def __init__(self, bytecode):
self.bytecode = bytecode
self.scopes = []
self.loc = ir.Loc(filename=bytecode.filename, line=1)
self.argspec = bytecode.argspec
# Control flow analysis
self.cfa = controlflow.ControlFlowAnalysis(bytecode)
self.cfa.run()
# Data flow analysis
self.dfa = dataflow.DataFlowAnalysis(self.cfa)
self.dfa.run()
global_scope = ir.Scope(parent=None, loc=self.loc)
self._fill_global_scope(global_scope)
self.scopes.append(global_scope)
# { inst offset : ir.Block }
self.blocks = {}
# { name: value } of global variables used by the bytecode
self.used_globals = {}
# Temp states during interpretation
self.current_block = None
self.current_block_offset = None
self.syntax_blocks = []
self.dfainfo = None
self.constants = {}
class CheckEquality(unittest.TestCase):
var_a = ir.Var(None, 'a', ir.unknown_loc)
var_b = ir.Var(None, 'b', ir.unknown_loc)
var_c = ir.Var(None, 'c', ir.unknown_loc)
var_d = ir.Var(None, 'd', ir.unknown_loc)
var_e = ir.Var(None, 'e', ir.unknown_loc)
loc1 = ir.Loc('mock', 1, 0)
loc2 = ir.Loc('mock', 2, 0)
loc3 = ir.Loc('mock', 3, 0)
def check(self, base, same=[], different=[]):
for s in same:
self.assertTrue(base == s)
for d in different:
self.assertTrue(base != d)
def _iter_inst(self):
for block in self.cfa.iterliveblocks():
firstinst = self.bytecode[block.body[0]]
self._start_new_block(firstinst)
for offset, kws in self.dfainfo.insts:
inst = self.bytecode[offset]
self.loc = ir.Loc(filename=self.bytecode.filename,
line=inst.lineno)
yield inst, kws
def _start_new_block(self, inst):
self.loc = ir.Loc(filename=self.bytecode.filename, line=inst.lineno)
oldblock = self.current_block
self.insert_block(inst.offset)
# Ensure the last block is terminated
if oldblock is not None and not oldblock.is_terminated:
jmp = ir.Jump(inst.offset, loc=self.loc)
oldblock.append(jmp)
# Get DFA block info
self.dfainfo = self.dfa.infos[self.current_block_offset]
self.assigner = Assigner()
def interpret(self):
firstblk = min(self.cfa.blocks.keys())
self.loc = ir.Loc(filename=self.bytecode.filename,
line=self.bytecode[firstblk].lineno)
self.scopes.append(ir.Scope(parent=self.current_scope, loc=self.loc))
self._fill_args_into_scope(self.current_scope)
# Interpret loop
for inst, kws in self._iter_inst():
self._dispatch(inst, kws)
# Clean up
self._insert_var_dels()
def _iter_inst(self):
for blkct, block in enumerate(self.cfa.iterliveblocks()):
firstinst = self.bytecode[block.body[0]]
self._start_new_block(firstinst)
if blkct == 0:
# Is first block
self.init_first_block()
for offset, kws in self.dfainfo.insts:
inst = self.bytecode[offset]
self.loc = ir.Loc(filename=self.bytecode.filename,
line=inst.lineno)
yield inst, kws
def test_IRScope(self):
filename = "<?>"
top = ir.Scope(parent=None, loc=ir.Loc(filename=filename, line=1))
local = ir.Scope(parent=top, loc=ir.Loc(filename=filename, line=2))
apple = local.define('apple', loc=ir.Loc(filename=filename, line=3))
self.assertTrue(local.get('apple') is apple)
self.assertEqual(len(local.localvars), 1)
orange = top.define('orange', loc=ir.Loc(filename=filename, line=4))
self.assertEqual(len(local.localvars), 1)
self.assertEqual(len(top.localvars), 1)
self.assertTrue(top.get('orange') is orange)
self.assertTrue(local.get('orange') is orange)
more_orange = local.define('orange', loc=ir.Loc(filename=filename,
line=5))
self.assertTrue(top.get('orange') is orange)
self.assertTrue(local.get('orange') is not orange)
self.assertTrue(local.get('orange') is more_orange)
try:
bad_orange = local.define('orange', loc=ir.Loc(filename=filename,
line=5))
except ir.RedefinedError:
pass
else:
self.fail("Expecting an %s" % ir.RedefinedError)
def interpret(self):
firstblk = min(self.cfa.blocks.keys())
self.loc = ir.Loc(filename=self.bytecode.filename,
line=self.bytecode[firstblk].lineno)
self.scopes.append(ir.Scope(parent=self.current_scope, loc=self.loc))
# Interpret loop
for inst, kws in self._iter_inst():
self._dispatch(inst, kws)
# Post-processing and analysis on generated IR
self._insert_var_dels()
self._compute_live_variables()
if self.generator_info:
self._compute_generator_info()
def test_loc(self):
a = ir.Loc('file', 1, 0)
b = ir.Loc('file', 1, 0)
c = ir.Loc('pile', 1, 0)
d = ir.Loc('file', 2, 0)
e = ir.Loc('file', 1, 1)
self.check(a, same=[b,], different=[c, d, e])
f = ir.Loc('file', 1, 0, maybe_decorator=False)
g = ir.Loc('file', 1, 0, maybe_decorator=True)
self.check(a, same=[f, g])
def _start_new_block(self, inst):
self.loc = ir.Loc(filename=self.bytecode.filename, line=inst.lineno)
oldblock = self.current_block
self.insert_block(inst.offset)
# Ensure the last block is terminated
if oldblock is not None and not oldblock.is_terminated:
jmp = ir.Jump(inst.offset, loc=self.loc)
oldblock.append(jmp)
# Get DFA block info
self.dfainfo = self.dfa.infos[self.current_block_offset]
# Insert PHI
self._insert_phi()
# Notify listeners for the new block
for fn in utils.dict_itervalues(self._block_actions):
fn(self.current_block_offset, self.current_block)
def __init__(self, bytecode):
self.bytecode = bytecode
self.scopes = []
self.loc = ir.Loc(filename=bytecode.filename, line=1)
self.arg_count = bytecode.arg_count
self.arg_names = bytecode.arg_names
# Control flow analysis
self.cfa = controlflow.ControlFlowAnalysis(bytecode)
self.cfa.run()
# Data flow analysis
self.dfa = dataflow.DataFlowAnalysis(self.cfa)
self.dfa.run()
global_scope = ir.Scope(parent=None, loc=self.loc)
self._fill_global_scope(global_scope)
self.scopes.append(global_scope)
# { inst offset : ir.Block }
self.blocks = {}
# { name: value } of global variables used by the bytecode
self.used_globals = {}
# { name: [definitions] } of local variables
self.definitions = collections.defaultdict(list)
# { ir.Block: { variable names (potentially) alive at start of block } }
self.block_entry_vars = {}
if self.bytecode.is_generator:
self.generator_info = GeneratorInfo()
else:
self.generator_info = None
# Temp states during interpretation
self.current_block = None
self.current_block_offset = None
self.syntax_blocks = []
self.dfainfo = None
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
