SoM for accelerated machine learning on edge devices
Variscite has announced a new, state-of-the-art System on Module (SoM) for efficient machine learning on edge devices. The VAR-SOM-MX93 is based on the NXP i.MX 93 processor, the industry’s first implementation of the Arm® neural processing unit, Ethos™-U65 microNPU, and offers a rich set of applications targeting industrial, IoT, smart home, automotive systems, and the wearables markets.
The VAR-SOM-MX93 is designed to accelerate machine learning (ML), and offers an energy flex architecture for efficient processing. Along with the 1.7 GHz Dual Cortex™-A55 NXP i.MX 93, the module uses an additional 250 MHz Cortex-M33 real-time co-processor and a dedicated Neural Processing Unit (NPU) 256 MACs operating up to 1.0 GHz and 2 OPS/MAC, for a combination of performance and efficiency within an optimized footprint that enables developers to create high-performance, cost-effective and energy-efficient ML applications.
The new SoM offers camera interfaces and high-quality image processing (MIPI-CSI2 and MIPI-DSI 1920×1200 24-bit) plus a range of connectivity options: certified dual-band WiFi, BT/BLE, dual GbE, dual USB2 and CAN-FD. Security is implemented via NXP’s EdgeLock® secure enclave, a preconfigured, self-managed, autonomous security subsystem.
“The VAR-SOM-MX93 provides customers with a high-quality, future-proof SoM that enables ML capabilities, security and energy efficiency required of today’s smartedge devices,” said Ofer Austerlitz, VP Business Development and Sales of Variscite. “This is the next generation of NXP processors and Variscite SoMs, for edge and endpoint computing that pushes the boundaries of what was previously possible.”
The VAR-SOM-MX93 is part of the VAR-SOM Pin2Pin product family, which allows customers to enjoy significant long-term advantages of scalability options as well as reduced development time, costs, and risks. Starting from i.MX6UL/i.MX6ULL modules, through i.MX 6, i.MX 8M Nano, i.MX 8M Mini, i.MX 8X up to i.MX 8M Plus and i.MX 8QuadMax based modules.
Also availble is an evaluation kit that includes the SoM with Symphony Board. The kit also includes a Low Voltage Differential Signalling (LVDS) display with a touch panel and display bridges.
Both the evaluation kit and the SoM are now available to Variscite partners and alpha customers receiving priority fulfillment. The VAR-SOM-MX93 is included in Variscite’s long-term longevity plan and will provide an expected availability of 15 years.
Python API for System on Modules simplifies Edge AI/ML
Startup raises seed funding for adaptive machine learning
Imagimob and Syntiant partner on production-ready tinyML
RISC-V embedded cores enable AI/ML edge customization
Process helps technology firms develop safer AI, machine learning