In-memory Compute (IMC) custom digital circuits deliver unprecedented efficiency.
Custom digital circuits that integrate compute directly in programmable memory (IMC) lead to huge leaps in efficiency while retaining datacenter accuracy.
Open, simplistic, scalable, and frictionless for ease of adoption.
Embracing the open-source software movement in AI frameworks and compiler, combined with the maturity and extensibility of our libraries and ML tools, makes adoption seamless.
ML Algorithms & Tools.
Seamlessly map existing trained models and option to design new models to take advantage of IMC hardware that intrinsically supports mulitple data types.
Fabric of chiplets delivers modularity and scale.
A fabric of chiplets built with low-power open interconnects, enhanced with low-latency FEC to take advantage of the “More Than Moore” paradigm. The Lego block approach from chip design to system design provides modularity and scalability across multiple applications.
Heterogenous, modular, and cost effective.
Hetero-Modular™ organic package that enables chiplet heterogeneity and scalability, while being readily available and cost-effective.
As opposed to forcing down the process curve with traditional digital architectures, we’re
re-thinking the physics of datacenter compute with a clean-slate approach to AI compute efficiency.