This tutorial video introduces memory workload analysis for CUDA applications with NVIDIA Nsight Compute. Memory bottlenecks can limit the performance of your GPU. This is especially true for content creation and other workloads that involve large amounts of data quickly streaming through memory. Use Nsight Compute memory workload analysis to maximize GPU memory bandwidth and optimize data access patterns. Highlights of this video tutorial include: Memory analysis chart: ▫️ This chart visualizes hardware memory locality and memory type, including the amount of read or written bytes between physical units. Overview of caches: ▫️ Memory requests in the kernel follow a hierarchy. L1 is checked first, then L2, and if the sector is not found, it is fetched from device memory. Optimizing caches: ▫️ Cache line allocation is crucial for optimal performance, ensuring efficient use of cache storage and reducing memory traffic between L1, L2, and device memory. Live demonstration: ▫️ Walkthrough optimizing a simple CUDA program that converts 8-bit PNGs from RGBA to grayscale. We inspect the impact of aligned reads and vectorized loads on memory efficiency. Interpreting memory analysis: ▫️ Key tips for how to read memory profiles to address the balance between hardware limitations and algorithmic efficiency. 0:00 - Introduction 0:58 - Memory Chart 3:51 - Cache Line Allocation 4:56 - L1 and L2 Cache 7:15 - Load and Store Address Spaces 8:48 - Sample Code 9:56 - Memory Workload Analysis 12:02 - Reading RGBA Values 13:08 - Aligned Loads 15:54 - Vectorized Loads 17:32 - Conclusion Important resources: ▫️ Introduction to NVIDIA Nsight Compute: https://www.youtube.com/watch?v=Iuy_RAvguBM ▫️ SOL Analysis with NVIDIA Nsight Compute: https://www.youtube.com/watch?v=uHN5fpfu8As ▫️ Memory Management on Modern GPU Architectures: https://resources.nvidia.com/gtcd-2020/GTC2020cwe21754?lx=3X9y6T ▫️Sample code: https://github.com/NVIDIA/nsight-training/tree/master/cuda/nsight_compute/vlog_memory_workload Learn more: ▫️ Memory chart Profiling Guide: https://docs.nvidia.com/nsight-compute/ProfilingGuide/index.html#memory-chart ▫️ Memory tables Profiling Guide: https://docs.nvidia.com/nsight-compute/ProfilingGuide/index.html#memory-tables ▫️ Ampere architecture overview for where caches are located on the chip: https://developer.nvidia.com/blog/nvidia-ampere-architecture-in-depth/ ▫️ GPU memory architecture: https://developer.download.nvidia.com/video/gputechconf/gtc/2020/presentations/s21819-optimizing-applications-for-nvidia-ampere-gpu-architecture.pdf ▫️ Local memory/register spilling: https://developer.download.nvidia.com/CUDA/training/register_spilling.pdf ▫️ Learn more about CUDA Developer Tools: https://developer.nvidia.com/tools-overview ▫️ Get started with NVIDIA Nsight Compute: https://developer.nvidia.com/nsight-compute ▫️ Join the NVIDIA Developer Program: https://nvda.ws/3OhiXfl ▫️ Dive deeper and ask questions on the NVIDIA Developer forums: https://forums.developer.nvidia.com/c/developer-tools/nsight-compute/114 ▫️ Read and subscribe to the NVIDIA Technical Blog: https://nvda.ws/3XHae9F This video series will help get you started with NVIDIA Nsight Developer Tools for CUDA. Grow your proficiency with the tools and apply the examples to your own development environment. Or return to specific episodes for a refresher on certain features and functionalities. We walk through analyzing performance reports, offer debugging tips and tricks, and show you the best ways to optimize your CUDA code. The series will focus primarily on Nsight Compute and Nsight Systems. Thanks for watching, and stay tuned for more episodes. #CUDA #Nsight #developertools #NVIDIA #HPC #LLM #CUDAtutorials