Create edge AI/tinyML products based on
Arm Cortex-M55
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

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

Car Dashboard

Samsung – SSD

BVG Group – BSP

NVIDIA Jetson device

Semiconductors – BSP

Semiconductors – LLVM Compiler



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.
Optimized neural network models that we have made to run on
Arm Cortex-M55 and Ethos-U55
Body parts detection (MoveNet.Thunder) - head, shoulders, elbows, knees
Supersampling (Deep Convolution Network)
... we are regularly working to add new items to this list
Tools: Arm Virtual Hardware(Corstone-300 U55/U65 in the cloud), C++, Python, The Vela compiler, Arm gcc
Xilinx Kria System-on-Modules (SoMs)
Face landmarks detection (PFLD)
Face recognition (Densebox)
Supersampling (Deep Convolution Network)
... we are regularly working to add new items to this list
Tools: Xilinx Vitis AI, Python, NVIDIA CUDA, RTX2080, Pytorch

Technical experience history

For over 20 years we have been creating development tools, network protocols and low-level software.




+1 (619) 314-9019
Hae Yeon Min
Wilmington, Delaware
legal address
San Diego, California
project managment, representative
Yerevan, Armenia
research & development center
Belgrade, Serbia
research & development center
Seoul, South Korea
Asia representative
Copyright © Grovety Inc.