Function benchmark_with_profiler

intermediate_source/pinmem_nonblock.py:171–192

(
    pinned,
    streamed,
)

# Our profiler: profiles the `inner` function and stores the results in a .json file
def benchmark_with_profiler(
    pinned,
    streamed,
) -> None:
    torch._C._profiler._set_cuda_sync_enabled_val(True)
    wait, warmup, active = 1, 1, 2
    num_steps = wait + warmup + active
    rank = 0
    with torch.profiler.profile(
        activities=[
            torch.profiler.ProfilerActivity.CPU,
            torch.profiler.ProfilerActivity.CUDA,
        ],
        schedule=torch.profiler.schedule(
            wait=wait, warmup=warmup, active=active, repeat=1, skip_first=1
        ),
    ) as prof:
        for step_idx in range(1, num_steps + 1):
            inner(streamed=streamed, pinned=pinned)
            if rank is None or rank == 0:
                prof.step()
    prof.export_chrome_trace(f"trace_streamed{int(streamed)}_pinned{int(pinned)}.json")


######################################################################