Whitepapers

How Machine Learning Transforms the Landscape For Embedded IoT Devices

The Ensemble family from Alif Semiconductor is among the first of this new generation of devices to reach the market, delivering more than 480 times the inferencing performance of the fastest conventional MCUs based on Cortex-M cores. The family contains single core and dual core Cortex-M55 MCUs, accelerated with Ethos-U55, as well as multicore fusion processors that combine Cortex-M55, Ethos-U55, and Cortex-A32.

Read More

AI/ML Design Flows

Alif’s MCUs are equipped with one or two “ML islands”. Each of these islands consists of a combination of Cortex-M55 and Ethos-U55 NPU (neural processing unit). The following document describes the steps how a model, that was trained and converted to a TFLite (quantized) format, needs to be further processed so it can take advantage of the NPU inference acceleration.

Read More

Arm Cortex-M55 Optimization and Tools

The Cortex-M55 is the first released CPU based on the Armv8.1-M architecture – the biggest architectural revision so far to the M-profile, in terms of its effect on general application code. This whitepaper looks at the comparative performance of current toolchains for the Cortex-M55 CPU as used in Alif MCUs and Fusion Processors and digs into the background, and the underlying new optimization issues.

Read More

Alif Ensemble Fusion Processors System Architecture

This whitepaper introduces the system architecture that the Ensemble family devices are built upon, along with important system concepts. It includes descriptions of the various software execution environments, memories, peripherals, and the connections between them. This document also describes the security enclave, debug, and deployment workflows along with an overview of the device boot process.

Read More