Is there any doc that can introduce __barrier_sync() and __barrier_sync_count()?

I can find __barrier_sync() and __barrier_sync_count() in this page(clang: lib/Headers/__clang_cuda_intrinsics.h Source File),
But I can’t find this two primitives in CUDA C++ Programming Guide.

Is __barrier_sync() and __barrier_sync_count() defined in cuda?

Yes, you can use it in cuda. see Compiler Explorer

It uses the barrier ptx instruction 1. Introduction — parallel-thread-execution 8.1 documentation

Its similar to __syncthreads()

Thank you for help.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.