def to_ops_stencil(param, accesses):
dims = len(accesses[0])
pts = len(accesses)
stencil_name = namespace['ops_stencil_name'](dims, param.name, pts)
stencil_array = Array(
name=stencil_name,
dimensions=(DefaultDimension(name='len', default_value=dims * pts), ),
dtype=np.int32,
)
ops_stencil = OpsStencil(stencil_name.upper())
return ops_stencil, [
Expression(
ClusterizedEq(
Eq(stencil_array,
ListInitializer(list(itertools.chain(*accesses)))))),
Expression(
ClusterizedEq(
Eq(
ops_stencil, namespace['ops_decl_stencil'](
dims, pts, Symbol(stencil_array.name),
Literal('"%s"' % stencil_name.upper())))))
]
def create_ops_par_loop(trees, ops_kernel, parameters, block, name_to_ops_dat,
accessible_origin, par_to_ops_stencil, dims):
it_range = []
devito_to_ops_indexer = 1
for tree in trees:
if isinstance(tree, IterationTree):
for i in tree:
it_range.extend(
[i.symbolic_min, i.symbolic_max + devito_to_ops_indexer])
range_array = Array(name='%s_range' % ops_kernel.name,
dimensions=(DefaultDimension(
name='range', default_value=len(it_range)), ),
dtype=np.int32,
scope='stack')
range_array_init = Expression(
ClusterizedEq(Eq(range_array, ListInitializer(it_range))))
ops_args = []
for p in parameters:
ops_arg = create_ops_arg(p, accessible_origin, name_to_ops_dat,
par_to_ops_stencil)
ops_args.append(
ops_arg.ops_type(ops_arg.ops_name, ops_arg.elements_per_point,
ops_arg.dtype, ops_arg.rw_flag))
ops_par_loop_call = Call(namespace['ops_par_loop'], [
Literal(ops_kernel.name),
Literal('"%s"' % ops_kernel.name), block, dims, range_array, *ops_args
])
return [range_array_init], ops_par_loop_call
def create_ops_par_loop(trees, ops_kernel, parameters, block, name_to_ops_dat,
accessible_origin, par_to_ops_stencil, dims):
it_range = []
for tree in trees:
if isinstance(tree, IterationTree):
for bounds in [it.bounds() for it in tree]:
it_range.extend(bounds)
range_array = Array(name='%s_range' % ops_kernel.name,
dimensions=(DefaultDimension(
name='range', default_value=len(it_range)), ),
dtype=np.int32,
scope='stack')
range_array_init = Expression(
ClusterizedEq(Eq(range_array, ListInitializer(it_range))))
ops_par_loop_call = Call(namespace['ops_par_loop'], [
Literal(ops_kernel.name),
Literal('"%s"' % ops_kernel.name), block, dims, range_array, *[
create_ops_arg(p, accessible_origin, name_to_ops_dat,
par_to_ops_stencil) for p in parameters
]
])
return [range_array_init], ops_par_loop_call
def new_ops_arg(self, indexed, is_Write):
"""
Create an :class:`Indexed` node using OPS representation.
Parameters
----------
indexed : :class:`Indexed`
Indexed object using devito representation.
Returns
-------
:class:`Indexed`
Indexed node using OPS representation.
"""
# Build the OPS arg identifier
time_index = split_affine(indexed.indices[TimeFunction._time_position])
ops_arg_id = ('%s%s' % (indexed.name, time_index.var)
if indexed.function.is_TimeFunction else indexed.name)
if ops_arg_id not in self.ops_args:
# Create the indexed object
ops_arg = Array(is_Write,
name=ops_arg_id,
dimensions=[Dimension(name=namespace['ops_acc'])],
dtype=indexed.dtype)
self.ops_args[ops_arg_id] = ops_arg
else:
ops_arg = self.ops_args[ops_arg_id]
# Get the space indices
if indexed.function.is_TimeFunction:
space_indices = [e for i, e in enumerate(
indexed.indices) if i != TimeFunction._time_position]
else:
space_indices = indexed.indices
# Define the Macro used in OPS arg index
access_macro = Macro(','.join(str(split_affine(i).shift) for i in space_indices))
# Create Indexed object representing the OPS arg access
new_indexed = Indexed(ops_arg.indexed, access_macro)
return new_indexed
def create_ops_dat(f, name_to_ops_dat, block):
ndim = f.ndim - (1 if f.is_TimeFunction else 0)
dim = Array(name=namespace['ops_dat_dim'](f.name),
dimensions=(DefaultDimension(name='dim',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
base = Array(name=namespace['ops_dat_base'](f.name),
dimensions=(DefaultDimension(name='base',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
d_p = Array(name=namespace['ops_dat_d_p'](f.name),
dimensions=(DefaultDimension(name='d_p',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
d_m = Array(name=namespace['ops_dat_d_m'](f.name),
dimensions=(DefaultDimension(name='d_m',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
base_val = [Zero() for i in range(ndim)]
# If f is a TimeFunction we need to create a ops_dat for each time stepping
# variable (eg: t1, t2)
if f.is_TimeFunction:
time_pos = f._time_position
time_index = f.indices[time_pos]
time_dims = f.shape[time_pos]
dim_val = f.shape[:time_pos] + f.shape[time_pos + 1:]
d_p_val = f._size_nodomain.left[time_pos + 1:]
d_m_val = [-i for i in f._size_nodomain.right[time_pos + 1:]]
ops_dat_array = Array(name=namespace['ops_dat_name'](f.name),
dimensions=(DefaultDimension(
name='dat', default_value=time_dims), ),
dtype=namespace['ops_dat_type'],
scope='stack')
dat_decls = []
for i in range(time_dims):
name = '%s%s%s' % (f.name, time_index, i)
dat_decls.append(namespace['ops_decl_dat'](block, 1,
Symbol(dim.name),
Symbol(base.name),
Symbol(d_m.name),
Symbol(d_p.name),
Byref(f.indexify([i])),
Literal('"%s"' %
f._C_typedata),
Literal('"%s"' % name)))
ops_decl_dat = Expression(
ClusterizedEq(Eq(ops_dat_array, ListInitializer(dat_decls))))
# Inserting the ops_dat array in case of TimeFunction.
name_to_ops_dat[f.name] = ops_dat_array
else:
ops_dat = OpsDat("%s_dat" % f.name)
name_to_ops_dat[f.name] = ops_dat
dim_val = f.shape
d_p_val = f._size_nodomain.left
d_m_val = [-i for i in f._size_nodomain.right]
ops_decl_dat = Expression(
ClusterizedEq(
Eq(
ops_dat,
namespace['ops_decl_dat'](block, 1, Symbol(dim.name),
Symbol(base.name),
Symbol(d_m.name),
Symbol(d_p.name),
Byref(f.indexify([0])),
Literal('"%s"' % f._C_typedata),
Literal('"%s"' % f.name)))))
dim_val = Expression(ClusterizedEq(Eq(dim, ListInitializer(dim_val))))
base_val = Expression(ClusterizedEq(Eq(base, ListInitializer(base_val))))
d_p_val = Expression(ClusterizedEq(Eq(d_p, ListInitializer(d_p_val))))
d_m_val = Expression(ClusterizedEq(Eq(d_m, ListInitializer(d_m_val))))
return OpsDatDecl(dim_val=dim_val,
base_val=base_val,
d_p_val=d_p_val,
d_m_val=d_m_val,
ops_decl_dat=ops_decl_dat)
def create_ops_dat(f, name_to_ops_dat, block):
ndim = f.ndim - (1 if f.is_TimeFunction else 0)
dim = Array(name=namespace['ops_dat_dim'](f.name),
dimensions=(DefaultDimension(name='dim',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
base = Array(name=namespace['ops_dat_base'](f.name),
dimensions=(DefaultDimension(name='base',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
d_p = Array(name=namespace['ops_dat_d_p'](f.name),
dimensions=(DefaultDimension(name='d_p',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
d_m = Array(name=namespace['ops_dat_d_m'](f.name),
dimensions=(DefaultDimension(name='d_m',
default_value=ndim), ),
dtype=np.int32,
scope='stack')
res = []
base_val = [Zero() for i in range(ndim)]
# If f is a TimeFunction we need to create a ops_dat for each time stepping
# variable (eg: t1, t2)
if f.is_TimeFunction:
time_pos = f._time_position
time_index = f.indices[time_pos]
time_dims = f.shape[time_pos]
dim_shape = sympify(f.shape[:time_pos] + f.shape[time_pos + 1:])
padding = f.padding[:time_pos] + f.padding[time_pos + 1:]
halo = f.halo[:time_pos] + f.halo[time_pos + 1:]
d_p_val = tuple(sympify([p[0] + h[0] for p, h in zip(padding, halo)]))
d_m_val = tuple(
sympify([-(p[1] + h[1]) for p, h in zip(padding, halo)]))
ops_dat_array = Array(name=namespace['ops_dat_name'](f.name),
dimensions=(DefaultDimension(
name='dat', default_value=time_dims), ),
dtype='ops_dat',
scope='stack')
dat_decls = []
for i in range(time_dims):
name = '%s%s%s' % (f.name, time_index, i)
name_to_ops_dat[name] = ops_dat_array.indexify(
[Symbol('%s%s' % (time_index, i))])
dat_decls.append(namespace['ops_decl_dat'](block, 1,
Symbol(dim.name),
Symbol(base.name),
Symbol(d_m.name),
Symbol(d_p.name),
Byref(f.indexify([i])),
Literal('"%s"' %
f._C_typedata),
Literal('"%s"' % name)))
ops_decl_dat = Expression(
ClusterizedEq(Eq(ops_dat_array, ListInitializer(dat_decls))))
else:
ops_dat = OpsDat("%s_dat" % f.name)
name_to_ops_dat[f.name] = ops_dat
d_p_val = tuple(
sympify([p[0] + h[0] for p, h in zip(f.padding, f.halo)]))
d_m_val = tuple(
sympify([-(p[1] + h[1]) for p, h in zip(f.padding, f.halo)]))
dim_shape = sympify(f.shape)
ops_decl_dat = Expression(
ClusterizedEq(
Eq(
ops_dat,
namespace['ops_decl_dat'](block, 1, Symbol(dim.name),
Symbol(base.name),
Symbol(d_m.name),
Symbol(d_p.name),
Byref(f.indexify([0])),
Literal('"%s"' % f._C_typedata),
Literal('"%s"' % f.name)))))
res.append(Expression(ClusterizedEq(Eq(dim, ListInitializer(dim_shape)))))
res.append(Expression(ClusterizedEq(Eq(base, ListInitializer(base_val)))))
res.append(Expression(ClusterizedEq(Eq(d_p, ListInitializer(d_p_val)))))
res.append(Expression(ClusterizedEq(Eq(d_m, ListInitializer(d_m_val)))))
res.append(ops_decl_dat)
return res
