Composable Computing
Abstract program intentions into expected behaviors
Composable Computing takes any application from the world of big data and machine learning computation and deconstructs it into a series of abstract behaviors that are easily defined as instructions.
Create a novel compiler to compose the expected behaviors
Composable Computing deploys an automated and inventive compiler that integrates directly into the backends for TensorFlow, ONNX, and PyTorch and translates those program behaviors to the processor. This enables existing AI code bases to integrate seamlessly.
Modify hardware in real-time to execute the program
Executing the program on hardware that is reconfigured in real time enables behavioral integration at the transistor level, as if the hardware were originally designed for the program. This ensures an optimal hardware organization that balances computational requirements for a given program, without having any knowledge of the program when the chip was designed.
ADVANTAGES
Composable compute platform for accelerating AI and ML environments
Flexibility
Future-ready for emerging models and diverse workloads
Faster Time-to-Results
40x-plus higher performance
Ease-of-Use
Fast development, broader use
Faster ROI
Rapid deployment, reduced TCO
A solution that meets you where you are
As the world increasingly becomes algorithmic and data-driven, data analytics must evolve to address dynamic analytic requirements. With our solution’s programmability and time scalability, engineers can develop applications and efficiently execute software for various computing needs across many industries in many different compute environments.
Click to see Deployment
On Cloud
Composable Computing is compatible with applications in the cloud…
On-Premise
…or it can integrate seamlessly with on-premise hardware.