huangmeng
/
axera-quan


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184
							nohup: ignoring input
[W Context.cpp:69] Warning: torch.set_deterministic is in beta, and its design and  functionality may change in the future. (function operator())
[36m[08 06:15:54 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:39] [0m[1;31mWRN migrate all stand-alone args into a single task[0m
[36m[08 06:15:54 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:159] [0mset task task_0's 0th input model path as /root/axera/axera-quan-hjj/model/efficientnet_size-160.onnx
[36m[08 06:15:54 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:178] [0mset task task_0's 0th output model path as /root/axera/axera-quan-hjj/joint/efficientnetb0-handpose.joint
[36m[08 06:15:54 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:297] [0mset task task_0's pulsar_conf.output_dir as /root/axera/axera-quan-hjj
/opt/venv/lib/python3.6/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at  /pytorch/c10/cuda/CUDAFunctions.cpp:100.)
  return torch._C._cuda_getDeviceCount() > 0
[36m[08 06:15:55 <frozen super_pulsar.func_wrappers.wrapper_pulsar_build>:17] [0mplanning task task_0
[36m[08 06:15:55 <frozen super_pulsar.func_wrappers.pulsar_build.neuwizard_step>:459] [0m[1;31mWRN affine_preprocess at QAT model compiling is deprecated, insert enforce_integers at front, please use scale_to_integers instead.[0m
[36m[08 06:15:55 <frozen super_pulsar.func_wrappers.wrapper_pulsar_build>:340] [0m################## Running task task_0 ##################
[36m[08 06:15:55 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:30] [0mpython3 /root/python_modules/super_pulsar/super_pulsar/toolchain_wrappers/wrapper_neuwizard.py --config /tmp/tmpmy092f06.prototxt
[36m[08 06:15:55 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] [W Context.cpp:69] Warning: torch.set_deterministic is in beta, and its design and  functionality may change in the future. (function operator())[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] ONNX Model Version 12 for "/root/axera/axera-quan-hjj/model/efficientnet_size-160.onnx"[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning load step finished; elapsed time: 0.01s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step finished; elapsed time: 0.01s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "native" finished; elapsed time: 0.16s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "native_no_bn" finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "pretransformed" finished; elapsed time: 1.77s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning calibrate step finished; elapsed time: 0.01s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "transformed" finished; elapsed time: 47.78s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "posttransformed" finished; elapsed time: 6.22s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "magma" finished; elapsed time: 1.51s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "magma_validified" finished; elapsed time: 0.34s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "lava_with_rtv" finished; elapsed time: 10.77s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning dump_joint_model step finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning evaluate step finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning ir_bit_macs step finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning ir_bit_float_params step finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning ir_bit_quantized_params step finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Loading model finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "onnx_step_1" finished; elapsed time: 0.01s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "onnx_step_2" finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "onnx" finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "native" finished; elapsed time: 0.07s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "native_no_bn" finished; elapsed time: 0.00s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "pretransformed" finished; elapsed time: 0.66s[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] /opt/venv/lib/python3.6/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at  /pytorch/c10/cuda/CUDAFunctions.cpp:100.)[0m
[36m[08 06:17:06 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] return torch._C._cuda_getDeviceCount() > 0[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Calibrating finished; elapsed time: 7.91s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "transformed" finished; elapsed time: 8.75s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "posttransformed" finished; elapsed time: 1.83s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "magma" finished; elapsed time: 0.68s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "magma_validified" finished; elapsed time: 0.06s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava_with_rtv" finished; elapsed time: 4.61s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dynamically planning transform step to "lava" finished; elapsed time: 0.02s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava" dynamically finished; elapsed time: 0.06s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dynamically planning transform step to "lava_onnx" finished; elapsed time: 0.55s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava_onnx" dynamically finished; elapsed time: 0.78s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dynamically planning transform step to "lava_onnx_axe" finished; elapsed time: 0.02s[0m
[36m[08 06:17:30 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava_onnx_axe" dynamically finished; elapsed time: 0.06s[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] /root/python_modules/neuwizard-latest/neuwizard/operators/lava/AX620/Conv2d.py:141: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at  /pytorch/torch/csrc/utils/tensor_numpy.cpp:141.)[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Joint model dumpped as "/root/axera/axera-quan-hjj/joint/model.lava_joint"[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dumping Joint Model finished; elapsed time: 4.17s[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Evaluation is not performed.[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Evaluating finished; elapsed time: 0.00s[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Overview Table of Bit MACs[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Domain   | native   | pretransformed   | transformed   | posttransformed   | magma   | lava   |[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] |----------|----------|------------------|---------------|-------------------|---------|--------|[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Bit MACs | 13G      | 52G              | 53G           | 61G               | 59G     | 60G    |[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Bit MACs measurement for each domain finished; elapsed time: 0.37s[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Overview Table of parameter size[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Domain               | native   | pretransformed   | transformed   | posttransformed   | magma   | lava   |[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] |----------------------|----------|------------------|---------------|-------------------|---------|--------|[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Parameter Size(bits) | 127M     | 326M             | 329M          | 339M              | 339M    | 339M   |[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Float Parameter size measurement for each domain finished; elapsed time: 0.54s[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Overview Table of parameter size[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Domain               | native   | pretransformed   | transformed   | posttransformed   | magma   | lava   |[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] |----------------------|----------|------------------|---------------|-------------------|---------|--------|[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Parameter Size(bits) | 32M      | 81M              | 82M           | 85M               | 84M     | 84M    |[0m
[36m[08 06:17:36 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Quantized Parameter size measurement for each domain finished; elapsed time: 0.63s[0m
[36m[08 06:17:39 <frozen super_pulsar.toolchain_wrappers.wrapper_joint>:509] [0mset op_8341's shape as [1, 8]
[36m[08 06:17:39 <frozen super_pulsar.toolchain_wrappers.wrapper_joint>:509] [0mset op_8341's shape as [1, 8]
[36m[08 06:17:41 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:535] [0m[32mDBG working in "/root/tmpo0o7ztk9"[0m
[36m[08 06:17:41 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:227] [0mpython3 pulsar.py gen /root/tmpo0o7ztk9/part_0.lava/part_0.lava env/ax620a_virtual_111_config.ini -b 1 -pe 16 --times_thres 0 --job_stealing 3 --checkall --param_compress --continuous_input --no_sim --hyper_params  run_cf.wait_mode=True
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] inference_report.log:[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-------------------------|:-----------------------------|:-------------|:-------------------|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:----------------|-------------:|---------------:|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:---------------|:-----------------|:-------------|:--------------|:------------|:---------------|:---------------|:-------------------|:---------------|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-----------------------|:------------------|:------------------|:------------------|:--------------------|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-----------------------|:-----------------|:--------------------|:--------------------|:--------------------|:------------------|:-----------------|:----------------|:----------------|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] profile stream EU: ld/st_ratio might include ringbuf/linebuf/feature_swap parts; mv_ratio migth have ringbuf part.[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:--------------------|-----------:|:--------------|:-----------------|:---------------|:----------------------|:--------------|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:---------------------------------------------|:----------------|:-----------------------|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-----------|-----------:|----------:|:--------|-------:|----------:|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] inference: 23.6 ms, 42.35 fps[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] qps = fps * batch_size = 42.35[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] simulated fps is based on DDR_BW: 1.59 GB/s[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] DDR IO stats:[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] ideal_input_data_size: 14116608 Byte,[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] ideal_output_data_size: 32 Byte,[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] extra_mid_io_data_size: 7109136 Byte,[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] total_io_data_size: 21225776 Byte[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] MAC per inference: 628214464 MAC@int8[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] MAC utils: 2.89 %[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] commit_id:[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:------------------------------------|-----------:|:-------------|[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] subgraph num: 4[0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
[36m[08 06:25:32 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] pulsar.py totally used 470s[0m
[36m[08 06:25:38 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:582] [0mFile saved: /root/axera/axera-quan-hjj/joint/efficientnetb0-handpose.joint
[36m[08 06:25:38 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:587] [0m[32mDBG cleared /root/tmpo0o7ztk9[0m
[0;32m| Pre_alloc OCM            | linebuffer(may SWAP later)   | ringbuffer   | parameter          |[0m
[0;32m| size(ratio of whole OCM) | 0(0.0)%                      | 0(0.0)%      | 116736(5.6)%       |[0m
[0;32m| range                    | (None, None)                 | (None, None) | (1980416, 2097152) |[0m
[0;32m| Pre_alloc DDR   |   ringbuffer |   feature_swap |[0m
[0;32m| size(M)         |         0.00 |           0.00 |[0m
[0;32m| profile conv   | work_cyc         | linebuf      | warmup_tail   | core_idle   | io_idle        | stride2_idle   | standalone_fetch   | MAC            |[0m
[0;32m| ratio in conv  | 2772180 (100.0%) | 32131 (1.2%) | 240800 (8.7%) | 0 (0.0%)    | 710439 (25.6%) | 831608 (30.0%) | 210 (0.0%)         | 545325 (19.7%) |[0m
[0;32m| profile ideal DDR_IO   | min_io_sum        | min_params_read   | min_inputs_read   | min_outputs_write   |[0m
[0;32m| DDR IO size (Byte)     | 14116640 (100.0%) | 14039808 (99.5%)  | 76800 (0.5%)      | 32 (0.0%)           |[0m
[0;32m| profile extra DDR_IO   | extra_ddr_io     | extra_params_read   | extra_inputs_read   | extra_outputs_wrt   | extra_swap_read   | extra_swap_wrt   | ddr_rb_read     | ddr_rb_wrt      |[0m
[0;32m| DDR IO size (Byte)     | 7109136 (100.0%) | 0 (0.0%)            | 1157384 (16.3%)     | 1106184 (15.6%)     | 0 (0.0%)          | 0 (0.0%)         | 2422784 (34.1%) | 2422784 (34.1%) |[0m
[0;32m| profile stream EU   |   work_cyc | ld_ratio      | ld_param_ratio   | mv_ratio       | mv_linebuffer_ratio   | st_ratio      |[0m
[0;32m| teng                |   18636864 | 1844691(9.9%) | 7460162(40.0%)   | 7509589(40.3%) | 40684(0.2%)           | 1781737(9.6%) |[0m
[0;32m| breakdown of mv_ratio in profile stream EU   | teng            | all_eus with mv-cmds   |[0m
[0;32m| total_cyc_num                                | 7509589(100.0%) | 7509589(100.0%)        |[0m
[0;32m| weight0_mode,convNxM,mode23,nopad            | 2404764(32.0%)  | 2404764(32.0%)         |[0m
[0;32m| teng_binary_mul                              | 1056050(14.1%)  | 1056050(14.1%)         |[0m
[0;32m| mv,affine,unpack_lsb                         | 565295(7.5%)    | 565295(7.5%)           |[0m
[0;32m| mv,broadcast                                 | 483148(6.4%)    | 483148(6.4%)           |[0m
[0;32m| teng_binary_sub                              | 451312(6.0%)    | 451312(6.0%)           |[0m
[0;32m| mv,resize                                    | 439020(5.8%)    | 439020(5.8%)           |[0m
[0;32m| mv,padding                                   | 389020(5.2%)    | 389020(5.2%)           |[0m
[0;32m| mv,subtensor                                 | 365393(4.9%)    | 365393(4.9%)           |[0m
[0;32m| mv,concat_c                                  | 328182(4.4%)    | 328182(4.4%)           |[0m
[0;32m| teng_binary_add                              | 308771(4.1%)    | 308771(4.1%)           |[0m
[0;32m| mv,pack_lsb                                  | 267240(3.6%)    | 267240(3.6%)           |[0m
[0;32m| weight0_mode,convNxM,mode20,nopad            | 251040(3.3%)    | 251040(3.3%)           |[0m
[0;32m| conv_transform                               | 85377(1.1%)     | 85377(1.1%)            |[0m
[0;32m| mv,padding_ch                                | 63717(0.8%)     | 63717(0.8%)            |[0m
[0;32m| const                                        | 44401(0.6%)     | 44401(0.6%)            |[0m
[0;32m| sigmoid                                      | 6129(0.1%)      | 6129(0.1%)             |[0m
[0;32m| weight0_mode,mode26,fc                       | 501(0.0%)       | 501(0.0%)              |[0m
[0;32m| revert_split                                 | 229(0.0%)       | 229(0.0%)              |[0m
[0;32m| EU         |   work_cyc |   tot_cyc | ratio   |    fps |   fps_bnd |[0m
[0;32m| conv-1core |    2772181 |  18888839 | 14.0%   | 42.350 |   288.580 |[0m
[0;32m| teng       |   18636864 |  18888839 | 98.0%   | 42.350 |    42.930 |[0m
[0;32m| breakdown of cmds_num for each op   |   cmds_num | percentage   |[0m
[0;32m| weight0_mode,convNxM,mode23,nopad   |       4590 | 35.20%       |[0m
[0;32m| mv,resize                           |       1306 | 10.01%       |[0m
[0;32m| mv,padding                          |        929 | 7.12%        |[0m
[0;32m| mv,affine,unpack_lsb                |        913 | 7.00%        |[0m
[0;32m| mv,concat_c                         |        863 | 6.62%        |[0m
[0;32m| mv,subtensor                        |        748 | 5.74%        |[0m
[0;32m| weight0_mode,mode23,nopad           |        699 | 5.36%        |[0m
[0;32m| weight0_mode,convNxM,mode26,nopad   |        585 | 4.49%        |[0m
[0;32m| weight0_mode,mode23                 |        543 | 4.16%        |[0m
[0;32m| weight0_mode,convNxM,mode20,nopad   |        492 | 3.77%        |[0m
[0;32m| weight0_mode,mode20,nopad           |        359 | 2.75%        |[0m
[0;32m| const                               |        199 | 1.53%        |[0m
[0;32m| conv_transform                      |        152 | 1.17%        |[0m
[0;32m| revert_split                        |        124 | 0.95%        |[0m
[0;32m| teng_binary_mul                     |        118 | 0.90%        |[0m
[0;32m| mv,padding_ch                       |         87 | 0.67%        |[0m
[0;32m| teng_binary_sub                     |         77 | 0.59%        |[0m
[0;32m| mv,broadcast                        |         76 | 0.58%        |[0m
[0;32m| teng_binary_add                     |         66 | 0.51%        |[0m
[0;32m| mv,pack_lsb                         |         53 | 0.41%        |[0m
[0;32m| sigmoid                             |         35 | 0.27%        |[0m
[0;32m| weight0_mode,mode20                 |         13 | 0.10%        |[0m
[0;32m| weight0_mode,mode26,fc              |          8 | 0.06%        |[0m
[0;32m| bgr_pack                            |          6 | 0.05%        |[0m
[0;32m| total_num                           |      13041 | 100%         |[0m
[34m06:25:37 [I]final_check: FINAL_CHECK: output op_8341 check successed![0m