def local_sort(key_arrs, data, ascending=True):
# convert StringArray to list(string) to enable swapping in sort
l_key_arrs = to_string_list(key_arrs)
l_data = to_string_list(data)
n_out = len(key_arrs[0])
sdc.timsort.sort(l_key_arrs, 0, n_out, l_data)
if not ascending:
sdc.timsort.reverseRange(l_key_arrs, 0, n_out, l_data)
cp_str_list_to_array(key_arrs, l_key_arrs)
cp_str_list_to_array(data, l_data)
def parallel_sort(key_arrs, data, ascending=True):
n_local = len(key_arrs[0])
n_total = sdc.distributed_api.dist_reduce(n_local,
np.int32(Reduce_Type.Sum.value))
n_pes = sdc.distributed_api.get_size()
my_rank = sdc.distributed_api.get_rank()
# similar to Spark's sample computation Partitioner.scala
sampleSize = min(samplePointsPerPartitionHint * n_pes, MIN_SAMPLES)
fraction = min(sampleSize / max(n_total, 1), 1.0)
n_loc_samples = min(math.ceil(fraction * n_local), n_local)
inds = np.random.randint(0, n_local, n_loc_samples)
samples = key_arrs[0][inds]
# print(sampleSize, fraction, n_local, n_loc_samples, len(samples))
all_samples = sdc.distributed_api.gatherv(samples)
all_samples = to_string_list(all_samples)
bounds = empty_like_type(n_pes - 1, all_samples)
if my_rank == MPI_ROOT:
all_samples.sort()
if not ascending:
all_samples = all_samples[::-1]
n_samples = len(all_samples)
step = math.ceil(n_samples / n_pes)
for i in range(n_pes - 1):
bounds[i] = all_samples[min((i + 1) * step, n_samples - 1)]
# print(bounds)
bounds = str_list_to_array(bounds)
bounds = sdc.distributed_api.prealloc_str_for_bcast(bounds)
sdc.distributed_api.bcast(bounds)
# calc send/recv counts
pre_shuffle_meta = alloc_pre_shuffle_metadata(key_arrs, data, n_pes, True)
node_id = 0
for i in range(n_local):
val = key_arrs[0][i]
# TODO: refactor
if node_id < (n_pes - 1) and (ascending and val >= bounds[node_id] or
(not ascending)
and val <= bounds[node_id]):
node_id += 1
update_shuffle_meta(pre_shuffle_meta, node_id, i, (val, ),
getitem_arr_tup(data, i), True)
shuffle_meta = finalize_shuffle_meta(key_arrs, data, pre_shuffle_meta,
n_pes, True)
# shuffle
recvs = alltoallv_tup(key_arrs + data, shuffle_meta)
out_key = _get_keys_tup(recvs, key_arrs)
out_data = _get_data_tup(recvs, key_arrs)
return out_key, out_data