Delivers up to 25 TOPS in a single chip and executes matrix multiplication operations without any external memory
The M1076 Analog Matrix Processor (AMP) by Mythic delivers up to 25 TOPS in a single chip for high-end edge AI applications. It integrates 76 AMP tiles to store up to 80M weight parameters and execute matrix multiplication operations without any external memory. This allows the M1076 to deliver the AI compute performance of a desktop GPU while consuming up to 1/10th of the power – all in a single chip.
Key Features include:
- On-chip DNN model execution and weight parameter storage with no external DRAM
- Execution of models at higher resolution and lower latency for better results
- 4-lane PCIe 2.1 interface with up to 2GB/s of bandwidth for inferencing processing
- Support for INT4, INT8, and INT16 operations
- Deterministic execution of AI models for predictable performance and power
- Typical power consumption running complex models 3~4W
Mythic provides powerful pre-qualified models for the most popular AI use cases. Models have been optimised to take advantage of the high-performance and low-power features of Mythic Analog Matrix Processors (Mythic AMPTM). Developers can focus on model performance and end-application integration instead of the time-consuming model development and training process.