Skip to content

M
macroplacement
Commit 158db901 by sakundu
Options

Merge branch 'main' of github.com:TILOS-AI-Institute/MacroPlacement into main

parents 286dd9bd 06a420cc
Showing with 5578 additions and 65 deletions
.gitignore
......@@ -4,11 +4,34 @@ Flows/job
Flows/util/__pycache__
CodeElements/*/*/__pycache__
CodeElements/Plc_client/test/
CodeElements/Plc_client/test/*/*
CodeElements/Plc_client/plc_client_os.py
CodeElements/Plc_client/test/*
CodeElements/Plc_client/__pycache__/*
CodeElements/Plc_client/proto_reader.py
CodeElements/Plc_client/plc_client.py
CodeElements/failed_proxy_plc/*
CodeElements/EvalCT/test/g657_ub5_nruns10_c5_r3_v3_rc1
CodeElements/EvalCT/snapshot*
CodeElements/EvalCT/circuit_training
CodeElements/EvalCT/__pycache__/
CodeElements/EvalCT/eval_run*.plc
CodeElements/EvalCT/eval_run*.plc
CodeElements/EvalCT/saved_policy/run_00/111/train/*
CodeElements/EvalCT/saved_policy/run_00/111/snapshot*.plc
CodeElements/EvalCT/saved_policy/run_00/111/rl*.plc
CodeElements/EvalCT/saved_policy/run_os_64128_g657_ub5_nruns10_c5_r3_v3_rc1
CodeElements/epoch_*.plc
CodeElements/FDPlacement/test/*
CodeElements/Plc_client/placement_util*.py
CodeElements/StatTest/test/ariane/*_vs_*
CodeElements/StatTest/test/flow2_68_1.3_ct/*
CodeElements/StatTest/test/ariane/*.plc
CodeElements/*/__pycache__/*
CodeElements/*.png
CodeElements/StatTest/*.csv
CodeElements/os.txt
CodeElements/EvalCT/test/ariane/*.plc
CodeElements/FDPlacement/fd.txt
CodeElements/StatTest/test/ariane/*.pb.txt
CodeElements/Plc_client/failed_proxy_plc/*
__pycache__/
__pycache__
......
CodeElements/EvalCT/README.md 0 → 100644
# Circuit Training Model Evaulation
## Quick Start
First, make sure you are under `CodeElements/EvalCT/`. To run `eval_ct.py`, we need to download `circuit_training` code under the same directory. Run the following command to get the stable version that we have tested.
```
# Compatible with Revision #90. Latest Version might cause errors
svn export -r 90 --force https://github.com/google-research/circuit_training.git/trunk/circuit_training
```
Next, we need to prepare your trained policy and the testcase you want to evaluate on. Assume you have trained models (which usually can be found under `./logs`), copy the run folder into `saved_model` folder. Make sure your testcase is under `./test`. The `ckptID` is the policy checkpoint ID saved after each iteration.
Finally, run the following command with path to netlist file, initial placement file and model run directory path.
```
$ python3 -m eval_ct --netlist ./test/ariane/netlist.pb.txt\
--plc ./test/ariane/initial.plc\
--rundir run_00\
--ckptID policy_checkpoint_0000103984
```
The placement will be stored under `CodeElements/EvalCT/` and named as `eval_[RUN_DIR]_to_[TESTCASE].plc`.
## Trained Policy
We are providing one of the run we trained from scratch using Google's Ariane testcase. **This should not be taken as representing the potential of Circuit Training**. We are only providing these trained weights here for the sake of testing. Please feel free to load any of your own trained weights. You may find similar file structure under `./logs` after training.
## View Your Result
You can view the result by supplying this placement file into the open-sourced Plc_client testbench and use the `display_canvas` function.
CodeElements/EvalCT/eval_ct.py 0 → 100755
import collections
import functools
import os
import time
from typing import Text
import statistics
import re
from absl import app
from absl import flags
from absl.flags import argparse_flags
from circuit_training.environment import environment
from circuit_training.environment import placement_util
from tf_agents.experimental.distributed import reverb_variable_container
from tf_agents.metrics import py_metric
from tf_agents.metrics import py_metrics
from tf_agents.policies import greedy_policy # pylint: disable=unused-import
from tf_agents.policies import py_tf_eager_policy
from tf_agents.policies import policy_loader
from tf_agents.train import actor
from tf_agents.train import learner
from tf_agents.train.utils import train_utils
from tf_agents.trajectories import trajectory
from tf_agents.utils import common
from tf_agents.policies import greedy_policy # pylint: disable=unused-import
from tf_agents.system import system_multiprocessing as multiprocessing
"""
Example
At ./MacroPlacement/CodeElement/EvalCT, run the following command:
$ cd EvalCT && python3 -m eval_ct --netlist ./test/ariane/netlist.pb.txt\
--plc ./test/ariane/initial.plc\
--rundir run_00\
--ckptID policy_checkpoint_0000103984\
&& cd -
"""
# InfoMetric_wirelength = 0.09238692254177283
# InfoMetric_congestion = 0.9468230846211636
# InfoMetric_density = 0.5462616496124097
class InfoMetric(py_metric.PyStepMetric):
"""Observer for graphing the environment info metrics."""
def __init__(
self,
env,
info_metric_key: Text,
buffer_size: int = 1,
name: Text = 'InfoMetric',
):
"""Observer reporting TensorBoard metrics at the end of each episode.
Args:
env: environment.
info_metric_key: a string key from the environment info to report,
e.g. wirelength, density, congestion.
buffer_size: size of the buffer for calculating the aggregated metrics.
name: name of the observer object.
"""
super(InfoMetric, self).__init__(name + '_' + info_metric_key)
self._env = env
self._info_metric_key = info_metric_key
self._buffer = collections.deque(maxlen=buffer_size)
def call(self, traj: trajectory.Trajectory):
"""Report the requested metrics at the end of each episode."""
# We collect the metrics from the info from the environment instead.
# The traj argument is kept to be compatible with the actor/learner API
# for metrics.
del traj
if self._env.done:
# placement_util.save_placement(self._env._plc, './reload_weight.plc', '')
metric_value = self._env.get_info()[self._info_metric_key]
self._buffer.append(metric_value)
def result(self):
return statistics.mean(self._buffer)
def reset(self):
self._buffer.clear()
def evaulate(model_dir, ckpt_id, create_env_fn):
# Create the path for the serialized greedy policy.
policy_saved_model_path = os.path.join(model_dir,
learner.POLICY_SAVED_MODEL_DIR,
learner.GREEDY_POLICY_SAVED_MODEL_DIR)
try:
assert os.path.isdir(policy_saved_model_path)
print("#[POLICY SAVED MODEL PATH] " + policy_saved_model_path)
except AssertionError:
print("[ERROR POLICY SAVED MODEL PATH NOT FOUND] " + policy_saved_model_path)
exit(0)
policy_saved_chkpt_path = os.path.join(model_dir,
learner.POLICY_SAVED_MODEL_DIR,
"checkpoints", ckpt_id)
try:
assert os.path.isdir(policy_saved_chkpt_path)
print("#[POLICY SAVED CHECKPOINT PATH] " + policy_saved_chkpt_path)
except AssertionError:
print("[ERROR POLICY SAVED CHECKPOINT PATH NOT FOUND] " + policy_saved_chkpt_path)
exit(0)
saved_model_pb_path = os.path.join(policy_saved_model_path, 'saved_model.pb')
try:
assert os.path.isfile(saved_model_pb_path)
print("#[SAVED MODEL PB PATH] " + saved_model_pb_path)
except AssertionError:
print("[ERROR SAVE MODEL PB PATH NOT FOUND] " + saved_model_pb_path)
exit(0)
policy = policy_loader.load(policy_saved_model_path, policy_saved_chkpt_path)
policy.get_initial_state()
print(policy.variables()[0].numpy())
train_step = train_utils.create_train_step()
# Create the environment.
env = create_env_fn()
# Create the evaluator actor.
info_metrics = [
InfoMetric(env, 'wirelength'),
InfoMetric(env, 'congestion'),
InfoMetric(env, 'density'),
]
eval_actor = actor.Actor(
env,
policy,
train_step,
episodes_per_run=1,
summary_dir=os.path.join(model_dir, learner.TRAIN_DIR, 'eval'),
metrics=[
py_metrics.NumberOfEpisodes(),
py_metrics.EnvironmentSteps(),
py_metrics.AverageReturnMetric(
name='eval_episode_return', buffer_size=1),
py_metrics.AverageEpisodeLengthMetric(buffer_size=1),
] + info_metrics,
name='performance')
eval_actor.run_and_log()
def main(args):
NETLIST_FILE = args.netlist
INIT_PLACEMENT = args.plc
POLICY_CHECKPOINT_ID = args.ckptID
GLOBAL_SEED = 111
CD_RUNTIME = False
RUN_NAME = args.rundir
# extract eval testcase name
EVAL_TESTCASE = re.search("/test/(.+?)/netlist.pb.txt", NETLIST_FILE).group(1)
create_env_fn = functools.partial(
environment.create_circuit_environment,
netlist_file=NETLIST_FILE,
init_placement=INIT_PLACEMENT,
is_eval=True,
save_best_cost=True,
output_plc_file=str('./eval_' + RUN_NAME + '_to_' + EVAL_TESTCASE + '.plc'),
global_seed=GLOBAL_SEED,
cd_finetune=CD_RUNTIME
)
evaulate(model_dir=os.path.join("./saved_policy", RUN_NAME, str(GLOBAL_SEED)),
ckpt_id=POLICY_CHECKPOINT_ID, create_env_fn=create_env_fn)
def parse_flags(argv):
parser = argparse_flags.ArgumentParser(
description='An argparse + app.run example')
parser.add_argument("--netlist", required=True,
help="Path to netlist in pb.txt")
parser.add_argument("--plc", required=True,
help="Path to plc in .plc")
parser.add_argument("--rundir", required=True,
help="Path to run directory that contains saved policies")
parser.add_argument("--ckptID", required=True,
help="Policy checkpoint ID")
return parser.parse_args(argv[1:])
if __name__ == '__main__':
app.run(main, flags_parser=parse_flags)
\ No newline at end of file
CodeElements/EvalCT/saved_policy/run_00/111/policies/collect_policy/policy_specs.pbtxt 0 → 100644
dict_value {
fields {
key: "collect_data_spec"
value {
named_tuple_value {
name: "Trajectory"
values {
key: "step_type"
value {
tensor_spec_value {
name: "step_type"
shape {
}
dtype: DT_INT32
}
}
}
values {
key: "observation"
value {
dict_value {
fields {
key: "current_node"
value {
bounded_tensor_spec_value {
name: "observation/current_node"
shape {
dim {
size: 1
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "edge_counts"
value {
bounded_tensor_spec_value {
name: "observation/edge_counts"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 28399
}
}
}
}
fields {
key: "grid_cols"
value {
bounded_tensor_spec_value {
name: "observation/grid_cols"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "grid_rows"
value {
bounded_tensor_spec_value {
name: "observation/grid_rows"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "horizontal_routes_per_micron"
value {
bounded_tensor_spec_value {
name: "observation/horizontal_routes_per_micron"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "is_node_placed"
value {
bounded_tensor_spec_value {
name: "observation/is_node_placed"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 1
}
}
}
}
fields {
key: "locations_x"
value {
bounded_tensor_spec_value {
name: "observation/locations_x"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "locations_y"
value {
bounded_tensor_spec_value {
name: "observation/locations_y"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "macro_horizontal_routing_allocation"
value {
bounded_tensor_spec_value {
name: "observation/macro_horizontal_routing_allocation"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "macro_vertical_routing_allocation"
value {
bounded_tensor_spec_value {
name: "observation/macro_vertical_routing_allocation"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "macros_h"
value {
bounded_tensor_spec_value {
name: "observation/macros_h"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "macros_w"
value {
bounded_tensor_spec_value {
name: "observation/macros_w"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "mask"
value {
bounded_tensor_spec_value {
name: "observation/mask"
shape {
dim {
size: 16384
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 1
}
}
}
}
fields {
key: "node_types"
value {
bounded_tensor_spec_value {
name: "observation/node_types"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 3
}
}
}
}
fields {
key: "normalized_num_edges"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_edges"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_hard_macros"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_hard_macros"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_port_clusters"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_port_clusters"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_soft_macros"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_soft_macros"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "sparse_adj_i"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_i"
shape {
dim {
size: 28400
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "sparse_adj_j"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_j"
shape {
dim {
size: 28400
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "sparse_adj_weight"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_weight"
shape {
dim {
size: 28400
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "vertical_routes_per_micron"
value {
bounded_tensor_spec_value {
name: "observation/vertical_routes_per_micron"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
}
}
}
values {
key: "action"
value {
bounded_tensor_spec_value {
name: "action"
shape {
}
dtype: DT_INT64
minimum {
dtype: DT_INT64
tensor_shape {
}
int64_val: 0
}
maximum {
dtype: DT_INT64
tensor_shape {
}
int64_val: 16383
}
}
}
}
values {
key: "policy_info"
value {
dict_value {
fields {
key: "dist_params"
value {
dict_value {
fields {
key: "logits"
value {
tensor_spec_value {
name: "GrlPolicyModel_logits"
shape {
dim {
size: 16384
}
}
dtype: DT_FLOAT
}
}
}
}
}
}
fields {
key: "value_prediction"
value {
tensor_spec_value {
shape {
}
dtype: DT_FLOAT
}
}
}
}
}
}
values {
key: "next_step_type"
value {
tensor_spec_value {
name: "step_type"
shape {
}
dtype: DT_INT32
}
}
}
values {
key: "reward"
value {
tensor_spec_value {
name: "reward"
shape {
}
dtype: DT_FLOAT
}
}
}
values {
key: "discount"
value {
bounded_tensor_spec_value {
name: "discount"
shape {
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
}
}
}
fields {
key: "policy_state_spec"
value {
tuple_value {
}
}
}
}
CodeElements/EvalCT/saved_policy/run_00/111/policies/greedy_policy/policy_specs.pbtxt 0 → 100644
dict_value {
fields {
key: "collect_data_spec"
value {
named_tuple_value {
name: "Trajectory"
values {
key: "step_type"
value {
tensor_spec_value {
name: "step_type"
shape {
}
dtype: DT_INT32
}
}
}
values {
key: "observation"
value {
dict_value {
fields {
key: "current_node"
value {
bounded_tensor_spec_value {
name: "observation/current_node"
shape {
dim {
size: 1
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "edge_counts"
value {
bounded_tensor_spec_value {
name: "observation/edge_counts"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 28399
}
}
}
}
fields {
key: "grid_cols"
value {
bounded_tensor_spec_value {
name: "observation/grid_cols"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "grid_rows"
value {
bounded_tensor_spec_value {
name: "observation/grid_rows"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "horizontal_routes_per_micron"
value {
bounded_tensor_spec_value {
name: "observation/horizontal_routes_per_micron"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "is_node_placed"
value {
bounded_tensor_spec_value {
name: "observation/is_node_placed"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 1
}
}
}
}
fields {
key: "locations_x"
value {
bounded_tensor_spec_value {
name: "observation/locations_x"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "locations_y"
value {
bounded_tensor_spec_value {
name: "observation/locations_y"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "macro_horizontal_routing_allocation"
value {
bounded_tensor_spec_value {
name: "observation/macro_horizontal_routing_allocation"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "macro_vertical_routing_allocation"
value {
bounded_tensor_spec_value {
name: "observation/macro_vertical_routing_allocation"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "macros_h"
value {
bounded_tensor_spec_value {
name: "observation/macros_h"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "macros_w"
value {
bounded_tensor_spec_value {
name: "observation/macros_w"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "mask"
value {
bounded_tensor_spec_value {
name: "observation/mask"
shape {
dim {
size: 16384
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 1
}
}
}
}
fields {
key: "node_types"
value {
bounded_tensor_spec_value {
name: "observation/node_types"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 3
}
}
}
}
fields {
key: "normalized_num_edges"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_edges"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_hard_macros"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_hard_macros"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_port_clusters"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_port_clusters"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_soft_macros"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_soft_macros"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "sparse_adj_i"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_i"
shape {
dim {
size: 28400
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "sparse_adj_j"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_j"
shape {
dim {
size: 28400
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "sparse_adj_weight"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_weight"
shape {
dim {
size: 28400
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "vertical_routes_per_micron"
value {
bounded_tensor_spec_value {
name: "observation/vertical_routes_per_micron"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
}
}
}
values {
key: "action"
value {
bounded_tensor_spec_value {
name: "action"
shape {
}
dtype: DT_INT64
minimum {
dtype: DT_INT64
tensor_shape {
}
int64_val: 0
}
maximum {
dtype: DT_INT64
tensor_shape {
}
int64_val: 16383
}
}
}
}
values {
key: "policy_info"
value {
tuple_value {
}
}
}
values {
key: "next_step_type"
value {
tensor_spec_value {
name: "step_type"
shape {
}
dtype: DT_INT32
}
}
}
values {
key: "reward"
value {
tensor_spec_value {
name: "reward"
shape {
}
dtype: DT_FLOAT
}
}
}
values {
key: "discount"
value {
bounded_tensor_spec_value {
name: "discount"
shape {
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
}
}
}
fields {
key: "policy_state_spec"
value {
tuple_value {
}
}
}
}
CodeElements/EvalCT/saved_policy/run_00/111/policies/policy/policy_specs.pbtxt 0 → 100644
dict_value {
fields {
key: "collect_data_spec"
value {
named_tuple_value {
name: "Trajectory"
values {
key: "step_type"
value {
tensor_spec_value {
name: "step_type"
shape {
}
dtype: DT_INT32
}
}
}
values {
key: "observation"
value {
dict_value {
fields {
key: "current_node"
value {
bounded_tensor_spec_value {
name: "observation/current_node"
shape {
dim {
size: 1
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "edge_counts"
value {
bounded_tensor_spec_value {
name: "observation/edge_counts"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 28399
}
}
}
}
fields {
key: "grid_cols"
value {
bounded_tensor_spec_value {
name: "observation/grid_cols"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "grid_rows"
value {
bounded_tensor_spec_value {
name: "observation/grid_rows"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "horizontal_routes_per_micron"
value {
bounded_tensor_spec_value {
name: "observation/horizontal_routes_per_micron"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "is_node_placed"
value {
bounded_tensor_spec_value {
name: "observation/is_node_placed"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 1
}
}
}
}
fields {
key: "locations_x"
value {
bounded_tensor_spec_value {
name: "observation/locations_x"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "locations_y"
value {
bounded_tensor_spec_value {
name: "observation/locations_y"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "macro_horizontal_routing_allocation"
value {
bounded_tensor_spec_value {
name: "observation/macro_horizontal_routing_allocation"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "macro_vertical_routing_allocation"
value {
bounded_tensor_spec_value {
name: "observation/macro_vertical_routing_allocation"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "macros_h"
value {
bounded_tensor_spec_value {
name: "observation/macros_h"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "macros_w"
value {
bounded_tensor_spec_value {
name: "observation/macros_w"
shape {
dim {
size: 5000
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "mask"
value {
bounded_tensor_spec_value {
name: "observation/mask"
shape {
dim {
size: 16384
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 1
}
}
}
}
fields {
key: "node_types"
value {
bounded_tensor_spec_value {
name: "observation/node_types"
shape {
dim {
size: 5000
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 3
}
}
}
}
fields {
key: "normalized_num_edges"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_edges"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_hard_macros"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_hard_macros"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_port_clusters"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_port_clusters"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "normalized_num_soft_macros"
value {
bounded_tensor_spec_value {
name: "observation/normalized_num_soft_macros"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
fields {
key: "sparse_adj_i"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_i"
shape {
dim {
size: 28400
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "sparse_adj_j"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_j"
shape {
dim {
size: 28400
}
}
dtype: DT_INT32
minimum {
dtype: DT_INT32
tensor_shape {
}
int_val: 0
}
maximum {
dtype: DT_INT32
tensor_shape {
}
int_val: 4999
}
}
}
}
fields {
key: "sparse_adj_weight"
value {
bounded_tensor_spec_value {
name: "observation/sparse_adj_weight"
shape {
dim {
size: 28400
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
fields {
key: "vertical_routes_per_micron"
value {
bounded_tensor_spec_value {
name: "observation/vertical_routes_per_micron"
shape {
dim {
size: 1
}
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 100.0
}
}
}
}
}
}
}
values {
key: "action"
value {
bounded_tensor_spec_value {
name: "action"
shape {
}
dtype: DT_INT64
minimum {
dtype: DT_INT64
tensor_shape {
}
int64_val: 0
}
maximum {
dtype: DT_INT64
tensor_shape {
}
int64_val: 16383
}
}
}
}
values {
key: "policy_info"
value {
tuple_value {
}
}
}
values {
key: "next_step_type"
value {
tensor_spec_value {
name: "step_type"
shape {
}
dtype: DT_INT32
}
}
}
values {
key: "reward"
value {
tensor_spec_value {
name: "reward"
shape {
}
dtype: DT_FLOAT
}
}
}
values {
key: "discount"
value {
bounded_tensor_spec_value {
name: "discount"
shape {
}
dtype: DT_FLOAT
minimum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 0.0
}
maximum {
dtype: DT_FLOAT
tensor_shape {
}
float_val: 1.0
}
}
}
}
}
}
}
fields {
key: "policy_state_spec"
value {
tuple_value {
}
}
}
}
CodeElements/EvalCT/test/ariane/initial.plc 0 → 100644
# Placement file for Circuit Training
# Source input file(s) : environment/test_data/ariane/netlist.pb.txt
# This file : environment/test_data/ariane/initial.plc
# Date : 2022-03-13 09:30:00
# Columns : 35 Rows : 33
# Width : 356.592 Height : 356.640
# Area : 99908.9764139
# Wirelength : 0.0
# Wirelength cost : 0.0
# Congestion cost : 0.0
# Block : ariane
# Routes per micron, hor : 70.33 ver : 74.51
# Routes used by macros, hor : 51.79 ver : 51.79
# Smoothing factor : 2
# Overlap threshold : 0.004
#
#
#
# Counts of node types:
# HARD_MACROs : 133
# HARD_MACRO_PINs : 11970
# MACROs : 932
# MACRO_PINs : 22802
# PORTs : 1231
# SOFT_MACROs : 799
# SOFT_MACRO_PINs : 10832
# STDCELLs : 0
#
# node_index x y orientation fixed
0 155.268 0.1975 - 1
1 216.676 0.1975 - 1
2 48.108 0.1975 - 1
3 200.032 0.1975 - 1
4 201.704 0.1975 - 1
5 202.388 0.1975 - 1
6 201.324 0.1975 - 1
7 203.072 0.1975 - 1
8 201.172 0.1975 - 1
9 203.984 0.1975 - 1
10 203.224 0.1975 - 1
11 203.832 0.1975 - 1
12 204.364 0.1975 - 1
13 204.212 0.1975 - 1
14 205.048 0.1975 - 1
15 206.036 0.1975 - 1
16 206.72 0.1975 - 1
17 213.408 0.1975 - 1
18 204.896 0.1975 - 1
19 212.952 0.1975 - 1
20 208.544 0.1975 - 1
21 209.988 0.1975 - 1
22 213.256 0.1975 - 1
23 210.368 0.1975 - 1
24 213.104 0.1975 - 1
25 211.432 0.1975 - 1
26 208.924 0.1975 - 1
27 209.076 0.1975 - 1
28 203.376 0.1975 - 1
29 205.2 0.1975 - 1
30 199.348 0.1975 - 1
31 200.26 0.1975 - 1
32 198.74 0.1975 - 1
33 199.5 0.1975 - 1
34 197.6 0.1975 - 1
35 199.88 0.1975 - 1
36 196.308 0.1975 - 1
37 199.652 0.1975 - 1
38 196.46 0.1975 - 1
39 196.992 0.1975 - 1
40 193.952 0.1975 - 1
41 195.7 0.1975 - 1
42 194.104 0.1975 - 1
43 195.852 0.1975 - 1
44 190.684 0.1975 - 1
45 192.812 0.1975 - 1
46 189.924 0.1975 - 1
47 193.8 0.1975 - 1
48 192.128 0.1975 - 1
49 191.824 0.1975 - 1
50 190.076 0.1975 - 1
51 196.156 0.1975 - 1
52 191.976 0.1975 - 1
53 196.004 0.1975 - 1
54 187.872 0.1975 - 1
55 195.396 0.1975 - 1
56 187.72 0.1975 - 1
57 195.548 0.1975 - 1
58 191.672 0.1975 - 1
59 191.064 0.1975 - 1
60 191.52 0.1975 - 1
61 187.568 0.1975 - 1
62 190.228 0.1975 - 1
63 186.124 0.1975 - 1
64 194.256 0.1975 - 1
65 196.612 0.1975 - 1
66 196.764 0.1975 - 1
67 172.216 0.1975 - 1
68 179.36 0.1975 - 1
69 182.4 0.1975 - 1
70 181.412 0.1975 - 1
71 178.22 0.1975 - 1
72 169.252 0.1975 - 1
73 178.372 0.1975 - 1
74 172.368 0.1975 - 1
75 178.524 0.1975 - 1
76 169.404 0.1975 - 1
77 76.608 0.226 - 1
78 88.92 0.1975 - 1
79 85.88 0.1975 - 1
80 105.84 0.177 - 1
81 77.9 0.1975 - 1
82 113.316 0.1975 - 1
83 75.924 0.1975 - 1
84 109.82 0.1975 - 1
85 63.536 0.1975 - 1
86 113.62 0.1975 - 1
87 76.836 0.1975 - 1
88 76.684 0.1975 - 1
89 99.484 0.1975 - 1
90 111.568 0.1975 - 1
91 107.856 0.177 - 1
92 76.988 0.1975 - 1
93 85.68 0.226 - 1
94 77.748 0.1975 - 1
95 85.576 0.1975 - 1
96 77.14 0.1975 - 1
97 103.824 0.226 - 1
98 85.196 0.1975 - 1
99 108.376 0.1975 - 1
100 77.292 0.1975 - 1
101 111.188 0.1975 - 1
102 60.192 0.1975 - 1
103 106.78 0.1975 - 1
104 87.932 0.1975 - 1
105 109.212 0.1975 - 1
106 80.028 0.1975 - 1
107 99.792 0.226 - 1
108 109.116 0.226 - 1
109 77.596 0.1975 - 1
110 100.472 0.1975 - 1
111 114.912 0.226 - 1
112 98.648 0.1975 - 1
113 114.912 0.1975 - 1
114 101.08 0.1975 - 1
115 77.444 0.1975 - 1
116 80.484 0.1975 - 1
117 66.12 0.1975 - 1
118 117.04 0.1975 - 1
119 60.344 0.1975 - 1
120 88.464 0.1975 - 1
121 112.328 0.1975 - 1
122 114.684 0.1975 - 1
123 106.092 0.177 - 1
124 98.496 0.1975 - 1
125 109.82 0.1975 - 1
126 66.728 0.1975 - 1
127 83.16 0.226 - 1
128 78.052 0.1975 - 1
129 91.728 0.226 - 1
130 113.62 0.1975 - 1
131 91.656 0.1975 - 1
132 92.188 0.1975 - 1
133 66.576 0.1975 - 1
134 112.176 0.1975 - 1
135 116.356 0.1975 - 1
136 78.624 0.177 - 1
137 93.252 0.1975 - 1
138 76.076 0.1975 - 1
139 79.724 0.1975 - 1
140 105.336 0.177 - 1
141 79.192 0.1975 - 1
142 78.432 0.1975 - 1
143 91.124 0.1975 - 1
144 78.28 0.1975 - 1
145 65.208 0.1975 - 1
146 84.168 0.226 - 1
147 106.722 0.177 - 1
148 109.668 0.1975 - 1
149 106.552 0.1975 - 1
150 109.516 0.1975 - 1
151 107.16 0.1975 - 1
152 116.128 0.1975 - 1
153 74.48 0.1975 - 1
154 63.232 0.1975 - 1
155 85.044 0.1975 - 1
156 84.512 0.1975 - 1
157 84.664 0.1975 - 1
158 63.84 0.1975 - 1
159 60.496 0.1975 - 1
160 106.096 0.1975 - 1
161 109.06 0.1975 - 1
162 85.5 0.1975 - 1
163 84.892 0.1975 - 1
164 99.636 0.1975 - 1
165 86.032 0.1975 - 1
166 104.576 0.1975 - 1
167 90.744 0.1975 - 1
168 88.084 0.1975 - 1
169 88.236 0.1975 - 1
170 86.412 0.1975 - 1
171 105.108 0.1975 - 1
172 79.876 0.1975 - 1
173 104.196 0.1975 - 1
174 76.228 0.1975 - 1
175 101.232 0.1975 - 1
176 96.9 0.1975 - 1
177 87.02 0.1975 - 1
178 93.936 0.1975 - 1
179 115.976 0.1975 - 1
180 115.824 0.1975 - 1
181 48.412 0.1975 - 1
182 111.112 0.1975 - 1
183 90.592 0.1975 - 1
184 67.032 0.1975 - 1
185 116.052 0.1975 - 1
186 100.928 0.1975 - 1
187 68.552 0.1975 - 1
188 68.4 0.1975 - 1
189 66.88 0.1975 - 1
190 106.248 0.1975 - 1
191 259.056 0.177 - 1
192 260.148 0.1975 - 1
193 261.212 0.1975 - 1
194 261.06 0.1975 - 1
195 261.82 0.1975 - 1
196 261.972 0.1975 - 1
197 259.16 0.1975 - 1
198 260.82 0.177 - 1
199 259.008 0.1975 - 1
200 259.16 0.1975 - 1
201 262.276 0.1975 - 1
202 259.312 0.1975 - 1
203 259.464 0.1975 - 1
204 257.108 0.1975 - 1
205 259.616 0.1975 - 1
206 259.768 0.1975 - 1
207 259.92 0.1975 - 1
208 263.036 0.1975 - 1
209 264.632 0.1975 - 1
210 266.228 0.1975 - 1
211 266.076 0.1975 - 1
212 265.924 0.1975 - 1
213 265.772 0.1975 - 1
214 265.164 0.1975 - 1
215 263.188 0.1975 - 1
216 260.604 0.1975 - 1
217 263.34 0.1975 - 1
218 260.452 0.1975 - 1
219 260.072 0.1975 - 1
220 263.644 0.1975 - 1
221 260.908 0.1975 - 1
222 263.796 0.1975 - 1
223 260.756 0.1975 - 1
224 264.404 0.1975 - 1
225 262.124 0.1975 - 1
226 265.62 0.1975 - 1
227 265.316 0.1975 - 1
228 264.024 0.1975 - 1
229 264.252 0.1975 - 1
230 263.492 0.1975 - 1
231 264.784 0.1975 - 1
232 265.012 0.1975 - 1
233 260.224 0.1975 - 1
234 265.468 0.1975 - 1
235 241.224 0.1975 - 1
236 247.76 0.1975 - 1
237 241.376 0.1975 - 1
238 241.528 0.1975 - 1
239 243.58 0.1975 - 1
240 247.608 0.1975 - 1
241 241.68 0.1975 - 1
242 247.456 0.1975 - 1
243 60.648 0.1975 - 1
244 110.628 0.226 - 1
245 71.364 0.1975 - 1
246 102.676 0.1975 - 1
247 105.26 0.1975 - 1
248 106.974 0.177 - 1
249 104.728 0.1975 - 1
250 104.88 0.1975 - 1
251 107.226 0.177 - 1
252 97.508 0.1975 - 1
253 88.704 0.226 - 1
254 107.856 0.226 - 1
255 80.56 0.1975 - 1
256 113.088 0.1975 - 1
257 60.8 0.1975 - 1
258 78.28 0.1975 - 1
259 86.184 0.1975 - 1
260 100.624 0.1975 - 1
261 88.2 0.177 - 1
262 78.736 0.1975 - 1
263 108.832 0.1975 - 1
264 104.424 0.1975 - 1
265 94.696 0.1975 - 1
266 79.04 0.1975 - 1
267 88.452 0.177 - 1
268 98.344 0.1975 - 1
269 88.16 0.1975 - 1
270 112.556 0.1975 - 1
271 80.18 0.1975 - 1
272 63.688 0.1975 - 1
273 78.888 0.1975 - 1
274 114.66 0.177 - 1
275 108.528 0.1975 - 1
276 88.312 0.1975 - 1
277 89.208 0.226 - 1
278 112.404 0.1975 - 1
279 64.372 0.1975 - 1
280 104.044 0.1975 - 1
281 77.824 0.1975 - 1
282 107.236 0.1975 - 1
283 85.12 0.1975 - 1
284 76.38 0.1975 - 1
285 93.556 0.1975 - 1
286 92.34 0.1975 - 1
287 254.904 0.1975 - 1
288 256.576 0.1975 - 1
289 67.944 0.1975 - 1
290 86.64 0.1975 - 1
291 90.72 0.226 - 1
292 89.908 0.1975 - 1
293 89.376 0.1975 - 1
294 92.72 0.1975 - 1
295 103.436 0.1975 - 1
296 92.036 0.1975 - 1
297 89.082 0.177 - 1
298 80.788 0.1975 - 1
299 86.336 0.1975 - 1
300 60.952 0.1975 - 1
301 103.892 0.1975 - 1
302 80.94 0.1975 - 1
303 88.616 0.1975 - 1
304 86.564 0.1975 - 1
305 90.896 0.1975 - 1
306 79.724 0.1975 - 1
307 81.244 0.1975 - 1
308 66.576 0.1975 - 1
309 110.96 0.1975 - 1
310 88.768 0.1975 - 1
311 81.092 0.1975 - 1
312 63 0.226 - 1
313 79.268 0.1975 - 1
314 81.396 0.1975 - 1
315 87.02 0.1975 - 1
316 80.18 0.1975 - 1
317 102.828 0.1975 - 1
318 91.124 0.1975 - 1
319 64.752 0.1975 - 1
320 88.704 0.177 - 1
321 63 0.177 - 1
322 106.932 0.1975 - 1
323 108.36 0.226 - 1
324 88.92 0.1975 - 1
325 108.224 0.1975 - 1
326 72.808 0.1975 - 1
327 81.624 0.1975 - 1
328 97.964 0.1975 - 1
329 91.884 0.1975 - 1
330 87.172 0.1975 - 1
331 119.624 0.1975 - 1
332 94.924 0.1975 - 1
333 89.072 0.1975 - 1
334 66.424 0.1975 - 1
335 110.124 0.226 - 1
336 97.902 0.177 - 1
337 99.18 0.1975 - 1
338 87.476 0.1975 - 1
339 93.784 0.1975 - 1
340 115.748 0.1975 - 1
341 81.776 0.1975 - 1
342 91.884 0.1975 - 1
343 76.532 0.1975 - 1
344 93.784 0.1975 - 1
345 111.132 0.226 - 1
346 89.224 0.1975 - 1
347 79.128 0.177 - 1
348 80.332 0.1975 - 1
349 68.248 0.1975 - 1
350 87.628 0.1975 - 1
351 85.348 0.1975 - 1
352 103.284 0.1975 - 1
353 96.596 0.1975 - 1
354 78.584 0.1975 - 1
355 87.948 0.226 - 1
356 87.78 0.1975 - 1
357 95.76 0.1975 - 1
358 107.844 0.1975 - 1
359 107.692 0.1975 - 1
360 85.652 0.1975 - 1
361 82.656 0.226 - 1
362 90.44 0.1975 - 1
363 93.24 0.226 - 1
364 48.716 0.1975 - 1
365 242.972 0.1975 - 1
366 243.124 0.1975 - 1
367 242.516 0.1975 - 1
368 243.428 0.1975 - 1
369 242.668 0.1975 - 1
370 242.82 0.1975 - 1
371 245.86 0.1975 - 1
372 248.824 0.1975 - 1
373 242.364 0.1975 - 1
374 243.276 0.1975 - 1
375 249.28 0.1975 - 1
376 245.176 0.1975 - 1
377 245.024 0.1975 - 1
378 245.328 0.1975 - 1
379 244.796 0.1975 - 1
380 244.644 0.1975 - 1
381 248.216 0.1975 - 1
382 240.616 0.1975 - 1
383 241.072 0.1975 - 1
384 248.368 0.1975 - 1
385 248.52 0.1975 - 1
386 240.464 0.1975 - 1
387 240.768 0.1975 - 1
388 240.92 0.1975 - 1
389 242.212 0.1975 - 1
390 240.008 0.1975 - 1
391 250.192 0.1975 - 1
392 240.16 0.1975 - 1
393 250.344 0.1975 - 1
394 241.908 0.1975 - 1
395 248.064 0.1975 - 1
396 247.912 0.1975 - 1
397 246.848 0.1975 - 1
398 247.304 0.1975 - 1
399 249.128 0.1975 - 1
400 247 0.1975 - 1
401 246.696 0.1975 - 1
402 245.708 0.1975 - 1
403 245.48 0.1975 - 1
404 244.492 0.1975 - 1
405 246.164 0.1975 - 1
406 246.012 0.1975 - 1
407 244.34 0.1975 - 1
408 247.152 0.1975 - 1
409 248.976 0.1975 - 1
410 246.316 0.1975 - 1
411 246.468 0.1975 - 1
412 244.188 0.1975 - 1
413 248.672 0.1975 - 1
414 250.648 0.1975 - 1
415 239.704 0.1975 - 1
416 250.496 0.1975 - 1
417 250.8 0.1975 - 1
418 239.856 0.1975 - 1
419 250.04 0.1975 - 1
420 242.06 0.1975 - 1
421 240.312 0.1975 - 1
422 243.732 0.1975 - 1
423 249.432 0.1975 - 1
424 243.884 0.1975 - 1
425 249.584 0.1975 - 1
426 244.036 0.1975 - 1
427 249.736 0.1975 - 1
428 249.888 0.1975 - 1
429 49.248 0.1975 - 1
430 49.552 0.1975 - 1
431 252.548 0.1975 - 1
432 49.856 0.1975 - 1
433 50.16 0.1975 - 1
434 50.692 0.1975 - 1
435 50.996 0.1975 - 1
436 51.3 0.1975 - 1
437 51.604 0.1975 - 1
438 52.136 0.1975 - 1
439 52.44 0.1975 - 1
440 52.744 0.1975 - 1
441 53.048 0.1975 - 1
442 53.58 0.1975 - 1
443 89.376 0.1975 - 1
444 252.396 0.1975 - 1
445 53.884 0.1975 - 1
446 54.188 0.1975 - 1
447 54.492 0.1975 - 1
448 54.644 0.1975 - 1
449 54.34 0.1975 - 1
450 54.036 0.1975 - 1
451 53.732 0.1975 - 1
452 53.428 0.1975 - 1
453 53.2 0.1975 - 1
454 52.896 0.1975 - 1
455 52.592 0.1975 - 1
456 52.288 0.1975 - 1
457 51.984 0.1975 - 1
458 103.132 0.1975 - 1
459 51.756 0.1975 - 1
460 89.68 0.1975 - 1
461 84.284 0.1975 - 1
462 90.288 0.1975 - 1
463 81.092 0.1975 - 1
464 115.9 0.1975 - 1
465 92.872 0.1975 - 1
466 82.46 0.1975 - 1
467 98.192 0.1975 - 1
468 112.024 0.1975 - 1
469 89.072 0.1975 - 1
470 105.588 0.177 - 1
471 87.948 0.177 - 1
472 115.292 0.1975 - 1
473 106.344 0.177 - 1
474 100.296 0.177 - 1
475 111.568 0.1975 - 1
476 113.24 0.1975 - 1
477 107.312 0.1975 - 1
478 107.844 0.1975 - 1
479 107.616 0.1975 - 1
480 114.532 0.1975 - 1
481 79.38 0.177 - 1
482 92.736 0.177 - 1
483 112.784 0.1975 - 1
484 114.408 0.177 - 1
485 107.996 0.1975 - 1
486 105.944 0.1975 - 1
487 108.756 0.1975 - 1
488 112.632 0.1975 - 1
489 88.616 0.1975 - 1
490 111.872 0.1975 - 1
491 104.58 0.177 - 1
492 95.76 0.177 - 1
493 112.644 0.177 - 1
494 114.156 0.177 - 1
495 112.392 0.177 - 1
496 99.792 0.177 - 1
497 112.48 0.1975 - 1
498 92.232 0.177 - 1
499 110.2 0.1975 - 1
500 100.044 0.177 - 1
501 93.024 0.1975 - 1
502 102.524 0.1975 - 1
503 102.22 0.1975 - 1
504 78.736 0.1975 - 1
505 102.372 0.1975 - 1
506 99.788 0.1975 - 1
507 91.602 0.177 - 1
508 86.436 0.177 - 1
509 109.364 0.1975 - 1
510 112.14 0.177 - 1
511 87.696 0.177 - 1
512 113.088 0.1975 - 1
513 111.888 0.177 - 1
514 110.808 0.1975 - 1
515 85.804 0.1975 - 1
516 67.792 0.1975 - 1
517 109.972 0.1975 - 1
518 103.572 0.177 - 1
519 91.352 0.1975 - 1
520 82.232 0.1975 - 1
521 85.68 0.177 - 1
522 79.632 0.177 - 1
523 83.98 0.1975 - 1
524 100.244 0.1975 - 1
525 79.04 0.1975 - 1
526 87.324 0.1975 - 1
527 92.492 0.1975 - 1
528 79.42 0.1975 - 1
529 86.716 0.1975 - 1
530 101.916 0.1975 - 1
531 115.444 0.1975 - 1
532 78.888 0.1975 - 1
533 110.352 0.1975 - 1
534 83.676 0.1975 - 1
535 62.496 0.226 - 1
536 90.972 0.1975 - 1
537 89.908 0.1975 - 1
538 75.772 0.1975 - 1
539 108.148 0.1975 - 1
540 86.688 0.177 - 1
541 83.524 0.1975 - 1
542 82.46 0.1975 - 1
543 83.372 0.1975 - 1
544 108.984 0.1975 - 1
545 108.528 0.1975 - 1
546 90.06 0.1975 - 1
547 82.612 0.1975 - 1
548 82.764 0.1975 - 1
549 82.992 0.1975 - 1
550 87.444 0.177 - 1
551 91.504 0.1975 - 1
552 61.236 0.177 - 1
553 81.32 0.1975 - 1
554 99.94 0.1975 - 1
555 102.98 0.1975 - 1
556 108.3 0.1975 - 1
557 79.572 0.1975 - 1
558 86.26 0.1975 - 1
559 64.524 0.1975 - 1
560 89.528 0.1975 - 1
561 88.768 0.1975 - 1
562 101.556 0.177 - 1
563 64.296 0.1975 - 1
564 78.128 0.1975 - 1
565 75.62 0.1975 - 1
566 101.808 0.177 - 1
567 90.09 0.177 - 1
568 87.192 0.177 - 1
569 113.904 0.177 - 1
570 90.342 0.177 - 1
571 61.104 0.1975 - 1
572 61.74 0.177 - 1
573 86.868 0.1975 - 1
574 110.656 0.1975 - 1
575 84.294 0.177 - 1
576 113.652 0.177 - 1
577 98.784 0.177 - 1
578 113.848 0.1975 - 1
579 102.816 0.226 - 1
580 99.332 0.1975 - 1
581 108.36 0.177 - 1
582 112.936 0.1975 - 1
583 108.108 0.177 - 1
584 102.816 0.177 - 1
585 107.464 0.1975 - 1
586 114.38 0.1975 - 1
587 97.052 0.1975 - 1
588 111.72 0.1975 - 1
589 98.154 0.177 - 1
590 102.828 0.1975 - 1
591 108.864 0.177 - 1
592 102.144 0.1975 - 1
593 109.116 0.177 - 1
594 98.344 0.1975 - 1
595 104.88 0.1975 - 1
596 111.796 0.1975 - 1
597 104.328 0.177 - 1
598 97.146 0.177 - 1
599 109.62 0.226 - 1
600 102.312 0.226 - 1
601 110.88 0.177 - 1
602 103.32 0.226 - 1
603 110.732 0.1975 - 1
604 96.642 0.177 - 1
605 110.352 0.1975 - 1
606 104.076 0.177 - 1
607 100.244 0.1975 - 1
608 98.496 0.1975 - 1
609 106.02 0.1975 - 1
610 106.476 0.1975 - 1
611 109.972 0.1975 - 1
612 106.172 0.1975 - 1
613 109.592 0.1975 - 1
614 85.428 0.177 - 1
615 111.416 0.1975 - 1
616 113.4 0.177 - 1
617 90.216 0.226 - 1
618 114.228 0.1975 - 1
619 111.416 0.1975 - 1
620 111.264 0.1975 - 1
621 101.992 0.1975 - 1
622 67.412 0.1975 - 1
623 86.94 0.177 - 1
624 104.958 0.177 - 1
625 102.676 0.1975 - 1
626 86.868 0.1975 - 1
627 91.732 0.1975 - 1
628 87.324 0.1975 - 1
629 82.764 0.1975 - 1
630 96.672 0.1975 - 1
631 102.06 0.177 - 1
632 87.856 0.1975 - 1
633 90.72 0.177 - 1
634 82.916 0.1975 - 1
635 93.632 0.1975 - 1
636 83.068 0.1975 - 1
637 100.624 0.1975 - 1
638 61.256 0.1975 - 1
639 81.624 0.1975 - 1
640 102.296 0.1975 - 1
641 102.564 0.177 - 1
642 102.448 0.1975 - 1
643 100.472 0.1975 - 1
644 79.876 0.1975 - 1
645 102.312 0.177 - 1
646 93.936 0.1975 - 1
647 79.572 0.1975 - 1
648 94.088 0.1975 - 1
649 83.22 0.1975 - 1
650 99.408 0.1975 - 1
651 84.056 0.1975 - 1
652 92.796 0.1975 - 1
653 94.24 0.1975 - 1
654 98.876 0.1975 - 1
655 93.328 0.1975 - 1
656 104.728 0.1975 - 1
657 93.24 0.177 - 1
658 64.22 0.1975 - 1
659 61.408 0.1975 - 1
660 98.192 0.1975 - 1
661 99.256 0.1975 - 1
662 100.092 0.1975 - 1
663 79.42 0.1975 - 1
664 99.288 0.177 - 1
665 99.94 0.1975 - 1
666 99.104 0.1975 - 1
667 88.464 0.1975 - 1
668 99.788 0.1975 - 1
669 109.136 0.1975 - 1
670 80.408 0.1975 - 1
671 81.776 0.1975 - 1
672 74.176 0.1975 - 1
673 107.352 0.226 - 1
674 116.046 0.177 - 1
675 115.52 0.1975 - 1
676 117.648 0.1975 - 1
677 119.016 0.1975 - 1
678 118.864 0.1975 - 1
679 115.368 0.1975 - 1
680 115.216 0.1975 - 1
681 115.672 0.1975 - 1
682 115.064 0.1975 - 1
683 115.416 0.226 - 1
684 116.66 0.1975 - 1
685 117.496 0.1975 - 1
686 116.508 0.1975 - 1
687 116.204 0.1975 - 1
688 115.14 0.1975 - 1
689 125.628 0.1975 - 1
690 117.344 0.1975 - 1
691 125.476 0.1975 - 1
692 119.168 0.1975 - 1
693 117.192 0.1975 - 1
694 96.264 0.226 - 1
695 97.66 0.1975 - 1
696 99.288 0.226 - 1
697 116.888 0.1975 - 1
698 80.64 0.226 - 1
699 97.272 0.226 - 1
700 96.768 0.226 - 1
701 80.388 0.177 - 1
702 81.144 0.226 - 1
703 83.412 0.177 - 1
704 80.892 0.177 - 1
705 81.144 0.177 - 1
706 81.396 0.177 - 1
707 80.136 0.177 - 1
708 82.404 0.177 - 1
709 71.668 0.1975 - 1
710 72.124 0.1975 - 1
711 65.394 0.177 - 1
712 64.89 0.177 - 1
713 65.646 0.177 - 1
714 65.898 0.177 - 1
715 67.032 0.177 - 1
716 66.15 0.177 - 1
717 71.972 0.1975 - 1
718 72.656 0.1975 - 1
719 67.41 0.177 - 1
720 71.82 0.1975 - 1
721 74.328 0.1975 - 1
722 74.176 0.1975 - 1
723 73.568 0.1975 - 1
724 72.884 0.1975 - 1
725 77.238 0.177 - 1
726 77.49 0.177 - 1
727 75.24 0.1975 - 1
728 76.734 0.177 - 1
729 78.876 0.177 - 1
730 78.12 0.177 - 1
731 76.986 0.177 - 1
732 75.468 0.1975 - 1
733 77.868 0.177 - 1
734 80.64 0.177 - 1
735 76.228 0.1975 - 1
736 79.884 0.177 - 1
737 107.388 0.1975 - 1
738 107.54 0.1975 - 1
739 84.588 0.1975 - 1
740 94.62 0.1975 - 1
741 90.06 0.1975 - 1
742 82.612 0.1975 - 1
743 96.368 0.1975 - 1
744 94.772 0.1975 - 1
745 90.44 0.1975 - 1
746 77.976 0.1975 - 1
747 80.028 0.1975 - 1
748 58.216 0.1975 - 1
749 112.86 0.1975 - 1
750 59.28 0.1975 - 1
751 112.708 0.1975 - 1
752 112.1 0.1975 - 1
753 59.432 0.1975 - 1
754 110.884 0.1975 - 1
755 59.584 0.1975 - 1
756 58.976 0.1975 - 1
757 105.184 0.1975 - 1
758 69.54 0.1975 - 1
759 105.716 0.1975 - 1
760 105.868 0.1975 - 1
761 108.68 0.1975 - 1
762 59.128 0.1975 - 1
763 106.324 0.1975 - 1
764 100.928 0.1975 - 1
765 69.844 0.1975 - 1
766 101.384 0.1975 - 1
767 101.08 0.1975 - 1
768 101.232 0.1975 - 1
769 100.776 0.1975 - 1
770 58.52 0.1975 - 1
771 58.824 0.1975 - 1
772 70.68 0.1975 - 1
773 68.932 0.1975 - 1
774 77.52 0.1975 - 1
775 68.78 0.1975 - 1
776 77.368 0.1975 - 1
777 59.736 0.1975 - 1
778 60.04 0.1975 - 1
779 69.084 0.1975 - 1
780 56.848 0.1975 - 1
781 56.696 0.1975 - 1
782 57 0.1975 - 1
783 57.152 0.1975 - 1
784 56.24 0.1975 - 1
785 55.632 0.1975 - 1
786 55.48 0.1975 - 1
787 55.784 0.1975 - 1
788 57.912 0.1975 - 1
789 55.936 0.1975 - 1
790 56.088 0.1975 - 1
791 56.392 0.1975 - 1
792 58.672 0.1975 - 1
793 57.456 0.1975 - 1
794 57.304 0.1975 - 1
795 73.72 0.1975 - 1
796 57.608 0.1975 - 1
797 58.064 0.1975 - 1
798 56.544 0.1975 - 1
799 57.76 0.1975 - 1
800 78.432 0.1975 - 1
801 76.684 0.1975 - 1
802 76.836 0.1975 - 1
803 76.988 0.1975 - 1
804 84.36 0.1975 - 1
805 88.008 0.1975 - 1
806 55.024 0.1975 - 1
807 90.212 0.1975 - 1
808 54.872 0.1975 - 1
809 55.328 0.1975 - 1
810 87.172 0.1975 - 1
811 55.176 0.1975 - 1
812 51.452 0.1975 - 1
813 51.148 0.1975 - 1
814 74.708 0.1975 - 1
815 50.844 0.1975 - 1
816 50.54 0.1975 - 1
817 50.312 0.1975 - 1
818 50.008 0.1975 - 1
819 49.704 0.1975 - 1
820 49.4 0.1975 - 1
821 49.096 0.1975 - 1
822 48.868 0.1975 - 1
823 48.564 0.1975 - 1
824 48.26 0.1975 - 1
825 47.956 0.1975 - 1
826 73.34 0.1975 - 1
827 77.672 0.1975 - 1
828 47.652 0.1975 - 1
829 47.424 0.1975 - 1
830 47.12 0.1975 - 1
831 46.816 0.1975 - 1
832 46.512 0.1975 - 1
833 46.208 0.1975 - 1
834 45.98 0.1975 - 1
835 45.676 0.1975 - 1
836 45.372 0.1975 - 1
837 45.068 0.1975 - 1
838 44.764 0.1975 - 1
839 44.536 0.1975 - 1
840 44.232 0.1975 - 1
841 77.14 0.1975 - 1
842 78.584 0.1975 - 1
843 100.8 0.177 - 1
844 98.952 0.1975 - 1
845 66.272 0.1975 - 1
846 101.052 0.177 - 1
847 101.304 0.177 - 1
848 113.148 0.177 - 1
849 96.064 0.1975 - 1
850 96.39 0.177 - 1
851 84.208 0.1975 - 1
852 70.528 0.1975 - 1
853 118.56 0.1975 - 1
854 85.272 0.1975 - 1
855 118.712 0.1975 - 1
856 95.004 0.177 - 1
857 120.232 0.1975 - 1
858 95.532 0.1975 - 1
859 96.824 0.1975 - 1
860 121.676 0.1975 - 1
861 95.456 0.1975 - 1
862 125.78 0.1975 - 1
863 124.336 0.1975 - 1
864 114.38 0.1975 - 1
865 94.752 0.177 - 1
866 70.376 0.1975 - 1
867 69.692 0.1975 - 1
868 111.636 0.177 - 1
869 84.74 0.1975 - 1
870 100.548 0.177 - 1
871 92.34 0.1975 - 1
872 103.824 0.177 - 1
873 99.54 0.177 - 1
874 89.334 0.177 - 1
875 114 0.1975 - 1
876 100.092 0.1975 - 1
877 84.798 0.177 - 1
878 82.004 0.1975 - 1
879 97.736 0.1975 - 1
880 113.468 0.1975 - 1
881 110.504 0.1975 - 1
882 110.628 0.177 - 1
883 106.4 0.1975 - 1
884 111.384 0.177 - 1
885 115.596 0.1975 - 1
886 94.374 0.177 - 1
887 105.792 0.1975 - 1
888 112.252 0.1975 - 1
889 108.612 0.177 - 1
890 114.988 0.1975 - 1
891 107.478 0.177 - 1
892 100.776 0.1975 - 1
893 114.836 0.1975 - 1
894 111.132 0.177 - 1
895 105.412 0.1975 - 1
896 102.98 0.1975 - 1
897 103.284 0.1975 - 1
898 85.424 0.1975 - 1
899 106.78 0.1975 - 1
900 95 0.1975 - 1
901 103.512 0.1975 - 1
902 105.032 0.1975 - 1
903 58.368 0.1975 - 1
904 105.564 0.1975 - 1
905 113.468 0.1975 - 1
906 111.948 0.1975 - 1
907 87.704 0.1975 - 1
908 65.36 0.1975 - 1
909 104.576 0.1975 - 1
910 62.016 0.1975 - 1
911 66.728 0.1975 - 1
912 84.968 0.1975 - 1
913 95.608 0.1975 - 1
914 97.888 0.1975 - 1
915 90.592 0.1975 - 1
916 61.864 0.1975 - 1
917 105.588 0.226 - 1
918 104.12 0.1975 - 1
919 98.648 0.1975 - 1
920 106.628 0.1975 - 1
921 97.204 0.1975 - 1
922 68.096 0.1975 - 1
923 110.504 0.1975 - 1
924 110.124 0.1975 - 1
925 96.976 0.1975 - 1
926 104.272 0.1975 - 1
927 91.58 0.1975 - 1
928 103.816 0.1975 - 1
929 83.828 0.1975 - 1
930 89.224 0.1975 - 1
931 97.508 0.1975 - 1
932 62.168 0.1975 - 1
933 104.424 0.1975 - 1
934 66.196 0.1975 - 1
935 103.968 0.1975 - 1
936 86.488 0.1975 - 1
937 92.948 0.1975 - 1
938 95.836 0.1975 - 1
939 97.356 0.1975 - 1
940 91.098 0.177 - 1
941 91.428 0.1975 - 1
942 94.392 0.1975 - 1
943 91.276 0.1975 - 1
944 69.236 0.1975 - 1
945 111.036 0.1975 - 1
946 67.64 0.1975 - 1
947 64.6 0.1975 - 1
948 65.284 0.1975 - 1
949 110.376 0.177 - 1
950 105.564 0.1975 - 1
951 65.512 0.1975 - 1
952 103.068 0.177 - 1
953 103.32 0.177 - 1
954 110.124 0.177 - 1
955 105.412 0.1975 - 1
956 96.368 0.1975 - 1
957 59.888 0.1975 - 1
958 91.35 0.177 - 1
959 95.228 0.1975 - 1
960 97.28 0.1975 - 1
961 94.088 0.1975 - 1
962 119.776 0.1975 - 1
963 96.216 0.1975 - 1
964 124.184 0.1975 - 1
965 124.032 0.1975 - 1
966 95.076 0.1975 - 1
967 123.88 0.1975 - 1
968 94.24 0.1975 - 1
969 96.748 0.1975 - 1
970 97.812 0.1975 - 1
971 119.928 0.1975 - 1
972 95.912 0.1975 - 1
973 93.404 0.1975 - 1
974 123.272 0.1975 - 1
975 120.536 0.1975 - 1
976 123.576 0.1975 - 1
977 123.728 0.1975 - 1
978 123.424 0.1975 - 1
979 69.388 0.1975 - 1
980 120.384 0.1975 - 1
981 119.472 0.1975 - 1
982 120.08 0.1975 - 1
983 120.764 0.1975 - 1
984 120.916 0.1975 - 1
985 114.228 0.1975 - 1
986 119.32 0.1975 - 1
987 117.8 0.1975 - 1
988 117.952 0.1975 - 1
989 118.256 0.1975 - 1
990 118.104 0.1975 - 1
991 107.084 0.1975 - 1
992 70.224 0.1975 - 1
993 118.408 0.1975 - 1
994 106.932 0.1975 - 1
995 85.728 0.1975 - 1
996 114.684 0.1975 - 1
997 113.772 0.1975 - 1
998 114.076 0.1975 - 1
999 114.532 0.1975 - 1
1000 113.924 0.1975 - 1
1001 97.65 0.177 - 1
1002 95.988 0.1975 - 1
1003 95.256 0.177 - 1
1004 95.228 0.1975 - 1
1005 109.872 0.177 - 1
1006 103.664 0.1975 - 1
1007 95.508 0.177 - 1
1008 91.98 0.177 - 1
1009 107.996 0.1975 - 1
1010 96.216 0.1975 - 1
1011 109.62 0.177 - 1
1012 87.476 0.1975 - 1
1013 109.364 0.1975 - 1
1014 99.56 0.1975 - 1
1015 83.372 0.1975 - 1
1016 83.904 0.1975 - 1
1017 109.368 0.177 - 1
1018 83.6 0.1975 - 1
1019 64.068 0.1975 - 1
1020 63.384 0.1975 - 1
1021 92.644 0.1975 - 1
1022 103.74 0.1975 - 1
1023 93.1 0.1975 - 1
1024 66.88 0.1975 - 1
1025 63.004 0.1975 - 1
1026 92.036 0.1975 - 1
1027 90.744 0.1975 - 1
1028 103.588 0.1975 - 1
1029 98.04 0.1975 - 1
1030 99.036 0.177 - 1
1031 82.232 0.1975 - 1
1032 62.7 0.1975 - 1
1033 101.612 0.1975 - 1
1034 63.504 0.226 - 1
1035 89.604 0.1975 - 1
1036 102.068 0.1975 - 1
1037 101.46 0.1975 - 1
1038 62.548 0.1975 - 1
1039 101.764 0.1975 - 1
1040 62.852 0.1975 - 1
1041 92.188 0.1975 - 1
1042 83.752 0.1975 - 1
1043 93.48 0.1975 - 1
1044 89.756 0.1975 - 1
1045 101.536 0.1975 - 1
1046 103.132 0.1975 - 1
1047 89.586 0.177 - 1
1048 86.032 0.1975 - 1
1049 92.492 0.1975 - 1
1050 89.838 0.177 - 1
1051 65.968 0.1975 - 1
1052 62.32 0.1975 - 1
1053 65.664 0.1975 - 1
1054 63.504 0.177 - 1
1055 62.748 0.177 - 1
1056 112.14 0.226 - 1
1057 115.794 0.177 - 1
1058 112.896 0.177 - 1
1059 115.542 0.177 - 1
1060 112.896 0.226 - 1
1061 115.29 0.177 - 1
1062 106.848 0.226 - 1
1063 115.038 0.177 - 1
1064 111.636 0.226 - 1
1065 104.58 0.226 - 1
1066 105.084 0.226 - 1
1067 106.092 0.226 - 1
1068 100.296 0.226 - 1
1069 101.808 0.226 - 1
1070 74.328 0.1975 - 1
1071 100.8 0.226 - 1
1072 75.088 0.1975 - 1
1073 73.872 0.1975 - 1
1074 101.304 0.226 - 1
1075 74.844 0.226 - 1
1076 74.718 0.177 - 1
1077 98.8 0.1975 - 1
1078 62.37 0.177 - 1
1079 61.488 0.226 - 1
1080 61.992 0.226 - 1
1081 61.992 0.177 - 1
1082 61.488 0.177 - 1
1083 61.256 0.1975 - 1
1084 61.56 0.1975 - 1
1085 61.712 0.1975 - 1
1086 61.636 0.1975 - 1
1087 61.864 0.1975 - 1
1088 63.252 0.177 - 1
1089 62.168 0.1975 - 1
1090 66.044 0.1975 - 1
1091 62.016 0.1975 - 1
1092 62.548 0.1975 - 1
1093 67.336 0.1975 - 1
1094 65.892 0.1975 - 1
1095 62.396 0.1975 - 1
1096 61.408 0.1975 - 1
1097 64.828 0.1975 - 1
1098 65.142 0.177 - 1
1099 65.74 0.1975 - 1
1100 65.588 0.1975 - 1
1101 65.436 0.1975 - 1
1102 64.676 0.1975 - 1
1103 64.144 0.1975 - 1
1104 62.7 0.1975 - 1
1105 65.056 0.1975 - 1
1106 62.852 0.1975 - 1
1107 63.46 0.1975 - 1
1108 63.308 0.1975 - 1
1109 63.156 0.1975 - 1
1110 63.764 0.1975 - 1
1111 67.184 0.1975 - 1
1112 74.936 0.1975 - 1
1113 67.032 0.1975 - 1
1114 74.024 0.1975 - 1
1115 70.832 0.1975 - 1
1116 74.708 0.1975 - 1
1117 96.52 0.1975 - 1
1118 123.12 0.1975 - 1
1119 125.324 0.1975 - 1
1120 125.172 0.1975 - 1
1121 125.02 0.1975 - 1
1122 124.868 0.1975 - 1
1123 124.716 0.1975 - 1
1124 122.968 0.1975 - 1
1125 122.816 0.1975 - 1
1126 122.664 0.1975 - 1
1127 124.564 0.1975 - 1
1128 101.764 0.1975 - 1
1129 63.004 0.1975 - 1
1130 65.816 0.1975 - 1
1131 91.224 0.226 - 1
1132 84.546 0.177 - 1
1133 83.664 0.226 - 1
1134 86.436 0.226 - 1
1135 82.656 0.177 - 1
1136 92.232 0.226 - 1
1137 82.908 0.177 - 1
1138 98.406 0.177 - 1
1139 95.38 0.1975 - 1
1140 97.398 0.177 - 1
1141 94.752 0.226 - 1
1142 95.76 0.226 - 1
1143 95.256 0.226 - 1
1144 94.248 0.226 - 1
1145 98.784 0.226 - 1
1146 96.894 0.177 - 1
1147 87.444 0.226 - 1
1148 86.94 0.226 - 1
1149 81.648 0.226 - 1
1150 82.152 0.226 - 1
1151 83.16 0.177 - 1
1152 83.79 0.177 - 1
1153 80.636 0.1975 - 1
1154 80.94 0.1975 - 1
1155 81.928 0.1975 - 1
1156 81.472 0.1975 - 1
1157 80.788 0.1975 - 1
1158 82.08 0.1975 - 1
1159 81.648 0.177 - 1
1160 81.9 0.177 - 1
1161 82.152 0.177 - 1
1162 83.22 0.1975 - 1
1163 84.132 0.1975 - 1
1164 84.042 0.177 - 1
1165 86.058 0.177 - 1
1166 85.05 0.177 - 1
1167 92.736 0.226 - 1
1168 73.492 0.1975 - 1
1169 94.392 0.1975 - 1
1170 94.544 0.1975 - 1
1171 76.532 0.1975 - 1
1172 72.96 0.1975 - 1
1173 71.516 0.1975 - 1
1174 71.668 0.1975 - 1
1175 76.38 0.1975 - 1
1176 71.82 0.1975 - 1
1177 71.972 0.1975 - 1
1178 76.076 0.1975 - 1
1179 93.492 0.177 - 1
1180 94.122 0.177 - 1
1181 93.744 0.226 - 1
1182 98.028 0.226 - 1
1183 96.012 0.177 - 1
1184 92.484 0.177 - 1
1185 93.744 0.177 - 1
1186 92.988 0.177 - 1
1187 72.124 0.1975 - 1
1188 69.996 0.1975 - 1
1189 71.136 0.1975 - 1
1190 70.984 0.1975 - 1
1191 72.58 0.1975 - 1
1192 72.276 0.1975 - 1
1193 73.112 0.1975 - 1
1194 72.428 0.1975 - 1
1195 43.928 0.1975 - 1
1196 43.624 0.1975 - 1
1197 63.612 0.1975 - 1
1198 43.32 0.1975 - 1
1199 43.092 0.1975 - 1
1200 42.788 0.1975 - 1
1201 42.484 0.1975 - 1
1202 42.18 0.1975 - 1
1203 41.876 0.1975 - 1
1204 41.572 0.1975 - 1
1205 41.344 0.1975 - 1
1206 41.04 0.1975 - 1
1207 40.736 0.1975 - 1
1208 40.432 0.1975 - 1
1209 67.792 0.1975 - 1
1210 67.184 0.1975 - 1
1211 40.128 0.1975 - 1
1212 39.9 0.1975 - 1
1213 39.596 0.1975 - 1
1214 39.292 0.1975 - 1
1215 38.988 0.1975 - 1
1216 38.684 0.1975 - 1
1217 38.456 0.1975 - 1
1218 38.152 0.1975 - 1
1219 37.848 0.1975 - 1
1220 37.544 0.1975 - 1
1221 37.24 0.1975 - 1
1222 37.012 0.1975 - 1
1223 36.708 0.1975 - 1
1224 63.992 0.1975 - 1
1225 64.98 0.1975 - 1
1226 178.752 0.1975 - 1
1227 176.244 0.1975 - 1
1228 177.46 0.1975 - 1
1229 175.408 0.1975 - 1
1230 176.396 0.1975 - 1
13201 312.56 86.67 N 0
13202 311.427 48.15 N 0
13203 312.446 28.89 N 0
13204 316.315 279.27 N 0
13205 339.102 202.23 N 0
13206 275.824 242.801 N 0
13207 283.204 164.783 N 0
13208 334.681 260.01 N 0
13209 341.914 182.97 N 0
13210 246.176 261.084 N 0
13211 280.392 184.043 N 0
13212 313.296 67.41 N 0
13213 341.914 96.3945 N 0
13214 341.914 25.804 N 0
13215 305.18 260.01 N 0
13216 306.276 145.523 N 0
13217 275.53 262.061 N 0
13218 276.002 89.6095 N 0
13219 304.886 223.541 N 0
13220 338.293 163.71 N 0
13221 245.947 241.824 N 0
13222 255.343 126.263 N 0
13223 340.845 115.655 N 0
13224 341.801 45.064 N 0
13225 312.387 9.63 N 0
13226 339.102 221.49 N 0
13227 308.938 125.19 N 0
13228 280.392 203.303 N 0
13229 311.121 105.93 N 0
13230 334.435 240.75 N 0
13231 336.435 144.45 N 0
13232 251.037 203.303 N 0
13233 263.221 145.523 N 0
13234 341.94 80.429 N 0
13235 342.005 61.334 N 0
13236 341.75 8.8835 N 0
13237 310.058 221.211 N 0
13238 310.892 163.978 N 0
13239 275.16 222.564 N 0
13240 251.037 184.043 N 0
13241 309.746 202.23 N 0
13242 312.56 182.97 N 0
13243 245.796 222.564 N 0
13244 253.85 164.783 N 0
13245 74.907 260.01 N 0
13246 133.617 199.473 N 0
13247 132.098 59.588 N 0
13248 102.743 131.443 N 0
13249 141.417 263.497 N 0
13250 132.965 177.525 N 0
13251 179.206 12.269 N 0
13252 102.743 112.183 N 0
13253 162.972 218.125 N 0
13254 179.669 100.485 N 0
13255 162.972 198.865 N 0
13256 16.1975 240.75 N 0
13257 16.1975 221.49 N 0
13258 32.4305 9.63 N 0
13259 14.6775 144.449 N 0
13260 112.061 279.27 N 0
13261 107.075 150.704 N 0
13262 73.3875 48.15 N 0
13263 44.0325 86.67 N 0
13264 141.417 244.237 N 0
13265 161.452 139.005 N 0
13266 162.972 179.605 N 0
13267 53.3515 298.53 N 0
13268 74.907 221.49 N 0
13269 91.1405 9.63 N 0
13270 73.3875 105.93 N 0
13271 112.061 235.806 N 0
13272 136.43 158.265 N 0
13273 122.926 35.1435 N 0
13274 103.454 92.9235 N 0
13275 184.513 256.645 N 0
13276 190.807 121.825 N 0
13277 192.327 179.605 N 0
13278 45.552 240.75 N 0
13279 77.7195 150.704 N 0
13280 149.85 15.8835 N 0
13281 102.743 73.664 N 0
13282 104.262 216.546 N 0
13283 132.098 131.443 N 0
13284 120.495 9.63 N 0
13285 102.743 54.4035 N 0
13286 200.126 218.125 N 0
13287 183.952 81.225 N 0
13288 195.139 160.344 N 0
13289 45.552 260.009 N 0
13290 14.6775 163.709 N 0
13291 14.6775 28.89 N 0
13292 44.0325 105.93 N 0
13293 74.907 240.75 N 0
13294 74.907 202.23 N 0
13295 44.0325 48.15 N 0
13296 73.3875 86.67 N 0
13297 221.682 198.865 N 0
13298 224.495 141.084 N 0
13299 221.682 179.605 N 0
13300 23.996 279.27 N 0
13301 16.1975 202.23 N 0
13302 14.6775 68.771 N 0
13303 44.0325 144.449 N 0
13304 141.417 282.758 N 0
13305 44.9005 182.969 N 0
13306 44.0325 67.41 N 0
13307 14.6775 125.19 N 0
13308 214.042 256.645 N 0
13309 246.646 98.4 N 0
13310 192.327 198.865 N 0
13311 53.3515 317.79 N 0
13312 15.5455 182.969 N 0
13313 14.6775 49.5115 N 0
13314 73.3875 125.19 N 0
13315 82.706 279.27 N 0
13316 45.552 202.23 N 0
13317 61.7855 28.89 N 0
13318 14.6775 105.93 N 0
13319 170.771 237.385 N 0
13320 161.452 119.746 N 0
13321 165.785 160.344 N 0
13322 45.552 221.49 N 0
13323 104.262 196.786 N 0
13324 61.7855 9.63 N 0
13325 48.3645 163.709 N 0
13326 103.61 169.964 N 0
13327 74.2555 182.969 N 0
13328 91.1405 28.89 N 0
13329 73.3875 67.41 N 0
13330 202.511 237.385 N 0
13331 195.139 141.084 N 0
13332 224.495 160.344 N 0
13333 133.758 100.485 N 0
13334 314.774 37.7577 N 0
13354 321.319 150.392 N 0
13357 261.626 236.421 N 0
13376 296.244 176.092 N 0
13386 283.374 138.768 N 0
13402 326.521 53.7131 N 0
13425 326.608 41.6708 N 0
13434 321.074 137.556 N 0
13472 290.107 130.575 N 0
13476 326.595 49.2981 N 0
13492 326.276 54.0355 N 0
13495 321.519 140.008 N 0
13499 284.779 224.782 N 0
13510 293.144 142.187 N 0
13517 326.511 51.92 N 0
13521 322 153.348 N 0
13530 269.47 232.643 N 0
13540 278.592 154.63 N 0
13543 123.101 127.011 N 0
13558 117.969 71.3248 N 0
13563 88.962 87.4022 N 0
13592 88.4983 86.1273 N 0
13613 86.4914 138.08 N 0
13619 120.142 162.016 N 0
13624 82.4604 151.047 N 0
13642 87.6245 140.205 N 0
13645 80.9853 135.647 N 0
13653 95.5688 206.634 N 0
13656 96.8993 41.5312 N 0
13666 88.4369 100.588 N 0
13679 150.993 168.362 N 0
13682 175.763 140.293 N 0
13696 177.169 146.562 N 0
13705 87.3942 161.363 N 0
13709 92.0591 205.221 N 0
13715 174.78 147.58 N 0
13721 91.0729 206.703 N 0
13727 73.7316 148.143 N 0
13734 79.0765 104.493 N 0
13746 179.82 139.149 N 0
13755 29.0271 78.8238 N 0
13764 68.6123 130.151 N 0
13771 83.272 151.49 N 0
13787 88.7318 175.028 N 0
13798 77.3018 149.05 N 0
13815 88.5304 39.3821 N 0
13829 179.826 140.706 N 0
13835 94.6554 41.9804 N 0
13866 100.606 31.389 N 0
13933 108.264 22.5057 N 0
14088 106.277 34.2939 N 0
14093 118.846 57.1702 N 0
14098 124.433 41.798 N 0
14103 203.827 40.7688 N 0
14144 311.024 46.0592 N 0
14159 273.664 10.9078 N 0
14179 200.462 22.8211 N 0
14194 295.056 42.5647 N 0
14235 263.511 27.3878 N 0
14247 278.378 8.02347 N 0
14263 218.066 117.565 N 0
14267 108.106 44.398 N 0
14270 118.231 21.8689 N 0
14280 277.564 9.57611 N 0
14306 119.573 111.528 N 0
14341 118.803 96.819 N 0
14371 123.97 142.269 N 0
14402 124.989 143.425 N 0
14407 280.091 22.6121 N 0
14421 273.786 33.6657 N 0
14426 175.256 141.003 N 0
14433 201.572 7.41756 N 0
14450 119.908 21.8108 N 0
14454 288.025 144.486 N 0
14484 142.959 109.375 N 0
14496 206.947 91.8626 N 0
14514 212.974 45.9913 N 0
14561 263.428 45.2239 N 0
14584 215.057 14.4005 N 0
14591 282.982 13.0023 N 0
14608 151.44 78.4743 N 0
14628 183.885 38.587 N 0
14637 278.034 109.528 N 0
14670 250.361 62.409 N 0
14678 219.423 16.9586 N 0
14684 271.133 114.807 N 0
14720 203.603 3.43601 N 0
14731 276.635 74.5329 N 0
14746 82.7451 138.678 N 0
14798 276.261 64.1613 N 0
14814 264.593 39.4665 N 0
14837 160.057 105.841 N 0
14851 293.505 80.0543 N 0
14858 189.5 55.1511 N 0
14868 289.422 120.227 N 0
14897 207.974 22.3375 N 0
14928 123.263 44.6681 N 0
14943 292.286 68.3698 N 0
14954 298.106 134.262 N 0
14977 248.093 49.4194 N 0
14986 257.367 66.8619 N 0
15021 290.554 28.637 N 0
15035 269.327 107.408 N 0
15070 256.779 71.6205 N 0
15109 69.1817 135.071 N 0
15161 173.702 36.7422 N 0
15185 292.748 62.7555 N 0
15200 120.407 82.3172 N 0
15241 294.299 61.1636 N 0
15247 248.357 18.5064 N 0
15264 228.846 38.0744 N 0
15292 203.368 35.4342 N 0
15321 90.0041 41.9847 N 0
15335 221.061 129.12 N 0
15348 196.496 63.8841 N 0
15364 134.505 72.2374 N 0
15375 258.909 7.96426 N 0
15380 284.392 71.3934 N 0
15396 233.669 24.042 N 0
15424 263.901 6.28865 N 0
15434 279.068 64.5494 N 0
15441 256.901 26.5584 N 0
15457 151.058 67.7897 N 0
15467 152.034 1.88292 N 0
15471 213.957 121.202 N 0
15477 160.705 71.1757 N 0
15512 275.797 49.3043 N 0
15523 174.076 49.8379 N 0
15539 284.454 114.128 N 0
15547 166.535 57.0731 N 0
15586 220.818 85.8166 N 0
15601 250.079 33.7099 N 0
15622 195.765 10.8115 N 0
15643 258.356 66.3535 N 0
15699 248.089 8.66958 N 0
15709 280.062 126.784 N 0
15719 272.133 54.6569 N 0
15735 64.9814 132.086 N 0
15770 221.057 62.7469 N 0
15790 88.2288 98.3159 N 0
15826 195.164 24.4106 N 0
15838 265.999 35.3773 N 0
15848 242.373 15.7005 N 0
15859 279.794 119.871 N 0
15883 166.081 0.978053 N 0
15892 149.483 177.481 N 0
15914 290.217 23.4155 N 0
15929 217.043 37.495 N 0
15943 156.708 96.9843 N 0
15979 105.92 42.2031 N 0
16009 208.59 29.0588 N 0
16032 256.134 35.4134 N 0
16056 279.128 125.191 N 0
16066 270.74 77.5424 N 0
16071 202.765 3.81193 N 0
16088 285.642 17.5391 N 0
16094 196.883 54.1249 N 0
16111 156.914 30.3136 N 0
16123 203.776 88.4984 N 0
16133 249.608 61.8461 N 0
16147 241.436 20.5544 N 0
16155 293.178 55.5756 N 0
16188 138.063 9.63134 N 0
16195 124.274 87.6154 N 0
16218 294.919 88.2857 N 0
16236 275.557 74.8013 N 0
16248 154.282 102.048 N 0
16266 293.221 37.0144 N 0
16277 198.143 104.689 N 0
16289 283.444 112.218 N 0
16299 275.989 17.7764 N 0
16307 283.836 25.0159 N 0
16333 203.437 43.5399 N 0
16347 217.556 10.5572 N 0
16360 167.76 148.282 N 0
16376 144.79 42.2492 N 0
16403 195.682 54.7911 N 0
16410 283.952 27.5284 N 0
16416 177.058 133.951 N 0
16423 229.138 65.3537 N 0
16475 235.098 133.017 N 0
16487 217.205 41.1967 N 0
16503 131.792 117.236 N 0
16507 211.184 18.8722 N 0
16524 239.045 6.56516 N 0
16529 81.3642 164.545 N 0
16539 238.16 52.5549 N 0
16566 280.113 132.769 N 0
16591 88.7363 42.441 N 0
16608 211.029 121.066 N 0
16614 247.45 111.157 N 0
16631 202.069 34.1973 N 0
16652 251.281 113.338 N 0
16657 287.638 72.0191 N 0
16666 158.459 98.2842 N 0
16679 285.808 79.5223 N 0
16687 220.186 74.1283 N 0
16716 119.495 118.394 N 0
16731 289.903 125.288 N 0
16740 174.305 25.1525 N 0
16745 101.862 40.9996 N 0
16758 138.818 86.5224 N 0
16776 291.784 100.759 N 0
16788 294.862 48.0326 N 0
16858 84.1545 171.17 N 0
16865 140.929 33.3266 N 0
16909 142.262 28.7526 N 0
16921 153.916 81.6638 N 0
16929 149.004 77.07 N 0
16944 266.252 56.2054 N 0
16985 140.26 80.1057 N 0
16995 216.789 29.9003 N 0
17031 163.666 34.5085 N 0
17045 286.913 38.2124 N 0
17060 264.638 8.87708 N 0
17071 163.805 76.6903 N 0
17076 160.43 79.1703 N 0
17087 176.891 37.6752 N 0
17101 231.24 121.104 N 0
17119 290.624 76.0678 N 0
17131 198.824 31.1209 N 0
17149 245.458 21.8062 N 0
17173 279.568 105.607 N 0
17233 243.543 11.1228 N 0
17245 185.36 45.756 N 0
17249 122.149 73.1676 N 0
17279 260.176 33.2729 N 0
17287 118.915 118.275 N 0
17308 114.55 44.5859 N 0
17317 164.215 46.2941 N 0
17323 277.277 115.703 N 0
17338 275.859 61.0028 N 0
17349 201.092 13.9408 N 0
17374 216.521 2.21545 N 0
17385 153.786 111.207 N 0
17392 224.56 79.4501 N 0
17407 173.518 56.0834 N 0
17418 238.704 115.355 N 0
17433 162.574 19.2913 N 0
17442 161.891 61.5188 N 0
17451 83.2094 137.012 N 0
17497 255.66 5.9245 N 0
17506 178.061 66.1047 N 0
17536 218.2 100.872 N 0
17542 281.595 150.703 N 0
17555 263.672 56.6759 N 0
17595 279.533 111.053 N 0
17610 274.853 47.5413 N 0
17619 278.413 71.9599 N 0
17650 292.298 112.554 N 0
17672 288.326 46.1023 N 0
17686 269.798 45.5466 N 0
17696 260.408 108.471 N 0
17709 253.919 59.986 N 0
17738 255.688 46.9206 N 0
17746 236.726 79.7562 N 0
17765 217.641 21.0124 N 0
17777 92.8228 56.8819 N 0
17781 147.46 88.4644 N 0
17801 211.145 116.991 N 0
17813 216.721 44.4611 N 0
17828 274.08 126.683 N 0
17843 240.582 68.152 N 0
17882 140.914 115.078 N 0
17889 233.234 107.717 N 0
17897 184.363 46.8156 N 0
17906 282.426 125.422 N 0
17920 92.2286 183.213 N 0
17927 213.181 5.20747 N 0
17942 63.8737 141.284 N 0
17957 243.968 7.32129 N 0
17968 247.214 76.0835 N 0
17988 187.405 57.1288 N 0
17998 182.097 56.4272 N 0
18017 292.892 22.9832 N 0
18034 245.531 77.9532 N 0
18080 280.941 54.5856 N 0
18084 248.141 74.6745 N 0
18116 285.267 24.6111 N 0
18143 277.212 3.7123 N 0
18154 289.643 135.209 N 0
18168 223.867 110.015 N 0
18174 210.243 110.267 N 0
18187 222.781 83.4477 N 0
18202 266.502 37.2561 N 0
18218 260.299 112.772 N 0
18226 291.141 111.777 N 0
18238 204.171 35.3373 N 0
18264 202.881 111.66 N 0
18272 271.716 29.3876 N 0
18278 273.289 120.763 N 0
18289 192.211 4.24388 N 0
18306 123.481 32.1886 N 0
18315 144.778 11.8163 N 0
18321 158.357 87.5934 N 0
18334 207.454 77.2124 N 0
18342 213.869 102.258 N 0
18346 141.788 42.6336 N 0
18369 255.781 39.0551 N 0
18401 221.153 7.4296 N 0
18417 281.048 144.651 N 0
18441 131.034 81.5541 N 0
18474 174.717 101.471 N 0
18491 234.665 83.6114 N 0
18511 281.583 55.051 N 0
18535 285.203 10.3101 N 0
18544 122.354 114.603 N 0
18588 178.532 67.2692 N 0
18607 199.798 38.6119 N 0
18623 163.818 2.58909 N 0
18635 259.784 111.568 N 0
18647 90.3572 41.9332 N 0
18665 283.687 53.8695 N 0
18675 229.874 108.188 N 0
18687 133.927 88.6039 N 0
18713 151.887 91.785 N 0
18738 273.409 105.13 N 0
18761 291.763 111.532 N 0
18773 159.672 47.6649 N 0
18778 247.201 11.3046 N 0
18786 245.705 54.1258 N 0
18810 182.196 24.4148 N 0
18817 204.534 61.0023 N 0
18837 177.641 56.0356 N 0
18855 101.929 39.1692 N 0
18899 68.3603 140.864 N 0
18908 243.231 49.984 N 0
18914 206.076 9.76155 N 0
18923 152.663 72.8447 N 0
18950 293.904 63.691 N 0
18974 198.56 109 N 0
18991 240.622 69.649 N 0
19002 253.869 9.38462 N 0
19009 248.289 110.712 N 0
19025 167.689 34.9193 N 0
19048 256.493 36.0374 N 0
19069 214.596 23.541 N 0
19094 245.101 29.4621 N 0
19137 195.041 53.0575 N 0
19140 242.265 23.6546 N 0
19159 126.83 114.259 N 0
19193 237.076 68.0317 N 0
19224 213.852 62.8326 N 0
19241 251.631 55.8106 N 0
19259 220.686 101.805 N 0
19302 220.145 54.5468 N 0
19344 276.614 39.951 N 0
19357 204.666 69.2074 N 0
19388 264.859 67.8047 N 0
19413 243.587 20.9278 N 0
19433 170.717 71.6308 N 0
19474 203.223 98.3009 N 0
19489 138.522 27.3048 N 0
19497 185.415 49.24 N 0
19500 209.693 112.391 N 0
19521 291.07 62.2123 N 0
19528 261.42 35.3658 N 0
19544 197.405 13.9894 N 0
19552 295.046 83.0625 N 0
19564 171.172 35.7241 N 0
19576 234.528 69.285 N 0
19590 274.4 18.9775 N 0
19600 192.118 68.5477 N 0
19614 274.42 30.6377 N 0
19634 289.719 10.0873 N 0
19643 180.148 28.3612 N 0
19668 165.06 76.525 N 0
19695 276.26 61.3041 N 0
19703 149.413 111.78 N 0
19737 284.55 107.056 N 0
19757 144.641 65.798 N 0
19766 123.752 93.6217 N 0
19779 167.273 17.7213 N 0
19786 264.869 108.614 N 0
19793 286.237 144.826 N 0
19803 239.346 112.228 N 0
19830 276.684 47.9957 N 0
19838 152.203 101.775 N 0
19872 189.16 43.8103 N 0
19877 137.679 117.257 N 0
19891 239.314 63.4282 N 0
19905 204.956 20.4283 N 0
19914 132.293 110.267 N 0
19946 154.169 58.0537 N 0
19954 178.924 58.488 N 0
19964 248.891 114.323 N 0
19983 195.247 0.921335 N 0
19990 291.219 101.583 N 0
20008 163.471 48.0851 N 0
20015 145.664 14.8228 N 0
20020 192.094 23.8369 N 0
20029 289.208 150.301 N 0
20033 86.7249 147.841 N 0
20037 263.933 51.9614 N 0
20051 243.601 150.414 N 0
20069 150.512 53.6515 N 0
20102 74.6075 136.047 N 0
20133 252.065 36.6229 N 0
20157 152.405 39.8544 N 0
20171 200.478 99.1674 N 0
20183 205.356 49.129 N 0
20200 131.965 73.6945 N 0
20214 128.683 87.2541 N 0
20224 183.404 36.7942 N 0
20229 251.94 64.0439 N 0
20245 136.503 40.1655 N 0
20284 182.438 60.5181 N 0
20291 69.4255 138.073 N 0
20313 203.664 46.1529 N 0
20329 290.146 40.2365 N 0
20342 188.853 36.0832 N 0
20349 225.826 84.9731 N 0
20359 146.353 85.8275 N 0
20373 258.214 74.2176 N 0
20384 247.977 76.8299 N 0
20406 133.305 121.717 N 0
20413 245.609 145.192 N 0
20429 256.583 51.7282 N 0
20432 223.897 46.3398 N 0
20486 214.496 44.2761 N 0
20501 275.577 37.3446 N 0
20509 256.069 93.4378 N 0
20543 189.957 28.8672 N 0
20550 177.64 35.491 N 0
20595 248.942 34.2187 N 0
20629 125.882 75.6845 N 0
20642 149.054 33.6913 N 0
20666 248.999 51.5788 N 0
20685 234.068 105.066 N 0
20711 230.917 111.274 N 0
20734 209.581 10.6205 N 0
20752 220.122 7.95501 N 0
20768 229.191 6.65669 N 0
20781 158.495 37.0742 N 0
20793 129.363 73.6963 N 0
20813 277.885 27.0031 N 0
20828 127.129 82.7439 N 0
20863 252.615 111.653 N 0
20872 229.68 127.411 N 0
20895 222.225 111.575 N 0
20907 233.667 73.7105 N 0
20913 250.854 38.9823 N 0
20944 286.253 39.7279 N 0
20960 239.857 43.5393 N 0
20989 244.229 60.7131 N 0
21015 293.143 12.204 N 0
21026 56.2014 119.979 N 0
21053 288.978 98.4382 N 0
21097 172.849 4.92822 N 0
21110 263.892 49.4022 N 0
21125 187.372 14.7433 N 0
21135 262.773 43.584 N 0
21166 256.224 80.3481 N 0
21186 261.947 19.9099 N 0
21221 268.147 28.417 N 0
21233 138.357 73.548 N 0
21247 258.762 19.6427 N 0
21277 270.024 17.4334 N 0
21289 265.64 19.6508 N 0
21325 288.92 6.87668 N 0
21336 251.558 63.0494 N 0
21342 258.895 74.0012 N 0
21346 206.829 67.0001 N 0
21358 91.4861 181.788 N 0
21364 276.136 62.9773 N 0
21388 293.277 98.5724 N 0
21393 125.305 87.1784 N 0
21409 199.613 112.159 N 0
21417 249.155 34.6339 N 0
21443 251.08 87.3454 N 0
21502 240.234 36.8663 N 0
21523 212.074 61.0016 N 0
21533 155.205 17.3852 N 0
21536 90.1728 43.972 N 0
21548 281.467 144.689 N 0
21562 219.164 120.417 N 0
21575 232.986 12.6248 N 0
21587 255.314 34.125 N 0
21608 160.321 89.2124 N 0
21618 217.276 31.0699 N 0
21642 235.654 125.761 N 0
21651 257.823 39.6966 N 0
21671 212.219 77.7244 N 0
21704 258.377 113.074 N 0
21717 264.934 3.62742 N 0
21729 286.621 71.7632 N 0
21736 251.411 52.9238 N 0
21739 150.935 92.567 N 0
21757 162.121 58.6039 N 0
21765 241.147 141.187 N 0
21781 203.927 83.6488 N 0
21806 125.462 32.6635 N 0
21816 261.91 26.5491 N 0
21838 281.002 41.8882 N 0
21855 282.683 104.251 N 0
21874 198.789 43.077 N 0
21896 274.923 10.1134 N 0
21910 204.592 36.9727 N 0
21924 145.693 94.3025 N 0
21938 185.636 28.5363 N 0
21950 190.029 108.929 N 0
21959 261.296 28.5632 N 0
21987 196.951 100.349 N 0
21997 191.896 43.9142 N 0
22000 96.6128 41.5601 N 0
22010 261.748 67.6897 N 0
22056 196.921 78.4681 N 0
22065 262.127 67.669 N 0
22116 232.028 40.8122 N 0
22148 240.927 134.823 N 0
22152 217.83 34.8185 N 0
22159 234.233 59.9731 N 0
22190 228.587 12.945 N 0
22204 138.659 86.9706 N 0
22218 238 98.415 N 0
22232 164.282 49.6589 N 0
22236 256.025 84.8993 N 0
22256 186.426 1.2395 N 0
22263 228.783 27.4075 N 0
22287 195.652 28.9539 N 0
22295 89.5977 179.385 N 0
22302 280.404 63.7932 N 0
22310 254.188 12.6065 N 0
22320 208.36 48.497 N 0
22337 238.153 51.8061 N 0
22374 214.523 50.0751 N 0
22410 240.265 125.592 N 0
22421 253.301 87.6417 N 0
22441 227.183 94.3702 N 0
22449 206.201 86.9335 N 0
22462 212.158 117.757 N 0
22488 278.857 104.848 N 0
22510 259.415 34.8512 N 0
22525 279.878 135.085 N 0
22529 262.694 52.1419 N 0
22541 152.649 45.4453 N 0
22545 140.247 12.1334 N 0
22552 237.76 5.57448 N 0
22566 205.687 17.1988 N 0
22578 259.341 74.9569 N 0
22589 234.712 69.768 N 0
22601 209.918 13.7825 N 0
22644 229.799 54.3667 N 0
22679 225.846 68.7683 N 0
22717 219.296 24.6614 N 0
22736 229.603 17.0104 N 0
22765 206.548 105.955 N 0
22776 191.974 32.7395 N 0
22783 196.263 22.4924 N 0
22790 235.535 28.039 N 0
22806 277.972 76.1455 N 0
22813 184.705 42.3134 N 0
22820 296.344 144.84 N 0
22823 279.131 118.213 N 0
22826 296.516 49.868 N 0
22834 268.856 96.938 N 0
22847 296.641 92.96 N 0
22850 318.715 249.084 N 0
22853 297.482 182.227 N 0
22856 318.437 234.329 N 0
22859 324.456 118.83 N 0
22866 295.723 187.498 N 0
22869 326.533 104.15 N 0
22874 320.693 232.228 N 0
22877 121.31 165.781 N 0
22882 90.0297 232.414 N 0
22888 119.633 160.844 N 0
22891 82.5139 136.085 N 0
22899 116.125 246.684 N 0
22905 119.376 223.409 N 0
22910 96.5216 180.072 N 0
22914 123.329 114.741 N 0
22918 103.336 29.585 N 0
22927 88.6625 102.433 N 0
22930 71.0571 129.881 N 0
22939 176.158 174.48 N 0
22943 136.473 187.766 N 0
22947 146.037 121.586 N 0
22951 163.124 102.552 N 0
22969 89.9456 227.782 N 0
22974 30.6494 250.623 N 0
22977 58.596 116.935 N 0
22980 96.9415 258.19 N 0
22983 96.3225 240.757 N 0
22989 93.4832 177.411 N 0
22996 133.887 141.324 N 0
22999 147.962 173.69 N 0
23005 150.114 168.215 N 0
23008 89.8595 245.847 N 0
23014 95.3706 226.716 N 0
23020 84.7615 135.143 N 0
23023 175.713 147.981 N 0
23038 90.251 227.317 N 0
23044 92.6258 206.565 N 0
23048 86.9235 136.916 N 0
23051 114.656 25.6419 N 0
23056 88.179 40.2285 N 0
23059 105.932 19.38 N 0
23062 180.68 209.969 N 0
23067 87.6945 136.193 N 0
23070 89.7034 234.545 N 0
23076 89.6985 241.474 N 0
23081 63.156 162.488 N 0
23084 29.1855 80.3765 N 0
23087 88.179 90.583 N 0
23090 63.2851 270.317 N 0
23096 63.156 163 N 0
23099 29.241 84.7997 N 0
23104 105.769 267.069 N 0
23110 96.057 180.454 N 0
23114 134.503 142.837 N 0
23117 67.9077 273.144 N 0
23122 67.9055 162.7 N 0
23125 29.1533 84.764 N 0
23129 95.0324 249.159 N 0
23135 93.4845 179.714 N 0
23138 88.179 101.586 N 0
23141 66.1393 173.219 N 0
23146 89.6925 197.701 N 0
23151 84.9045 134.94 N 0
23154 124.041 189.567 N 0
23157 45.4184 23.3463 N 0
23247 46.88 38.4 N 0
23250 88.4722 94.4615 N 0
23314 107.794 19.6369 N 0
23385 45.2506 19.4634 N 0
23391 108.974 20.7018 N 0
23553 115.669 20.1873 N 0
23668 87.7177 159.068 N 0
23684 135.471 3.35201 N 0
23751 206.26 67.3404 N 0
23764 270.379 55.56 N 0
23767 119.318 46.8987 N 0
23783 270.577 130.337 N 0
23817 236.034 210.162 N 0
23835 296.485 191.697 N 0
23871 230.574 56.006 N 0
23881 300.541 136.147 N 0
23885 195.883 48.4849 N 0
23899 128.618 19.605 N 0
23902 298.12 75.394 N 0
23906 47.0225 38.4 N 0
23909 59.166 58.32 N 0
23912 129.732 78.12 N 0
23915 160.955 107.364 N 0
23919 146.388 129.125 N 0
23924 163.561 89.64 N 0
23927 163.96 43.5245 N 0
23931 117.506 47.665 N 0
23935 130.919 19.38 N 0
23938 146.176 142.8 N 0
23941 133.34 76.377 N 0
23944 121.436 44.8935 N 0
23947 209.576 6.50564 N 0
23953 268.248 107.905 N 0
23956 278.75 58.2546 N 0
23960 119.563 96.7765 N 0
23964 118.502 83.863 N 0
23967 128.351 110.795 N 0
23970 145.676 53.5585 N 0
23975 224.951 42.48 N 0
23978 160.901 36.7882 N 0
23987 114.348 25.3964 N 0
23992 277.689 58.0185 N 0
23996 291.279 94.0554 N 0
24000 90.5423 42.9421 N 0
24009 102.264 44.6535 N 0
24012 267.733 127.926 N 0
24016 217.632 74.581 N 0
24019 279.595 154.596 N 0
24022 314.636 157.267 N 0
24026 151.546 153.734 N 0
24032 148.038 185.598 N 0
24036 146.495 143.961 N 0
24039 159.859 149.372 N 0
24071 295.946 1.3842 N 0
24076 257.81 137.116 N 0
24085 187.081 66.8735 N 0
24088 241.002 58.2995 N 0
24093 88.2659 95.9705 N 0
24107 118.448 104.946 N 0
24111 119.301 77.52 N 0
24114 145.414 188.681 N 0
24121 180.554 210.827 N 0
24133 202.191 96.3633 N 0
24147 201.591 60.2579 N 0
24185 233.684 55.8567 N 0
24189 220.882 74.2135 N 0
24192 131.15 75.345 N 0
24195 146.436 144.713 N 0
24202 117.506 44.8935 N 0
24205 127.115 21.525 N 0
24212 129.516 72.7865 N 0
24215 117.506 49.838 N 0
24218 265.801 101.157 N 0
24222 93.998 41.5885 N 0
24236 45.0067 36.797 N 0
24254 132.363 14.831 N 0
24258 326.228 100.533 N 0
24263 179.294 44.88 N 0
24266 57.3156 125.472 N 0
24282 239.364 59.1843 N 0
24287 251.753 120.377 N 0
24293 249.346 88.0488 N 0
24301 125.212 132.205 N 0
24308 146.991 139.834 N 0
24311 54.183 115.767 N 0
24314 194.461 90.975 N 0
24317 298.595 106.92 N 0
24320 28.6425 25.32 N 0
24323 117.58 70.3568 N 0
24328 259.46 116.074 N 0
24332 266.473 99.428 N 0
24335 28.6425 24.36 N 0
24338 28.9275 82.439 N 0
24342 107.262 29.1454 N 0
24378 324.28 115.867 N 0
24381 82.8657 139.832 N 0
24393 204.932 46.434 N 0
24396 234.142 41.7002 N 0
24400 192.374 67.2547 N 0
24411 235.237 54.4498 N 0
24431 198.781 92.9365 N 0
24438 146.889 68.0145 N 0
24441 178.804 132.572 N 0
24446 145.773 44.486 N 0
24449 88.2635 91.831 N 0
24452 263.348 114.398 N 0
24456 146.234 141.987 N 0
24459 205.746 92.4722 N 0
24468 273.918 20.0129 N 0
24474 152.333 106.92 N 0
24477 154.46 67.35 N 0
24480 240.975 55.5985 N 0
24483 192.722 61.3014 N 0
24488 210.002 55.069 N 0
24502 204.969 96.0307 N 0
24519 290.096 154.297 N 0
24525 175.389 71.16 N 0
24528 245.691 53.6037 N 0
24537 265.852 30.724 N 0
24540 226.692 92.1438 N 0
24548 164.298 82.9279 N 0
24564 193.214 97.2629 N 0
24570 167.796 92.344 N 0
24574 198.786 86.6745 N 0
24577 169.161 90.7355 N 0
24580 135.038 112.483 N 0
24583 119.4 59.4692 N 0
24587 153.013 140.673 N 0
24594 227.59 20.256 N 0
24597 182.889 110.235 N 0
24600 142.731 141.451 N 0
24603 245.293 84.3375 N 0
24607 203.452 105.693 N 0
24616 85.9173 172.848 N 0
24628 238.435 171.101 N 0
24631 279.173 151.615 N 0
24634 110.566 22.6615 N 0
24691 59.4225 78.6 N 0
24694 260.421 84.053 N 0
24697 260.264 27.609 N 0
24700 184.492 71.475 N 0
24703 266.883 59.08 N 0
24708 132.208 76.282 N 0
24711 157.572 109.996 N 0
24714 270.135 135.773 N 0
24717 275.553 58.4955 N 0
24720 205.386 53.3227 N 0
24723 252.936 108.656 N 0
24726 261.368 97.1449 N 0
24736 224.535 29.3109 N 0
24748 117.506 49.838 N 0
24751 231.855 94.7505 N 0
24754 117.506 49.029 N 0
24757 203.549 125.371 N 0
24772 204.616 70.8295 N 0
24783 208.389 94.0126 N 0
24797 88.2616 84.9088 N 0
24813 58.482 127.08 N 0
24816 122.515 70.4995 N 0
24819 28.6425 35.88 N 0
24822 228.863 96.815 N 0
24828 218.499 120.752 N 0
24831 234.505 48.4731 N 0
24867 90.2053 39.7381 N 0
24886 291.436 89.726 N 0
24889 149.954 168.728 N 0
24892 146.775 121.693 N 0
24895 241.516 77.26 N 0
24898 63.954 58.32 N 0
24901 164.878 109.596 N 0
24904 252.453 61.32 N 0
24907 115.189 66.7431 N 0
24913 189.163 60.713 N 0
24916 216.915 92.4641 N 0
24927 227.94 110.435 N 0
24934 232.116 57.5212 N 0
24962 217.052 131.334 N 0
CodeElements/EvalCT/test/ariane/netlist.pb.txt 0 → 100644
This source diff could not be displayed because it is too large. You can view the blob instead.
CodeElements/Plc_client/plc_client_os.py
......@@ -10,6 +10,7 @@ import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
import numpy as np
import traceback, sys
import random
"""plc_client_os docstrings.
......@@ -144,6 +145,7 @@ class PlacementCost(object):
"""
private function: Protobuf Netlist Parser
"""
print("#[INFO] Reading from " + self.netlist_file)
with open(self.netlist_file) as fp:
line = fp.readline()
node_cnt = 0
......@@ -245,6 +247,7 @@ class PlacementCost(object):
if node_name == "__metadata__":
# skipping metadata header
logging.info('[INFO NETLIST PARSER] skipping invalid net input')
elif attr_dict['type'][1] == 'macro':
# soft macro
# check if all required information is obtained
......@@ -387,7 +390,8 @@ class PlacementCost(object):
# store current node indx
self.port_indices.append(node_cnt-1)
# mapping connection degree to each macros
# 1. mapping connection degree to each macros
# 2. update offset based on Hard macro orientation
self.__update_connection()
# all hard macros are placed on canvas initially
......@@ -439,6 +443,9 @@ class PlacementCost(object):
# Width and Height should be defined on the same one-line
_width = float(line_item[1])
_height = float(line_item[3])
elif all(it in line_item for it in ['Area', 'stdcell', 'macros']):
# Total core area of modules
_area = float(line_item[3])
elif "Area" in line_item:
# Total core area of modules
_area = float(line_item[1])
......@@ -482,7 +489,7 @@ class PlacementCost(object):
elif all(it in line_item for it in ['MACROs'])\
and len(line_item) == 2:
_macros_cnt = int(line_item[1])
elif all(re.match(r'[0-9NEWS\.\-]+', it) for it in line_item)\
elif all(re.match(r'[0-9FNEWS\.\-]+', it) for it in line_item)\
and len(line_item) == 5:
# [node_index] [x] [y] [orientation] [fixed]
_node_plc[int(line_item[0])] = line_item[1:]
......@@ -556,9 +563,10 @@ class PlacementCost(object):
# restore placement for each module
try:
# print(sorted(list(info_dict['node_plc'].keys())))
assert sorted(self.port_indices +\
self.hard_macro_indices +\
self.soft_macro_indices) == list(info_dict['node_plc'].keys())
self.soft_macro_indices) == sorted(list(info_dict['node_plc'].keys()))
except AssertionError:
print('[ERROR PLC INDICES MISMATCH]', len(sorted(self.port_indices +\
self.hard_macro_indices +\
......@@ -572,6 +580,7 @@ class PlacementCost(object):
mod_y = float(info_dict['node_plc'][mod_idx][1])
mod_orient = info_dict['node_plc'][mod_idx][2]
mod_ifFixed = int(info_dict['node_plc'][mod_idx][3])
except Exception as e:
print('[ERROR PLC PARSER] %s' % str(e))
......@@ -589,6 +598,7 @@ class PlacementCost(object):
# set meta information
if ifReadComment:
print("[INFO] Retrieving Meta information from .plc comments")
self.set_canvas_size(info_dict['width'], info_dict['height'])
self.set_placement_grid(info_dict['columns'], info_dict['rows'])
self.set_block_name(info_dict['block'])
......@@ -619,6 +629,10 @@ class PlacementCost(object):
print("[ERROR UPDATE CONNECTION] MACRO pins not found")
continue
# also update pin offset based on macro orientation
orientation = macro.get_orientation()
self.update_macro_orientation(macro_idx, orientation)
# Soft macro
elif self.is_node_soft_macro(macro_idx):
if macro_name in self.soft_macros_to_inpins.keys():
......@@ -709,8 +723,9 @@ class PlacementCost(object):
# Retrieve current pin node position
pin_node = self.modules_w_pins[pin_idx]
pin_node_x_offset, pin_node_y_offset = pin_node.get_offset()
# Google's Plc client DOES NOT compute (node_position + pin_offset) when reading input
return (ref_node_x + pin_node_x_offset, ref_node_y + pin_node_y_offset)
# return pin_node.get_pos()
def get_wirelength(self) -> float:
"""
......@@ -726,6 +741,9 @@ class PlacementCost(object):
x_coord = []
y_coord = []
# default value of weight
weight_fact = 1.0
# NOTE: connection only defined on PORT, soft/hard macro pins
if curr_type == "PORT" and mod.get_sink():
# add source position
......@@ -739,39 +757,47 @@ class PlacementCost(object):
# retrieve sink object
sink = self.modules_w_pins[sink_idx]
# only consider placed sink
ref_sink = self.modules_w_pins[self.get_ref_node_id(sink_idx)]
if not ref_sink.get_placed_flag():
continue
# retrieve location
# ref_sink = self.modules_w_pins[self.get_ref_node_id(sink_idx)]
# if not placed, skip this edge
# if not ref_sink.get_placed_flag():
# x_coord.append(0)
# y_coord.append(0)
# else:# retrieve location
x_coord.append(self.__get_pin_position(sink_idx)[0])
y_coord.append(self.__get_pin_position(sink_idx)[1])
elif curr_type == "MACRO_PIN":
ref_mod = self.modules_w_pins[self.get_ref_node_id(mod_idx)]
if not ref_mod.get_placed_flag():
continue
# # if not placed, skip this edge
# if not ref_mod.get_placed_flag():
# continue
# get pin weight
weight_fact = mod.get_weight()
# add source position
x_coord.append(self.__get_pin_position(mod_idx)[0])
y_coord.append(self.__get_pin_position(mod_idx)[1])
if mod.get_sink():
if mod.get_weight() != 0:
norm_fact = mod.get_weight()
for input_list in mod.get_sink().values():
for sink_name in input_list:
# retrieve indx in modules_w_pins
input_idx = self.mod_name_to_indices[sink_name]
# sink_ref_mod = self.modules_w_pins[self.get_ref_node_id(mod_idx)]
# if not placed, skip this edge
# if not sink_ref_mod.get_placed_flag():
# x_coord.append(0)
# y_coord.append(0)
# else:
# retrieve location
x_coord.append(self.__get_pin_position(input_idx)[0])
y_coord.append(self.__get_pin_position(input_idx)[1])
if x_coord:
if norm_fact != 1.0:
total_hpwl += norm_fact * \
(abs(max(x_coord) - min(x_coord)) + \
abs(max(y_coord) - min(y_coord)))
else:
total_hpwl += (abs(max(x_coord) - min(x_coord))\
+ abs(max(y_coord) - min(y_coord)))
total_hpwl += weight_fact * \
(abs(max(x_coord) - min(x_coord)) + \
abs(max(y_coord) - min(y_coord)))
return total_hpwl
def abu(self, xx, n = 0.1):
......@@ -988,8 +1014,8 @@ class PlacementCost(object):
module = self.modules_w_pins[module_idx]
# skipping unplaced module
if not module.get_placed_flag():
continue
# if not module.get_placed_flag():
# continue
module_h = module.get_height()
module_w = module.get_width()
......@@ -1720,7 +1746,6 @@ class PlacementCost(object):
[IGNORE] THIS DOES NOT AFFECT DENSITY. SHOULD WE IMPLEMENT THIS AT ALL?
make soft macros as squares
"""
return
for mod_idx in self.soft_macro_indices:
mod = self.modules_w_pins[mod_idx]
mod_area = mod.get_width() * mod.get_height()
......@@ -1945,6 +1970,47 @@ class PlacementCost(object):
mod.set_orientation(orientation)
macro = self.modules_w_pins[node_idx]
macro_name = macro.get_name()
hard_macro_pins = self.hard_macros_to_inpins[macro_name]
orientation = macro.get_orientation()
# update all pin offset
for pin_name in hard_macro_pins:
pin = self.modules_w_pins[self.mod_name_to_indices[pin_name]]
x_offset, y_offset = pin.get_offset()
x_offset_org = x_offset
if orientation == "N":
pass
elif orientation == "FN":
x_offset = -x_offset
pin.set_offset(x_offset, y_offset)
elif orientation == "S":
x_offset = -x_offset
y_offset = -y_offset
pin.set_offset(x_offset, y_offset)
elif orientation == "FS":
y_offset = -y_offset
pin.set_offset(x_offset, y_offset)
elif orientation == "E":
x_offset = y_offset
y_offset = -x_offset_org
pin.set_offset(x_offset, y_offset)
elif orientation == "FE":
x_offset = -y_offset
y_offset = -x_offset_org
pin.set_offset(x_offset, y_offset)
elif orientation == "W":
x_offset = -y_offset
y_offset = x_offset_org
pin.set_offset(x_offset, y_offset)
elif orientation == "FW":
x_offset = y_offset
y_offset = x_offset_org
pin.set_offset(x_offset, y_offset)
def update_port_sides(self):
"""
Define Port "Side" by its location on canvas
......@@ -2316,6 +2382,356 @@ class PlacementCost(object):
plt.show()
plt.close('all')
'''
FD Placement below shares the same functionality as the FDPlacement/fd_placement.py
'''
def __ifOverlap(self, u_i, v_i, ux=0, uy=0, vx=0, vy=0):
'''
Detect if the two modules are overlapping or not (w/o using block structure)
'''
# extract first macro
u_side = self.modules_w_pins[u_i].get_height()
u_x1 = self.modules_w_pins[u_i].get_pos()[0] + ux - u_side/2 # left
u_x2 = self.modules_w_pins[u_i].get_pos()[0] + ux + u_side/2 # right
u_y1 = self.modules_w_pins[u_i].get_pos()[1] + uy + u_side/2 # top
u_y2 = self.modules_w_pins[u_i].get_pos()[1] + uy - u_side/2 # bottom
# extract second macro
v_side = self.modules_w_pins[v_i].get_height()
v_x1 = self.modules_w_pins[v_i].get_pos()[0] + vx - v_side/2 # left
v_x2 = self.modules_w_pins[v_i].get_pos()[0] + vx + v_side/2 # right
v_y1 = self.modules_w_pins[v_i].get_pos()[1] + vy + v_side/2 # top
v_y2 = self.modules_w_pins[v_i].get_pos()[1] + vy - v_side/2 # bottom
return u_x1 < v_x2 and u_x2 > v_x1 and u_y1 > v_y2 and u_y2 < v_y1
def __repulsive_force(self, repel_factor, node_i, node_j):
'''
Calculate repulsive force between two nodes node_i, node_j
'''
if repel_factor == 0.0:
return 0.0, 0.0
# retrieve module instance
mod_i = self.modules_w_pins[node_i]
mod_j = self.modules_w_pins[node_j]
# retrieve module position
x_i, y_i = mod_i.get_pos()
x_j, y_j = mod_j.get_pos()
# get dist between x and y
x_dist = x_i - x_j
y_dist = y_i - y_j
# get dist of hypotenuse
hypo_dist = math.sqrt(x_dist**2 + y_dist**2)
# compute force in x and y direction
if hypo_dist <= 1e-10:
return math.sqrt(repel_factor), math.sqrt(repel_factor)
else:
f_x = repel_factor * x_dist / hypo_dist
f_y = repel_factor * y_dist / hypo_dist
return f_x, f_y
def __repulsive_force_hard_macro(self, repel_factor, h_node_i, s_node_j):
'''
Calculate repulsive force between hard macro and soft macro
'''
if repel_factor == 0.0:
return 0.0, 0.0
# retrieve module instance
h_mod_i = self.modules_w_pins[h_node_i]
s_mod_j = self.modules_w_pins[s_node_j]
# retrieve module position
x_i, y_i = h_mod_i.get_pos()
x_j, y_j = s_mod_j.get_pos()
# get dist between x and y
x_dist = x_i - x_j
y_dist = y_i - y_j
# get dist of hypotenuse
hypo_dist = math.sqrt(x_dist**2 + y_dist**2)
# compute force in x and y direction
if hypo_dist <= 1e-10 or self.__ifOverlap(h_node_i, s_node_j):
return x_dist/hypo_dist * (h_mod_i.get_height()/2 + s_mod_j.get_height()/2),\
y_dist/hypo_dist * (h_mod_i.get_height()/2 + s_mod_j.get_height()/2)
else:
return 0.0, 0.0
def __attractive_force(self, io_factor, attract_factor, node_i, node_j, io_flag = True, attract_exponent = 1):
'''
Calculate repulsive force between two nodes node_i, node_j
'''
# retrieve module instance
mod_i = self.modules_w_pins[node_i]
mod_j = self.modules_w_pins[node_j]
# retrieve module position
x_i, y_i = mod_i.get_pos()
x_j, y_j = mod_j.get_pos()
# get dist between x and y
x_dist = x_i - x_j - mod_i.get_height()/2 - mod_j.get_height()/2
y_dist = y_i - y_j - mod_i.get_height()/2 - mod_j.get_height()/2
# get dist of hypotenuse
hypo_dist = math.sqrt(x_dist**2 + y_dist**2)
# compute force in x and y direction
if hypo_dist <= 0.0 or self.__ifOverlap(u_i=node_i, v_i=node_j):
return 0.0, 0.0
else:
if io_flag:
temp_f = io_factor * (hypo_dist ** attract_exponent)
else:
temp_f = attract_factor * (hypo_dist ** attract_exponent)
f_x = x_dist / hypo_dist * temp_f
f_y = y_dist / hypo_dist * temp_f
return f_x, f_y
def __centralize(self, mod_id):
'''
Pull the modules to the nearest center of the gridcell
'''
mod = self.modules_w_pins[mod_id]
mod_x, mod_y = mod.get_pos()
# compute grid cell col
# why / 2.0?
col = round((mod_x - self.grid_width / 2.0) / self.grid_width)
if (col < 0):
col = 0
elif col > self.grid_col - 1:
col = self.grid_col - 1
row = round((mod_y - self.grid_height / 2.0) / self.grid_height)
if (row < 0):
row = 0
elif row > self.grid_row - 1:
row = self.grid_row - 1
mod.set_pos((col + 0.5) * self.grid_width, (row + 0.5) * self.grid_height)
def __centeralize_circle(self, mod_id):
'''
Pull the modules to a randomized unit circle in the center of the canvas
'''
r = 1 * math.sqrt(random.random())
theta = random.random() * 2 * math.pi
centerX = self.width / 2
centerY = self.height / 2
self.modules_w_pins[mod_id].set_pos(centerX + r * math.cos(theta), centerY + r * math.sin(theta))
def __boundary_check(self, mod_id):
'''
Make sure all the clusters are placed within the canvas
'''
mod = self.modules_w_pins[mod_id]
mod_x, mod_y = mod.get_pos()
if mod_x < 0.0:
mod_x = 0.0
if mod_x > self.width:
mod_x = self.width
if mod_y < 0.0:
mod_y = 0.0
if mod_y > self.height:
mod_y = self.height
mod.set_pos(mod_x, mod_y)
def __fd_placement(self, io_factor, max_displacement, attract_factor, repel_factor):
'''
Force-directed Placement for standard-cell clusters
'''
# store x/y displacement for all soft macro disp
soft_macro_disp = {}
for mod_idx in self.soft_macro_indices:
soft_macro_disp[mod_idx] = [0.0, 0.0]
def add_displace(mod_id, x_disp, y_disp):
'''
Add the displacement
'''
soft_macro_disp[mod_id][0] += x_disp
soft_macro_disp[mod_id][1] += y_disp
def update_location(mod_id, x_disp, y_disp):
'''
Update the displacement to the coordiante
'''
x_pos, y_pos = self.modules_w_pins[mod_id].get_pos()
# logging.info("{} {} {} {}".format(x_pos, y_pos, x_disp, y_disp))
self.modules_w_pins[mod_id].set_pos(x_pos + x_disp, y_pos + y_disp)
def piecewise_sigmoid(x, shift = 50):
if x >= 0:
return 1/(math.exp(-x+shift) + 1)
else:
return -1/(math.exp(x+shift) + 1)
##SOFT_SOFT REPEL###############################################################################################
# calculate the repulsive forces
# repulsive forces between stdcell clusters
if repel_factor != 0.0:
# temp storing the soft macro count
xr_collection = [0] * len(self.modules_w_pins)
yr_collection = [0] * len(self.modules_w_pins)
# repulsive forces between stdcell clusters and stdcell clusters
for mod_i in self.soft_macro_indices:
for mod_j in self.soft_macro_indices:
if (mod_i <= mod_j):
continue
repul_x, repul_y = self.__repulsive_force(repel_factor=repel_factor,
node_i=mod_i, node_j=mod_j)
xr_collection[mod_i] += 1.0 * repul_x
yr_collection[mod_i] += 1.0 * repul_y
xr_collection[mod_j] += -1.0 * repul_x
yr_collection[mod_j] += -1.0 * repul_y
# finding max x y displacement
max_x_disp, max_y_disp = (0.0, 0.0)
for xr, yr in zip(xr_collection, yr_collection):
if xr != 0.0:
max_x_disp = max(max_x_disp, abs(xr))
if yr != 0.0:
max_y_disp = max(max_y_disp, abs(yr))
# prevent zero division
if max_x_disp == 0.0:
max_x_disp = 1.0
if max_y_disp == 0.0:
max_y_disp = 1.0
scaling = 2.0
for mod_idx in self.soft_macro_indices:
add_displace(mod_idx, scaling * xr_collection[mod_idx] / max_x_disp, scaling * yr_collection[mod_idx] / max_y_disp)
##SOFT_HARD REPEL###############################################################################################
if repel_factor != 0.0:
# temp storing the soft macro count
xr_collection = [0] * len(self.modules_w_pins)
yr_collection = [0] * len(self.modules_w_pins)
# repulsive forces between stdcell clusters and macros
for mod_i in self.soft_macro_indices:
for mod_j in self.hard_macro_indices:
repul_x, repul_y = self.__repulsive_force_hard_macro(repel_factor=repel_factor,
h_node_i=mod_i, s_node_j=mod_j)
xr_collection[mod_i] += 1.0 * repul_x
yr_collection[mod_i] += 1.0 * repul_y
# finding max x y displacement
max_x_disp, max_y_disp = (0.0, 0.0)
for xr, yr in zip(xr_collection, yr_collection):
if xr != 0.0:
max_x_disp = max(max_x_disp, abs(xr))
if yr != 0.0:
max_y_disp = max(max_y_disp, abs(yr))
# prevent zero division
if max_x_disp == 0.0:
max_x_disp = 1.0
if max_y_disp == 0.0:
max_y_disp = 1.0
scaling = 4.0
for mod_idx in self.soft_macro_indices:
add_displace(mod_idx, scaling * xr_collection[mod_idx] / max_x_disp, scaling * yr_collection[mod_idx] / max_y_disp)
##NET ATTRACT###################################################################################################
if attract_factor != 0.0:
# temp storing the soft macro count
xr_collection = [0] * len(self.modules_w_pins)
yr_collection = [0] * len(self.modules_w_pins)
# calculate the attractive force
# traverse each edge
# the adj_matrix is a symmetric matrix
for driver_pin_idx, driver_pin in enumerate(self.modules_w_pins):
# only for soft macro
if driver_pin_idx in self.soft_macro_pin_indices and driver_pin.get_sink():
driver_mod_idx = self.get_ref_node_id(driver_pin_idx)
for sink_pin_name in driver_pin.get_sink().keys():
sink_mod_idx = self.mod_name_to_indices[sink_pin_name]
# if overlapped, dont attract further
if self.__ifOverlap(driver_mod_idx, sink_mod_idx):
continue
attrac_x, attrac_y = self.__attractive_force(io_factor=io_factor,
attract_factor=attract_factor,
node_i=driver_mod_idx,
node_j=sink_mod_idx
)
# if overlapped, dont attract further
if self.__ifOverlap(driver_mod_idx, sink_mod_idx, attrac_x, attrac_y):
continue
xr_collection[driver_mod_idx] += piecewise_sigmoid(-1.0 * attrac_x)
yr_collection[driver_mod_idx] += piecewise_sigmoid(-1.0 * attrac_y)
# finding max x y displacement
max_x_disp, max_y_disp = (0.0, 0.0)
for xr, yr in zip(xr_collection, yr_collection):
if xr != 0.0:
max_x_disp = max(max_x_disp, abs(xr))
if yr != 0.0:
max_y_disp = max(max_y_disp, abs(yr))
# prevent zero division
if max_x_disp == 0.0:
max_x_disp = 1.0
if max_y_disp == 0.0:
max_y_disp = 1.0
# not too much attract
scaling = 0.1
for mod_idx in self.soft_macro_indices:
add_displace(mod_idx, scaling * xr_collection[mod_idx] / max_x_disp, scaling * yr_collection[mod_idx] / max_y_disp)
for mod_idx in soft_macro_disp.keys():
# push all the macros to the nearest center of gridcell
update_location(mod_idx, *soft_macro_disp[mod_idx])
# Moved to here to save a for loop
# Based on our understanding, the stdcell clusters can be placed
# at any place in the canvas instead of the center of gridcells
self.__boundary_check(mod_idx)
def optimize_stdcells(self, use_current_loc, move_stdcells, move_macros,
log_scale_conns, use_sizes, io_factor, num_steps,
max_move_distance, attract_factor, repel_factor):
# initialize the position for all the macros and stdcell clusters
# YW: here I will ignore centering Macros since CT placement does that
for mod_idx in self.soft_macro_indices:
self.__centeralize_circle(mod_id = mod_idx)
for epoch_id, iterations in enumerate(num_steps):
logging.info("#[OPTIMIZING STDCELs] at num_step {}:".format(str(epoch_id)))
print("[INFO] max_displaccment = ", max_move_distance[epoch_id])
print("[INFO] attractive_factor = ", attract_factor[epoch_id])
print("[INFO] repulsive_factor = ", repel_factor[epoch_id])
print("[INFO] io_factor = ", io_factor)
print("[INFO] number of iteration = ", iterations)
for iter in range(iterations):
logging.info("# iteration {}:".format(str(iter)))
self.__fd_placement(io_factor=io_factor,
max_displacement=max_move_distance[epoch_id],
attract_factor=attract_factor[epoch_id],
repel_factor=repel_factor[epoch_id])
self.save_placement('epoch_{}.plc'.format(str(epoch_id)))
# Board Entity Definition
class Port:
......@@ -2336,6 +2752,12 @@ class PlacementCost(object):
def get_orientation(self):
return self.orientation
def get_height(self):
return 0
def get_width(self):
return 0
def add_connection(self, module_name):
# NOTE: assume PORT names does not contain slash
......@@ -2699,6 +3121,10 @@ class PlacementCost(object):
def get_offset(self):
return self.x_offset, self.y_offset
def set_offset(self, x_offset, y_offset):
self.x_offset = x_offset
self.y_offset = y_offset
def get_name(self):
return self.name
......@@ -2734,19 +3160,6 @@ class PlacementCost(object):
def get_type(self):
return "MACRO_PIN"
# TODO finish this
# class StandardCell:
# def __init__( self, name,
# x = 0.0, y = 0.0, weight = 1.0):
# self.name = name
# self.x = float(x)
# self.y = float(y)
# self.x_offset = 0.0 # not used
# self.y_offset = 0.0 # not used
# self.macro_name = macro_name
# self.weight = weight
# self.sink = {}
def main():
test_netlist_dir = './Plc_client/test/'+\
'ariane_68_1.3'
......
CodeElements/Plc_client/plc_client_os_test.py
......@@ -4,7 +4,6 @@ import pandas as pd
import sys
import os
import traceback
import argparse
import math
import re
from random import randrange
......@@ -56,6 +55,18 @@ Example:
--marh 7.143\
--marv 8.339\
--smooth 2
$ python3 -m Plc_client.plc_client_os_test --netlist ./Plc_client/test/g657_ub5_nruns10_c5_r3_v3_rc1/netlist.pb.txt\
--plc ./Plc_client/test/g657_ub5_nruns10_c5_r3_v3_rc1/legalized.plc\
--width 1357.360\
--height 1356.880\
--col 22\
--row 30\
--rpmh 11.285\
--rpmv 12.605\
--marh 7.143\
--marv 8.339\
--smooth 0
$ python3 -m Plc_client.plc_client_os_test --netlist ./Plc_client/test/0P2M0m/netlist.pb.txt\
--width 500\
......@@ -68,6 +79,18 @@ Example:
--marv 5\
--smooth 2
$ python3 -m Plc_client.plc_client_os_test --netlist ./Plc_client/test/ariane_fd/ariane.pb.txt\
--plc ./Plc_client/test/ariane_fd/ariane.plc\
--width 1599.99\
--height 1598.8\
--col 27\
--row 23\
--rpmh 70.330\
--rpmv 74.510\
--marh 51.790\
--marv 51.790\
--smooth 2
Todo:
* Clean up code
* Extract argument from command line
......@@ -214,7 +237,7 @@ class PlacementCostTest():
print(" +++ TEST METADATA: PASS +++")
print(" +++++++++++++++++++++++++++")
def view_canvas(self, ifInital, ifReadComment):
def view_canvas(self, ifInital=False, ifReadComment=False):
print("############################ VIEW CANVAS ############################")
self.plc_os = plc_client_os.PlacementCost(netlist_file=self.NETLIST_PATH,
macro_macro_x_spacing=50,
......@@ -229,8 +252,16 @@ class PlacementCostTest():
ifInital=ifInital,
ifValidate=False,
ifReadComment=ifReadComment)
self.plc_os.set_routes_per_micron(self.RPMH, self.RPMV)
self.plc_os.set_macro_routing_allocation(self.MARH, self.MARV)
self.plc_os.set_congestion_smooth_range(self.SMOOTH)
self.plc_os.set_canvas_size(self.CANVAS_WIDTH, self.CANVAS_HEIGHT)
self.plc_os.set_placement_grid(self.GRID_COL, self.GRID_ROW)
# show canvas
self.plc_os.make_soft_macros_square()
self.plc_os.display_canvas(annotate=False, amplify=False)
def test_proxy_cost(self):
print("############################ TEST PROXY COST ############################")
......@@ -245,6 +276,8 @@ class PlacementCostTest():
self.plc.get_overlap_threshold()
print("overlap_threshold default", self.plc.get_overlap_threshold())
# self.plc.make_soft_macros_square()
if self.PLC_PATH:
print("#[PLC FILE FOUND] Loading info from .plc file")
self.plc_os.set_canvas_boundary_check(False)
......@@ -256,23 +289,34 @@ class PlacementCostTest():
self.plc.restore_placement(self.PLC_PATH)
else:
print("#[PLC FILE MISSING] Using only netlist info")
# self.plc.make_soft_macros_square()
self.plc.set_routes_per_micron(self.RPMH, self.RPMV)
self.plc_os.set_routes_per_micron(self.RPMH, self.RPMV)
# self.plc.make_soft_macros_square()
self.plc.set_macro_routing_allocation(self.MARH, self.MARV)
self.plc_os.set_macro_routing_allocation(self.MARH, self.MARV)
# self.plc.make_soft_macros_square()
self.plc.set_congestion_smooth_range(self.SMOOTH)
self.plc_os.set_congestion_smooth_range(self.SMOOTH)
self.plc.set_canvas_size(self.CANVAS_WIDTH, self.CANVAS_HEIGHT)
# self.plc.make_soft_macros_square()
self.plc.set_placement_grid(self.GRID_COL, self.GRID_ROW)
# self.plc.make_soft_macros_square() # in effect
self.plc.set_canvas_size(self.CANVAS_WIDTH, self.CANVAS_HEIGHT)
self.plc_os.set_canvas_size(self.CANVAS_WIDTH, self.CANVAS_HEIGHT)
self.plc_os.set_placement_grid(self.GRID_COL, self.GRID_ROW)
self.plc.make_soft_macros_square()
self.plc_os.make_soft_macros_square()
# self.plc.make_soft_macros_square()
# self.plc_os.make_soft_macros_square()
# [IGNORE] create_blockage must be defined BEFORE set_canvas_size
# and set_placement_grid in order to be considered on the canvas
......@@ -297,7 +341,7 @@ class PlacementCostTest():
str(self.plc.get_cost()), self.plc_os.get_cost()))
print("GL WIRELENGTH: ", self.plc.get_wirelength())
print("OS WIRELENGTH: ", self.plc_os.get_wirelength())
exit(1)
# exit(1)
# Density
try:
......@@ -421,19 +465,11 @@ class PlacementCostTest():
except Exception as e:
print("[ERROR WIRELENGTH] Discrepancies found when computing wirelength -- GL {}, OS {}".format(
str(self.plc.get_cost()), self.plc_os.get_cost()))
# if remove all soft macros
# soft_macro_indices = [
# m for m in self.plc.get_macro_indices() if self.plc.is_node_soft_macro(m)
# ]
# for mod_idx in soft_macro_indices:
# self.plc_os.unplace_node(mod_idx)
# self.plc.unplace_node(mod_idx)
print("GL WIRELENGTH: ", self.plc.get_wirelength())
print("OS WIRELENGTH: ", self.plc_os.get_wirelength())
def test_proxy_density(self):
print("############################ TEST PROXY DENSITY ############################")
# Google's Binary Executable
......@@ -718,18 +754,6 @@ class PlacementCostTest():
init_placement=self.PLC_PATH
)
if self.PLC_PATH:
print("#[PLC FILE FOUND] Loading info from .plc file")
self.plc_util_os.set_canvas_boundary_check(False)
self.plc_util_os.restore_placement(self.PLC_PATH,
ifInital=True,
ifValidate=True,
ifReadComment=False)
self.plc_util.set_canvas_boundary_check(False)
self.plc_util.restore_placement(self.PLC_PATH)
else:
print("#[PLC FILE MISSING] Using only netlist info")
self.extractor = observation_extractor.ObservationExtractor(
plc=self.plc_util, observation_config=self._observation_config
)
......@@ -843,6 +867,42 @@ class PlacementCostTest():
self.plc_util_os.display_canvas(annotate=False)
def test_fd(self):
print("############################ TEST GOOGLE's FD Placer ############################")
self.plc_util = placement_util.create_placement_cost(
plc_client=plc_client,
netlist_file=self.NETLIST_PATH,
init_placement=self.PLC_PATH
)
self.plc_util_os = placement_util.create_placement_cost(
plc_client=plc_client_os,
netlist_file=self.NETLIST_PATH,
init_placement=self.PLC_PATH
)
self.plc_util.set_routes_per_micron(self.RPMH, self.RPMV)
self.plc_util_os.set_routes_per_micron(self.RPMH, self.RPMV)
self.plc_util.set_macro_routing_allocation(self.MARH, self.MARV)
self.plc_util_os.set_macro_routing_allocation(self.MARH, self.MARV)
self.plc_util.set_congestion_smooth_range(self.SMOOTH)
self.plc_util_os.set_congestion_smooth_range(self.SMOOTH)
self.plc_util.set_canvas_size(self.CANVAS_WIDTH, self.CANVAS_HEIGHT)
self.plc_util.set_placement_grid(self.GRID_COL, self.GRID_ROW)
self.plc_util_os.set_canvas_size(self.CANVAS_WIDTH, self.CANVAS_HEIGHT)
self.plc_util_os.set_placement_grid(self.GRID_COL, self.GRID_ROW)
placement_util.fd_placement_schedule(self.plc_util)
for node_index in placement_util.nodes_of_types(self.plc_util, ['MACRO']):
x_pos, y_pos = self.plc_util.get_node_location(node_index)
self.plc_util_os.set_soft_macro_position(node_index, x_pos, y_pos)
self.plc_util_os.display_canvas(annotate=False, amplify=False)
def test_environment(self):
print("############################ TEST ENVIRONMENT ############################")
env = environment.CircuitEnv(
......@@ -912,6 +972,26 @@ class PlacementCostTest():
print(" +++ TEST ENVIRONMENT: PASS +++")
print(" ++++++++++++++++++++++++++++++")
def test_fd_placement(self):
print("############################ TEST FDPLACEMENT ############################")
self.plc_util_os = placement_util.create_placement_cost(
plc_client=plc_client_os,
netlist_file=self.NETLIST_PATH,
init_placement=self.PLC_PATH
)
# placement util is incapable of setting routing resources
self.plc_util_os.set_routes_per_micron(self.RPMH, self.RPMV)
self.plc_util_os.set_macro_routing_allocation(self.MARH, self.MARV)
self.plc_util_os.set_congestion_smooth_range(self.SMOOTH)
self.plc_util_os.set_canvas_size(self.CANVAS_WIDTH, self.CANVAS_HEIGHT)
self.plc_util_os.set_placement_grid(self.GRID_COL, self.GRID_ROW)
placement_util.fd_placement_schedule(self.plc_util_os)
self.plc_util_os.display_canvas(annotate=False, amplify=False)
def parse_flags(argv):
parser = argparse_flags.ArgumentParser(
......@@ -970,7 +1050,8 @@ def main(args):
Uncomment any available tests
"""
# PCT.test_metadata()
PCT.test_proxy_cost()
# PCT.test_proxy_cost()
# PCT.test_proxy_hpwl()
# PCT.test_proxy_density()
# PCT.test_proxy_congestion()
# PCT.test_placement_util(keep_save_file=False)
......@@ -978,7 +1059,9 @@ def main(args):
# PCT.test_miscellaneous()
# PCT.test_observation_extractor()
# PCT.view_canvas()
# PCT.test_fd()
# PCT.test_environment()
PCT.test_fd_placement()
if __name__ == '__main__':
......
CodeElements/Plc_client/stat_test.py 0 → 100644
import re
import os, sys
import math
import numpy as np
import logging
import matplotlib.pyplot as plt
import pandas as pd
from torch import argmax
# disable scientific notation
np.set_printoptions(suppress=True)
# print full array
np.set_printoptions(threshold=sys.maxsize)
'''
META INFO
'''
# Directory that stores all plc file (must come from the same netlist)
PLC_DIR = "Plc_client/test/ariane"
assert os.path.isdir(PLC_DIR)
# Top X% of largest movement range
TOP_X = 1
# List to store every plc coordinate
PLC_COORD = []
# scan through every .plc file
for __, __, files in os.walk(PLC_DIR):
for plc_file in files:
if plc_file.endswith((".plc")):
plc_pth = os.path.join(PLC_DIR, plc_file)
print("[INFO] Reading plc file {}".format(plc_pth))
# store in numpy array for ease of computation
temp_coord = np.empty((1,2), float)
for cnt, line in enumerate(open(plc_pth, 'r')):
line_item = re.findall(r'[0-9A-Za-z\.\-]+', line)
# skip empty lines
if len(line_item) == 0:
continue
if all(re.match(r'[0-9FNEWS\.\-]+', it) for it in line_item)\
and len(line_item) == 5:
# extract pos
temp_coord = np.append(temp_coord, np.array([[float(line_item[1]),float(line_item[2])]]), axis=0)
# remove header row
temp_coord = temp_coord[1:, :]
# make sure every plc is aligned
if PLC_COORD:
assert PLC_COORD[-1].shape == temp_coord.shape
PLC_COORD.append(temp_coord)
print(temp_coord)
del temp_coord
# store all pair-wise distance
abs_dist_plc = np.empty((PLC_COORD[-1].shape[0],1), float)
# pair-wise distance of all plc files
for i in range(len(PLC_COORD)):
for j in range(len(PLC_COORD)):
if i == j:
continue
# find x/y position diff
diff_coord = PLC_COORD[i] - PLC_COORD[j]
# x_diff^2, y_diff^2
diff_coord = np.power(diff_coord, 2)
# sqrt(x_diff^2 + y_diff^2)
abs_dist_coord = np.sqrt(diff_coord[:, 0] + diff_coord[:, 1])
abs_dist_plc = np.append(abs_dist_plc, abs_dist_coord.reshape((-1, 1)), axis=1)
# remove header col
abs_dist_plc = abs_dist_plc[:, 1:]
TOP_N = int(math.floor(abs_dist_plc.shape[0] * (TOP_X/100.0)))
print(TOP_N)
'''
MACRO placement maximum distance + visual
'''
# across all the plc diff, the max distance [row wise]
max_dist = np.amax(abs_dist_plc, axis=1)
# top-n max distance
topn_max_dist_idx = np.argpartition(max_dist, -TOP_N)[-TOP_N:]
topn_max_dist_val = np.take(max_dist, topn_max_dist_idx)
x = range(topn_max_dist_val.shape[0])
y = topn_max_dist_val
n = topn_max_dist_idx
fig, ax = plt.subplots()
ax.set_title("Top {}% Maximum Placement Range".format(TOP_X))
ax.scatter(x, y, c = 'b')
ax.set_xlabel("module index")
ax.set_ylabel("distance")
for i, txt in enumerate(n):
ax.annotate(txt, (x[i], y[i]))
plt.show()
'''
MACRO placement box plot visual
'''
abs_dist_plc_df = pd.DataFrame(data=abs_dist_plc)
topn_max_dist_df = abs_dist_plc_df.iloc[topn_max_dist_idx, :]
topn_max_dist_df.T.boxplot()
plt.title("Top {}% Placement Range".format(TOP_X))
plt.xlabel("module index")
plt.ylabel("distance")
plt.show()
'''
MACRO placement variane test
'''
'''
MACRO placement std dev test
'''
CodeElements/StatTest/proxy_corr_test.py 0 → 100755
import re
import os, sys
import math
import numpy as np
import logging
import matplotlib.pyplot as plt
import pandas as pd
import pandas as pd
SHEET_ID = '1dtG4uHzdw-Lfe_Vcm5uBRNjjxXNA4gmVarTr86hjYVo'
SHEET_NAME = 'Proxy_Cost_Comparison'
url = f'https://docs.google.com/spreadsheets/d/{SHEET_ID}/gviz/tq?tqx=out:csv&sheet={SHEET_NAME}'
proxy_df = pd.read_csv(url)
proxy_df = proxy_df.loc[:, ~proxy_df.isnull().all()]
print(proxy_df.columns)
proxy_df['postCTS_Congestion (V)'] = proxy_df['postCTS_Congestion (V)'].str.rstrip('%').astype('float') / 100.0
# compute correlation between postRouteOpt_std_cell_area and density_cost
print("postRoute_std_cell_area VS. Density_Cost",
proxy_df["postRoute_std_cell_area (um^2)"].corr(proxy_df["Density_Cost"]))
print("postRouteOpt_std_cell_area VS. Density_Cost",
proxy_df["postRouteOpt_std_cell_area (um^2)"].corr(proxy_df["Density_Cost"]))
# compute correlation between postRouteOpt_wirelength (um) and wirelength_cost
print("postRoute_wirelength VS. Wirelength_Cost",
proxy_df["postRoute_wirelength (um)"].corr(proxy_df["Wirelength_Cost"]))
print("postRouteOpt_wirelength VS. Wirelength_Cost",
proxy_df["postRouteOpt_wirelength (um)"].corr(proxy_df["Wirelength_Cost"]))
# compute correlation between postCTS_Congestion and congestion_cost
print("postCTS_Congestion VS. Congestion_Cost",
proxy_df["postCTS_Congestion (V)"].corr(proxy_df["Congestion_Cost"]))
\ No newline at end of file
CodeElements/StatTest/stat_test.py 0 → 100755
import re
import os, sys
import math
import numpy as np
import logging
import matplotlib.pyplot as plt
import pandas as pd
from StatTest import util
# disable scientific notation
np.set_printoptions(suppress=True)
# print full array
np.set_printoptions(threshold=sys.maxsize)
"""Statistical Test docstrings.
* Robustness
* Use EvalCT for fixed policy rollout on the same training
set but different initialization.
* Stability
* Macro Movement Range
* Additional Note
* Loading weight back for training
"""
######################## META INFO ########################
# Directory that stores all plc file (must come from the same netlist)
PLC_DIR = "StatTest/test/flow2_68_1.3_ct"
PLC_PATH_COLLECTION = []
assert os.path.isdir(PLC_DIR)
# Top X% of largest movement range
TOP_X = 5
# List to store every plc coordinate
PLC_COORD = []
# hold hard macro, soft macro, port count
def init_method(plc_dir):
"""
Scan through every .plc file
"""
for __, __, files in os.walk(plc_dir):
for plc_file in files:
if plc_file.endswith((".plc")):
plc_pth = os.path.join(plc_dir, plc_file)
# plc path
PLC_PATH_COLLECTION.append(plc_pth)
print("#[INFO] Reading plc file {}".format(plc_pth))
# store in numpy array for ease of computation
temp_coord = np.empty((1,2), float)
for cnt, line in enumerate(open(plc_pth, 'r')):
line_item = re.findall(r'[0-9A-Za-z\.\-]+', line)
# skip empty lines
if len(line_item) == 0:
continue
if all(re.match(r'[0-9FNEWS\.\-]+', it) for it in line_item)\
and len(line_item) == 5:
# extract pos
temp_coord = np.append(temp_coord, np.array([[float(line_item[1]),float(line_item[2])]]), axis=0)
elif all(it in line_item for it in ['HARD', 'MACROs'])\
and len(line_item) == 3:
hard_macros_cnt = int(line_item[2])
elif all(it in line_item for it in ['PORTs'])\
and len(line_item) == 2:
ports_cnt = int(line_item[1])
elif all(it in line_item for it in ['SOFT', 'MACROs'])\
and len(line_item) == 3:
soft_macros_cnt = int(line_item[2])
# remove header row
temp_coord = temp_coord[1:, :]
# make sure every plc is aligned
if PLC_COORD:
assert PLC_COORD[-1].shape == temp_coord.shape
assert temp_coord.shape[0] == hard_macros_cnt + soft_macros_cnt + ports_cnt
PLC_COORD.append(temp_coord)
# print(temp_coord)
del temp_coord
return ports_cnt, hard_macros_cnt, soft_macros_cnt
def get_abs_dist():
# store all pair-wise distance
abs_dist_plc = np.empty((PLC_COORD[-1].shape[0],1), float)
# pair-wise distance of all plc files
for i in range(len(PLC_COORD)):
for j in range(len(PLC_COORD)):
if i == j:
continue
# find x/y position diff
diff_coord = PLC_COORD[i] - PLC_COORD[j]
# x_diff^2, y_diff^2
diff_coord = np.power(diff_coord, 2)
# sqrt(x_diff^2 + y_diff^2)
abs_dist_coord = np.sqrt(diff_coord[:, 0] + diff_coord[:, 1])
abs_dist_plc = np.append(abs_dist_plc, abs_dist_coord.reshape((-1, 1)), axis=1)
# remove header col
return abs_dist_plc[:, 1:]
def main():
ports_cnt, hard_macros_cnt, soft_macros_cnt = init_method(PLC_DIR)
abs_dist_plc = get_abs_dist()
print(hard_macros_cnt, ports_cnt, soft_macros_cnt)
hard_abs_dist_plc = abs_dist_plc[ports_cnt:(hard_macros_cnt+ports_cnt), :]
soft_abs_dist_plc = abs_dist_plc[ports_cnt+hard_macros_cnt:hard_macros_cnt+ports_cnt+soft_macros_cnt, :]
# PORT_IDX = list(range(0, ports_cnt, 1))
# HARD_MACRO_IDX = list(range(ports_cnt, hard_macros_cnt+ports_cnt, 1))
# SOFT_MACRO_IDX = list(range(hard_macros_cnt+ports_cnt, hard_macros_cnt+soft_macros_cnt+ports_cnt, 1))
# top n hard macro
HM_TOP_N = int(math.floor(hard_abs_dist_plc.shape[0] * (TOP_X/100.0)))
# top n soft macro
SM_TOP_N = int(math.floor(soft_abs_dist_plc.shape[0] * (TOP_X/100.0)))
print("[INFO] Using TOP {}% Largest Hard Macro Movement --- {} Macros in total.".format(TOP_X, HM_TOP_N))
print("[INFO] Using TOP {}% Largest Soft Macro Movement --- {} Macros in total.".format(TOP_X, SM_TOP_N))
############ HARD MACRO placement range maximum distance + visual ###############
# across all the plc diff, the max distance [row wise]
hm_max_dist = np.amax(hard_abs_dist_plc, axis=1)
# top-n max distance
hm_topn_max_dist_idx = np.argpartition(hm_max_dist, -HM_TOP_N)[-HM_TOP_N:]
hm_topn_max_dist_val = np.take(hm_max_dist, hm_topn_max_dist_idx)
x = range(hm_topn_max_dist_val.shape[0])
y = hm_topn_max_dist_val
n = hm_topn_max_dist_idx
fig, ax = plt.subplots()
ax.set_title("Top {}% Hard Macro Maximum Placement Range".format(TOP_X))
ax.scatter(x, y, c = 'b')
ax.set_xlabel("module index")
ax.set_ylabel("distance")
for i, txt in enumerate(n):
ax.annotate(txt, (x[i], y[i]))
plt.show()
############ SOFT MACRO placement range maximum distance + visual ###############
# across all the plc diff, the max distance [row wise]
sm_max_dist = np.amax(soft_abs_dist_plc, axis=1)
# top-n max distance
sm_topn_max_dist_idx = np.argpartition(sm_max_dist, -SM_TOP_N)[-SM_TOP_N:]
sm_topn_max_dist_val = np.take(sm_max_dist, sm_topn_max_dist_idx)
x = range(sm_topn_max_dist_val.shape[0])
y = sm_topn_max_dist_val
n = sm_topn_max_dist_idx
fig, ax = plt.subplots()
ax.set_title("Top {}% Soft Macro Maximum Placement Range".format(TOP_X))
ax.scatter(x, y, c = 'b')
ax.set_xlabel("module index")
ax.set_ylabel("distance")
for i, txt in enumerate(n):
ax.annotate(txt, (x[i], y[i]))
plt.show()
######################## HARD MACRO placement range box plot visual #############
hard_abs_dist_plc_df = pd.DataFrame(data=hard_abs_dist_plc)
hm_topn_max_dist_df = hard_abs_dist_plc_df.iloc[hm_topn_max_dist_idx, :]
hm_topn_max_dist_df.T.boxplot()
plt.title("Top {}% Hard Macro Placement Range".format(TOP_X))
plt.xlabel("module index")
plt.ylabel("distance")
plt.show()
######################## SOFT MACRO placement range box plot visual #############
soft_abs_dist_plc_df = pd.DataFrame(data=soft_abs_dist_plc)
sm_topn_max_dist_df = soft_abs_dist_plc_df.iloc[sm_topn_max_dist_idx, :]
sm_topn_max_dist_df.T.boxplot()
plt.title("Top {}% Soft Macro Placement Range".format(TOP_X))
plt.xlabel("module index")
plt.ylabel("distance")
plt.show()
######################## Density Heatmap ########################
util.extract_density_map(
os.path.join(PLC_DIR, "netlist.pb.txt"),
PLC_PATH_COLLECTION[0],
ifshow=True
)
######################## Congestion Heatmap #####################
util.extract_congestion_map(
os.path.join(PLC_DIR, "netlist.pb.txt"),
PLC_PATH_COLLECTION[0],
marh=7.143,
marv=8.339,
rpmh=11.285,
rpmv=12.605,
congestion_smooth_range=2,
ifshow=True
)
######################## L1 Norm & SSIM #####################
# pair-wise distance of all plc files
DENS_SMI = []
DENS_L1 = []
VCONG_SMI = []
VCONG_L1 = []
HCONG_SMI = []
HCONG_L1 = []
for i in range(len(PLC_PATH_COLLECTION)):
for j in range(len(PLC_PATH_COLLECTION)):
if i == j:
continue
print("####### Heat Map Comparison between {} and {} #######".format(os.path.basename(PLC_PATH_COLLECTION[i])
,os.path.basename(PLC_PATH_COLLECTION[j])))
dens_i = util.extract_density_map(os.path.join(PLC_DIR, "netlist.pb.txt"),
PLC_PATH_COLLECTION[i],
ifshow=False)
dens_j = util.extract_density_map(os.path.join(PLC_DIR, "netlist.pb.txt"),
PLC_PATH_COLLECTION[j],
ifshow=False)
print("#[INFO] Density map SMI: {}".format(util.SSIM(dens_i, dens_j)))
print("#[INFO] Density map L1 Dist: {}".format(util.l1_norm(dens_i, dens_j)))
DENS_SMI.append(util.SSIM(dens_i, dens_j))
DENS_L1.append(util.l1_norm(dens_i, dens_j))
vcong_i, hcong_i = util.extract_congestion_map(
os.path.join(PLC_DIR, "netlist.pb.txt"),
PLC_PATH_COLLECTION[i],
marh=7.143,
marv=8.339,
rpmh=11.285,
rpmv=12.605,
congestion_smooth_range=2,
ifshow=False
)
vcong_j, hcong_j = util.extract_congestion_map(
os.path.join(PLC_DIR, "netlist.pb.txt"),
PLC_PATH_COLLECTION[j],
marh=7.143,
marv=8.339,
rpmh=11.285,
rpmv=12.605,
congestion_smooth_range=2,
ifshow=False
)
print("#[INFO] V Congestion map SMI: {}".format(util.SSIM(vcong_i, vcong_j)))
print("#[INFO] V Congestion map L1 Dist: {}".format(util.l1_norm(vcong_i, vcong_j)))
print("#[INFO] H Congestion map SMI: {}".format(util.SSIM(hcong_i, hcong_j)))
print("#[INFO] H Congestion map L1 Dist: {}".format(util.l1_norm(hcong_i, hcong_j)))
VCONG_SMI.append(util.SSIM(vcong_i, vcong_j))
VCONG_L1.append(util.l1_norm(vcong_i, vcong_j))
HCONG_SMI.append(util.SSIM(hcong_i,hcong_j))
HCONG_L1.append(util.l1_norm(hcong_i, hcong_j))
print("DENS_SMI Range ({} ~ {})".format(min(DENS_SMI), max(DENS_SMI)))
print("DENS_L1 Range ({} ~ {})".format(min(DENS_L1), max(DENS_L1)))
print("VCONG_SMI Range ({} ~ {})".format(min(VCONG_SMI), max(VCONG_SMI)))
print("VCONG_L1 Range ({} ~ {})".format(min(VCONG_L1), max(VCONG_L1)))
print("HCONG_SMI Range ({} ~ {})".format(min(HCONG_SMI), max(HCONG_SMI)))
print("HCONG_L1 Range ({} ~ {})".format(min(HCONG_L1), max(HCONG_L1)))
if __name__ == "__main__":
main()
\ No newline at end of file
CodeElements/StatTest/util.py 0 → 100644
import os, sys
import pandas as pd
import numpy as np
import seaborn as sns
from Plc_client import plc_client_os
from Plc_client import placement_util_os as placement_util
import matplotlib.pyplot as plt
from skimage.metrics import structural_similarity
def heatmap(arr, title, show=True):
"""
util function for generating heat map from numpy arrays
"""
sns.set()
ax = sns.heatmap(arr, vmin=0, vmax=1, cmap="YlGnBu")
ax.set_title(title)
ax.set_xlabel("Columns")
ax.set_ylabel("Rows")
if show:
plt.show()
else:
plt.clf()
def extract_density_map(netlist_path, plc_path, ifshow=True):
"""
wrapper function for extracting density map
"""
plc_util_os = placement_util.create_placement_cost(
plc_client=plc_client_os,
netlist_file=netlist_path,
init_placement=plc_path
)
grid_cols, grid_rows = plc_util_os.get_grid_num_columns_rows()
dens_map = np.array(plc_util_os.get_grid_cells_density()).reshape(grid_rows, grid_cols)
heatmap(dens_map, "Placement Density Heatmap", ifshow)
return dens_map
def extract_congestion_map(netlist_path, plc_path, rpmh, rpmv, marh, marv, congestion_smooth_range, ifshow=True):
"""
wrapper function for extracting congestion map
"""
plc_util_os = placement_util.create_placement_cost(
plc_client=plc_client_os,
netlist_file=netlist_path,
init_placement=plc_path
)
plc_util_os.set_routes_per_micron(rpmh, rpmv)
plc_util_os.set_macro_routing_allocation(marh, marv)
plc_util_os.set_congestion_smooth_range(congestion_smooth_range)
grid_cols, grid_rows = plc_util_os.get_grid_num_columns_rows()
# vertical routing congestion map
vcong_map = np.array(plc_util_os.get_vertical_routing_congestion()).reshape(grid_rows, grid_cols)
heatmap(vcong_map, "Placement Vertical Congestion Heatmap", ifshow)
# horizontal routing congestion map
hcong_map = np.array(plc_util_os.get_horizontal_routing_congestion()).reshape(grid_rows, grid_cols)
heatmap(hcong_map, "Placement Horizontal Congestion Heatmap", ifshow)
return vcong_map, hcong_map
def SSIM(a, b):
return structural_similarity(a, b)
def l1_norm(a, b):
return np.linalg.norm(normalize(a)-normalize(b), ord=1)
def normalize(a):
return (a - np.min(a)) / (np.max(a) - np.min(a))
\ No newline at end of file
Markdown is supported
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