MM1108 / ME1108 M.2 Cards
M1108 Mythic AMP performance in a compact form-factor
Overview
Features
Workflow
Models
Resources

- M1108 Mythic AMP™ with support for up to 113M weights on-chip
- Model parameters stored and matrix operations executed on-chip by AMP tiles
- No external DRAM required
- 4-lane PCIe 2.1 for up to 2GB/s bandwidth
- SMBus for EEPROM and PMIC access
- Support for standard frameworks, including PyTorch, TensorFlow 2.0, and Caffe
- Pre-qualified networks including object detectors, classifiers, pose estimators, with more being added
- OS Support: Ubuntu, NVIDIA L4T, and Windows (future release)
DNN models developed in standard frameworks such as Pytorch, Caffe, and TensorFlow are implemented and deployed on the Mythic Analog Matrix Processor (Mythic AMP™) using Mythic’s AI software workflow. Models are optimized, quantized from FP32 to INT8, and then retrained for the Mythic Analog Compute Engine (Mythic ACE™) prior to being processed through Mythic’s powerful graph compiler. Resultant binaries and model weights are then programmed into the Mythic AMP for inference. Pre-qualified models are also available for developers to quickly evaluate the Mythic AMP solution.

Mythic provides powerful pre-qualified models for the most popular AI use cases. Models have been optimized to take advantage of the high-performance and low-power features of Mythic Analog Matrix Processors (Mythic AMP™). Developers can focus on model performance and end-application integration instead of the time-consuming model development and training process. Available pre-qualified models in development:
Mythic is continuously adding more pre-qualified models and use cases to our portfolio. For more information, please contact
sales@mythic-ai.com