Discussion

Decoupling Compute and Memory for Async GPUs

Cool open-source project that introduces a new programming model for decoupling compute and memory for NVIDIA GPUs that supports asynchronous memory operations (e.g., Hopper). 12% perf improvement over SOTA and 67% less kernel code.

Paper: "VDCores: Resource Decoupled Programming and Execution for Asynchronous GPU" arXiv:2605.03190

8 points yiyingzhang 4 months ago 2 comments

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton