def test_flag_condition():
f_arr = np.zeros((2, 2, 2), dtype=np.float64)
mask_arr = np.zeros((2, 2), dtype=np.uint64)
mask_arr[0, 1] = (1 << 3)
mask_arr[1, 0] = (1 << 5)
mask_arr[1, 1] = (1 << 3) + (1 << 5)
f = Field.create_from_numpy_array('f', f_arr, index_dimensions=1)
mask = Field.create_from_numpy_array('mask', mask_arr)
v1 = 42.3
v2 = 39.7
v3 = 119.87
assignments = [
Assignment(f(0), flag_cond(3, mask(0), v1)),
Assignment(f(1), flag_cond(5, mask(0), v2, v3))
]
kernel = create_kernel(assignments).compile()
kernel(f=f_arr, mask=mask_arr)
reference = np.zeros((2, 2, 2), dtype=np.float64)
reference[0, 1, 0] = v1
reference[1, 1, 0] = v1
reference[0, 0, 1] = v3
reference[0, 1, 1] = v3
reference[1, 0, 1] = v2
reference[1, 1, 1] = v2
np.testing.assert_array_equal(f_arr, reference)
def test_indexed_cuda_kernel():
try:
import pycuda
except ImportError:
pycuda = None
if pycuda:
from pystencils.gpucuda import make_python_function
import pycuda.gpuarray as gpuarray
from pystencils.gpucuda.kernelcreation import created_indexed_cuda_kernel
arr = np.zeros((3, 4))
dtype = np.dtype([('x', int), ('y', int), ('value', arr.dtype)])
index_arr = np.zeros((3, ), dtype=dtype)
index_arr[0] = (0, 2, 3.0)
index_arr[1] = (1, 3, 42.0)
index_arr[2] = (2, 1, 5.0)
indexed_field = Field.create_from_numpy_array('index', index_arr)
normal_field = Field.create_from_numpy_array('f', arr)
update_rule = Assignment(normal_field[0, 0], indexed_field('value'))
ast = created_indexed_cuda_kernel([update_rule], [indexed_field])
kernel = make_python_function(ast)
gpu_arr = gpuarray.to_gpu(arr)
gpu_index_arr = gpuarray.to_gpu(index_arr)
kernel(f=gpu_arr, index=gpu_index_arr)
gpu_arr.get(arr)
for i in range(index_arr.shape[0]):
np.testing.assert_allclose(arr[index_arr[i]['x'],
index_arr[i]['y']],
index_arr[i]['value'],
atol=1e-13)
else:
print("Did not run test on GPU since no pycuda is available")
def test_sliced_iteration_llvm():
size = (4, 4)
src_arr = np.ones(size)
dst_arr = np.zeros_like(src_arr)
src_field = Field.create_from_numpy_array('src', src_arr)
dst_field = Field.create_from_numpy_array('dst', dst_arr)
a, b = sp.symbols("a b")
update_rule = Assignment(dst_field[0, 0],
(a * src_field[0, 1] + a * src_field[0, -1] +
b * src_field[1, 0] + b * src_field[-1, 0]) / 4)
x_end = TypedSymbol("x_end", "int")
s = make_slice[1:x_end, 1]
x_end_value = size[1] - 1
import pystencils.llvm as llvm_generator
ast = llvm_generator.create_kernel(sympy_cse_on_assignment_list(
[update_rule]),
iteration_slice=s)
kernel = llvm_generator.make_python_function(ast)
kernel(src=src_arr, dst=dst_arr, a=1.0, b=1.0, x_end=x_end_value)
expected_result = np.zeros(size)
expected_result[1:x_end_value, 1] = 1
np.testing.assert_almost_equal(expected_result, dst_arr)
def test_full_scalar_field():
"""Tests fully (un)packing a scalar field (from)to a GPU buffer."""
fields = _generate_fields()
for (src_arr, gpu_src_arr, gpu_dst_arr, gpu_buffer_arr) in fields:
src_field = Field.create_from_numpy_array("src_field", src_arr)
dst_field = Field.create_from_numpy_array("dst_field", src_arr)
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
field_type=FieldType.BUFFER,
dtype=src_arr.dtype)
pack_eqs = [Assignment(buffer.center(), src_field.center())]
pack_types = {
'src_field': gpu_src_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
pack_code = create_cuda_kernel(pack_eqs, type_info=pack_types)
pack_kernel = make_python_function(pack_code)
pack_kernel(buffer=gpu_buffer_arr, src_field=gpu_src_arr)
unpack_eqs = [Assignment(dst_field.center(), buffer.center())]
unpack_types = {
'dst_field': gpu_dst_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
unpack_code = create_cuda_kernel(unpack_eqs, type_info=unpack_types)
unpack_kernel = make_python_function(unpack_code)
unpack_kernel(dst_field=gpu_dst_arr, buffer=gpu_buffer_arr)
dst_arr = gpu_dst_arr.get()
np.testing.assert_equal(src_arr, dst_arr)
def test_full_scalar_field():
"""Tests fully (un)packing a scalar field (from)to a buffer."""
fields = _generate_fields()
for (src_arr, dst_arr, buffer_arr) in fields:
src_field = Field.create_from_numpy_array("src_field", src_arr)
dst_field = Field.create_from_numpy_array("dst_field", dst_arr)
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
field_type=FieldType.BUFFER,
dtype=src_arr.dtype)
pack_eqs = [Assignment(buffer.center(), src_field.center())]
pack_code = create_kernel(pack_eqs,
data_type={
'src_field': src_arr.dtype,
'buffer': buffer.dtype
})
pack_kernel = pack_code.compile()
pack_kernel(buffer=buffer_arr, src_field=src_arr)
unpack_eqs = [Assignment(dst_field.center(), buffer.center())]
unpack_code = create_kernel(unpack_eqs,
data_type={
'dst_field': dst_arr.dtype,
'buffer': buffer.dtype
})
unpack_kernel = unpack_code.compile()
unpack_kernel(dst_field=dst_arr, buffer=buffer_arr)
np.testing.assert_equal(src_arr, dst_arr)
def wiener_filtering(complex_field: Field, output_weight_field: Field, sigma):
assert complex_field.index_dimensions == 3
assert output_weight_field.index_dimensions == 1
assignments = []
norm_factor = complex_field.index_shape[0] * complex_field.index_shape[1]
wiener_sum = []
for stack_index in range(complex_field.index_shape[0]):
for patch_index in range(complex_field.index_shape[1]):
magnitude = sum(complex_field.center(stack_index, patch_index, i) ** 2 for i in (0, 1))
val = magnitude / norm_factor # implementation differ whether to apply norm_factor on val on wien
wien = val / (val + sigma * sigma)
wiener_sum.append(wien**2)
assignments.extend(
pystencils.Assignment(complex_field.center(stack_index, patch_index, i),
complex_field.center(stack_index, patch_index, i) * wien)
for i in (0, 1)
)
assignments.append(pystencils.Assignment(
output_weight_field.center(stack_index), 1 / sympy.Add(*wiener_sum)
))
return AssignmentCollection(assignments)
def generic_instationary_filter(input_field: pystencils.Field,
output_field: pystencils.Field,
stencil,
weighting_function,
normalize_weights=True):
"""Implements a generic instationary filter.
The filter weight depends on the current stencil offset, the function value there and
the central function value at stencil center.
:param input_field:
:type input_field: pystencils.Field
:param output_field:
:type output_field: pystencils.Field
:param stencil:
:param weighting_function: A function that takes current offset, offset function value and
stencils center function value
:param normalize_weights: whether or not to normalize weights to a sum of one
"""
weights = 0
sum = 0
for s in stencil:
weight = weighting_function(s, input_field[s], input_field.center())
weights += weight
sum += weight * input_field[s]
assignments = AssignmentCollection(
{output_field.center(): sum / weights if normalize_weights else sum})
return assignments
def apply_wieners(complex_field: Field, wieners: Field, output_weight_field: Field):
assert complex_field.index_dimensions == 3
assert wieners.index_dimensions == 2
assert output_weight_field.index_dimensions == 1
assignments = []
wiener_sum = []
for stack_index in range(complex_field.index_shape[0]):
for patch_index in range(complex_field.index_shape[1]):
wien = wieners(stack_index, patch_index)
wiener_sum.append(wien**2)
assignments.extend(
pystencils.Assignment(complex_field.center(stack_index, patch_index, i),
complex_field.center(stack_index, patch_index, i) * wien)
for i in (0, 1)
)
assignments.append(pystencils.Assignment(
output_weight_field.center(stack_index), 1 / sympy.Add(*wiener_sum)
))
return AssignmentCollection(assignments)
def test_jacobi_fixed_field_size():
size = (30, 20)
src_field_llvm = np.random.rand(*size)
src_field_py = np.copy(src_field_llvm)
dst_field_llvm = np.zeros(size)
dst_field_py = np.zeros(size)
f = Field.create_from_numpy_array("f", src_field_llvm)
d = Field.create_from_numpy_array("d", dst_field_llvm)
jacobi = Assignment(d[0, 0], (f[1, 0] + f[-1, 0] + f[0, 1] + f[0, -1]) / 4)
ast = create_kernel([jacobi])
for x in range(1, size[0] - 1):
for y in range(1, size[1] - 1):
dst_field_py[
x,
y] = 0.25 * (src_field_py[x - 1, y] + src_field_py[x + 1, y] +
src_field_py[x, y - 1] + src_field_py[x, y + 1])
jit = generate_and_jit(ast)
jit('kernel', dst_field_llvm, src_field_llvm)
error = np.sum(np.abs(dst_field_py - dst_field_llvm))
np.testing.assert_almost_equal(error, 0.0)
def hard_thresholding(complex_field: Field, output_weight_field, threshold):
assert complex_field.index_dimensions == 3
assert output_weight_field.index_dimensions == 1
assignments = []
for stack_index in range(complex_field.index_shape[0]):
num_nonzeros = []
for patch_index in range(complex_field.index_shape[1]):
magnitude = sum(complex_field.center(stack_index, patch_index, i) ** 2 for i in (0, 1))
assignments.extend(
pystencils.Assignment(complex_field.center(stack_index, patch_index, i),
sympy.Piecewise(
(complex_field.center(stack_index, patch_index, i),
magnitude > threshold ** 2), (0, True)))
for i in (0, 1)
)
num_nonzeros.append(sympy.Piecewise((1, magnitude > threshold ** 2), (0, True)))
assignments.append(pystencils.Assignment(
output_weight_field.center(stack_index), sympy.Add(*num_nonzeros)
))
return AssignmentCollection(assignments)
def test_jacobi_variable_field_size():
size = (3, 3, 3)
f = Field.create_generic("f", 3)
d = Field.create_generic("d", 3)
jacobi = Assignment(
d[0, 0, 0], (f[1, 0, 0] + f[-1, 0, 0] + f[0, 1, 0] + f[0, -1, 0]) / 4)
ast = create_kernel([jacobi])
src_field_llvm = np.random.rand(*size)
src_field_py = np.copy(src_field_llvm)
dst_field_llvm = np.zeros(size)
dst_field_py = np.zeros(size)
for x in range(1, size[0] - 1):
for y in range(1, size[1] - 1):
for z in range(1, size[2] - 1):
dst_field_py[x, y, z] = 0.25 * (
src_field_py[x - 1, y, z] + src_field_py[x + 1, y, z] +
src_field_py[x, y - 1, z] + src_field_py[x, y + 1, z])
kernel = make_python_function(ast, {
'f': src_field_llvm,
'd': dst_field_llvm
})
kernel()
error = np.sum(np.abs(dst_field_py - dst_field_llvm))
np.testing.assert_almost_equal(error, 0.0)
def test_variable_sized_fields():
src_field = Field.create_generic('src', spatial_dimensions=2)
dst_field = Field.create_generic('dst', spatial_dimensions=2)
update_rule = Assignment(dst_field[0, 0],
(src_field[0, 1] + src_field[0, -1] +
src_field[1, 0] + src_field[-1, 0]) / 4)
ast = create_cuda_kernel(sympy_cse_on_assignment_list([update_rule]))
kernel = make_python_function(ast)
size = (3, 3)
src_arr = np.random.rand(*size)
src_arr = add_ghost_layers(src_arr)
dst_arr = np.zeros_like(src_arr)
gpu_src_arr = gpuarray.to_gpu(src_arr)
gpu_dst_arr = gpuarray.to_gpu(dst_arr)
kernel(src=gpu_src_arr, dst=gpu_dst_arr)
gpu_dst_arr.get(dst_arr)
stencil = np.array([[0, 1, 0], [1, 0, 1], [0, 1, 0]]) / 4.0
reference = convolve(remove_ghost_layers(src_arr),
stencil,
mode='constant',
cval=0.0)
reference = add_ghost_layers(reference)
np.testing.assert_almost_equal(reference, dst_arr)
def test_ghost_layer():
size = (6, 5)
src_arr = np.ones(size)
dst_arr = np.zeros_like(src_arr)
src_field = Field.create_from_numpy_array('src',
src_arr,
index_dimensions=0)
dst_field = Field.create_from_numpy_array('dst',
dst_arr,
index_dimensions=0)
update_rule = Assignment(dst_field[0, 0], src_field[0, 0])
ghost_layers = [(1, 2), (2, 1)]
ast = create_cuda_kernel([update_rule],
ghost_layers=ghost_layers,
indexing_creator=LineIndexing)
kernel = make_python_function(ast)
gpu_src_arr = gpuarray.to_gpu(src_arr)
gpu_dst_arr = gpuarray.to_gpu(dst_arr)
kernel(src=gpu_src_arr, dst=gpu_dst_arr)
gpu_dst_arr.get(dst_arr)
reference = np.zeros_like(src_arr)
reference[ghost_layers[0][0]:-ghost_layers[0][1],
ghost_layers[1][0]:-ghost_layers[1][1]] = 1
np.testing.assert_equal(reference, dst_arr)
def __init__(self, boundary, method, pdf_field_sparse):
full_pdf_field = Field.create_generic('pdfFull', spatial_dimensions=method.dim, index_dimensions=1)
additional_data_field = Field.create_generic('additionalData', spatial_dimensions=1,
dtype=boundary.additional_data)
boundary_eqs = boundary(full_pdf_field, self.DIR_SYMBOL, method, additional_data_field)
neighbor_offsets = {fa.offsets for eq in boundary_eqs for fa in eq.atoms(Field.Access)}
neighbor_offsets = list(neighbor_offsets)
neighbor_offsets_dtype = [(self.NEIGHBOR_IDX_NAME.format(i), np.uint32)
for i in range(len(neighbor_offsets))]
index_field_dtype = np.dtype([('dir', np.uint32),
*neighbor_offsets_dtype,
*boundary.additional_data])
index_field = Field.create_generic('indexField', spatial_dimensions=1, dtype=index_field_dtype)
boundary_eqs = boundary(full_pdf_field, self.DIR_SYMBOL, method, index_field)
offset_subs = {off: sp.Symbol(self.NEIGHBOR_IDX_NAME.format(i)) for i, off in enumerate(neighbor_offsets)}
new_boundary_eqs = []
for eq in boundary_eqs:
substitutions = {
fa: pdf_field_sparse.absolute_access([index_field(offset_subs[fa.offsets].name)], fa.index)
for fa in eq.atoms(Field.Access)
if fa.field == full_pdf_field
}
new_boundary_eqs.append(eq.subs(substitutions))
self.boundary_eqs = new_boundary_eqs
self.boundary_eqs_orig = boundary_eqs
self.method = method
self.index_field_dtype = index_field_dtype
self.neighbor_offsets = neighbor_offsets
self.index_field = index_field
def test_fixed_size_mismatch_check():
"""Create kernel with two differently sized but constant fields """
src = np.zeros((20, 21, 9))
dst = np.zeros((21, 21, 9))
sym_src = Field.create_from_numpy_array("src", src, index_dimensions=1)
sym_dst = Field.create_from_numpy_array("dst", dst, index_dimensions=1)
update_rule = Assignment(sym_dst(0), sym_src[-1, 1](1) + sym_src[1, -1](2))
with pytest.raises(ValueError) as e:
create_kernel([update_rule])
assert 'Differently sized field accesses' in str(e.value)
def aggregate(block_scores: Field,
patch_input_field: Field,
destination_field: Field,
block_stencil,
matching_stencil,
threshold,
max_selected,
compilation_target,
patch_weights: Field = None,
accumulated_weights: Field = None,
**compilation_kwargs):
max_offset = max(max(o) for o in matching_stencil)
max_offset += max(max(o) for o in block_stencil)
offset = pystencils_reco.typed_symbols('_o:%i' % patch_input_field.spatial_dimensions, 'int32')
copies = []
assert destination_field.index_dimensions == 2
assert destination_field.index_shape[-1] == len(block_stencil)
n, nth_hit = pystencils_reco.typed_symbols('_n, nth_hit', 'int32')
for i, s in enumerate(block_stencil):
shifted = tuple(s + o for s, o in zip(offset, s))
weight = patch_weights.center(nth_hit) if patch_weights else 1
assignment = pystencils.Assignment(_get_dummy_symbol(),
sympy.Function('atomicAdd')(address_of(patch_input_field[shifted]),
weight * destination_field.center(nth_hit, i)))
copies.append(assignment)
if accumulated_weights:
assignment = pystencils.Assignment(_get_dummy_symbol(),
sympy.Function('atomicAdd')(
address_of(accumulated_weights[shifted]), weight))
copies.append(assignment)
assignments = AssignmentCollection(copies)
ast = pystencils.create_kernel(assignments,
target=compilation_target,
data_type=patch_input_field.dtype,
ghost_layers=max_offset,
**compilation_kwargs)
ast._body = Select(ast.body,
what=offset,
from_iterable=matching_stencil,
predicate=block_scores.center(n) < threshold,
counter_symbol=n,
hit_counter_symbol=nth_hit,
compilation_target=compilation_target,
max_selected=max_selected)
return ast.compile()
def test_subset_cell_values():
"""Tests (un)packing a subset of cell values of the a field (from)to a buffer."""
num_cell_values = 7
# Cell indices of the field to be (un)packed (from)to the buffer
cell_indices = [1, 3, 5, 6]
fields = _generate_fields(stencil_directions=num_cell_values)
for (src_arr, gpu_src_arr, gpu_dst_arr, gpu_buffer_arr) in fields:
src_field = Field.create_from_numpy_array("src_field",
gpu_src_arr,
index_dimensions=1)
dst_field = Field.create_from_numpy_array("dst_field",
gpu_src_arr,
index_dimensions=1)
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
index_dimensions=1,
field_type=FieldType.BUFFER,
dtype=gpu_src_arr.dtype)
pack_eqs = []
# Since we are packing all cell values for all cells, then
# the buffer index is equivalent to the field index
for buffer_idx, cell_idx in enumerate(cell_indices):
eq = Assignment(buffer(buffer_idx), src_field(cell_idx))
pack_eqs.append(eq)
pack_types = {
'src_field': gpu_src_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
pack_code = create_cuda_kernel(pack_eqs, type_info=pack_types)
pack_kernel = make_python_function(pack_code)
pack_kernel(buffer=gpu_buffer_arr, src_field=gpu_src_arr)
unpack_eqs = []
for buffer_idx, cell_idx in enumerate(cell_indices):
eq = Assignment(dst_field(cell_idx), buffer(buffer_idx))
unpack_eqs.append(eq)
unpack_types = {
'dst_field': gpu_dst_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
unpack_code = create_cuda_kernel(unpack_eqs, type_info=unpack_types)
unpack_kernel = make_python_function(unpack_code)
unpack_kernel(buffer=gpu_buffer_arr, dst_field=gpu_dst_arr)
dst_arr = gpu_dst_arr.get()
mask_arr = np.ma.masked_where((src_arr - dst_arr) != 0, src_arr)
np.testing.assert_equal(dst_arr, mask_arr.filled(int(0)))
def test_subset_cell_values():
"""Tests (un)packing a subset of cell values of the a field (from)to a buffer."""
num_cell_values = 19
# Cell indices of the field to be (un)packed (from)to the buffer
cell_indices = [1, 5, 7, 8, 10, 12, 13]
fields = _generate_fields(num_directions=num_cell_values)
for (src_arr, dst_arr, bufferArr) in fields:
src_field = Field.create_from_numpy_array("src_field",
src_arr,
index_dimensions=1)
dst_field = Field.create_from_numpy_array("dst_field",
dst_arr,
index_dimensions=1)
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
index_dimensions=1,
field_type=FieldType.BUFFER,
dtype=src_arr.dtype)
pack_eqs = []
# Since we are packing all cell values for all cells, then
# the buffer index is equivalent to the field index
for buffer_idx, cell_idx in enumerate(cell_indices):
eq = Assignment(buffer(buffer_idx), src_field(cell_idx))
pack_eqs.append(eq)
pack_code = create_kernel(pack_eqs,
data_type={
'src_field': src_arr.dtype,
'buffer': buffer.dtype
})
pack_kernel = pack_code.compile()
pack_kernel(buffer=bufferArr, src_field=src_arr)
unpack_eqs = []
for buffer_idx, cell_idx in enumerate(cell_indices):
eq = Assignment(dst_field(cell_idx), buffer(buffer_idx))
unpack_eqs.append(eq)
unpack_code = create_kernel(unpack_eqs,
data_type={
'dst_field': dst_arr.dtype,
'buffer': buffer.dtype
})
unpack_kernel = unpack_code.compile()
unpack_kernel(buffer=bufferArr, dst_field=dst_arr)
mask_arr = np.ma.masked_where((src_arr - dst_arr) != 0, src_arr)
np.testing.assert_equal(dst_arr, mask_arr.filled(int(0)))
def test_fixed_and_variable_field_check():
"""Create kernel with two variable sized fields - calling them with different sizes"""
src = np.zeros((20, 21, 9))
sym_src = Field.create_from_numpy_array("src", src, index_dimensions=1)
sym_dst = Field.create_generic("dst",
spatial_dimensions=2,
index_dimensions=1)
update_rule = Assignment(sym_dst(0), sym_src[-1, 1](1) + sym_src[1, -1](2))
with pytest.raises(ValueError) as e:
create_kernel(update_rule)
assert 'Mixing fixed-shaped and variable-shape fields' in str(e.value)
def test_fixed_size_mismatch_check():
"""Create kernel with two differently sized but constant fields """
src = np.zeros((20, 21, 9))
dst = np.zeros((21, 21, 9))
sym_src = Field.create_from_numpy_array("src", src, index_dimensions=1)
sym_dst = Field.create_from_numpy_array("dst", dst, index_dimensions=1)
update_rule = Assignment(sym_dst(0), sym_src[-1, 1](1) + sym_src[1, -1](2))
try:
create_kernel([update_rule])
assert False, "Expected ValueError because fields with different sized where passed"
except ValueError:
pass
def test_all_cell_values():
"""Tests (un)packing all cell values of the a field (from)to a buffer."""
num_cell_values = 7
fields = _generate_fields(stencil_directions=num_cell_values)
for (src_arr, gpu_src_arr, gpu_dst_arr, gpu_buffer_arr) in fields:
src_field = Field.create_from_numpy_array("src_field",
gpu_src_arr,
index_dimensions=1)
dst_field = Field.create_from_numpy_array("dst_field",
gpu_src_arr,
index_dimensions=1)
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
index_dimensions=1,
field_type=FieldType.BUFFER,
dtype=gpu_src_arr.dtype)
pack_eqs = []
# Since we are packing all cell values for all cells, then
# the buffer index is equivalent to the field index
for idx in range(num_cell_values):
eq = Assignment(buffer(idx), src_field(idx))
pack_eqs.append(eq)
pack_types = {
'src_field': gpu_src_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
pack_code = create_cuda_kernel(pack_eqs, type_info=pack_types)
pack_kernel = make_python_function(pack_code)
pack_kernel(buffer=gpu_buffer_arr, src_field=gpu_src_arr)
unpack_eqs = []
for idx in range(num_cell_values):
eq = Assignment(dst_field(idx), buffer(idx))
unpack_eqs.append(eq)
unpack_types = {
'dst_field': gpu_dst_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
unpack_code = create_cuda_kernel(unpack_eqs, type_info=unpack_types)
unpack_kernel = make_python_function(unpack_code)
unpack_kernel(buffer=gpu_buffer_arr, dst_field=gpu_dst_arr)
dst_arr = gpu_dst_arr.get()
np.testing.assert_equal(src_arr, dst_arr)
def create_copy_kernel(domain_size,
from_slice,
to_slice,
index_dimensions=0,
index_dim_shape=1,
dtype=np.float64):
"""Copies a rectangular part of an array to another non-overlapping part"""
f = Field.create_generic("pdfs",
len(domain_size),
index_dimensions=index_dimensions,
dtype=dtype)
normalized_from_slice = normalize_slice(from_slice, f.spatial_shape)
normalized_to_slice = normalize_slice(to_slice, f.spatial_shape)
offset = [
s1.start - s2.start
for s1, s2 in zip(normalized_from_slice, normalized_to_slice)
]
assert offset == [s1.stop - s2.stop for s1, s2 in zip(normalized_from_slice, normalized_to_slice)], \
"Slices have to have same size"
update_eqs = []
if index_dimensions < 2:
index_dim_shape = [index_dim_shape]
for i in product(*[range(d) for d in index_dim_shape]):
eq = Assignment(f(*i), f[tuple(offset)](*i))
update_eqs.append(eq)
ast = create_cuda_kernel(update_eqs,
iteration_slice=to_slice,
skip_independence_check=True)
return ast
def test_fixed_and_variable_field_check():
"""Create kernel with two variable sized fields - calling them with different sizes"""
src = np.zeros((20, 21, 9))
sym_src = Field.create_from_numpy_array("src", src, index_dimensions=1)
sym_dst = Field.create_generic("dst",
spatial_dimensions=2,
index_dimensions=1)
update_rule = Assignment(sym_dst(0), sym_src[-1, 1](1) + sym_src[1, -1](2))
try:
create_kernel([update_rule])
assert False, "Expected ValueError because fields with different sized where passed"
except ValueError:
pass
def extend_to_size_of_other_field(this_field: pystencils.Field,
other_field: pystencils.Field):
this_field.coordinate_transform = sp.DiagMatrix(
sp.Matrix([
this_field.spatial_shape[i] / other_field.spatial_shape[i]
for i in range(len(this_field.spatial_shape))
]))
def create_copy_kernel(domain_size,
from_slice,
to_slice,
index_dimensions=0,
index_dim_shape=1,
dtype=np.float64):
"""Copies a rectangular part of an array to another non-overlapping part"""
if index_dimensions not in (0, 1):
raise NotImplementedError(
"Works only for one or zero index coordinates")
f = Field.create_generic("pdfs",
len(domain_size),
index_dimensions=index_dimensions,
dtype=dtype)
normalized_from_slice = normalize_slice(from_slice, f.spatial_shape)
normalized_to_slice = normalize_slice(to_slice, f.spatial_shape)
offset = [
s1.start - s2.start
for s1, s2 in zip(normalized_from_slice, normalized_to_slice)
]
assert offset == [s1.stop - s2.stop for s1, s2 in zip(normalized_from_slice, normalized_to_slice)], \
"Slices have to have same size"
update_eqs = []
for i in range(index_dim_shape):
eq = Assignment(f(i), f[tuple(offset)](i))
update_eqs.append(eq)
ast = create_cuda_kernel(update_eqs,
iteration_slice=to_slice,
skip_independence_check=True)
return make_python_function(ast)
def generic_stationary_filter(input_field: pystencils.Field,
output_field: pystencils.Field,
stencil,
weighting_function,
normalize_weights=True):
"""generic_function_filter
:param input_field:
:type input_field: pystencils.Field
:param output_field:
:type output_field: pystencils.Field
:param stencil:
:param weighting_function: A function that takes a offset tuple and transfers it to weighting of the function value
:param normalize_weights: whether or not to normalize weights to a sum of one
"""
weights = 0
sum = 0
for s in stencil:
weight = weighting_function(s)
weights += weight
sum += weight * input_field[s]
assignments = AssignmentCollection(
{output_field.center(): sum / weights if normalize_weights else sum})
return assignments
def test_all_cell_values():
"""Tests (un)packing all cell values of the a field (from)to a buffer."""
num_cell_values = 19
fields = _generate_fields(num_directions=num_cell_values)
for (src_arr, dst_arr, bufferArr) in fields:
src_field = Field.create_from_numpy_array("src_field",
src_arr,
index_dimensions=1)
dst_field = Field.create_from_numpy_array("dst_field",
dst_arr,
index_dimensions=1)
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
index_dimensions=1,
field_type=FieldType.BUFFER,
dtype=src_arr.dtype)
pack_eqs = []
# Since we are packing all cell values for all cells, then
# the buffer index is equivalent to the field index
for idx in range(num_cell_values):
eq = Assignment(buffer(idx), src_field(idx))
pack_eqs.append(eq)
pack_code = create_kernel(pack_eqs,
data_type={
'src_field': src_arr.dtype,
'buffer': buffer.dtype
})
pack_kernel = pack_code.compile()
pack_kernel(buffer=bufferArr, src_field=src_arr)
unpack_eqs = []
for idx in range(num_cell_values):
eq = Assignment(dst_field(idx), buffer(idx))
unpack_eqs.append(eq)
unpack_code = create_kernel(unpack_eqs,
data_type={
'dst_field': dst_arr.dtype,
'buffer': buffer.dtype
})
unpack_kernel = unpack_code.compile()
unpack_kernel(buffer=bufferArr, dst_field=dst_arr)
np.testing.assert_equal(src_arr, dst_arr)
def test_field_layouts():
num_cell_values = 7
for layout_str in ['numpy', 'fzyx', 'zyxf', 'reverse_numpy']:
fields = _generate_fields(stencil_directions=num_cell_values,
layout=layout_str)
for (src_arr, gpu_src_arr, gpu_dst_arr, gpu_buffer_arr) in fields:
src_field = Field.create_from_numpy_array("src_field",
gpu_src_arr,
index_dimensions=1)
dst_field = Field.create_from_numpy_array("dst_field",
gpu_src_arr,
index_dimensions=1)
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
index_dimensions=1,
field_type=FieldType.BUFFER,
dtype=src_arr.dtype)
pack_eqs = []
# Since we are packing all cell values for all cells, then
# the buffer index is equivalent to the field index
for idx in range(num_cell_values):
eq = Assignment(buffer(idx), src_field(idx))
pack_eqs.append(eq)
pack_types = {
'src_field': gpu_src_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
pack_code = create_cuda_kernel(pack_eqs, type_info=pack_types)
pack_kernel = make_python_function(pack_code)
pack_kernel(buffer=gpu_buffer_arr, src_field=gpu_src_arr)
unpack_eqs = []
for idx in range(num_cell_values):
eq = Assignment(dst_field(idx), buffer(idx))
unpack_eqs.append(eq)
unpack_types = {
'dst_field': gpu_dst_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
unpack_code = create_cuda_kernel(unpack_eqs,
type_info=unpack_types)
unpack_kernel = make_python_function(unpack_code)
unpack_kernel(buffer=gpu_buffer_arr, dst_field=gpu_dst_arr)
def mean_filter(input_field: pystencils.Field, output_field: pystencils.Field,
stencil):
assignments = {
output_field.center():
sum(input_field[t] for t in stencil) / len(stencil)
}
return assignments
def test_field_slice():
"""Tests (un)packing slices of a scalar field (from)to a buffer."""
fields = _generate_fields()
for d in ['N', 'S', 'NW', 'SW', 'TNW', 'B']:
for (src_arr, gpu_src_arr, gpu_dst_arr, gpu_buffer_arr) in fields:
# Extract slice from N direction of the field
slice_dir = direction_string_to_offset(d, dim=len(src_arr.shape))
pack_slice = get_slice_before_ghost_layer(slice_dir)
unpack_slice = get_ghost_region_slice(slice_dir)
src_field = Field.create_from_numpy_array("src_field",
src_arr[pack_slice])
dst_field = Field.create_from_numpy_array("dst_field",
src_arr[unpack_slice])
buffer = Field.create_generic("buffer",
spatial_dimensions=1,
field_type=FieldType.BUFFER,
dtype=src_arr.dtype)
pack_eqs = [Assignment(buffer.center(), src_field.center())]
pack_types = {
'src_field': gpu_src_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
pack_code = create_cuda_kernel(pack_eqs, type_info=pack_types)
pack_kernel = make_python_function(pack_code)
pack_kernel(buffer=gpu_buffer_arr,
src_field=gpu_src_arr[pack_slice])
# Unpack into ghost layer of dst_field in N direction
unpack_eqs = [Assignment(dst_field.center(), buffer.center())]
unpack_types = {
'dst_field': gpu_dst_arr.dtype,
'buffer': gpu_buffer_arr.dtype
}
unpack_code = create_cuda_kernel(unpack_eqs,
type_info=unpack_types)
unpack_kernel = make_python_function(unpack_code)
unpack_kernel(buffer=gpu_buffer_arr,
dst_field=gpu_dst_arr[unpack_slice])
dst_arr = gpu_dst_arr.get()
np.testing.assert_equal(src_arr[pack_slice], dst_arr[unpack_slice])
