Krishna Rangasayee, SiMa.ai | Supercloud 4
summary
SiMa.ai claims a machine-learning system-on-chip that delivers L2+/L3 vehicle-class inference at 50 watts for L2+ versus 300–600 W peers, and asserts 10x performance per watt over legacy architectures. The product combines Arm TrustZone and Synopsys IP for boot-to-run security, an ML SoC silicon taped with TSMC, and a software stack that runs any CV model and a no-code Edgematic pipeline to build, compile and deploy real-time edge inference.
AI-written summary · about
chapters (15)
- 0:00Introduction to edge AI
- 1:05Founding SiMa.ai
- 3:55Latency challenges in edge AI
- 4:59Hardware software co-design
- 7:29Edge market potential
- 8:53Key use cases today
- 9:55Autonomous vehicles reality
- 13:10Chip design innovation pace
- 16:05US chip manufacturing concerns
- 17:28Privacy and security at edge
- 20:15ML SOC architecture benefits
- 21:40Software centric approach
- 23:27Market opportunity at edge
- 25:54Future of edge innovation
- 27:18Closing remarks
