Skip to content
Snippets Groups Projects
Commit be3a0418 authored by Yaman Umuroglu's avatar Yaman Umuroglu
Browse files

[Refactor] use correct attribute accessors for custom op codegen

parent 6907c12d
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
src/finn/custom_op/fpgadataflow/__init__.py
+ 2
− 7
View file @ be3a0418
from abc import abstractmethod
import os
from finn.custom_op import CustomOp
import finn.core.utils as util
class HLSCustomOp(CustomOp):
......@@ -37,10 +36,6 @@ class HLSCustomOp(CustomOp):
"""
self.code_gen_dict = {}
self.tmp_dir = ""
self.code_gen_dir = util.get_by_name(onnx_node.attribute, "code_gen_dir")
self.executable_path = ""
def get_nodeattr_types(self):
return {"code_gen_dir": ("s", False, ""), "executable_path": ("s", False, "")}
......@@ -62,8 +57,8 @@ class HLSCustomOp(CustomOp):
# transform list into long string separated by '\n'
code_gen_line = "\n".join(self.code_gen_dict[key])
template = template.replace(key, code_gen_line)
f = open(os.path.join(self.tmp_dir, "execute_{}.cpp".format(node.op_type)), "w")
code_gen_dir = self.get_nodeattr("code_gen_dir")
f = open(os.path.join(code_gen_dir, "execute_{}.cpp".format(node.op_type)), "w")
f.write(template)
f.close()
......
src/finn/custom_op/fpgadataflow/streamingfclayer_batch.py
+ 17
− 43
View file @ be3a0418
import os
import subprocess
import tempfile as tmp
import numpy as np
......@@ -151,7 +150,6 @@ class StreamingFCLayer_Batch(HLSCustomOp):
return ret
def generate_weights(self, model):
weights = model.get_initializer(self.onnx_node.input[1])
# convert weights into hlslib-compatible format
weight_tensor = self.get_hls_compatible_weight_tensor(weights)
......@@ -164,7 +162,8 @@ class StreamingFCLayer_Batch(HLSCustomOp):
weight_tensor, export_wdt, "weights", True, True
)
# write weights into params.h
f_weights = open("{}/params.h".format(self.tmp_dir), "w")
code_gen_dir = self.get_nodeattr("code_gen_dir")
f_weights = open("{}/params.h".format(code_gen_dir), "w")
if export_wdt.bitwidth() != 1:
f_weights.write(
......@@ -200,7 +199,8 @@ class StreamingFCLayer_Batch(HLSCustomOp):
threshold_tensor, tdt, "thresholds", False, True
)
# write thresholds into thresh.h
f_thresh = open("{}/thresh.h".format(self.tmp_dir), "w")
code_gen_dir = self.get_nodeattr("code_gen_dir")
f_thresh = open("{}/thresh.h".format(code_gen_dir), "w")
tdt_hls = tdt.get_hls_datatype_str()
odt_hls = self.get_output_datatype().get_hls_datatype_str()
f_thresh.write(
......@@ -218,13 +218,8 @@ class StreamingFCLayer_Batch(HLSCustomOp):
def execute_node(self, context, graph):
node = self.onnx_node
# make temporary directory for generated files
self.tmp_dir = tmp.mkdtemp(prefix=str(node.op_type) + "_")
# create empty list for temporary files to enable the option
# to delete the files after the execution
temp_files = []
# TODO ensure codegen dir exists
code_gen_dir = self.get_nodeattr("code_gen_dir")
# create a npy file fore each input of the node (in_ind is input index)
in_ind = 0
for inputs in node.input:
......@@ -239,48 +234,25 @@ class StreamingFCLayer_Batch(HLSCustomOp):
if self.get_input_datatype() == DataType.BIPOLAR:
# store bipolar activations as binary
np.save(
os.path.join(self.tmp_dir, "input_{}.npy".format(in_ind)),
os.path.join(code_gen_dir, "input_{}.npy".format(in_ind)),
(context[inputs] + 1) / 2,
)
else:
np.save(
os.path.join(self.tmp_dir, "input_{}.npy".format(in_ind)),
os.path.join(code_gen_dir, "input_{}.npy".format(in_ind)),
context[inputs],
)
temp_files.append("{}/input_{}.npy".format(self.tmp_dir, in_ind))
elif in_ind > 2:
raise Exception("Unexpected input found for StreamingFCLayer")
in_ind += 1
temp_files.append("{}/params.h".format(self.tmp_dir))
temp_files.append("{}/thresh.h".format(self.tmp_dir))
# code generation
self.code_generation(context)
# c++ compilation and execution flow
temp_files.append("{}/execute_{}.cpp".format(self.tmp_dir, node.op_type))
bash_compile = """g++ -o {}/execute_{} {}/execute_{}.cpp
/workspace/cnpy/cnpy.cpp -I/workspace/finn/src/finn/data/cpp -I/workspace/cnpy/
-I/workspace/finn-hlslib -I/workspace/vivado-hlslib
--std=c++11 -lz""".format(
self.tmp_dir, node.op_type, self.tmp_dir, node.op_type
)
process_compile = subprocess.Popen(bash_compile.split(), stdout=subprocess.PIPE)
process_compile.communicate()
bash_execute = "{}/execute_{}".format(self.tmp_dir, node.op_type)
process_execute = subprocess.Popen(bash_execute.split(), stdout=subprocess.PIPE)
# execute precompiled executable
executable_path = self.get_nodeattr("executable_path")
# TODO sanity check executable
process_execute = subprocess.Popen(executable_path, stdout=subprocess.PIPE)
process_execute.communicate()
temp_files.append("{}/execute_{}".format(self.tmp_dir, node.op_type))
temp_files.append("{}/output.npy".format(self.tmp_dir))
# load output npy file
output = np.load("{}/output.npy".format(self.tmp_dir))
output = np.load("{}/output.npy".format(code_gen_dir))
context[node.output[0]] = output
# deleting temporary files
# for temp_file in temp_files:
# os.remove(temp_file)
def global_includes(self):
self.code_gen_dict["$GLOBALS$"] = ['#include "weights.hpp"']
......@@ -309,13 +281,14 @@ class StreamingFCLayer_Batch(HLSCustomOp):
]
def read_npy_data(self):
code_gen_dir = self.get_nodeattr("code_gen_dir")
dtype = self.get_input_datatype()
elem_bits = dtype.bitwidth()
packed_bits = self.get_instream_width()
packed_hls_type = "ap_uint<%d>" % packed_bits
elem_hls_type = dtype.get_hls_datatype_str()
npy_type = "float"
npy_in = "%s/input_0.npy" % self.tmp_dir
npy_in = "%s/input_0.npy" % code_gen_dir
self.code_gen_dict["$READNPYDATA$"] = []
self.code_gen_dict["$READNPYDATA$"].append(
'npy2apintstream<%s, %s, %d, %s>("%s", in0);'
......@@ -352,13 +325,14 @@ class StreamingFCLayer_Batch(HLSCustomOp):
]
def dataoutstrm(self):
code_gen_dir = self.get_nodeattr("code_gen_dir")
dtype = self.get_output_datatype()
elem_bits = dtype.bitwidth()
packed_bits = self.get_outstream_width()
packed_hls_type = "ap_uint<%d>" % packed_bits
elem_hls_type = dtype.get_hls_datatype_str()
npy_type = "float"
npy_out = "%s/output.npy" % self.tmp_dir
npy_out = "%s/output.npy" % code_gen_dir
nf = int(self.get_nodeattr("MH") / self.get_nodeattr("PE"))
shape = (1, nf, self.get_nodeattr("PE"))
shape_cpp_str = str(shape).replace("(", "{").replace(")", "}")
......
src/finn/custom_op/fpgadataflow/streamingmaxpool_batch.py
+ 18
− 39
View file @ be3a0418
import os
import subprocess
import tempfile as tmp
import numpy as np
......@@ -25,48 +24,26 @@ class StreamingMaxPool_Batch(HLSCustomOp):
def execute_node(self, context, graph):
node = self.onnx_node
# make temporary directory for generated files
self.tmp_dir = tmp.mkdtemp(prefix=str(node.op_type) + "_")
# create empty list for temporary files to enable the option
# to delete the files after the execution
temp_files = []
code_gen_dir = self.get_nodeattr("code_gen_dir")
# create a npy file fore each input of the node (in_ind is input index)
in_ind = 0
for inputs in node.input:
np.save(
os.path.join(self.tmp_dir, "input_{}.npy".format(in_ind)),
context[inputs],
)
temp_files.append("{}/input_{}.npy".format(self.tmp_dir, in_ind))
if in_ind == 0:
np.save(
os.path.join(code_gen_dir, "input_{}.npy".format(in_ind)),
context[inputs],
)
else:
raise Exception("Unexpected input found for StreamingMaxPool_Batch")
in_ind += 1
# code generation
self.code_generation()
# c++ compilation and execution flow
temp_files.append("{}/execute_{}.cpp".format(self.tmp_dir, node.op_type))
bash_compile = """g++ -o {}/execute_{} {}/execute_{}.cpp
/workspace/cnpy/cnpy.cpp -I/workspace/cnpy/
-I/workspace/finn-hlslib -I/workspace/vivado-hlslib
--std=c++11 -lz""".format(
self.tmp_dir, node.op_type, self.tmp_dir, node.op_type
)
process_compile = subprocess.Popen(bash_compile.split(), stdout=subprocess.PIPE)
process_compile.communicate()
bash_execute = "{}/execute_{}".format(self.tmp_dir, node.op_type)
process_execute = subprocess.Popen(bash_execute.split(), stdout=subprocess.PIPE)
# execute precompiled executable
executable_path = self.get_nodeattr("executable_path")
# TODO sanity check executable
process_execute = subprocess.Popen(executable_path, stdout=subprocess.PIPE)
process_execute.communicate()
temp_files.append("{}/execute_{}".format(self.tmp_dir, node.op_type))
temp_files.append("{}/output.npy".format(self.tmp_dir))
# load output npy file
output = np.load("{}/output.npy".format(self.tmp_dir))
output = np.load("{}/output.npy".format(code_gen_dir))
context[node.output[0]] = output
# deleting temporary files
# for temp_file in temp_files:
# os.remove(temp_file)
def global_includes(self):
self.code_gen_dict["$GLOBALS$"] = ['#include "maxpool.h"']
......@@ -85,13 +62,14 @@ class StreamingMaxPool_Batch(HLSCustomOp):
def read_npy_data(self):
node = self.onnx_node
code_gen_dir = self.get_nodeattr("code_gen_dir")
# c++ code to read out an npy file
# and put it in hls::stream in the correct order
self.code_gen_dict["$READNPYDATA$"] = []
input_ind = 0
input_file_names = []
for inputs in node.input:
input_file_names.append("{}/input_{}.npy".format(self.tmp_dir, input_ind))
input_file_names.append("{}/input_{}.npy".format(code_gen_dir, input_ind))
input_ind += 1
input_ind = 0
......@@ -183,11 +161,12 @@ class StreamingMaxPool_Batch(HLSCustomOp):
self.code_gen_dict["$DATAOUTSTREAM$"].append("}")
def save_as_npy(self):
numReps = 2
code_gen_dir = self.get_nodeattr("code_gen_dir")
numReps = 1
self.code_gen_dict["$SAVEASCNPY$"] = [
"""cnpy::npy_save("{}/output.npy",&output_data_vector[0],
{{{},{},{}}},"w");""".format(
self.tmp_dir,
code_gen_dir,
numReps,
self.get_nodeattr("NumChannels"),
int(self.get_nodeattr("ImgDim") / self.get_nodeattr("PoolDim")),
......
src/finn/transformation/fpgadataflow/code_gen_transformation.py
+ 9
− 43
View file @ be3a0418
......@@ -6,55 +6,21 @@ from finn.core.utils import get_by_name
from finn.transformation import Transformation
def code_gen_transformation(node, model):
def _codegen_single_node(node, model):
"""Call custom implementation to generate code for single custom node
and create folder that contains all the generated files"""
op_type = node.op_type
try:
# lookup op_type in registry of CustomOps
inst = registry.custom_op[op_type](node)
# get the path of the code generation directory
code_gen_dir = inst.code_gen_dir
code_gen_dir = code_gen_dir.s.decode("UTF-8")
# parameter is empty
if not code_gen_dir:
tmp_dir = tmp.mkdtemp(prefix="code_gen_" + str(node.op_type) + "_")
inst.tmp_dir = tmp_dir
inst.code_generation(model)
# check if directory exists
if os.path.isdir(tmp_dir):
if len(os.listdir(tmp_dir)) == 0:
raise Exception("Code was not generated!")
else:
inst.code_gen_dir = tmp_dir
model.set_attribute(node, "code_gen_dir", tmp_dir)
else:
raise Exception("Code was not generated!")
# there is already a code gen directory
else:
# check directory for files
if os.path.isdir(code_gen_dir):
if len(os.listdir(code_gen_dir)) == 0:
os.rmdir(code_gen_dir)
tmp_dir = tmp.mkdtemp(prefix="code_gen_" + str(node.op_type) + "_")
inst.tmp_dir = tmp_dir
inst.code_generation(model)
if os.path.isdir(tmp_dir):
if len(os.listdir(tmp_dir)) == 0:
raise Exception("Code was not generated!")
else:
inst.code_gen_dir = tmp_dir
model.set_attribute(node, "code_gen_dir", tmp_dir)
else:
raise Exception("Code was not generated!")
# else: attribute is correctly set
else:
inst.code_gen_dir = tmp_dir
model.set_attribute(node, "code_gen_dir", tmp_dir)
code_gen_dir = inst.get_nodeattr("code_gen_dir")
# ensure that there is a directory
if code_gen_dir == "" or not os.path.isdir(code_gen_dir):
code_gen_dir = tmp.mkdtemp(prefix="code_gen_" + str(node.op_type) + "_")
inst.set_nodeattr("code_gen_dir", code_gen_dir)
# ensure that there is generated code inside the dir
inst.code_generation(model)
except KeyError:
# exception if op_type is not supported
raise Exception("Custom op_type %s is currently not supported." % op_type)
......@@ -69,5 +35,5 @@ class CodeGen(Transformation):
backend_attribute = get_by_name(node.attribute, "backend")
backend_value = backend_attribute.s.decode("UTF-8")
if backend_value == "fpgadataflow":
code_gen_transformation(node, model)
_codegen_single_node(node, model)
return (model, False)
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment