omlins / ParallelStencil.jl

Package for writing high-level code for parallel high-performance stencil computations that can be deployed on both GPUs and CPUs
BSD 3-Clause "New" or "Revised" License
301 stars 31 forks source link

Fix stream sync for AMDGPU backend #109

Closed luraess closed 10 months ago

luraess commented 11 months ago

Fixes #108

luraess commented 11 months ago

Now all tests pass again without having to use AMDGPU.HIP.device_synchronize().

luraess commented 11 months ago

@omlins