Function inner

intermediate_source/pinmem_nonblock.py:155–167

(pinned: bool, streamed: bool)

# The function we want to profile
def inner(pinned: bool, streamed: bool):
    with torch.cuda.stream(s) if streamed else contextlib.nullcontext():
        if pinned:
            t1_cuda = t1_cpu_pinned.to(device, non_blocking=True)
        else:
            t2_cuda = t2_cpu_paged.to(device, non_blocking=True)
        t_star_cuda_h2d_event = s.record_event()
    # This operation can be executed during the CPU to GPU copy if and only if the tensor is pinned and the copy is
    #  done in the other stream
    t3_cuda_mul = t3_cuda * t3_cuda * t3_cuda
    t3_cuda_h2d_event = torch.cuda.current_stream().record_event()
    t_star_cuda_h2d_event.synchronize()
    t3_cuda_h2d_event.synchronize()


# Our profiler: profiles the `inner` function and stores the results in a .json file