the edge. We believe that such solutions are not compatible with the real-time processing, power, and low-cost requirements of these applications,” said Schie. “Today, we are reshaping the landscape by enabling complete solutions that include a sensor, an analog front end, and AI processing at low cost, and suitable for even the smallest form factors — without the need to digitize input data.”
AIStorm initially targets two huge markets, mobile/wearable and ADAS:
- AIStorm IoT Vision / IoT Waveform Solutions: Designed for imaging and HID/biometric applications in mobile phones, cameras, wearables & IoT applications, AIStorm offers AI-in-sensor solutions for tasks such as fingerprint sensing, gesture control, heart monitoring and heart-based identification, occupancy sensing, facial recognition, voice input, earbud, drone imaging, image stabilization, and security and intersection cameras. Custom optics or high CMRR PGA solutions are offered integrated with semi-custom variants of AIStorm’s high-performance analog AI engines.
- AIStorm ADAS Solutions: Designed for advanced driver-assistance systems, AIStorm introduces CIS, SPAD / SiPM and SiGe sensors coupled to its analog AI engines, which eliminate the need for digitization and allow continuous processing of incoming data. These systems outperform ADC solutions, which can easily miss or distort incoming information and struggle to provide selective real-time data harvesting. Solutions at NIR, 1550nm and CIS are offered, as well as mirror, biasing, high-voltage driver, image-stabilization, and image-processing solutions. Other solutions include gesture control, eye-blink monitoring, voice, and wavelet-based failure detection.
Using sensor data directly—without digitization—enables real-time processing
AI systems require information be available in digital form before they can process data, however sensor data is analog. Processing this digital information requires advanced and costly GPU/NPUs that are not suitable for mobile devices because they require continuous digitization of input data, which consumes significant power and introduces unavoidable digitization delay (latency). AIStorm negates these disadvantages by processing sensor data directly in its native analog form—in real time—by using charge-domain processing instead of GPU/digital processing.
“As digital AI processing seems to reach its limits, the next generation of deep-learning systems will require analog AI cores. With our recent investment in AIStorm, we affirm our belief that the time is right for embedded analog AI-in-sensor technology, and that AIStorm technology is the right solution,” said Dr. Avi Strum, SVP/GM of the sensors business unit of TowerJazz. “The combination of TowerJazz’s rich imaging and non-imaging sensors technologies with AIStorm’s artificial intelligence core will provide unique solutions to the industrial, commercial, and automotive markets.”
AIStorm is the pioneer and leader in AI-in-sensor processing, which eliminates the latency, power and cost associated with digital GPU/NPU-based implementations at the edge. AIStorm is headquartered in Silicon Valley and led by a team that includes industry veterans responsible for development of more than a thousand products, as well as for P&L and significant revenue growth at leading semiconductor companies. For more information, visit https://aistorm.ai