appropriate substitution for nvvm_atomic_load_add_f32?

Project Infrastructure LLVM Dev List Archives
1

I notice nvvm_atomic_load_add_f32 was removed. Is there a well known substitution for atomic_load_add?

2

I notice nvvm_atomic_load_add_f32 was removed. Is there a well known substitution for atomic_load_add?

I don't know the specifics of this intrinsic and backend, but the
native IR atomicrmw instruction has grown fadd/fsub operation support,
so that seems like it ought to be the canonical replacement.

Cheers,
Nicolai