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 Biren GPU Architecture
- Biren platform overview and key use cases
- Hardware components: cores, memory structure, and compute clusters
- Architectural comparison with NVIDIA and AMD GPUs
Establishing the Biren Programming Environment
- Installing the Biren SDK and runtime components
- Exploring the toolchain and compiler architecture
- Structuring basic projects and managing the build process
Developing Applications with the Biren Stack
- Thread and block organizational models
- Managing memory and handling data transfers
- Designing kernels and implementing launch patterns
Migrating from CUDA to Biren
- Strategies for translating CUDA code
- Mapping common APIs and adapting functionalities
- Hands-on code conversion labs and practical exercises
Debugging and Profiling Strategies
- Leveraging Biren’s debugger and profiler tools
- Identifying performance bottlenecks
- Analyzing memory access patterns for optimization
Advanced Optimization Techniques
- Managing thread scheduling and instruction pipelining
- Utilizing loop unrolling and shared memory effectively
- Fine-tuning kernels for maximum throughput
Real-World Case Studies and Applications
- Training models using Biren accelerators
- Porting and profiling vision or NLP models
- Benchmarking performance against CUDA/NVIDIA ecosystems
Summary and Recommended Next Steps
Requirements
- Solid understanding of GPU architecture and parallel processing concepts
- Proficiency in GPU programming environments such as CUDA, OpenCL, or similar frameworks
- Working knowledge of deep learning frameworks like PyTorch or TensorFlow
Target Audience
- HPC Developers
- AI Infrastructure Engineers
- Performance Optimization Specialists
21 Hours
Testimonials (2)
The extensive selection of tools presented
Miruna Buzduga - Aeronamic Eastern Europe
Course - AI Enablement Training for Engineers
Step by step training with a lot of exercises. It was like a workshop and I am very glad about that.
