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
Introduction to Biren GPU Architecture
- Overview of Biren and its primary use cases.
- Hardware layout details: cores, memory structures, and compute clusters.
- Comparative analysis with NVIDIA and AMD GPUs.
Configuring the Biren Programming Environment
- Installing the Biren SDK and runtime components.
- Gaining a clear understanding of the toolchain and compiler model.
- Exploring basic project structures and the build workflow.
GPU Programming with the Biren Stack
- Detailed examination of thread and block models.
- Managing memory operations and data transfers efficiently.
- Developing kernels and understanding launch patterns.
Porting from CUDA to Biren
- Effective techniques for translating CUDA code.
- Mapping common APIs and identifying necessary adaptations.
- Hands-on labs and practice sessions focused on code conversion.
Debugging and Profiling
- Utilizing Biren’s specialized debugger and profiler tools.
- Techniques for identifying performance bottlenecks.
- Analyzing memory access patterns to drive optimization.
Optimization Strategies
- Advanced thread scheduling and instruction pipelining.
- Applying loop unrolling and leveraging shared memory.
- Fine-tuning kernels to maximize throughput.
Case Studies and Application Examples
- Practical demonstration of model training using Biren accelerators.
- Porting and profiling vision or NLP models.
- Performance comparison against CUDA/NVIDIA standards.
Summary and Future Directions
Requirements
- A solid grasp of GPU architecture and parallel processing concepts.
- Practical experience with GPU programming environments such as CUDA, OpenCL, or similar frameworks.
- Familiarity with deep learning frameworks like PyTorch or TensorFlow.
Target Audience
- HPC developers.
- AI infrastructure engineers.
- Specialists focused on performance optimization.
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.