def bench_dot(lhs_shape,
rhs_shape,
lhs_stype,
rhs_stype,
lhs_den,
rhs_den,
trans_lhs,
ctx,
num_repeat=10,
fw="mxnet",
distribution="uniform"):
set_default_device(ctx)
assert fw == "mxnet" or fw == "scipy"
# Set funcs
dot_func_sparse = mx.nd.sparse.dot if fw == "mxnet" else sp.spmatrix.dot
dot_func_dense = mx.nd.dot if fw == "mxnet" else np.dot
# Create matrix instances
lhs_nd = rand_ndarray(lhs_shape,
lhs_stype,
density=lhs_den,
distribution=distribution)
# only uniform distribution supported for rhs
if rhs_stype == 'csr':
rhs_nd = rand_ndarray(rhs_shape,
rhs_stype,
density=rhs_den,
distribution=distribution)
else:
rhs_nd = rand_ndarray(rhs_shape,
rhs_stype,
density=rhs_den,
distribution="uniform")
lhs_dns = None
rhs_dns = None
dense_cost = None
sparse_cost = None
if fw == "mxnet":
lhs_dns = lhs_nd if lhs_stype == 'default' else lhs_nd.tostype(
'default')
rhs_dns = rhs_nd if rhs_stype == 'default' else rhs_nd.tostype(
'default')
# One warm up run, verify correctness
out = dot_func_sparse(lhs_nd, rhs_dns, trans_lhs)
out_expected = dot_func_dense(lhs_dns, rhs_dns, trans_lhs)
assert_almost_equal(out.asnumpy(),
out_expected.asnumpy(),
rtol=1e-1,
atol=1e-1)
sparse_cost = measure_cost(num_repeat, False, False,
dot_func_sparse, lhs_nd, rhs_nd,
trans_lhs)
dense_cost = measure_cost(num_repeat, False, False, dot_func_dense,
lhs_dns, rhs_dns, trans_lhs)
else:
lhs_dns = lhs_nd.asnumpy()
rhs_dns = rhs_nd.asnumpy()
lhs_nd = sp.csr_matrix(lhs_nd.asnumpy())
rhs_nd = rhs_nd.asnumpy()
# One warm up run, verify correctness
lhs_nd_copy = sp.spmatrix.transpose(
lhs_nd) if trans_lhs else lhs_nd
out = dot_func_sparse(lhs_nd_copy, rhs_dns)
sparse_cost = measure_cost(num_repeat, trans_lhs, False,
dot_func_sparse, lhs_nd, rhs_nd)
dense_cost = measure_cost(num_repeat, trans_lhs, True,
dot_func_dense, lhs_dns, rhs_dns)
speedup = dense_cost / sparse_cost
# Print results
m = lhs_shape[0]
k = lhs_shape[1]
n = rhs_shape[1]
result_pattern = '{:15.1f} {:15.1f} {:>10} {:8d} {:8d} {:8d} {:13.2f} {:13.2f} {:8.2f}'
results = result_pattern.format(lhs_den * 100, rhs_den * 100, str(ctx),
m, k, n, sparse_cost * 1000,
dense_cost * 1000, speedup)
print(results)
# Licensed to the Apache Software Foundation (ASF) under one # or more contributor license agreements. See the NOTICE file # distributed with this work for additional information # regarding copyright ownership. The ASF licenses this file # to you under the Apache License, Version 2.0 (the # "License"); you may not use this file except in compliance # with the License. You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, # software distributed under the License is distributed on an # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY # KIND, either express or implied. See the License for the # specific language governing permissions and limitations # under the License. import mxnet as mx from mxnet.test_utils import set_default_device import os import sys curr_path = os.path.dirname(os.path.abspath(os.path.expanduser(__file__))) sys.path.insert(0, os.path.join(curr_path, '../unittest')) from test_tvm_op import * set_default_device(mx.gpu(0))
def f():
set_default_device(mx.gpu(11))
device_list.append(device.current_device())
