llama.cpp
544f409b - vulkan : argsort barriers must be under uniform control flow (ggml/951)

Commit
1 year ago
vulkan : argsort barriers must be under uniform control flow (ggml/951) a return before a barrier (that happens only in some threads in a workgroup) leads to UB. While the old code actually works on some devices, it fails on some others (i.e. "smaller" GPUs). BTW, I think it would be better to set specialization constants when the graph is built, in that way the local workgroup could be sized appropriately. But it would take a lot of work. Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>
Author
Committer
Parents
Loading