Grovety – EdgeAI / tinyML

YOU

Create edge AI/tinyML products based on

Arm Cortex-M55

Ethos-U55

Xilinx Kria

Adapt and optimize neural networks, develop board support packages and firmware

Create and optimize
Neural Networks

Adapt your NNs Model Zoo for target hardware and optimize it using hardware features (including ML compiler, assembler optimization)

Create new AI accelerators with either MCUs or FPGAs

Develop SDK, ML compilers, BSPs, demo kits, model zoo

Our Expertise in Embedded

We simplify and optimize neural network inference for Arm Cortex-M55 and Ethos-U55, Xilinx Kria based Edge ML solutions. We leverage TVM, uTVM, TF Lite, Vela, Vitis AI, and LLVM. We accomplish this via ML compiler tuning and fine manual optimization on the assembler level.

Network-based Transfer Learning

Semiconductors – TVM Translator for AI accelerator (Tensor processor)

TVM optimization for ARMv7-M+

Launching Audio Processing Inference on Knowles IA8201

Embedded

We develop board support packages, drivers, and other system software. We leverage Linux, ERIKA, Zephyr, FreeRTOS, U-Boot, Yocto, OpenEmbedded, and more.

Chilicon Power – Obsolete Wi-Fi module Replacement

Smart Control Case for TWS Earbuds

Semiconductors – LLVM Compiler

ERIKA RTOS

SDK

We develop compilers, simulators, toolchains, and IDEs. We utilise LLVM, LLDB, GDB, and Eclipse.

Samsung – SDK

Semiconductors – TVM

Semiconductors – LLVM Compiler

Translator for AI accelerator (Tensor processor)

TVM optimization for ARMv7-M+

Products

Using our SDK and ML experience in the Embedded field we are now optimizing popular networks and preparing them to run on devices based on Arm and Xilinx platforms.

➞ If you are developing end devices we are able to provide you ready-to-run networks as well as develop new ones to fit your scenarios.

➞ If you are developing neural networks we can help you adapt and optimize them for your target platforms.