June 7, 2021

Mythic M1076 400x275Mythic, which develops analog AI processors with compute-in-memory technology, has launched the new M1076 Analog Matrix Processor (Mythic AMP) to address performance, scalability and power efficiency for edge AI applications. The M1076 AMP comes in several form factors: a stand-alone processor; an ultra-compact PCIe M.2 card; and a PCIe card with up to 16 AMPs. The new products will be available for evaluation beginning in July 2021.

The processors can support up to 25 TOPS of AI compute in a 3W power envelope, consuming up to 10x less power than a typical system-on-chip (SoC) or GPU solution, Mythic said. In a 16-chip configuration, the M1076 AMP PCIe card delivers up to 400 TOPS of AI compute while only consuming 75W. The processor has been optimized to scale from edge endpoints to server applications, addressing vertical markets that include smart cities, industrial applications, enterprise applications, collaborative robotics, and consumer devices.

“Mythic’s groundbreaking inference solution takes AI processing and energy-efficiency to new heights,” said Tim Vehling, senior vice president, product and business development at Mythic. “With its ability to scale from a compact single-chip to a powerful 16-chip PCIe card solution, the M1076 AMP makes it easier for developers to integrate powerful AI applications in a wider range of devices that are constrained by size, power, and thermal management challenges.”

The M1076 AMP combines power efficiency with performance into a 22 mm by 30 mm PCIe M.2 A+E Key card for space-constrained embedded edge AI applications. For edge AI systems that require more demanding workloads, including many streams, multiple large, deep neural networks, and higher-resolutions and frame rates, a PCIe card form-factor with 16 Mythic AMPs supporting up to 400 TOPS and 1.28 billion weights in a 75W power profile can be utilized, Mythic added.

The M1076 AMP is ideal for video analytics workloads, including object detection, classification, and depth estimation for industrial machine vision, autonomous drones, surveillance cameras, and network video recorders. The processor can also support cutting-edge AR/VR applications with low latency human body pose estimation, expected to drive future devices in smart fitness, gaming, and collaborative robotics.

The company recently announced raising $70 million in Series C funding, bringing the company’s total funding to $165.2 million. With its new round of funding, the company said it will focus on scaling production of the company’s solutions, investing in its technology roadmap, and increasing support for its customer base across Asia Pacific, Europe, and the U.S.

For more details on the new M1075 processor, head to the Mythic website.