Saltar al contenido principal

Curso completo próximamente

GPU Architecture for AI and Compute Workloads

7 capítulos · 31 lecciones

  1. 1. Parallel Processing Fundamentals

    4 lecciones

    Understand why GPUs excel at throughput and how parallelism differs from CPU execution models.

  2. 2. GPU Memory Architecture

    5 lecciones

    Learn how memory capacity, bandwidth, and bus width determine real-world performance.

  3. 3. Data Movement and Bottlenecks

    4 lecciones

    Identify and resolve performance bottlenecks caused by data transfer between CPU and GPU.

  4. 4. Optimizing AI Inference Workloads

    5 lecciones

    Apply GPU memory and compute strategies to model serving, embeddings, and retrieval systems.

  5. 5. Training and Fine-Tuning Considerations

    4 lecciones

    Understand GPU memory demands during training and how to work within hardware limits.

  6. 6. Reading GPU Specifications Strategically

    5 lecciones

    Evaluate GPU options by matching specs to workload requirements, not marketing claims.

  7. 7. Profiling and Performance Tuning

    4 lecciones

    Use profiling tools to measure GPU utilization, memory usage, and identify optimization opportunities.

Recibe un correo cuando abra este curso