def gen_loops(self, node):
dim = len(self.output_grid.shape)
ret_node = None
cur_node = None
for d in xrange(dim):
dim_var = self.gen_fresh_var()
self.dim_vars.append(dim_var)
initial = cpp_ast.CNumber(self.output_grid.ghost_depth)
end = cpp_ast.CNumber(self.output_grid.shape[d] -
self.output_grid.ghost_depth - 1)
increment = cpp_ast.CNumber(1)
if d == 0:
ret_node = cpp_ast.For(dim_var, add_one(initial), add_one(end),
increment, cpp_ast.Block())
cur_node = ret_node
elif d == dim - 2:
cur_node.body = StencilConvertASTCilk.CilkFor(
dim_var, add_one(initial), add_one(end), increment,
cpp_ast.Block())
cur_node = cur_node.body
else:
cur_node.body = cpp_ast.For(dim_var, add_one(initial),
add_one(end), increment,
cpp_ast.Block())
cur_node = cur_node.body
return (cur_node, ret_node)
def visit_interior_kernel(self, node):
cur_node, ret_node = self.gen_loops(node)
body = cpp_ast.Block()
self.output_index_var = cpp_ast.CName(self.gen_fresh_var())
body.append(cpp_ast.Value("int", self.output_index_var))
body.append(
cpp_ast.Assign(
self.output_index_var,
self.gen_array_macro(self.output_grid_name,
[cpp_ast.CName(x)
for x in self.dim_vars])))
replaced_body = None
for gridname in self.argdict.keys():
replaced_body = [
ast_tools.ASTNodeReplacer(ast.Name(gridname, None),
ast.Name("_my_" + gridname,
None)).visit(x)
for x in node.body
]
body.extend([self.visit(x) for x in replaced_body])
cur_node.body = body
return ret_node
def visit_StencilModel(self, node):
self.argdict = dict()
for i in range(len(node.input_grids)):
self.var_names.append(node.input_grids[i].name)
self.argdict[node.input_grids[i].name] = self.input_grids[i]
self.argdict[self.output_grid_name] = self.output_grid
assert node.border_kernel.body == [], 'Border kernels not yet implemented'
func_name = "kernel"
arg_names = [x.name
for x in node.input_grids] + [self.output_grid_name]
args = [
cpp_ast.Pointer(cpp_ast.Value("PyObject", x)) for x in arg_names
]
body = cpp_ast.Block()
# generate the code to unpack arrays into C++ pointers and macros for accessing
# the arrays
body.extend([self.gen_array_macro_definition(x) for x in self.argdict])
body.extend(self.gen_array_unpack())
body.append(self.visit_interior_kernel(node.interior_kernel))
return cpp_ast.FunctionBody(
cpp_ast.FunctionDeclaration(cpp_ast.Value("void", func_name),
args), body)
def gen_loops(self, node):
dim = len(self.output_grid.shape)
ret_node = None
cur_node = None
def add_one(n):
if self.inject_failure == 'loop_off_by_one':
return cpp_ast.CNumber(n.num + 1)
else:
return n
for d in xrange(dim):
dim_var = self.gen_fresh_var()
self.dim_vars.append(dim_var)
initial = cpp_ast.CNumber(self.output_grid.ghost_depth)
end = cpp_ast.CNumber(self.output_grid.shape[d] -
self.output_grid.ghost_depth - 1)
increment = cpp_ast.CNumber(1)
if d == 0:
ret_node = cpp_ast.For(dim_var, add_one(initial), add_one(end),
increment, cpp_ast.Block())
cur_node = ret_node
elif d == dim - 2:
# add OpenMP parallel pragma to 2nd innermost loop
pragma = cpp_ast.Pragma("omp parallel for")
for_node = cpp_ast.For(dim_var, add_one(initial), add_one(end),
increment, cpp_ast.Block())
cur_node.body = cpp_ast.Block(contents=[pragma, for_node])
cur_node = for_node
elif d == dim - 1:
# add ivdep pragma to innermost node
pragma = cpp_ast.Pragma("ivdep")
for_node = cpp_ast.For(dim_var, add_one(initial), add_one(end),
increment, cpp_ast.Block())
cur_node.body = cpp_ast.Block(contents=[pragma, for_node])
cur_node = for_node
else:
cur_node.body = cpp_ast.For(dim_var, add_one(initial),
add_one(end), increment,
cpp_ast.Block())
cur_node = cur_node.body
return (cur_node, ret_node)
def visit_FunctionDef(self, node):
declarator = cpp_ast.Value('void', node.name)
args = self.visit(node.args)
body = cpp_ast.Block([self.visit(x) for x in node.body])
return declarator, args, body
def visit_For(self, node):
_iters = self.visit(node.iter)
targets = self.visit(node.target)
#are we iterating over a data object?
if type(_iters) is cpp_ast.CName and _iters.name in self.data_model:
_iters = [_iters]
targets = [targets]
#co-iterating over a set of datasets!
if type(_iters) is list:
#set up the loop variable and weight
self.loopvar.append(self.loopvar[-1] + 'i')
loopvar = cpp_ast.CName(self.loopvar[-1])
body = []
weight_loop = self.weighted and reduce(lambda a, b: a or b, [
(_iter.name in self.data_model
and self.data_model[_iter.name].should_subsample)
for _iter in _iters
])
if weight_loop:
self.aggregate_on(loopvar)
# add the temporary children to the data model
for target, _iter in zip(targets, _iters):
if not (type(_iter) is cpp_ast.CName
and _iter.name in self.data_model):
raise ValueError(
"Cannot iterate over unknown data object: '%s'" %
_iter.name)
parent_model = self.data_model[_iter.name]
if type(target) is not cpp_ast.CName:
raise ValueError("Not a valid iteration target: '%s'" %
str(target))
if target.name in self.data_model:
raise ValueError("Cannot reuse iteration target: '%s'" %
target.name)
target_model = self.data_model[
target.name] = parent_model.branch(name=target.name)
ctype = target_model.scalar_t.ctype()
decl = cpp_ast.Value(
ctype, target.name) if target_model.is_scalar(
) else cpp_ast.Pointer(cpp_ast.Value(ctype, target.name))
init = parent_model.declare_child(target_model, loopvar)
#init = cpp_ast.Subscript( _iter, loopvar) if target_model.is_scalar() \
# else cpp_ast.BinOp( _iter, '+', cpp_ast.BinOp( loopvar , '*', parent_model.element_size() ) )
body.append(cpp_ast.Assign(decl, init))
# visit the body of the for
body += [self.visit(x) for x in node.body]
# generate the C for intializer
ret = cpp_ast.RawFor( cpp_ast.Assign( cpp_ast.Value( 'int', loopvar ), cpp_ast.CNumber(0) ), \
cpp_ast.Compare( loopvar, '<', cpp_ast.CNumber( self.data_model[ _iter.name ].dimensions[0] ) ), \
cpp_ast.UnaryOp( '++', loopvar ), cpp_ast.Block( body ) )
# remove temporary children from data model and otherwise clean up
self.loopvar = self.loopvar[:-1]
for target in targets:
del self.data_model[target.name]
if weight_loop:
self.aggregate_off(loopvar)
# return
return ret
#or perhaps, a known range.
elif isinstance(_iters, cpp_ast.CNumber):
return cpp_ast.RawFor( cpp_ast.Assign( cpp_ast.Value( 'int', targets ), cpp_ast.CNumber(0) ), \
cpp_ast.Compare( targets, '<', _iter ), cpp_ast.UnaryOp( '++', target ), \
cpp_ast.Block([ self.visit( x ) for x in node.body ] ) )
else:
raise ValueError(
'Loop iterand "%s" is not a numeric expression or known data object'
% str(_iters))
