综合项目：重排逐笔表并证明缺失减少

def address(groups, row, col, n_rows, elem_bytes=ELEM_BYTES):    base = 0    for group in groups:        if col in group:            return base + (row * len(group) + group.index(col)) * elem_bytes        base += n_rows * len(group) * elem_bytes1    raise ValueError("column %d is in no group" % col)print(address([[0, 1, 2]], 2, 1, 10))print(address([[0], [1], [2]], 2, 1, 10))print(address([[1, 2], [0]], 3, 0, 10))

56
96
184

def workload_trace(groups, n_rows, reads, rows):    return [address(groups, row, col, n_rows) for row in rows for col in reads]def layout_misses(groups, n_rows, reads, rows=None):    rows = range(n_rows) if rows is None else rows    return count_misses(workload_trace(groups, n_rows, reads, rows))def compare_layouts(layouts, n_rows, reads, rows=None):    return {name: layout_misses(groups, n_rows, reads, rows) for name, groups in layouts.items()}def best_layout(misses):    return min(misses, key=misses.get)def time_ns(accesses, misses, hit_ns=HIT_NS, miss_ns=MISS_NS):    return (accesses - misses) * hit_ns + misses * miss_nsprint(workload_trace([[0, 1]], 4, [1, 0], [2]))for job, reads in WORKLOADS.items():    rows = sampled_rows(4000) if job == "lookup" else None    result = compare_layouts(LAYOUTS, 4000, reads, rows)    print(job, result, "->", best_layout(result))

[40, 32]
scan {'aos': 4000, 'soa': 500, 'hybrid': 2000} -> soa
quote {'aos': 4000, 'soa': 1500, 'hybrid': 2000} -> soa
lookup {'aos': 1000, 'soa': 8000, 'hybrid': 2000} -> aos

def study(bars):    n_rows = min(int(bars.shape[0]), 4000)    misses = {}    accesses = 0    for job, reads in WORKLOADS.items():        rows = sampled_rows(n_rows) if job == "lookup" else None        misses[job] = compare_layouts(LAYOUTS, n_rows, reads, rows)        accesses += len(reads) * (len(rows) if rows is not None else n_rows)    mixed = {name: sum(misses[job][name] for job in WORKLOADS) for name in LAYOUTS}    best = best_layout(mixed)    return {"mixed": mixed, "mixed_best": best, "reduction": mixed["aos"] / mixed[best],            "ns": {name: time_ns(accesses, mixed[name]) for name in LAYOUTS}}out = study(load_bars())print(out["mixed"], "->", out["mixed_best"])print(round(out["reduction"], 2), "times fewer misses than the array of structs")print({name: round(ns / 1000) for name, ns in out["ns"].items()}, "microseconds")

{'aos': 9000, 'soa': 10000, 'hybrid': 6000} -> hybrid
1.5 times fewer misses than the array of structs
{'aos': 735, 'soa': 814, 'hybrid': 498} microseconds