结构体数组与数组结构体

def address(layout, row, col, n_rows, n_cols, elem_bytes=8):    if layout == "aos":        return (row * n_cols + col) * elem_bytes1    return (col * n_rows + row) * elem_bytesclose = 3print("aos:", [address("aos", row, close, 100, 5) for row in range(4)])print("soa:", [address("soa", row, close, 100, 5) for row in range(4)])

aos: [24, 64, 104, 144]
soa: [2400, 2408, 2416, 2424]

def scan_column(layout, col, n_rows, n_cols):    return [address(layout, row, col, n_rows, n_cols) for row in range(n_rows)]for layout in ("aos", "soa"):    misses = count_misses(scan_column(layout, 3, 1000, 5))    print(layout, "misses:", misses, "- useful share:", round(1000 * 8 / (misses * 64), 3))

aos misses: 625 - useful share: 0.2
soa misses: 125 - useful share: 1.0

def scan_rows(layout, rows, n_rows, n_cols):    return [address(layout, row, col, n_rows, n_cols) for row in rows for col in range(n_cols)]rows = list(range(0, 1000, 7))for layout in ("aos", "soa"):    print(layout, "misses:", count_misses(scan_rows(layout, rows, 1000, 5)))

aos misses: 214
soa misses: 625

def compare(n_rows, n_cols, col, rows):    out = {}    for layout in ("aos", "soa"):        out[layout] = {            "column": count_misses(scan_column(layout, col, n_rows, n_cols)),            "rows": count_misses(scan_rows(layout, rows, n_rows, n_cols)),        }    return outdef best_layout(n_column_scans, n_row_reads, n_rows, n_cols, col, rows):    counts = compare(n_rows, n_cols, col, rows)    totals = {layout: n_column_scans * counts[layout]["column"] + n_row_reads * counts[layout]["rows"] for layout in counts}    return "soa" if totals["soa"] < totals["aos"] else "aos"rows = list(range(0, 1000, 7))for scans, reads in ((1, 4), (1, 2), (1, 1), (4, 1)):    print(scans, "column scans per", reads, "row reads:", best_layout(scans, reads, 1000, 5, 3, rows))

1 column scans per 4 row reads: aos
1 column scans per 2 row reads: aos
1 column scans per 1 row reads: soa
4 column scans per 1 row reads: soa