The World's First Photonic Computing Platform
Reduce the carbon footprint and operating cost of your datacenter while powering the most advanced neural networks (and the next generation) with a fundamentally new, powerful and efficient computing platform: photonics.
You can’t increase the power supply to the building, so you either build a new one or find better hardware. We enable your roadmap for bigger, more capable neural network models— increasing product margins and allowing you to deploy new features all while minimizing your environmental footprint.
A Performance Scaling Paradigm
Photonics enables multiple operations within the same area.
Performance / Power
The Envise 4S features 16 Envise Chips in a 4-U server configuration with only 3kW power consumption. 4S is a building block for a rack-scale Envise inference system that can run the largest neural networks developed to date at unprecedented performance — 3 times higher IPS than the Nvidia DGX-A100 with 8 times the IPS/W on BERT-Base SQuAD.
Massive on-chip activation and weight storage enabling state-of-the-art neural network execution without leaving the processor.
Standards-based host and interconnect interface. Revolutionary compute, standard communications.
RISC cores per Envise processor. Generic off-load capabilities.
Ultra-high performance out-of-order super-scalar processing architecture.
Deployment-grade reliability, availability, and serviceability features. Next generation compute with the reliability of standard electronics.
400Gbps Lightmatter interconnect fabric per Envise chip — enabling large model scale-out. Running the most advanced neural networks on the planet.
- 16xLightmatter Envise
- 2xAMD EPYC 7002 series host processors
- 3TB NVMe SSD
- 6.4Tbps LM-Fabric for scale-out
- 2x200G Ethernet Smart NIC
- Gigabit ethernet for IPMI management
- 3kW TDP
- 4U form factor
Vision and Control
E-Commerce & Advertising
Predictive & Preventative Maintenance
Analysis of Digital Signal
Natural Language Processing