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
CANN Optimization Capabilities Overview
- Handling inference performance within CANN.
- Defining optimization goals for edge and embedded AI systems.
- Understanding 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.
- Modifying computational graphs for optimization.
Profiling Tools and Performance Metrics
- Employing the CANN Profiling Tool (profiler) for workload analysis.
- Analyzing kernel execution times and identifying bottlenecks.
- Conducting memory access profiling and applying tiling strategies.
Custom Operator Development with TIK
- Overview of TIK and the operator programming model.
- Implementing a custom operator using TIK DSL.
- Testing and benchmarking operator performance.
Advanced Operator Optimization with TVM
- Introduction to TVM integration with CANN.
- Auto-tuning strategies for computational graphs.
- Guidance on when and how to switch between TVM and TIK.
Memory Optimization Techniques
- Managing memory layout and buffer placement.
- Strategies 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
- Robust understanding of deep learning model architectures and training workflows.
- Hands-on experience with model deployment using CANN, TensorFlow, or PyTorch.
- Familiarity with Linux CLI, shell scripting, and Python programming.
Target Audience
- AI performance engineers.
- Inference optimization specialists.
- Developers working with edge AI or real-time systems.
14 Hours
