Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Overview of CANN Optimization Capabilities
- Approaches to handling inference performance within CANN.
- Optimization objectives for edge and embedded AI systems.
- Insights into AI Core utilization and memory allocation.
Leveraging the Graph Engine for Analysis
- Introduction to the Graph Engine and its execution pipeline.
- Visualizing operator graphs and runtime metrics.
- Adjusting computational graphs for enhanced performance.
Profiling Tools and Performance Metrics
- Employing the CANN Profiling Tool (profiler) for workload analysis.
- Examining kernel execution times and identifying bottlenecks.
- Profiling memory access and implementing tiling strategies.
Custom Operator Development with TIK
- Overview of TIK and the operator programming model.
- Building custom operators using the TIK DSL.
- Testing and benchmarking operator performance.
Advanced Operator Optimization with TVM
- Introduction to TVM integration with CANN.
- Auto-tuning strategies for computational graphs.
- Guidelines on when and how to switch between TVM and TIK.
Memory Optimization Techniques
- Managing memory layout and buffer placement.
- Methods to reduce on-chip memory consumption.
- Best practices for asynchronous execution and resource reuse.
Real-World Deployment and Case Studies
- Case study: Performance tuning for a smart city camera pipeline.
- Case study: Optimizing the inference stack for autonomous vehicles.
- Guidelines for iterative profiling and continuous improvement.
Summary and Next Steps
Requirements
- Solid grasp of deep learning model architectures and training workflows.
- Hands-on experience deploying models using CANN, TensorFlow, or PyTorch.
- Proficiency in Linux CLI, shell scripting, and Python programming.
Target Audience
- AI performance engineers.
- Specialists in inference optimization.
- Developers engaged in edge AI or real-time systems.
14 Hours
