def run_pass(self, state):
"""Run inlining of overloads
"""
if self._DEBUG:
print('before overload inline'.center(80, '-'))
print(state.func_id.unique_name)
print(state.func_ir.dump())
print(''.center(80, '-'))
from numba.core.inline_closurecall import (InlineWorker,
callee_ir_validator)
inline_worker = InlineWorker(
state.typingctx,
state.targetctx,
state.locals,
state.pipeline,
state.flags,
callee_ir_validator,
state.typemap,
state.calltypes,
)
modified = False
work_list = list(state.func_ir.blocks.items())
# use a work list, look for call sites via `ir.Expr.op == call` and
# then pass these to `self._do_work` to make decisions about inlining.
while work_list:
label, block = work_list.pop()
for i, instr in enumerate(block.body):
# TO-DO: other statements (setitem)
if isinstance(instr, ir.Assign):
expr = instr.value
if isinstance(expr, ir.Expr):
workfn = self._do_work_expr
if guard(workfn, state, work_list, block, i, expr,
inline_worker):
modified = True
break # because block structure changed
if self._DEBUG:
print('after overload inline'.center(80, '-'))
print(state.func_id.unique_name)
print(state.func_ir.dump())
print(''.center(80, '-'))
if modified:
# Remove dead blocks, this is safe as it relies on the CFG only.
cfg = compute_cfg_from_blocks(state.func_ir.blocks)
for dead in cfg.dead_nodes():
del state.func_ir.blocks[dead]
# clean up blocks
dead_code_elimination(state.func_ir,
typemap=state.type_annotation.typemap)
# clean up unconditional branches that appear due to inlined
# functions introducing blocks
state.func_ir.blocks = simplify_CFG(state.func_ir.blocks)
if self._DEBUG:
print('after overload inline DCE'.center(80, '-'))
print(state.func_id.unique_name)
print(state.func_ir.dump())
print(''.center(80, '-'))
return True
def generic(self, args, kws):
"""
Type the overloaded function by compiling the appropriate
implementation for the given args.
"""
disp, new_args = self._get_impl(args, kws)
if disp is None:
return
# Compile and type it for the given types
disp_type = types.Dispatcher(disp)
# Store the compiled overload for use in the lowering phase if there's
# no inlining required (else functions are being compiled which will
# never be used as they are inlined)
if not self._inline.is_never_inline:
# need to run the compiler front end up to type inference to compute
# a signature
from numba.core import typed_passes, compiler
from numba.core.inline_closurecall import InlineWorker
fcomp = disp._compiler
flags = compiler.Flags()
# Updating these causes problems?!
#fcomp.targetdescr.options.parse_as_flags(flags,
# fcomp.targetoptions)
#flags = fcomp._customize_flags(flags)
# spoof a compiler pipline like the one that will be in use
tyctx = fcomp.targetdescr.typing_context
tgctx = fcomp.targetdescr.target_context
compiler_inst = fcomp.pipeline_class(
tyctx,
tgctx,
None,
None,
None,
flags,
None,
)
inline_worker = InlineWorker(
tyctx,
tgctx,
fcomp.locals,
compiler_inst,
flags,
None,
)
# If the inlinee contains something to trigger literal arg dispatch
# then the pipeline call will unconditionally fail due to a raised
# ForceLiteralArg exception. Therefore `resolve` is run first, as
# type resolution must occur at some point, this will hit any
# `literally` calls and because it's going via the dispatcher will
# handle them correctly i.e. ForceLiteralArg propagates. This having
# the desired effect of ensuring the pipeline call is only made in
# situations that will succeed. For context see #5887.
resolve = disp_type.dispatcher.get_call_template
template, pysig, folded_args, kws = resolve(new_args, kws)
ir = inline_worker.run_untyped_passes(disp_type.dispatcher.py_func)
(typemap, return_type, calltypes,
_) = typed_passes.type_inference_stage(self.context, ir,
folded_args, None)
sig = Signature(return_type, folded_args, None)
# this stores a load of info for the cost model function if supplied
# it by default is None
self._inline_overloads[sig.args] = {'folded_args': folded_args}
# this stores the compiled overloads, if there's no compiled
# overload available i.e. function is always inlined, the key still
# needs to exist for type resolution
# NOTE: If lowering is failing on a `_EmptyImplementationEntry`,
# the inliner has failed to inline this entry corretly.
impl_init = _EmptyImplementationEntry('always inlined')
self._compiled_overloads[sig.args] = impl_init
if not self._inline.is_always_inline:
# this branch is here because a user has supplied a function to
# determine whether to inline or not. As a result both compiled
# function and inliner info needed, delaying the computation of
# this leads to an internal state mess at present. TODO: Fix!
sig = disp_type.get_call_type(self.context, new_args, kws)
self._compiled_overloads[sig.args] = disp_type.get_overload(
sig)
# store the inliner information, it's used later in the cost
# model function call
iinfo = _inline_info(ir, typemap, calltypes, sig)
self._inline_overloads[sig.args] = {
'folded_args': folded_args,
'iinfo': iinfo
}
else:
sig = disp_type.get_call_type(self.context, new_args, kws)
self._compiled_overloads[sig.args] = disp_type.get_overload(sig)
return sig