def inline_calls_inner(func_ir, block, stmt, i, py_func):
call_expr = stmt.value
scope = block.scope
callee_ir = numba.compiler.run_frontend(py_func)
# relabel callee_ir by adding an offset
max_label = max(func_ir.blocks.keys())
callee_blocks = add_offset_to_labels(callee_ir.blocks, max_label + 1)
callee_ir.blocks = callee_blocks
min_label = min(callee_blocks.keys())
max_label = max(callee_blocks.keys())
# init _max_label global in ir_utils before using next_label()
ir_utils._max_label = max_label
# rename all variables in callee blocks
var_table = get_name_var_table(callee_ir.blocks)
new_var_dict = {}
for name, var in var_table.items():
new_var = scope.define(mk_unique_var(var.name), loc=var.loc)
new_var_dict[name] = new_var
replace_vars(callee_ir.blocks, new_var_dict)
# replace callee arguments
args = list(call_expr.args)
# TODO: replace defaults (add to args)
_replace_args(callee_ir.blocks, args)
# split caller blocks into two
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
block.body = block.body[:i]
block.body.append(ir.Jump(min_label, stmt.loc))
# replace Return with assignment to LHS
_replace_returns(callee_ir.blocks, stmt.target, new_label)
# insert all new blocks
for label, bl in callee_ir.blocks.items():
func_ir.blocks[label] = bl
# run inline_calls recursively to transform other calls
inline_calls(func_ir)
return
def get_stencil_ir(sf, typingctx, args, scope, loc, input_dict, typemap,
calltypes):
"""get typed IR from stencil bytecode
"""
from numba.targets.cpu import CPUContext
from numba.targets.registry import cpu_target
from numba.annotations import type_annotations
from numba.compiler import type_inference_stage
# get untyped IR
stencil_func_ir = sf.kernel_ir.copy()
# copy the IR nodes to avoid changing IR in the StencilFunc object
stencil_blocks = copy.deepcopy(stencil_func_ir.blocks)
stencil_func_ir.blocks = stencil_blocks
name_var_table = ir_utils.get_name_var_table(stencil_func_ir.blocks)
if "out" in name_var_table:
raise ValueError("Cannot use the reserved word 'out' in stencil kernels.")
# get typed IR with a dummy pipeline (similar to test_parfors.py)
targetctx = CPUContext(typingctx)
with cpu_target.nested_context(typingctx, targetctx):
tp = DummyPipeline(typingctx, targetctx, args, stencil_func_ir)
numba.rewrites.rewrite_registry.apply(
'before-inference', tp, tp.func_ir)
tp.typemap, tp.return_type, tp.calltypes = type_inference_stage(
tp.typingctx, tp.func_ir, tp.args, None)
type_annotations.TypeAnnotation(
func_ir=tp.func_ir,
typemap=tp.typemap,
calltypes=tp.calltypes,
lifted=(),
lifted_from=None,
args=tp.args,
return_type=tp.return_type,
html_output=numba.config.HTML)
# make block labels unique
stencil_blocks = ir_utils.add_offset_to_labels(stencil_blocks,
ir_utils.next_label())
min_label = min(stencil_blocks.keys())
max_label = max(stencil_blocks.keys())
ir_utils._max_label = max_label
if config.DEBUG_ARRAY_OPT == 1:
print("Initial stencil_blocks")
ir_utils.dump_blocks(stencil_blocks)
# rename variables,
var_dict = {}
for v, typ in tp.typemap.items():
new_var = ir.Var(scope, mk_unique_var(v), loc)
var_dict[v] = new_var
typemap[new_var.name] = typ # add new var type for overall function
ir_utils.replace_vars(stencil_blocks, var_dict)
if config.DEBUG_ARRAY_OPT == 1:
print("After replace_vars")
ir_utils.dump_blocks(stencil_blocks)
# add call types to overall function
for call, call_typ in tp.calltypes.items():
calltypes[call] = call_typ
arg_to_arr_dict = {}
# replace arg with arr
for block in stencil_blocks.values():
for stmt in block.body:
if isinstance(stmt, ir.Assign) and isinstance(stmt.value, ir.Arg):
if config.DEBUG_ARRAY_OPT == 1:
print("input_dict", input_dict, stmt.value.index,
stmt.value.name, stmt.value.index in input_dict)
arg_to_arr_dict[stmt.value.name] = input_dict[stmt.value.index].name
stmt.value = input_dict[stmt.value.index]
if config.DEBUG_ARRAY_OPT == 1:
print("arg_to_arr_dict", arg_to_arr_dict)
print("After replace arg with arr")
ir_utils.dump_blocks(stencil_blocks)
ir_utils.remove_dels(stencil_blocks)
stencil_func_ir.blocks = stencil_blocks
return stencil_func_ir, sf.get_return_type(args)[0], arg_to_arr_dict
def inline_closure_call(self, block, i, callee):
"""Inline the body of `callee` at its callsite (`i`-th instruction of `block`)
"""
scope = block.scope
instr = block.body[i]
call_expr = instr.value
_debug_print("Found closure call: ", instr, " with callee = ", callee)
func_ir = self.func_ir
# first, get the IR of the callee
from_ir = self.get_ir_of_code(callee.code)
from_blocks = from_ir.blocks
# 1. relabel from_ir by adding an offset
max_label = max(func_ir.blocks.keys())
from_blocks = add_offset_to_labels(from_blocks, max_label + 1)
from_ir.blocks = from_blocks
min_label = min(from_blocks.keys())
max_label = max(from_blocks.keys())
# reset globals in ir_utils before we use it
ir_utils._max_label = max_label
ir_utils.visit_vars_extensions = {}
# 2. rename all local variables in from_ir with new locals created in func_ir
from_scopes = _get_all_scopes(from_blocks)
_debug_print("obj_IR has scopes: ", from_scopes)
# one function should only have one local scope
assert(len(from_scopes) == 1)
from_scope = from_scopes[0]
var_dict = {}
for var in from_scope.localvars._con.values():
if not (var.name in callee.code.co_freevars):
var_dict[var.name] = scope.make_temp(var.loc)
_debug_print("Before local var rename: var_dict = ", var_dict)
_debug_dump(from_ir)
replace_vars(from_blocks, var_dict)
_debug_print("After local var rename: ")
_debug_dump(from_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))
_replace_args_with(from_blocks, args)
_debug_print("After arguments rename: ")
_debug_dump(from_ir)
# 4. replace freevar with actual closure var
if callee.closure:
closure = func_ir.get_definition(callee.closure)
assert(isinstance(closure, ir.Expr) and closure.op == 'build_tuple')
assert(len(callee.code.co_freevars) == len(closure.items))
_debug_print("callee's closure = ", closure)
_replace_freevars(from_blocks, closure.items)
_debug_print("After closure rename: ")
_debug_dump(from_ir)
# 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
_replace_returns(from_blocks, instr.target, new_label)
# 7. insert all new blocks, and add back definitions
for label, block in from_blocks.items():
# block scope must point to parent's
block.scope = scope
_add_definition(func_ir, block)
func_ir.blocks[label] = block
new_blocks.append((label, block))
_debug_print("After merge: ")
_debug_dump(func_ir)
return new_blocks
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
