This is a followup to my previous post, prefix sum on Vulkan. Last year, I got a fancy algorithm for this problem running well on one device. This time, I will dive into the question of how to make it work well across a wide range of devices. The short answer is, it can be made to work pretty portably on Vulkan and DX12, but Metal remains out of reach, at least for now, as is WebGPU. Even on Vulkan, there are some sharp edges to watch out for.
No pages have linked to this URL yet.