def execute_datadescriptor_ooc(dd, res_name=None):
# only lift by one
res_ds = dd.dshape
res_shape, res_dt = to_numpy(dd.dshape)
lifted = dd.kerneltree._fused.kernel.lift(1,'C')
cf = lifted.ctypes_func
# element readers for operands
args = [(ct._type_,
arr.arr._data.element_reader(1),
arr.arr.dshape.shape[1:])
for ct, arr in izip(cf.argtypes[:-1], dd.args)]
res_dd = BLZDataDescriptor(blz.zeros((0,) + res_shape[1:],
dtype = res_dt,
rootdir = res_name))
res_ct = ctypes.c_double*3
res_buffer = res_ct()
res_buffer_entry = (cf.argtypes[-1]._type_,
ctypes.pointer(res_buffer),
res_shape[1:])
with res_dd.element_appender() as ea:
for i in xrange(res_shape[0]):
args_i = [(t, er.read_single((i,)), sh)
for t, er, sh in args]
args_i.append(res_buffer_entry)
cf_args = [_convert(*foo) for foo in args_i]
cf(*[ctypes.byref(x) for x in cf_args])
ea.append(ctypes.addressof(res_buffer),1)
return blaze.Array(res_dd)
def execute_datadescriptor_ooc_2(dd, res_name=None):
res_ds = dd.dshape
res_shape, res_dt = to_numpy(dd.dshape)
lifted = dd.kerneltree._fused.kernel.lift(1,'C')
cf = lifted.ctypes_func
res_ctype = cf.argtypes[-1]._type_
args = [(ct._type_,
arr.arr._data.element_reader(1),
arr.arr.dshape.shape[1:])
for ct, arr in izip(cf.argtypes[:-1], dd.args)]
res_dd = BLZDataDescriptor(blz.zeros((0,) + res_shape[1:],
dtype = res_dt,
rootdir = res_name))
with res_dd.element_appender() as dst:
for i in xrange(res_shape[0]):
# advance sources
tpl = (i,)
cf_args = [_mk_array_c_ref(t, er.read_single(tpl), sh)
for t, er, sh in args ]
with dst.buffered_ptr() as dst_ptr:
cf_args.append(_mk_array_c_ref(res_ctype,
dst_ptr,
res_shape[1:]))
cf(*cf_args)
return blaze.Array(res_dd)
def interpret(func, env, args, storage=None, **kwds):
assert len(args) == len(func.args)
# Make a copy, since we're going to mutate our IR!
func = copy_function(func)
# If it's a BLZ output, we want an interpreter that streams
# the processing through in chunks
if storage is not None:
if len(func.type.restype.shape) == 0:
raise TypeError('Require an array, not a scalar, for outputting to BLZ')
env['stream-outer'] = True
result_ndim = env['result-ndim'] = len(func.type.restype.shape)
else:
# Convert any persistent inputs to memory
# TODO: should stream the computation in this case
for i, arg in enumerate(args):
if isinstance(arg._data, BLZDataDescriptor):
args[i] = arg[:]
# Update environment with dynd type information
dynd_types = dict((arg, get_dynd_type(array))
for arg, array in zip(func.args, args)
if isinstance(array._data, DyNDDataDescriptor))
env['dynd-types'] = dynd_types
# Lift ckernels
func, env = run_pipeline(func, env, run_time_passes)
if storage is None:
# Evaluate once
values = dict(zip(func.args, args))
interp = CKernelInterp(values)
visit(interp, func)
return interp.result
else:
res_shape, res_dt = blaze.datashape.to_numpy(func.type.restype)
dim_size = operator.index(res_shape[0])
row_size = ndt.type(str(func.type.restype.subarray(1))).data_size
chunk_size = min(max(1, (1024*1024) // row_size), dim_size)
# Evaluate by streaming the outermost dimension,
# and using the BLZ data descriptor's append
dst_dd = BLZDataDescriptor(blz.zeros((0,)+res_shape[1:], res_dt,
rootdir=storage.path))
# Loop through all the chunks
for chunk_start in range(0, dim_size, chunk_size):
# Tell the interpreter which chunk size to use (last
# chunk might be smaller)
chunk_size = min(chunk_size, dim_size - chunk_start)
# Evaluate the chunk
args_chunk = [arg[chunk_start:chunk_start+chunk_size]
if len(arg.dshape.shape) == result_ndim
else arg for arg in args]
values = dict(zip(func.args, args_chunk))
interp = CKernelChunkInterp(values, chunk_size, result_ndim)
visit(interp, func)
chunk = interp.result._data.dynd_arr()
dst_dd.append(chunk)
return blaze.Array(dst_dd)
