Grovety specializes in AI-powered devices development, making trained neural networks fit for inference on microcontrollers, solving tasks of neural networks learning and fine-tuning, transfer learning on microcontrollers (On Device Learning, ODL), staying focused on LLVM and TVM frameworks. For Arm-based AI chipmakers - TVM and LLVM adaptation for the best AI tasks performance for Arm IP-cores based chips (including Ethos-U55, -U65) For Arm-based AI accelerators users - AI-Powered Devices Development - Optimizing  neural network inferences for Arm IP-cores based hardware platform (power consumption, compression, and performance) - Neural network design and implementation - Execution infrastructure deployment - OTA updates infrastructure design - Neural network and hardware platform selection to solve your task with the best performance/cost ratio - Remote Continuous Integration on the real hardware set-up and support

Solution Briefs

  • thumbnail: C/C++ Clang/LLVM Compiler Adaptation for AI Accelerator based on Arm Cortex-A5
    C/C++ Clang/LLVM Compiler Adaptation for AI Accelerator based on Arm Cortex-A5

    LLVM Clang adaptation and optimizations tools for automatic code generation using vector functionality

    Learn More
  • thumbnail: Multithread AI Software Development Support in Proprietary IDE
    Multithread AI Software Development Support in Proprietary IDE

    Proprietary IDE Enhancement to support creating multithreaded AI applications for the “Flip-Chip” multicrystal assembly.

    Learn More

Insights

  • Saving Wildlife by Using AI-powered Trap Camera Based on Arm Ethos-U55 Arm Tech Talk
    Saving Wildlife by Using AI-powered Trap Camera Based on Arm Ethos-U55

    This talk from Grovety will showcase how smart wildlife camera traps with AI capabilities powered by the Arm Ethos-U55 are being used in conservation efforts to save the endangered Persian leopards.

    Learn More
  • Minimizing Resource Usage in Microcontrollers for Cost Effective Solutions Video
    Minimizing Resource Usage in Microcontrollers for Cost Effective Solutions

    The spotlight will be on Fine-Tuning strategy - approach that plays a critical role in optimizing neural network inference. We'll illustrate how Apache TVM significantly aids in reducing device cost and energy consumption.

    Learn More