def _analyze_call_set_REP(self, lhs, args, array_dists, fdef=None):
for v in args:
if (is_array(self.typemap, v.name)
or is_array_container(self.typemap, v.name)
or isinstance(self.typemap[v.name], DataFrameType)):
dprint("dist setting call arg REP {} in {}".format(
v.name, fdef))
array_dists[v.name] = Distribution.REP
if (is_array(self.typemap, lhs)
or is_array_container(self.typemap, lhs)
or isinstance(self.typemap[lhs], DataFrameType)):
dprint("dist setting call out REP {} in {}".format(lhs, fdef))
array_dists[lhs] = Distribution.REP
def _set_REP(self, var_list, array_dists):
for var in var_list:
varname = var.name
# Handle SeriesType since it comes from Arg node and it could
# have user-defined distribution
if (is_array(self.typemap, varname)
or is_array_container(self.typemap, varname)
or isinstance(self.typemap[varname],
(SeriesType, DataFrameType))):
dprint("dist setting REP {}".format(varname))
array_dists[varname] = Distribution.REP
# handle tuples of arrays
var_def = guard(get_definition, self.func_ir, var)
if (var_def is not None and isinstance(var_def, ir.Expr)
and var_def.op == 'build_tuple'):
tuple_vars = var_def.items
self._set_REP(tuple_vars, array_dists)
def _analyze_assign(self, inst, array_dists, parfor_dists):
lhs = inst.target.name
rhs = inst.value
# treat return casts like assignments
if isinstance(rhs, ir.Expr) and rhs.op == 'cast':
rhs = rhs.value
if isinstance(rhs,
ir.Var) and (is_array(self.typemap, lhs)
or isinstance(self.typemap[lhs],
(SeriesType, DataFrameType))
or is_array_container(self.typemap, lhs)):
self._meet_array_dists(lhs, rhs.name, array_dists)
return
elif (is_array(self.typemap, lhs) and isinstance(rhs, ir.Expr)
and rhs.op == 'inplace_binop'):
# distributions of all 3 variables should meet (lhs, arg1, arg2)
arg1 = rhs.lhs.name
arg2 = rhs.rhs.name
dist = self._meet_array_dists(arg1, arg2, array_dists)
dist = self._meet_array_dists(arg1, lhs, array_dists, dist)
self._meet_array_dists(arg1, arg2, array_dists, dist)
return
elif isinstance(rhs,
ir.Expr) and rhs.op in ['getitem', 'static_getitem']:
self._analyze_getitem(inst, lhs, rhs, array_dists)
return
elif isinstance(rhs, ir.Expr) and rhs.op == 'build_tuple':
# parallel arrays can be packed and unpacked from tuples
# e.g. boolean array index in test_getitem_multidim
return
elif (isinstance(rhs, ir.Expr) and rhs.op == 'getattr'
and rhs.attr == 'T' and is_array(self.typemap, lhs)):
# array and its transpose have same distributions
arr = rhs.value.name
self._meet_array_dists(lhs, arr, array_dists)
# keep lhs in table for dot() handling
self._T_arrs.add(lhs)
return
elif (isinstance(rhs, ir.Expr) and rhs.op == 'getattr'
and isinstance(self.typemap[rhs.value.name], DataFrameType)
and rhs.attr == 'to_csv'):
return
elif (isinstance(rhs, ir.Expr) and rhs.op == 'getattr'
and rhs.attr in [
'shape', 'ndim', 'size', 'strides', 'dtype', 'itemsize',
'astype', 'reshape', 'ctypes', 'transpose', 'tofile', 'copy'
]):
pass # X.shape doesn't affect X distribution
elif isinstance(rhs, ir.Expr) and rhs.op == 'call':
self._analyze_call(lhs, rhs, rhs.func.name, rhs.args, array_dists)
# handle for A in arr_container: ...
# A = pair_first(iternext(getiter(arr_container)))
# TODO: support getitem of container
elif isinstance(rhs, ir.Expr) and rhs.op == 'pair_first' and is_array(
self.typemap, lhs):
arr_container = guard(_get_pair_first_container, self.func_ir, rhs)
if arr_container is not None:
self._meet_array_dists(lhs, arr_container.name, array_dists)
return
elif isinstance(rhs, ir.Expr) and rhs.op in ('getiter', 'iternext'):
# analyze array container access in pair_first
return
elif isinstance(rhs, ir.Arg):
if rhs.name in self.metadata['distributed']:
if lhs not in array_dists:
array_dists[lhs] = Distribution.OneD
elif rhs.name in self.metadata['threaded']:
if lhs not in array_dists:
array_dists[lhs] = Distribution.Thread
else:
dprint("replicated input ", rhs.name, lhs)
self._set_REP([inst.target], array_dists)
else:
self._set_REP(inst.list_vars(), array_dists)
return