A high-performance inference engine
for the most demanding environments
Origin E8 provides the high performance needed for ADAS, autonomous, and datacenter applications. Origin E8's architecture enables optimized memory management that drastically reduces DRAM requirements, cutting BOM costs and reducing power. Origin E8 enables multi-job support for better utilization of hardware resources and reductions in system costs. Its highly efficient neural network engine allows designers to develop products using passive cooling, further reducing system costs.
- Performance efficient 18 TOPS/Watt
- 36K-56K MACS
- Multi-job support
- Advanced activation memory management
- Low latency
- Predictable deterministic performance
- Compatible with various DNN models
- Hardware scheduler for NN
- Processes model as trained, no need for software optimizations
- Use familiar open-source platforms like TFlite
Industry-leading performance and power efficiency.
Architected to support demanding workloads with maximum efficiency.
Reduces hardware requirement for multiple models.
Drastically reduces memory requirements.
Deterministic, real-time performance.
Flexible, future proof support.
Simple software stack.
Achieve same accuracy your trained model.
Simplifies deployment to end customers.
- Speedup AI inference performance dramatically
- Avoid system over-design and bloated system costs
- Flexibility and reduced cost
- Optimal performance for heavy workloads
- Suitable for system critical applications
- Scalable architecture meets a wide range of application requirements
- No heavy software support burden
- Speeds deployment
- Best in class platform support
to our News
Sign up today and receive helpful
resources delivered directly
to your inbox.