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
Foundations of Biren GPU Architecture
- Overview of Biren technology and key application scenarios.
- Hardware configuration: examining cores, memory structures, and compute clusters.
- Comparative analysis with NVIDIA and AMD GPU architectures.
Configuring the Biren Development Ecosystem
- Installation of the Biren SDK and runtime components.
- Understanding the toolchain mechanics and compiler model.
- Reviewing basic project structures and build workflows.
Programming with the Biren Stack
- Exploring thread and block organizational models.
- Managing memory resources and data transfer operations.
- Developing kernels and understanding launch patterns.
Migrating from CUDA to Biren
- Strategies for translating CUDA codebases.
- Mapping common APIs and handling necessary adaptations.
- Hands-on labs and practice sessions for code conversion.
Diagnostic Tools: Debugging and Profiling
- Leveraging Biren’s integrated debugger and profiler.
- Techniques for identifying performance bottlenecks.
- Optimizing memory access patterns and execution flow.
Advanced Optimization Strategies
- Managing thread scheduling and instruction pipelining.
- Utilizing loop unrolling and shared memory effectively.
- Refining kernel performance for maximum throughput.
Practical Applications and Case Studies
- Training machine learning models utilizing Biren accelerators.
- Porting and profiling vision or NLP models.
- Performance benchmarking against CUDA/NVIDIA solutions.
Recap and Future Directions
Requirements
- Solid knowledge of GPU architecture and parallel processing concepts.
- Prior experience working with CUDA, OpenCL, or analogous GPU programming frameworks.
- Proficiency with major deep learning frameworks, such as PyTorch or TensorFlow.
Target Audience
- HPC developers.
- AI infrastructure engineers.
- Specialists in performance optimization.
Testimonials (1)
The trainer's open and warm style, and the accessible language.
OPREAN ADELA - Aeronamic Eastern Europe
Course - AI Enablement Training for Engineers
Machine Translated