def inline_calls(func_ir, _locals):
work_list = list(func_ir.blocks.items())
while work_list:
label, block = work_list.pop()
for i, instr in enumerate(block.body):
if isinstance(instr, ir.Assign):
lhs = instr.target
expr = instr.value
if isinstance(expr, ir.Expr) and expr.op == 'call':
func_def = guard(get_definition, func_ir, expr.func)
if (isinstance(func_def, (ir.Global, ir.FreeVar))
and isinstance(func_def.value, CPUDispatcher)):
py_func = func_def.value.py_func
inline_out = inline_closure_call(
func_ir, py_func.__globals__, block, i, py_func,
work_list=work_list)
# TODO remove if when inline_closure_call() output fix
# is merged in Numba
if isinstance(inline_out, tuple):
var_dict = inline_out[1]
# TODO: update '##distributed' and '##threaded' in _locals
_locals.update((var_dict[k].name, v)
for k, v in func_def.value.locals.items()
if k in var_dict)
# for block in new_blocks:
# work_list.append(block)
# current block is modified, skip the rest
# (included in new blocks)
break
# sometimes type inference fails after inlining since blocks are inserted
# at the end and there are agg constraints (categorical_split case)
# CFG simplification fixes this case
func_ir.blocks = ir_utils.simplify_CFG(func_ir.blocks)
def inline_new_blocks(func_ir, block, i, callee_blocks, work_list=None):
# adopted from inline_closure_call
scope = block.scope
instr = block.body[i]
# 1. relabel callee_ir by adding an offset
callee_blocks = add_offset_to_labels(callee_blocks,
ir_utils._max_label + 1)
callee_blocks = ir_utils.simplify_CFG(callee_blocks)
max_label = max(callee_blocks.keys())
# reset globals in ir_utils before we use it
ir_utils._max_label = max_label
topo_order = find_topo_order(callee_blocks)
# 5. split caller blocks into two
new_blocks = []
new_block = ir.Block(scope, block.loc)
new_block.body = block.body[i + 1:]
new_label = ir_utils.next_label()
func_ir.blocks[new_label] = new_block
new_blocks.append((new_label, new_block))
block.body = block.body[:i]
min_label = topo_order[0]
block.body.append(ir.Jump(min_label, instr.loc))
# 6. replace Return with assignment to LHS
numba.inline_closurecall._replace_returns(callee_blocks, instr.target,
new_label)
# remove the old definition of instr.target too
if (instr.target.name in func_ir._definitions):
func_ir._definitions[instr.target.name] = []
# 7. insert all new blocks, and add back definitions
for label in topo_order:
# block scope must point to parent's
block = callee_blocks[label]
block.scope = scope
numba.inline_closurecall._add_definitions(func_ir, block)
func_ir.blocks[label] = block
new_blocks.append((label, block))
if work_list is not None:
for block in new_blocks:
work_list.append(block)
return callee_blocks
def _mk_stencil_parfor(self, label, in_args, out_arr, stencil_ir,
index_offsets, target, return_type, stencil_func,
arg_to_arr_dict):
""" Converts a set of stencil kernel blocks to a parfor.
"""
gen_nodes = []
stencil_blocks = stencil_ir.blocks
if config.DEBUG_ARRAY_OPT == 1:
print("_mk_stencil_parfor", label, in_args, out_arr, index_offsets,
return_type, stencil_func, stencil_blocks)
ir_utils.dump_blocks(stencil_blocks)
in_arr = in_args[0]
# run copy propagate to replace in_args copies (e.g. a = A)
in_arr_typ = self.typemap[in_arr.name]
in_cps, out_cps = ir_utils.copy_propagate(stencil_blocks, self.typemap)
name_var_table = ir_utils.get_name_var_table(stencil_blocks)
ir_utils.apply_copy_propagate(
stencil_blocks,
in_cps,
name_var_table,
self.typemap,
self.calltypes)
if config.DEBUG_ARRAY_OPT == 1:
print("stencil_blocks after copy_propagate")
ir_utils.dump_blocks(stencil_blocks)
ir_utils.remove_dead(stencil_blocks, self.func_ir.arg_names, stencil_ir,
self.typemap)
if config.DEBUG_ARRAY_OPT == 1:
print("stencil_blocks after removing dead code")
ir_utils.dump_blocks(stencil_blocks)
# create parfor vars
ndims = self.typemap[in_arr.name].ndim
scope = in_arr.scope
loc = in_arr.loc
parfor_vars = []
for i in range(ndims):
parfor_var = ir.Var(scope, mk_unique_var(
"$parfor_index_var"), loc)
self.typemap[parfor_var.name] = types.intp
parfor_vars.append(parfor_var)
start_lengths, end_lengths = self._replace_stencil_accesses(
stencil_blocks, parfor_vars, in_args, index_offsets, stencil_func,
arg_to_arr_dict)
if config.DEBUG_ARRAY_OPT == 1:
print("stencil_blocks after replace stencil accesses")
ir_utils.dump_blocks(stencil_blocks)
# create parfor loop nests
loopnests = []
equiv_set = self.array_analysis.get_equiv_set(label)
in_arr_dim_sizes = equiv_set.get_shape(in_arr)
assert ndims == len(in_arr_dim_sizes)
for i in range(ndims):
last_ind = self._get_stencil_last_ind(in_arr_dim_sizes[i],
end_lengths[i], gen_nodes, scope, loc)
start_ind = self._get_stencil_start_ind(
start_lengths[i], gen_nodes, scope, loc)
# start from stencil size to avoid invalid array access
loopnests.append(numba.parfor.LoopNest(parfor_vars[i],
start_ind, last_ind, 1))
# We have to guarantee that the exit block has maximum label and that
# there's only one exit block for the parfor body.
# So, all return statements will change to jump to the parfor exit block.
parfor_body_exit_label = max(stencil_blocks.keys()) + 1
stencil_blocks[parfor_body_exit_label] = ir.Block(scope, loc)
exit_value_var = ir.Var(scope, mk_unique_var("$parfor_exit_value"), loc)
self.typemap[exit_value_var.name] = return_type.dtype
# create parfor index var
for_replacing_ret = []
if ndims == 1:
parfor_ind_var = parfor_vars[0]
else:
parfor_ind_var = ir.Var(scope, mk_unique_var(
"$parfor_index_tuple_var"), loc)
self.typemap[parfor_ind_var.name] = types.containers.UniTuple(
types.intp, ndims)
tuple_call = ir.Expr.build_tuple(parfor_vars, loc)
tuple_assign = ir.Assign(tuple_call, parfor_ind_var, loc)
for_replacing_ret.append(tuple_assign)
if config.DEBUG_ARRAY_OPT == 1:
print("stencil_blocks after creating parfor index var")
ir_utils.dump_blocks(stencil_blocks)
# empty init block
init_block = ir.Block(scope, loc)
if out_arr == None:
in_arr_typ = self.typemap[in_arr.name]
shape_name = ir_utils.mk_unique_var("in_arr_shape")
shape_var = ir.Var(scope, shape_name, loc)
shape_getattr = ir.Expr.getattr(in_arr, "shape", loc)
self.typemap[shape_name] = types.containers.UniTuple(types.intp,
in_arr_typ.ndim)
init_block.body.extend([ir.Assign(shape_getattr, shape_var, loc)])
zero_name = ir_utils.mk_unique_var("zero_val")
zero_var = ir.Var(scope, zero_name, loc)
if "cval" in stencil_func.options:
cval = stencil_func.options["cval"]
# TODO: Loosen this restriction to adhere to casting rules.
if return_type.dtype != typing.typeof.typeof(cval):
raise ValueError("cval type does not match stencil return type.")
temp2 = return_type.dtype(cval)
else:
temp2 = return_type.dtype(0)
full_const = ir.Const(temp2, loc)
self.typemap[zero_name] = return_type.dtype
init_block.body.extend([ir.Assign(full_const, zero_var, loc)])
so_name = ir_utils.mk_unique_var("stencil_output")
out_arr = ir.Var(scope, so_name, loc)
self.typemap[out_arr.name] = numba.types.npytypes.Array(
return_type.dtype,
in_arr_typ.ndim,
in_arr_typ.layout)
dtype_g_np_var = ir.Var(scope, mk_unique_var("$np_g_var"), loc)
self.typemap[dtype_g_np_var.name] = types.misc.Module(np)
dtype_g_np = ir.Global('np', np, loc)
dtype_g_np_assign = ir.Assign(dtype_g_np, dtype_g_np_var, loc)
init_block.body.append(dtype_g_np_assign)
dtype_np_attr_call = ir.Expr.getattr(dtype_g_np_var, return_type.dtype.name, loc)
dtype_attr_var = ir.Var(scope, mk_unique_var("$np_attr_attr"), loc)
self.typemap[dtype_attr_var.name] = types.functions.NumberClass(return_type.dtype)
dtype_attr_assign = ir.Assign(dtype_np_attr_call, dtype_attr_var, loc)
init_block.body.append(dtype_attr_assign)
stmts = ir_utils.gen_np_call("full",
np.full,
out_arr,
[shape_var, zero_var, dtype_attr_var],
self.typingctx,
self.typemap,
self.calltypes)
equiv_set.insert_equiv(out_arr, in_arr_dim_sizes)
init_block.body.extend(stmts)
self.replace_return_with_setitem(stencil_blocks, exit_value_var,
parfor_body_exit_label)
if config.DEBUG_ARRAY_OPT == 1:
print("stencil_blocks after replacing return")
ir_utils.dump_blocks(stencil_blocks)
setitem_call = ir.SetItem(out_arr, parfor_ind_var, exit_value_var, loc)
self.calltypes[setitem_call] = signature(
types.none, self.typemap[out_arr.name],
self.typemap[parfor_ind_var.name],
self.typemap[out_arr.name].dtype
)
stencil_blocks[parfor_body_exit_label].body.extend(for_replacing_ret)
stencil_blocks[parfor_body_exit_label].body.append(setitem_call)
# simplify CFG of parfor body (exit block could be simplified often)
# add dummy return to enable CFG
stencil_blocks[parfor_body_exit_label].body.append(ir.Return(0,
ir.Loc("stencilparfor_dummy", -1)))
stencil_blocks = ir_utils.simplify_CFG(stencil_blocks)
stencil_blocks[max(stencil_blocks.keys())].body.pop()
if config.DEBUG_ARRAY_OPT == 1:
print("stencil_blocks after adding SetItem")
ir_utils.dump_blocks(stencil_blocks)
pattern = ('stencil', [start_lengths, end_lengths])
parfor = numba.parfor.Parfor(loopnests, init_block, stencil_blocks,
loc, parfor_ind_var, equiv_set, pattern, self.flags)
gen_nodes.append(parfor)
gen_nodes.append(ir.Assign(out_arr, target, loc))
return gen_nodes
def inline_closure_call(func_ir, glbls, block, i, callee, typingctx=None,
arg_typs=None, typemap=None, calltypes=None,
work_list=None):
"""Inline the body of `callee` at its callsite (`i`-th instruction of `block`)
`func_ir` is the func_ir object of the caller function and `glbls` is its
global variable environment (func_ir.func_id.func.__globals__).
`block` is the IR block of the callsite and `i` is the index of the
callsite's node. `callee` is either the called function or a
make_function node. `typingctx`, `typemap` and `calltypes` are typing
data structures of the caller, available if we are in a typed pass.
`arg_typs` includes the types of the arguments at the callsite.
"""
scope = block.scope
instr = block.body[i]
call_expr = instr.value
debug_print = _make_debug_print("inline_closure_call")
debug_print("Found closure call: ", instr, " with callee = ", callee)
# support both function object and make_function Expr
callee_code = callee.code if hasattr(callee, 'code') else callee.__code__
callee_defaults = callee.defaults if hasattr(callee, 'defaults') else callee.__defaults__
callee_closure = callee.closure if hasattr(callee, 'closure') else callee.__closure__
# first, get the IR of the callee
callee_ir = get_ir_of_code(glbls, callee_code)
callee_blocks = callee_ir.blocks
# 1. relabel callee_ir by adding an offset
max_label = max(func_ir.blocks.keys())
callee_blocks = add_offset_to_labels(callee_blocks, max_label + 1)
callee_blocks = simplify_CFG(callee_blocks)
callee_ir.blocks = callee_blocks
min_label = min(callee_blocks.keys())
max_label = max(callee_blocks.keys())
# reset globals in ir_utils before we use it
ir_utils._max_label = max_label
debug_print("After relabel")
_debug_dump(callee_ir)
# 2. rename all local variables in callee_ir with new locals created in func_ir
callee_scopes = _get_all_scopes(callee_blocks)
debug_print("callee_scopes = ", callee_scopes)
# one function should only have one local scope
assert(len(callee_scopes) == 1)
callee_scope = callee_scopes[0]
var_dict = {}
for var in callee_scope.localvars._con.values():
if not (var.name in callee_code.co_freevars):
new_var = scope.define(mk_unique_var(var.name), loc=var.loc)
var_dict[var.name] = new_var
debug_print("var_dict = ", var_dict)
replace_vars(callee_blocks, var_dict)
debug_print("After local var rename")
_debug_dump(callee_ir)
# 3. replace formal parameters with actual arguments
args = list(call_expr.args)
if callee_defaults:
debug_print("defaults = ", callee_defaults)
if isinstance(callee_defaults, tuple): # Python 3.5
args = args + list(callee_defaults)
elif isinstance(callee_defaults, ir.Var) or isinstance(callee_defaults, str):
defaults = func_ir.get_definition(callee_defaults)
assert(isinstance(defaults, ir.Const))
loc = defaults.loc
args = args + [ir.Const(value=v, loc=loc)
for v in defaults.value]
else:
raise NotImplementedError(
"Unsupported defaults to make_function: {}".format(defaults))
debug_print("After arguments rename: ")
_debug_dump(callee_ir)
# 4. replace freevar with actual closure var
if callee_closure:
closure = func_ir.get_definition(callee_closure)
debug_print("callee's closure = ", closure)
if isinstance(closure, tuple):
cellget = ctypes.pythonapi.PyCell_Get
cellget.restype = ctypes.py_object
cellget.argtypes = (ctypes.py_object,)
items = tuple(cellget(x) for x in closure)
else:
assert(isinstance(closure, ir.Expr)
and closure.op == 'build_tuple')
items = closure.items
assert(len(callee_code.co_freevars) == len(items))
_replace_freevars(callee_blocks, items)
debug_print("After closure rename")
_debug_dump(callee_ir)
if typingctx:
from numba import compiler
f_typemap, f_return_type, f_calltypes = compiler.type_inference_stage(
typingctx, callee_ir, arg_typs, None)
canonicalize_array_math(callee_ir, f_typemap,
f_calltypes, typingctx)
# remove argument entries like arg.a from typemap
arg_names = [vname for vname in f_typemap if vname.startswith("arg.")]
for a in arg_names:
f_typemap.pop(a)
typemap.update(f_typemap)
calltypes.update(f_calltypes)
_replace_args_with(callee_blocks, args)
# 5. split caller blocks into two
new_blocks = []
new_block = ir.Block(scope, block.loc)
new_block.body = block.body[i + 1:]
new_label = next_label()
func_ir.blocks[new_label] = new_block
new_blocks.append((new_label, new_block))
block.body = block.body[:i]
block.body.append(ir.Jump(min_label, instr.loc))
# 6. replace Return with assignment to LHS
topo_order = find_topo_order(callee_blocks)
_replace_returns(callee_blocks, instr.target, new_label)
# remove the old definition of instr.target too
if (instr.target.name in func_ir._definitions):
func_ir._definitions[instr.target.name] = []
# 7. insert all new blocks, and add back definitions
for label in topo_order:
# block scope must point to parent's
block = callee_blocks[label]
block.scope = scope
_add_definitions(func_ir, block)
func_ir.blocks[label] = block
new_blocks.append((label, block))
debug_print("After merge in")
_debug_dump(func_ir)
if work_list != None:
for block in new_blocks:
work_list.append(block)
return callee_blocks
