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 the Chinese AI GPU Ecosystem
- Comparison of Huawei Ascend, Biren, and Cambricon MLU
- Comparison between CUDA and CANN, Biren SDK, and BANGPy models
- Industry trends and vendor ecosystems
Preparing for Migration
- Assessing your CUDA codebase
- Identifying target platforms and SDK versions
- Installing toolchains and setting up the environment
Code Translation Techniques
- Porting CUDA memory access and kernel logic
- Mapping compute grid and thread models
- Options for automated versus manual translation
Platform-Specific Implementations
- Utilizing Huawei CANN operators and custom kernels
- Understanding the Biren SDK conversion pipeline
- Rebuilding models with BANGPy (Cambricon)
Cross-Platform Testing and Optimization
- Profiling execution on each target platform
- Comparing memory tuning and parallel execution
- Performance tracking and iterative improvement
Managing Mixed GPU Environments
- Hybrid deployments involving multiple architectures
- Fallback strategies and device detection
- Implementing abstraction layers for code maintainability
Case Studies and Best Practices
- Porting vision and NLP models to Ascend or Cambricon
- Retrofitting inference pipelines on Biren clusters
- Handling version mismatches and API gaps
Summary and Next Steps
Requirements
- Experience in programming with CUDA or GPU-based applications
- Understanding of GPU memory models and compute kernels
- Familiarity with AI model deployment or acceleration workflows
Audience
- GPU programmers
- System architects
- Porting specialists
21 Hours
