NUMA 效应

print([node_of_thread(thread, 2) for thread in range(4)])for thread_node in (0, 1):    print("thread on node", thread_node, [LOCAL_NS if page_node == thread_node else REMOTE_NS for page_node in (0, 1)])

[0, 0, 1, 1]
thread on node 0 [80.0, 130.0]
thread on node 1 [130.0, 80.0]

def first_touch_placement(trace, threads_per_node):    placement = {}    for thread, address in trace:        page = address // PAGE_BYTES        if page not in placement:            placement[page] = node_of_thread(thread, threads_per_node)    return placementdef interleaved_placement(trace, n_nodes):    return {page: page % n_nodes for page in {address // PAGE_BYTES for _, address in trace}}trace = [(0, 0), (0, 4096), (3, 8192), (1, 4100)]print(first_touch_placement(trace, 2))print(interleaved_placement(trace, 2))

{0: 0, 1: 0, 2: 1}
{0: 0, 1: 1, 2: 0}

def access_costs(trace, placement, threads_per_node):    local = 0    remote = 0    for thread, address in trace:        if placement[address // PAGE_BYTES] == node_of_thread(thread, threads_per_node):            local += 1        else:            remote += 1    return {"local": local, "remote": remote, "ns": local * LOCAL_NS + remote * REMOTE_NS}def partition_trace(n_records, n_threads, record_bytes):    chunk = n_records // n_threads    return [(thread, record * record_bytes) for thread in range(n_threads) for record in range(thread * chunk, (thread + 1) * chunk)]work = partition_trace(400, 4, 512)single = first_touch_placement([(0, address) for _, address in work], 2)owners = first_touch_placement(work, 2)spread = interleaved_placement(work, 2)for name, placement in (("single", single), ("owners", owners), ("interleaved", spread)):    print(name, access_costs(work, placement, 2))

single {'local': 200, 'remote': 200, 'ns': 42000.0}
owners {'local': 400, 'remote': 0, 'ns': 32000.0}
interleaved {'local': 208, 'remote': 192, 'ns': 41600.0}