M1108 Analog Matrix Processor

Overview
Features
Workflow
Models
Resources

The M1108 Mythic AMP™ delivers up to 35 TOPS in a single chip for high-end edge AI applications. The M1108 integrates 108 AMP tiles to store up to 113M weight parameters and execute matrix multiplication operations without any external memory. This allows the M1108 to deliver the AI compute performance of a desktop GPU while consuming 1/10th the power - all in a single chip.

Array of 108 AMP tiles, each with a Mythic Analog Compute Engine (Mythic ACE™)
Capacity for up to 113M weights - able to run single or multiple complex DNNs entirely on-chip
On-chip DNN model execution and weight parameter storage with no external DRAM
Deterministic execution of AI models for predictable performance and power
Execution of models at higher resolution and lower latency for better results
Support for INT4, INT8, and INT16 operations
4-lane PCIe 2.1 interface with up to 2GB/s of bandwidth for inferencing processing
Available I/Os – 10 GPIOs and UARTs
19mm x 19mm BGA package
Typical power consumption running complex models ~4W

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: