Maia 200: A Software Defined Dataflow System for Large-Scale AI Acceleration
Maia 200 enhances AI acceleration with software-defined dataflow architecture for improved efficiency.
Maia 200 is an advanced AI accelerator delivering high performance of 10 145 Tflop/s FP4 and 5072 Tflop/s FP8 within a 750W TDP and 7 TB/s HBM bandwidth. It exemplifies a new class of Software Defined Locally Accessed Dataflow Architectures (SDLA), programming dataflow engines to enhance efficiency and scalability. This innovative approach addresses modern AI computing challenges, achieving significant cost and energy savings while enabling massive parallelism for AI inference workloads.
This synthesis was produced from its source by AI; there is no human editor or manual review step. How we work