def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
inp = context[node.input[0]]
exp_shape = self.get_normal_input_shape()
if mode == "cppsim":
output = inp
output = np.asarray([output], dtype=np.float32).reshape(*exp_shape)
context[node.output[0]] = output
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
# create a npy file for the input of the node
assert (
str(inp.dtype) == "float32"
), """Input datatype is
not float32 as expected."""
expected_inp_shape = self.get_folded_input_shape()
reshaped_input = inp.reshape(expected_inp_shape)
if DataType[self.get_nodeattr("dataType")] == DataType.BIPOLAR:
# store bipolar activations as binary
reshaped_input = (reshaped_input + 1) / 2
export_idt = DataType.BINARY
else:
export_idt = DataType[self.get_nodeattr("dataType")]
# make copy before saving the array
reshaped_input = reshaped_input.copy()
np.save(os.path.join(code_gen_dir, "input_0.npy"), reshaped_input)
sim = self.get_rtlsim()
nbits = self.get_instream_width()
inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits
)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
output = self.rtlsim(sim, inp)
odt = DataType[self.get_nodeattr("dataType")]
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
out_shape = self.get_folded_output_shape()
rtlsim_output_to_npy(
output, out_npy_path, odt, out_shape, packed_bits, target_bits
)
# load and reshape output
output = np.load(out_npy_path)
oshape = self.get_normal_output_shape()
output = np.asarray([output], dtype=np.float32).reshape(*oshape)
context[node.output[0]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")""".format(
mode
)
)
def rtlsim_exec(model, execution_context):
"""Use PyVerilator to execute given model with stitched IP. The execution
context contains the input values."""
if PyVerilator is None:
raise ImportError("Installation of PyVerilator is required.")
# ensure stitched ip project already exists
assert os.path.isfile(model.get_metadata_prop("wrapper_filename")), """The
file name from metadata property "wrapper_filename" doesn't exist."""
assert os.path.isdir(model.get_metadata_prop("vivado_stitch_proj")), """The
directory from metadata property "vivado_stitch_proj" doesn't exist"""
trace_file = model.get_metadata_prop("rtlsim_trace")
# extract input shape
# TODO extend for multiple inputs
i_name = model.graph.input[0].name
i_tensor = execution_context[i_name]
i_dt = model.get_tensor_datatype(i_name)
first_node = getCustomOp(model.find_consumer(i_name))
i_stream_w = first_node.get_instream_width()
# convert input into time multiplexed shape
i_folded_shape = first_node.get_folded_input_shape()
# TODO any other layout transformations need to happen here!
i_tensor = i_tensor.reshape(i_folded_shape)
# extract output shape
o_name = model.graph.output[0].name
o_shape = model.get_tensor_shape(o_name)
o_dt = model.get_tensor_datatype(o_name)
last_node = getCustomOp(model.find_producer(o_name))
o_folded_shape = last_node.get_folded_output_shape()
o_stream_w = last_node.get_outstream_width()
packedBits = o_stream_w
targetBits = o_dt.bitwidth()
# pack input
packed_input = npy_to_rtlsim_input(i_tensor, i_dt, i_stream_w)
num_out_values = last_node.get_number_output_values()
# prepare pyverilator model
rtlsim_so = model.get_metadata_prop("rtlsim_so")
if (rtlsim_so is None) or (not os.path.isfile(rtlsim_so)):
sim = pyverilate_stitched_ip(model)
model.set_metadata_prop("rtlsim_so", sim.lib._name)
else:
sim = PyVerilator(rtlsim_so)
_reset_rtlsim(sim)
_toggle_clk(sim)
ret = _run_rtlsim(sim, packed_input, num_out_values, trace_file)
packed_output = ret[0]
model.set_metadata_prop("sim_cycles", str(ret[1]))
# unpack output and put into context
o_folded_tensor = rtlsim_output_to_npy(packed_output, None, o_dt,
o_folded_shape, packedBits,
targetBits)
execution_context[o_name] = o_folded_tensor.reshape(o_shape)
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
mem_mode = self.get_nodeattr("mem_mode")
node = self.onnx_node
# TODO ensure codegen dir exists
if mode == "cppsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_cppsim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")""".format(
mode
)
)
# create a npy file fore each input of the node (in_ind is input index)
in_ind = 0
for inputs in node.input:
# it is assumed that the first input of the node is the data input
# the second input are the weights
# the third input are the thresholds
if in_ind == 0:
assert (
str(context[inputs].dtype) == "float32"
), """Input datatype is
not float32 as expected."""
expected_inp_shape = self.get_folded_input_shape()
reshaped_input = context[inputs].reshape(expected_inp_shape)
if self.get_input_datatype() == DataType.BIPOLAR:
# store bipolar activations as binary
reshaped_input = (reshaped_input + 1) / 2
export_idt = DataType.BINARY
else:
export_idt = self.get_input_datatype()
# make copy before saving the array
reshaped_input = reshaped_input.copy()
np.save(
os.path.join(code_gen_dir, "input_{}.npy".format(in_ind)),
reshaped_input,
)
elif in_ind > 2:
raise Exception("Unexpected input found for StreamingFCLayer")
in_ind += 1
if mode == "cppsim":
# execute the precompiled model
super().exec_precompiled_singlenode_model()
# load output npy file
super().npy_to_dynamic_output(context)
# reinterpret binary output as bipolar where needed
if self.get_output_datatype() == DataType.BIPOLAR:
out = context[node.output[0]]
out = 2 * out - 1
context[node.output[0]] = out
assert (
context[node.output[0]].shape == self.get_folded_output_shape()
), """Output shape is not as expected"""
# reshape output to have expected shape
oshape = self.get_normal_output_shape()
context[node.output[0]] = context[node.output[0]].reshape(*oshape)
elif mode == "rtlsim":
sim = self.get_rtlsim()
nbits = self.get_instream_width()
inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits
)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
if mem_mode == "external" or mem_mode == "decoupled":
wnbits = self.get_weightstream_width()
export_wdt = self.get_weight_datatype()
# we have converted bipolar weights to binary for export,
# so use it as such for weight generation
if self.get_weight_datatype() == DataType.BIPOLAR:
export_wdt = DataType.BINARY
wei = npy_to_rtlsim_input(
"{}/weights.npy".format(code_gen_dir), export_wdt, wnbits
)
num_w_reps = np.prod(self.get_nodeattr("numInputVectors"))
io_dict = {
"inputs": {"in0": inp, "weights": wei * num_w_reps},
"outputs": {"out": []},
}
self.rtlsim_multi_io(sim, io_dict)
output = io_dict["outputs"]["out"]
else:
output = self.rtlsim(sim, inp)
odt = self.get_output_datatype()
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
out_shape = self.get_folded_output_shape()
rtlsim_output_to_npy(
output, out_npy_path, odt, out_shape, packed_bits, target_bits
)
# load and reshape output
output = np.load(out_npy_path)
oshape = self.get_normal_output_shape()
output = np.asarray([output], dtype=np.float32).reshape(*oshape)
context[node.output[0]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")""".format(
mode
)
)
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
# TODO ensure codegen dir exists
if mode == "cppsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_cppsim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")""".format(
mode
)
)
# create a npy file fore each input of the node (in_ind is input index)
in_ind = 0
for inputs in node.input:
# it is assumed that the first input of the node is the data input
# the second input are the weights
# the third input are the thresholds
if in_ind == 0:
assert (
str(context[inputs].dtype) == "float32"
), """Input datatype is
not float32 as expected."""
expected_inp_shape = self.get_folded_input_shape()
reshaped_input = context[inputs].reshape(expected_inp_shape)
# make copy before saving the array
reshaped_input = reshaped_input.copy()
np.save(
os.path.join(code_gen_dir, "input_{}.npy".format(in_ind)),
reshaped_input,
)
elif in_ind > 2:
raise Exception(
"Unexpected input found for Vector_Vector_Activate_Unit"
)
in_ind += 1
if mode == "cppsim":
# execute the precompiled model
super().exec_precompiled_singlenode_model()
# load output npy file
super().npy_to_dynamic_output(context)
assert (
context[node.output[0]].shape == self.get_folded_output_shape()
), """Output shape is not as expected"""
# reshape output to have expected shape
oshape = self.get_normal_output_shape()
context[node.output[0]] = context[node.output[0]].reshape(*oshape)
elif mode == "rtlsim":
sim = self.get_rtlsim()
nbits = self.get_instream_width()
idt = self.get_input_datatype()
inp = npy_to_rtlsim_input("{}/input_0.npy".format(code_gen_dir), idt, nbits)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
output = self.rtlsim(sim, inp)
odt = self.get_output_datatype()
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
out_shape = self.get_folded_output_shape()
rtlsim_output_to_npy(
output, out_npy_path, odt, out_shape, packed_bits, target_bits
)
# load and reshape output
output = np.load(out_npy_path)
oshape = self.get_normal_output_shape()
output = np.asarray([output], dtype=np.float32).reshape(*oshape)
context[node.output[0]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")""".format(
mode
)
)
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
exp_ishape = self.get_normal_input_shape()
exp_oshape = self.get_normal_output_shape()
folded_oshape = self.get_folded_output_shape()
# TODO ensure codegen dir exists
if mode == "cppsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_cppsim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
inp = context[node.input[0]]
assert str(inp.dtype) == "float32", "Input datatype is not float32"
assert (inp.shape == exp_ishape), """Input shape doesn't
match expected shape (1, ifm_dim, ifm_dim, ifm_ch)."""
if self.get_input_datatype() == DataType["BIPOLAR"]:
# store bipolar activations as binary
inp = (inp + 1) / 2
export_idt = DataType["BINARY"]
else:
export_idt = self.get_input_datatype()
# no reshaping for input since assuming no folding on input
# make copy before saving array
reshaped_input = inp.copy()
np.save(os.path.join(code_gen_dir, "input_0.npy"), reshaped_input)
if mode == "cppsim":
# execute the precompiled model
super().exec_precompiled_singlenode_model()
# load output npy file
super().npy_to_dynamic_output(context)
assert (context[node.output[0]].shape == folded_oshape), "cppsim \
did not produce expected ofolded utput shape"
context[node.output[0]] = context[node.output[0]].reshape(
*exp_oshape)
elif mode == "rtlsim":
sim = self.get_rtlsim()
nbits = self.get_instream_width()
rtlsim_inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
rtlsim_output = self.rtlsim(sim, rtlsim_inp)
odt = export_idt
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
out_shape = self.get_folded_output_shape()
rtlsim_output_to_npy(rtlsim_output, out_npy_path, odt, out_shape,
packed_bits, target_bits)
# load and reshape output
output = np.load(out_npy_path)
output = np.asarray([output],
dtype=np.float32).reshape(*exp_oshape)
context[node.output[0]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
# binary -> bipolar if needed
if self.get_output_datatype() == DataType["BIPOLAR"]:
out = context[node.output[0]]
out = 2 * out - 1
context[node.output[0]] = out
assert (context[node.output[0]].shape == exp_oshape), """Output
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
exp_ishape = self.get_normal_input_shape()
folded_ishape = self.get_folded_input_shape()
exp_oshape = self.get_normal_output_shape()
folded_oshape = self.get_folded_output_shape()
# TODO ensure codegen dir exists
if mode == "cppsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_cppsim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
inp = context[node.input[0]]
assert str(inp.dtype) == "float32", "Input datatype is not float32"
assert (inp.shape == exp_ishape), """Input shape doesn't
match expected shape (batch_size,odim,odim,k*k*ifm_ch)."""
export_idt = self.get_input_datatype()
reshaped_input = inp.reshape(folded_ishape)
np.save(os.path.join(code_gen_dir, "input_0.npy"), reshaped_input)
if mode == "cppsim":
# execute the precompiled model
super().exec_precompiled_singlenode_model()
# load output npy file
super().npy_to_dynamic_output(context)
assert (context[node.output[0]].shape == folded_oshape
), "cppsim did not produce expected folded output shape"
context[node.output[0]] = context[node.output[0]].reshape(
*exp_oshape)
elif mode == "rtlsim":
sim = self.get_rtlsim()
nbits = self.get_instream_width()
rtlsim_inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
rtlsim_output = self.rtlsim(sim, rtlsim_inp)
odt = self.get_output_datatype()
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
out_shape = self.get_folded_output_shape()
rtlsim_output_to_npy(rtlsim_output, out_npy_path, odt, out_shape,
packed_bits, target_bits)
# load and reshape output
output = np.load(out_npy_path)
output = np.asarray([output],
dtype=np.float32).reshape(*exp_oshape)
context[node.output[0]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
assert (context[node.output[0]].shape == exp_oshape), """Output
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
exp_ishape = self.get_normal_input_shape()
exp_oshape = self.get_normal_output_shape()
folded_ishape = self.get_folded_input_shape()
folded_oshape = self.get_folded_output_shape()
if mode == "cppsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_cppsim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
inp = context[node.input[0]]
assert str(inp.dtype) == "float32", "Input datatype is not float32"
assert inp.shape == exp_ishape, """Input shape doesn't match expected shape ."""
export_idt = self.get_input_datatype()
# reshape input into folded form
inp = inp.reshape(folded_ishape)
# make copy before saving array
reshaped_input = inp.copy()
np.save(os.path.join(code_gen_dir, "input_0.npy"), reshaped_input)
if mode == "cppsim":
# execute the precompiled model
super().exec_precompiled_singlenode_model()
# load output npy file
super().npy_to_dynamic_outputs(context,
["output0.npy", "output1.npy"])
assert (context[node.output[0]].shape == folded_oshape), "cppsim \
did not produce expected ofolded utput shape"
assert (context[node.output[1]].shape == folded_oshape), "cppsim \
did not produce expected ofolded utput shape"
context[node.output[0]] = context[node.output[0]].reshape(
*exp_oshape)
context[node.output[1]] = context[node.output[1]].reshape(
*exp_oshape)
elif mode == "rtlsim":
sim = self.get_rtlsim()
nbits = self.get_instream_width()
rtlsim_inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
rtlsim_dict = {
"inputs": {
"in0": rtlsim_inp
},
"outputs": {
"out0": [],
"out1": []
},
}
self.rtlsim_multi_io(sim, rtlsim_dict)
odt = self.get_output_datatype()
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_shape = self.get_folded_output_shape()
out_npy_path = "{}/output0.npy".format(code_gen_dir)
rtlsim_output_to_npy(
rtlsim_dict["outputs"]["out0"],
out_npy_path,
odt,
out_shape,
packed_bits,
target_bits,
)
# load and reshape output 0
output = np.load(out_npy_path)
output = np.asarray([output],
dtype=np.float32).reshape(*exp_oshape)
context[node.output[0]] = output
out_npy_path = "{}/output1.npy".format(code_gen_dir)
rtlsim_output_to_npy(
rtlsim_dict["outputs"]["out1"],
out_npy_path,
odt,
out_shape,
packed_bits,
target_bits,
)
# load and reshape output 1
output = np.load(out_npy_path)
output = np.asarray([output],
dtype=np.float32).reshape(*exp_oshape)
context[node.output[1]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
assert (context[node.output[0]].shape == exp_oshape
), """Output0 shape doesn't match expected shape."""
assert (context[node.output[1]].shape == exp_oshape
), """Output1 shape doesn't match expected shape."""
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
exp_shape = self.get_normal_input_shape()
folded_ishape = self.get_folded_input_shape()
# TODO ensure codegen dir exists
if mode == "cppsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_cppsim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")""".format(
mode
)
)
inp = context[node.input[0]]
assert str(inp.dtype) == "float32", "Input datatype is not float32"
assert inp.shape == tuple(
exp_shape
), "Input shape does not match expected shape."
if self.get_input_datatype() == DataType.BIPOLAR:
# store bipolar activations as binary
inp = (inp + 1) / 2
export_idt = DataType.BINARY
else:
export_idt = self.get_input_datatype()
# reshape input into folded shape
reshaped_input = inp.reshape(folded_ishape)
# make copy before saving array
reshaped_input = reshaped_input.copy()
np.save(os.path.join(code_gen_dir, "input_0.npy"), reshaped_input)
if mode == "cppsim":
output = inp
output = np.asarray([output], dtype=np.float32).reshape(*exp_shape)
context[node.output[0]] = output
elif mode == "rtlsim":
sim = self.get_rtlsim()
nbits = self.get_instream_width()
rtlsim_inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits
)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
rtlsim_output = self.rtlsim(sim, rtlsim_inp)
odt = export_idt
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
out_shape = self.get_folded_output_shape()
rtlsim_output_to_npy(
rtlsim_output, out_npy_path, odt, out_shape, packed_bits, target_bits
)
# load and reshape output
output = np.load(out_npy_path)
output = np.asarray([output], dtype=np.float32).reshape(exp_shape)
context[node.output[0]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to "rtlsim" """.format(
mode
)
)
# binary -> bipolar if needed
if self.get_output_datatype() == DataType.BIPOLAR:
out = context[node.output[0]]
out = 2 * out - 1
context[node.output[0]] = out
assert context[node.output[0]].shape == tuple(
exp_shape
), """Output
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
exp_ishape = self.get_normal_input_shape()
exp_oshape = self.get_normal_output_shape()
folded_ishape = self.get_folded_input_shape()
folded_oshape = self.get_folded_output_shape()
if mode == "cppsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_cppsim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
inp = context[node.input[0]]
assert str(inp.dtype) == "float32", "Input datatype is not float32"
assert inp.shape == exp_ishape, """Input shape doesn't match expected shape ."""
export_idt = self.get_input_datatype()
# reshape input into folded form
inp = inp.reshape(folded_ishape)
# make copy before saving array
reshaped_input = inp.copy()
np.save(os.path.join(code_gen_dir, "input_0.npy"), reshaped_input)
if mode == "cppsim":
# execute the precompiled model
super().exec_precompiled_singlenode_model()
# load output npy file
super().npy_to_dynamic_output(context)
assert (context[node.output[0]].shape == folded_oshape), "cppsim \
did not produce expected ofolded utput shape"
context[node.output[0]] = context[node.output[0]].reshape(
*exp_oshape)
elif mode == "rtlsim":
sim = self.get_rtlsim()
nbits = self.get_instream_width()
rtlsim_inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
rtlsim_output = self.rtlsim(sim, rtlsim_inp)
odt = self.get_output_datatype()
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
out_shape = self.get_folded_output_shape()
rtlsim_output_to_npy(rtlsim_output, out_npy_path, odt, out_shape,
packed_bits, target_bits)
# load and reshape output
output = np.load(out_npy_path)
output = np.asarray([output],
dtype=np.float32).reshape(*exp_oshape)
context[node.output[0]] = output
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("cppsim", "rtlsim")"""
.format(mode))
assert (context[node.output[0]].shape == exp_oshape
), """Output shape doesn't match expected shape."""
# TopK ind output normally uses TensorProto.INT64, which
# can cause issues for the node-by-node simulation in FINN
# (as the custom DataType system always assumes float containers)
# so cast the output to int64
ret = context[node.output[0]]
context[node.output[0]] = ret.astype(np.int64)
def rtlsim_exec(model, execution_context, pre_hook=None, post_hook=None):
"""Use PyVerilator to execute given model with stitched IP. The execution
context contains the input values. Hook functions can be optionally
specified to observe/alter the state of the circuit, receiving the
PyVerilator sim object as their first argument:
- pre_hook : hook function to be called before sim start (after reset)
- post_hook : hook function to be called after sim end
"""
if PyVerilator is None:
raise ImportError("Installation of PyVerilator is required.")
# ensure stitched ip project already exists
assert os.path.isfile(model.get_metadata_prop("wrapper_filename")), """The
file name from metadata property "wrapper_filename" doesn't exist."""
assert os.path.isdir(model.get_metadata_prop("vivado_stitch_proj")), """The
directory from metadata property "vivado_stitch_proj" doesn't exist"""
trace_file = model.get_metadata_prop("rtlsim_trace")
# extract input shape
# TODO extend for multiple inputs
i_name = model.graph.input[0].name
i_tensor = execution_context[i_name]
i_dt = model.get_tensor_datatype(i_name)
first_node = getCustomOp(model.find_consumer(i_name))
i_stream_w = first_node.get_instream_width()
# convert input into time multiplexed shape
i_folded_shape = first_node.get_folded_input_shape()
batchsize = i_tensor.shape[0]
# override batch size for input
i_folded_shape = list(i_folded_shape)
i_folded_shape[0] = batchsize
i_folded_shape = tuple(i_folded_shape)
# TODO any other layout transformations need to happen here!
i_tensor = i_tensor.reshape(i_folded_shape)
# extract output shape
o_name = model.graph.output[0].name
o_shape = model.get_tensor_shape(o_name)
o_dt = model.get_tensor_datatype(o_name)
last_node = getCustomOp(model.find_producer(o_name))
o_folded_shape = last_node.get_folded_output_shape()
# override batch size from actual input
o_shape = list(o_shape)
o_shape[0] = batchsize
o_shape = tuple(o_shape)
o_folded_shape = list(o_folded_shape)
o_folded_shape[0] = batchsize
o_folded_shape = tuple(o_folded_shape)
o_stream_w = last_node.get_outstream_width()
packedBits = o_stream_w
targetBits = o_dt.bitwidth()
# pack input
packed_input = npy_to_rtlsim_input(i_tensor, i_dt, i_stream_w)
num_out_values = last_node.get_number_output_values()
num_out_values *= batchsize
# prepare pyverilator model
rtlsim_so = model.get_metadata_prop("rtlsim_so")
if (rtlsim_so is None) or (not os.path.isfile(rtlsim_so)):
sim = pyverilate_stitched_ip(model)
model.set_metadata_prop("rtlsim_so", sim.lib._name)
else:
sim = PyVerilator(rtlsim_so, auto_eval=False)
ret = _run_rtlsim(
sim,
packed_input,
num_out_values,
trace_file,
pre_hook=pre_hook,
post_hook=post_hook,
)
packed_output = ret[0]
model.set_metadata_prop("cycles_rtlsim", str(ret[1]))
# unpack output and put into context
o_folded_tensor = rtlsim_output_to_npy(packed_output, None, o_dt,
o_folded_shape, packedBits,
targetBits)
execution_context[o_name] = o_folded_tensor.reshape(o_shape)
def rtlsim_exec(model, execution_context, pre_hook=None, post_hook=None):
"""Use PyVerilator to execute given model with stitched IP. The execution
context contains the input values. Hook functions can be optionally
specified to observe/alter the state of the circuit, receiving the
PyVerilator sim object as their first argument:
- pre_hook : hook function to be called before sim start (after reset)
- post_hook : hook function to be called after sim end
"""
if PyVerilator is None:
raise ImportError("Installation of PyVerilator is required.")
# ensure stitched ip project already exists
assert os.path.isfile(
model.get_metadata_prop("wrapper_filename")
), """The
file name from metadata property "wrapper_filename" doesn't exist."""
assert os.path.isdir(
model.get_metadata_prop("vivado_stitch_proj")
), """The
directory from metadata property "vivado_stitch_proj" doesn't exist"""
trace_file = model.get_metadata_prop("rtlsim_trace")
if trace_file is None:
trace_file = ""
extra_verilator_args = model.get_metadata_prop("extra_verilator_args")
if extra_verilator_args is None:
extra_verilator_args = []
else:
extra_verilator_args = eval(extra_verilator_args)
# extract i/o info to prepare io_dict
io_dict = {"inputs": {}, "outputs": {}}
if_dict = eval(model.get_metadata_prop("vivado_stitch_ifnames"))
# go over and prepare inputs
for i, i_vi in enumerate(model.graph.input):
i_name = i_vi.name
i_tensor = execution_context[i_name]
i_dt = model.get_tensor_datatype(i_name)
first_node_onnx = model.find_consumer(i_name)
first_node = getCustomOp(first_node_onnx)
node_inp_ind = list(first_node_onnx.input).index(i_name)
if node_inp_ind == 0:
# default node input (input 0)
i_stream_w = first_node.get_instream_width()
i_folded_shape = first_node.get_folded_input_shape()
else:
# not input 0; node must support specifying inp index
# for these functions
i_stream_w = first_node.get_instream_width(node_inp_ind)
i_folded_shape = first_node.get_folded_input_shape(node_inp_ind)
batchsize = i_tensor.shape[0]
# override batch size for input
i_folded_shape = list(i_folded_shape)
i_folded_shape[0] = batchsize
i_folded_shape = tuple(i_folded_shape)
# TODO any other layout transformations need to happen here!
i_tensor = i_tensor.reshape(i_folded_shape)
# pack input for rtlsim
packed_input = npy_to_rtlsim_input(i_tensor, i_dt, i_stream_w)
# add to io_dict
if_name = if_dict["s_axis"][i][0]
io_dict["inputs"][if_name] = packed_input
# go over outputs to determine how many values will be produced
num_out_values = 0
o_tensor_info = []
for o, o_vi in enumerate(model.graph.output):
# output in io_dict just needs an empty list
if_name = if_dict["m_axis"][o][0]
io_dict["outputs"][if_name] = []
# extract output shape
o_name = o_vi.name
o_shape = model.get_tensor_shape(o_name)
o_dt = model.get_tensor_datatype(o_name)
last_node = getCustomOp(model.find_producer(o_name))
o_folded_shape = last_node.get_folded_output_shape()
# override batch size from actual input
o_shape = list(o_shape)
o_shape[0] = batchsize
o_shape = tuple(o_shape)
o_folded_shape = list(o_folded_shape)
o_folded_shape[0] = batchsize
o_folded_shape = tuple(o_folded_shape)
o_stream_w = last_node.get_outstream_width()
o_tensor_info.append((o_stream_w, o_dt, o_folded_shape, o_shape))
num_out_values += batchsize * last_node.get_number_output_values()
# prepare pyverilator model
rtlsim_so = model.get_metadata_prop("rtlsim_so")
if (rtlsim_so is None) or (not os.path.isfile(rtlsim_so)):
sim = pyverilate_stitched_ip(model, extra_verilator_args=extra_verilator_args)
model.set_metadata_prop("rtlsim_so", sim.lib._name)
else:
sim = PyVerilator(rtlsim_so, auto_eval=False)
# reset and call rtlsim, including any pre/post hooks
reset_rtlsim(sim)
if pre_hook is not None:
pre_hook(sim)
n_cycles = rtlsim_multi_io(sim, io_dict, num_out_values, trace_file, sname="_")
if post_hook is not None:
post_hook(sim)
# unpack outputs and put back into execution context
for o, o_vi in enumerate(model.graph.output):
o_name = o_vi.name
if_name = if_dict["m_axis"][o][0]
o_stream_w, o_dt, o_folded_shape, o_shape = o_tensor_info[o]
packed_output = io_dict["outputs"][if_name]
o_folded_tensor = rtlsim_output_to_npy(
packed_output, None, o_dt, o_folded_shape, o_stream_w, o_dt.bitwidth()
)
execution_context[o_name] = o_folded_tensor.reshape(o_shape)
model.set_metadata_prop("cycles_rtlsim", str(n_cycles))
def execute_node(self, context, graph):
mode = self.get_nodeattr("exec_mode")
node = self.onnx_node
mw = self.get_nodeattr("MW")
mh = self.get_nodeattr("MH")
simd = self.get_nodeattr("SIMD")
pe = self.get_nodeattr("PE")
sf = mw // simd
nf = mh // pe
# TODO ensure codegen dir exists
if mode == "npysim":
code_gen_dir = self.get_nodeattr("code_gen_dir_npysim")
elif mode == "rtlsim":
code_gen_dir = self.get_nodeattr("code_gen_dir_ipgen")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("npysim", "rtlsim")"""
.format(mode))
# create a npy file fore each input of the node (in_ind is input index)
in_ind = 0
for inputs in node.input:
# it is assumed that the first input of the node is the data input
# the second input are the weights
# the third input are the thresholds
if in_ind == 0:
assert (str(
context[inputs].dtype) == "float32"), """Input datatype is
not float32 as expected."""
expected_inp_shape = (1, sf, simd)
reshaped_input = context[inputs].reshape(expected_inp_shape)
if self.get_input_datatype() == DataType.BIPOLAR:
# store bipolar activations as binary
reshaped_input = (reshaped_input + 1) / 2
export_idt = DataType.BINARY
else:
export_idt = self.get_input_datatype()
np.save(
os.path.join(code_gen_dir, "input_{}.npy".format(in_ind)),
reshaped_input,
)
elif in_ind > 2:
raise Exception("Unexpected input found for StreamingFCLayer")
in_ind += 1
if mode == "npysim":
# execute the precompiled model
super().exec_precompiled_singlenode_model()
# load output npy file
super().npy_to_dynamic_output(context)
# reinterpret binary output as bipolar where needed
if self.get_output_datatype() == DataType.BIPOLAR:
out = context[node.output[0]]
out = 2 * out - 1
context[node.output[0]] = out
assert context[node.output[0]].shape == (
1,
nf,
pe,
), """Output shape is not
as expected (1, nf, pe)"""
# reshape output to have expected shape
context[node.output[0]] = context[node.output[0]].reshape(1, mh)
elif mode == "rtlsim":
if PyVerilator is None:
raise ImportError("Installation of PyVerilator is required.")
prefixed_top_name = "%s_%s" % (node.name, node.name)
# check if needed file exists
verilog_file = "{}/project_{}/sol1/impl/verilog/{}.v".format(
code_gen_dir, node.name, prefixed_top_name)
if os.path.isfile(verilog_file):
nbits = self.get_instream_width()
inp = npy_to_rtlsim_input(
"{}/input_0.npy".format(code_gen_dir), export_idt, nbits)
sim = PyVerilator.build(
verilog_file,
verilog_path=[
"{}/project_{}/sol1/impl/verilog/".format(
code_gen_dir, node.name)
],
)
super().reset_rtlsim(sim)
super().toggle_clk(sim)
output = self.rtlsim(sim, inp)
odt = self.get_output_datatype()
target_bits = odt.bitwidth()
packed_bits = self.get_outstream_width()
out_npy_path = "{}/output.npy".format(code_gen_dir)
rtlsim_output_to_npy(output, out_npy_path, odt, (1, nf, pe),
packed_bits, target_bits)
# load and reshape output
output = np.load(out_npy_path)
output = np.asarray([output], dtype=np.float32).reshape(1, mh)
context[node.output[0]] = output
else:
raise Exception("""Found no verilog files for this node,
did you run the codegen_ipgen transformation?""")
else:
raise Exception(
"""Invalid value for attribute exec_mode! Is currently set to: {}
has to be set to one of the following value ("npysim", "rtlsim")"""
.format(mode))