News for hackers. Stuff that matters.
Re:Decoupling Compute and Memory for Async GPUs by bobbyzhu2008 on Thursday June 25, 2026 @01:10PM (#48676402)
67% less kernel code is the more interesting number here — Hopper's async capabilities have been underutilized largely because the programming model is painful. Curious how it handles cases where compute and memory phases aren't cleanly separable.

There are no comments on this comment yet.