def test_product(dtype, nelem):
if np.dtype(dtype).kind == 'i':
data = np.ones(nelem, dtype=dtype)
# Set at most 30 items to [0..2) to keep the value within 2^32
for _ in range(30):
data[random.randrange(nelem)] = random.random() * 2
else:
data = gen_rand(dtype, nelem)
print('max', data.max(), 'min', data.min())
d_data = cuda.to_device(data)
d_result = cuda.device_array(libgdf.gdf_reduce_optimal_output_size(),
dtype=d_data.dtype)
col_data = new_column()
gdf_dtype = get_dtype(dtype)
libgdf.gdf_column_view(col_data, unwrap_devary(d_data), ffi.NULL, nelem,
gdf_dtype)
libgdf.gdf_product_generic(col_data, unwrap_devary(d_result),
d_result.size)
got = d_result.copy_to_host()[0]
expect = np.product(data)
print('expect:', expect)
print('got:', got)
np.testing.assert_array_almost_equal(expect, got)
def test_sum_of_squares(dtype, nelem):
data = gen_rand(dtype, nelem)
d_data = rmm.to_device(data)
d_result = rmm.device_array(libgdf.gdf_reduce_optimal_output_size(),
dtype=d_data.dtype)
col_data = new_column()
gdf_dtype = get_dtype(dtype)
libgdf.gdf_column_view(col_data, unwrap_devary(d_data), ffi.NULL, nelem,
gdf_dtype)
libgdf.gdf_sum_of_squares(col_data, unwrap_devary(d_result), d_result.size)
got = d_result.copy_to_host()[0]
expect = (data ** 2).sum()
print('expect:', expect)
print('got:', got)
if np.dtype(dtype).kind == 'i':
if 0 <= expect <= np.iinfo(dtype).max:
np.testing.assert_array_almost_equal(expect, got)
else:
print('overflow, passing')
else:
np.testing.assert_array_almost_equal(expect, got,
decimal=accuracy_for_dtype[dtype])
def apply_reduce(fn, inp):
# allocate output+temp array
outsz = libgdf.gdf_reduce_optimal_output_size()
out = rmm.device_array(outsz, dtype=inp.dtype)
# call reduction
fn(inp.cffi_view, unwrap_devary(out), outsz)
# return 1st element
return out[0]
def apply_reduce(fn, inp):
# allocate output+temp array
outsz = libgdf.gdf_reduce_optimal_output_size()
out = cuda.device_array(outsz, dtype=inp.dtype)
# call reduction
fn(inp.cffi_view, unwrap_devary(out), outsz)
# return 1st element
return out[0]
def test_sum(dtype, nelem):
data = gen_rand(dtype, nelem)
d_data = cuda.to_device(data)
d_result = cuda.device_array(libgdf.gdf_reduce_optimal_output_size(),
dtype=d_data.dtype)
col_data = new_column()
gdf_dtype = get_dtype(dtype)
libgdf.gdf_column_view(col_data, unwrap_devary(d_data), ffi.NULL, nelem,
gdf_dtype)
libgdf.gdf_sum_generic(col_data, unwrap_devary(d_result), d_result.size)
got = d_result.copy_to_host()[0]
expect = data.sum()
print('expect:', expect)
print('got:', got)
np.testing.assert_array_almost_equal(expect, got)
def test_max(dtype, nelem):
data = gen_rand(dtype, nelem)
d_data = rmm.to_device(data)
d_result = rmm.device_array(libgdf.gdf_reduce_optimal_output_size(),
dtype=d_data.dtype)
col_data = new_column()
gdf_dtype = get_dtype(dtype)
libgdf.gdf_column_view(col_data, unwrap_devary(d_data), ffi.NULL, nelem,
gdf_dtype)
libgdf.gdf_max(col_data, unwrap_devary(d_result), d_result.size)
got = d_result.copy_to_host()[0]
expect = data.max()
print('expect:', expect)
print('got:', got)
assert expect == got
def test_sum_masked(nelem):
dtype = np.float64
data = gen_rand(dtype, nelem)
mask = gen_rand(np.int8, (nelem + 8 - 1) // 8)
d_data = cuda.to_device(data)
d_mask = cuda.to_device(mask)
d_result = cuda.device_array(libgdf.gdf_reduce_optimal_output_size(),
dtype=d_data.dtype)
col_data = new_column()
gdf_dtype = get_dtype(dtype)
libgdf.gdf_column_view(col_data, unwrap_devary(d_data),
unwrap_devary(d_mask), nelem, gdf_dtype)
libgdf.gdf_sum_generic(col_data, unwrap_devary(d_result), d_result.size)
got = d_result.copy_to_host()[0]
boolmask = buffer_as_bits(mask)[:nelem]
expect = data[boolmask].sum()
np.testing.assert_almost_equal(expect, got)
