Radar ·
Understanding Latency Hiding in GPUs
Material by Vasily Volkov of UC Berkeley explores GPU architecture and performance concepts that are not covered in depth in a well-known parallel programming book.
Material by Vasily Volkov of UC Berkeley discusses latency hiding and GPU architecture. According to its description, it covers performance concepts not explored in depth in *Programming Massively Parallel Processors*.
It is a resource for engineers seeking to deepen their knowledge of GPU architecture and performance. If you use AI to study or apply the material, do not submit internal code, data, or documents without authorization; follow your organization’s policies and remove confidential information.
Original source: Entendendo o ocultamento de latência em GPUs