Think Silicon - NEOX GA100
Last updated
Last updated
NEOX GA100 is the industry first RISC-V general purpose GPU for the MCU market enabling graphics, AI and compute on the same IP. It builds on Think Silicon’s hugely successful NEMA Pico GPU series.
It addresses the Graphics and AI requirements for a diverse set of vertical markets in the embedded space including wearables (smartwatches, smart glasses, hearables), smart home (thermostats, speakers, cameras, washing machines), mobility (e-bikes, e-scooters) and industrial HMI/IOT.
NEOX | GA100 is delivered with a complete suite of AI tools and libraries (NEOX AI SDK) for Tflite for MCU ecosystem. The NEOX AI SDK has been integrated into Edge Impulse platform enabling ML developers to access a complete set of ML tools to collect and shape data, perform model training and easily assess how much inference time, power consumption and RAM/Flash will be required for their specific AI use case on the NEOX® | GA100. Example use cases that would be ideal targets for NEOX GA100 include detecting health anomalies, audio processing and computer vision
Interested users can deploy their AI algorithms on the NEOX GA100 hardware by downloading a NEOX® | Bits ISO image onto the Xilinx ZU19EG FPGA development board. The ISO image includes an out-of-box software environment designed to showcase and validate the graphics and AI technology developed by Think Silicon.
For further information, please contact Think Silicon AI Application Engineering team info_ai_tsi@amat.com.
Since Think Silicon's Neox SDK has been integrated into Edge Impulse for evaluation of model performance. There is no dependencies to install to utilized this feature. You may contact Think Silicon for a copy of the SDK and inquire about physically evaluation of their devices.
Edge Impulse is platform that can collect data, process, and train many different types of models that are capable of running on the Neox GA100. Please follow the Getting Started guides to create your first project.
Many of the Think Silicon AI-SDK tools are integrated into the backend of Edge Impulse. Below we describe each tool from the AI-SDK that is used to get the best performing models you must specify your project's deployment target as Think Silicon Neox GA100 (200 MHz). The tools are automatically used during training and deployment if the Neox target is chosen.
When you start a project on Edge Impulse you may be asked to specify which device you intend to run on. Please choose the Think Silicon Neox GA100 (200 MHz) option in the dialog. This will ensure that the Think Silicon simulators will be used to generate information like inferencing time, RAM, and flash information specifically for the Neox GA100.
The Graph Analyzer checks if a TFLITE graph is supported by the Neox device. This tool checks the operators of the graph and if the graph has operators not supported will give information in the log file outputs during model training and deployment.
The Model Compiler quantizes and then analyzes the model to apply optimizations to ensure the best performance for running on Neox.
In order to achieve full hardware acceleration models must be converted from their original format to run on a Neox enabled device. The Think Silicon Neox Deployment Block outputs a TFLITE graph that would be capable of running on the Neox. You may use this output with the Neox SDK to evaluate model performance on a Neox device. Please contact Think Silicon for a physical evaluation model of the Neox GA100
