Hi guys! So here is the second on the overview I started with the previous video on how to implement and optimize the Reduction algorithm in WGSL for WebGPU. This time we will cover the Nividia kernels version 4,5,6 and 7, with the last one providing the most amazing performances! As usual, if you have any question or remarks (or notice I'm saying something completely wrong 🤣!) please don't hesitate to let me know in the comments 😉!
Some code snippets are available for this experiment in https://github.com/roche-emmanuel/ner... in the 001_gpu_reduction folder.
On this page of the site you can watch the video online [NVL #41] Tutorial: Finalizing Reduction compute shaders optimizations overview in Native WebGPU with a duration of hours minute second in good quality, which was uploaded by the user The Lone Engineer 12 April 2024, share the link with friends and acquaintances, this video has already been watched 187 times on youtube and it was liked by 6 viewers. Enjoy your viewing!