MLSoC™ Evaluation Board

Highlights

SiMa.ai’s Machine Learning System on Chip (MLSoC) Evaluation Board is a versatile board that uses the SiMa.ai MLSoC device.

Some of its key features include:

PCIe form factor (195.65mm x 111.15mm) with standard 98-pin PCB edge connector to interface with any standard host PC or motherboard.
Enables all the interfaces of the device and supports PCIe Gen 4.0 up to x8 lanes (x2, x4, x8), LPDDR4 x4, I2C x2, eMMC, QSPI-8 x2, 1G Ethernet x4 ports via SFP, JTAG, UART x2, Micro SD, and GPIO interfaces.
Designed to offer the highest performance for low power embedded edge machine learning applications.
MLSoC offers heterogeneous cores for processing any ML workload. Quad Arm A65 cores, a Machine Learning Accelerator (MLA) block that provides up to 50 TOPS for ML acceleration along with a Computer Vision Processor (CVP) to address any ML computational needs.
MLSoC is available in industrial and consumer temperature grades.
Supports two configurations:

o PCIe card: To function as an ML accelerator card.

o Standalone card: Uses up to four 1G Ethernet ports for ingress and egress traffic and can be used for easy bench evaluation and debug of the MLSoC device.

Find the Edge and Go Beyond

SiMa.ai’s MLSoC delivers high-performance effortless machine-learning for computer vision based embedded edge applications in markets such as smart vision, robotics, industry 4.0, autonomous vehicles, drones, and the government sector.

It is designed to meet the challenges of integrating machine learning into next generation edge applications.

The functional block diagram of the MLSoC Evaluation Board is shown below.