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.
Duration 14 hours
Course Outline
Foundations of Custom Operator Development
- Rationale for building custom operators, including specific use cases and constraints.
- Analysis of CANN runtime structure and key operator integration points.
- Overview of TBE, TIK, and TVM within the broader Huawei AI ecosystem.
Low-Level Operator Programming with TIK
- Exploring the TIK programming model and its supported APIs.
- Managing memory and implementing tiling strategies within TIK.
- Processes for creating, compiling, and registering custom operators with CANN.
Validation and Testing of Custom Operators
- Conducting unit and integration tests for operators within the execution graph.
- Troubleshooting kernel-level performance bottlenecks.
- Visualizing operator execution flows and buffer behaviors.
Scheduling and Optimization via TVM
- Understanding TVM’s role as a compiler for tensor operations.
- Crafting custom operator schedules within the TVM framework.
- Applying TVM for tuning, benchmarking, and code generation specific to Ascend.
Framework and Model Integration
- Registering custom operators for compatibility with MindSpore and ONNX.
- Ensuring model integrity and managing fallback behaviors effectively.
- Managing multi-operator graphs with mixed precision support.
Case Studies and Advanced Optimization Techniques
- Case study: Optimizing high-efficiency convolution for small input shapes.
- Case study: Enhancing memory-aware attention operator performance.
- Best practices for deploying custom operators across various devices.
Conclusions and Future Directions
Requirements
- Profound understanding of AI model architectures and operator-level computations.
- Hands-on experience with Python and Linux development environments.
- Familiarity with neural network compilers or graph-level optimization techniques.
Target Audience
- Compiler engineers specializing in AI toolchain development.
- Systems developers dedicated to low-level AI performance tuning.
- Developers creating custom operators or targeting emerging AI workloads.
Custom Corporate Training
Training solutions designed exclusively for businesses.
- Customized Content: We adapt the syllabus and practical exercises to the real goals and needs of your project.
- Flexible Schedule: Dates and times adapted to your team's agenda.
- Format: Online (live), In-company (at your offices), or Hybrid.
Price per private group, online live training, starting from 3200 € + VAT*
Contact us for an exact quote and to hear our latest promotions
