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 21 hours
Course Outline
Core Performance Concepts and Metrics
- Latency, throughput, power consumption, and resource utilization
- Distinguishing between system-level and model-level bottlenecks
- Profiling techniques for inference versus training
Profiling on Huawei Ascend
- Leveraging CANN Profiler and MindInsight
- Diagnosing kernel and operator performance
- Managing offload patterns and memory mapping
Profiling on Biren GPU
- Utilizing Biren SDK performance monitoring capabilities
- Optimizing kernel fusion, memory alignment, and execution queues
- Conducting power and temperature-aware profiling
Profiling on Cambricon MLU
- Using BANGPy and Neuware performance tools
- Gaining kernel-level visibility and interpreting logs
- Integrating MLU profilers with deployment frameworks
Graph and Model-Level Optimization
- Strategies for graph pruning and quantization
- Operator fusion and restructuring computational graphs
- Standardizing input sizes and adjusting batch parameters
Memory and Kernel Optimization
- Enhancing memory layout and data reuse
- Managing buffers efficiently across different chipsets
- Applying platform-specific kernel tuning techniques
Cross-Platform Best Practices
- Ensuring performance portability through abstraction strategies
- Creating shared tuning pipelines for multi-chip environments
- Case study: tuning an object detection model across Ascend, Biren, and MLU
Summary and Recommendations for Next Steps
Requirements
- Practical experience in AI model training or deployment pipelines
- Solid grasp of GPU/MLU computing principles and model optimization techniques
- Foundational knowledge of performance profiling tools and key metrics
Target Audience
- Performance engineers
- Machine learning infrastructure teams
- AI system architects
