123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201 |
- 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[15 08:18:40 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:39] [0m[1;31mWRN migrate all stand-alone args into a single task[0m
- [36m[15 08:18:40 <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/yolov8-jump.onnx
- [36m[15 08:18:40 <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/yolov8n-jump.joint
- [36m[15 08:18:40 <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[15 08:18:41 <frozen super_pulsar.func_wrappers.wrapper_pulsar_build>:17] [0mplanning task task_0
- [36m[15 08:18:41 <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[15 08:18:41 <frozen super_pulsar.func_wrappers.wrapper_pulsar_build>:340] [0m################## Running task task_0 ##################
- [36m[15 08:18:41 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:30] [0mpython3 /root/python_modules/super_pulsar/super_pulsar/toolchain_wrappers/wrapper_neuwizard.py --config /tmp/tmpnu8ile81.prototxt
- [36m[15 08:18:41 <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[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] ONNX Model Version 12 for "/root/axera/axera-quan-hjj/model/yolov8-jump.onnx"[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning load step finished; elapsed time: 0.01s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step finished; elapsed time: 0.02s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "native" finished; elapsed time: 0.26s[0m
- [36m[15 08:19:09 <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[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "pretransformed" finished; elapsed time: 0.39s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning calibrate step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "transformed" finished; elapsed time: 21.33s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "posttransformed" finished; elapsed time: 0.75s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "magma" finished; elapsed time: 0.53s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "magma_validified" finished; elapsed time: 0.11s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning transform step to "lava_with_rtv" finished; elapsed time: 2.65s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning dump_joint_model step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning evaluate step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning ir_bit_macs step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning ir_bit_float_params step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Planning ir_bit_quantized_params step finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Loading model finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "onnx_step_1" finished; elapsed time: 0.01s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "onnx_step_2" finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "onnx" finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "native" finished; elapsed time: 0.10s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "native_no_bn" finished; elapsed time: 0.00s[0m
- [36m[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "pretransformed" finished; elapsed time: 0.13s[0m
- [36m[15 08:19:09 <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[15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] return torch._C._cuda_getDeviceCount() > 0[0m
- [36m[15 08:21:25 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Calibrating finished; elapsed time: 136.18s[0m
- [36m[15 08:21:25 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Recalibrating for op_283_FeatureQuantization_Global_Backward, op_282:cat is missing[0m
- [36m[15 08:42:19 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Recalibrating for op_327_FeatureQuantization_Global_Backward, op_326:cat is missing[0m
- [36m[15 09:12:23 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Recalibrating for op_349_FeatureQuantization_Global_Backward, op_348:cat is missing[0m
- [36m[15 09:44:41 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Recalibrating for op_396_FeatureQuantization_Global_Backward, op_395:cat is missing[0m
- [36m[15 10:19:43 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Recalibrating for op_418_FeatureQuantization_Global_Backward, op_417:cat is missing[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "transformed" finished; elapsed time: 9283.48s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "posttransformed" finished; elapsed time: 0.49s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "magma" finished; elapsed time: 0.21s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "magma_validified" finished; elapsed time: 0.03s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava_with_rtv" finished; elapsed time: 1.16s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dynamically planning transform step to "lava" finished; elapsed time: 0.01s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava" dynamically finished; elapsed time: 0.02s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dynamically planning transform step to "lava_onnx" finished; elapsed time: 0.35s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava_onnx" dynamically finished; elapsed time: 0.47s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dynamically planning transform step to "lava_onnx_axe" finished; elapsed time: 0.06s[0m
- [36m[15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Transforming to "lava_onnx_axe" dynamically finished; elapsed time: 0.22s[0m
- [36m[15 10:56:18 <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[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 65, 80, 80]) [-1, 65, 6400][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 65, 40, 40]) [-1, 65, 1600][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 65, 20, 20]) [-1, 65, 400][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 65, 80, 80]) [-1, 65, 6400][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 65, 40, 40]) [-1, 65, 1600][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 65, 20, 20]) [-1, 65, 400][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 32, 80, 80]) [-1, 32, 6400][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 32, 40, 40]) [-1, 32, 1600][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 32, 20, 20]) [-1, 32, 400][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 32, 80, 80]) [-1, 32, 6400][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 32, 40, 40]) [-1, 32, 1600][0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] axe.Transpose torch.Size([1, 32, 20, 20]) [-1, 32, 400][0m
- [36m[15 10:56:18 <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[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Dumping Joint Model finished; elapsed time: 5.84s[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Evaluation is not performed.[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Evaluating finished; elapsed time: 0.00s[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Overview Table of Bit MACs[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Domain | native | pretransformed | transformed | posttransformed | magma | lava |[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] |----------|----------|------------------|---------------|-------------------|---------|--------|[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Bit MACs | 383G | 368G | 372G | 401G | 378G | 389G |[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Bit MACs measurement for each domain finished; elapsed time: 0.09s[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Overview Table of parameter size[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Domain | native | pretransformed | transformed | posttransformed | magma | lava |[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] |----------------------|----------|------------------|---------------|-------------------|---------|--------|[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Parameter Size(bits) | 104M | 106M | 107M | 112M | 112M | 140M |[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Float Parameter size measurement for each domain finished; elapsed time: 0.25s[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Overview Table of parameter size[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Domain | native | pretransformed | transformed | posttransformed | magma | lava |[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] |----------------------|----------|------------------|---------------|-------------------|---------|--------|[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] | Parameter Size(bits) | 26M | 26M | 27M | 28M | 27M | 29M |[0m
- [36m[15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] [0m[32mDBG [neuwizard] Quantized Parameter size measurement for each domain finished; elapsed time: 0.24s[0m
- [36m[15 10:56:22 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:535] [0m[32mDBG working in "/root/tmpr6wfr1xx"[0m
- [36m[15 10:56:22 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:227] [0mpython3 pulsar.py gen /root/tmpr6wfr1xx/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[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] inference_report.log:[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-------------------------|:-----------------------------|:-------------|:-------------------|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:----------------|-------------:|---------------:|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:---------------|:-----------------|:--------------|:--------------|:------------|:--------------|:----------------|:-------------------|:----------------|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-----------------------|:------------------|:------------------|:------------------|:--------------------|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-----------------------|:-----------------|:--------------------|:--------------------|:--------------------|:------------------|:-----------------|:--------------|:-------------|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <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[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:--------------------|-----------:|:---------------|:-----------------|:---------------|:----------------------|:---------------|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:---------------------------------------------|:----------------|:-----------------------|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:-----------|-----------:|----------:|:--------|-------:|----------:|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] inference: 21.2 ms, 47.14 fps[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] qps = fps * batch_size = 47.14[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <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[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] DDR IO stats:[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] ideal_input_data_size: 4317504 Byte,[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] ideal_output_data_size: 6536000 Byte,[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] extra_mid_io_data_size: 7475200 Byte,[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] total_io_data_size: 18328704 Byte[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] MAC per inference: 6109250560 MAC@int8[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] MAC utils: 31.25 %[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] commit_id:[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] |:----------------------------------------------|-----------:|:-------------|[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] subgraph num: 6[0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] [0m
- [36m[15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] [0m[32mDBG [pulsar] pulsar.py totally used 232s[0m
- [36m[15 11:00:36 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:582] [0mFile saved: /root/axera/axera-quan-hjj/joint/yolov8n-jump.joint
- [36m[15 11:00:36 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:587] [0m[32mDBG cleared /root/tmpr6wfr1xx[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)% | 112128(5.3)% |[0m
- [0;32m| range | (None, None) | (None, None) | (1985024, 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 | 7776900 (100.0%) | 195139 (2.5%) | 273265 (3.5%) | 0 (0.0%) | 225640 (2.9%) | 1489405 (19.2%) | 285 (0.0%) | 5303168 (68.2%) |[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) | 10853504 (100.0%) | 3907904 (36.0%) | 409600 (3.8%) | 6536000 (60.2%) |[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) | 7475200 (100.0%) | 0 (0.0%) | 3788800 (50.7%) | 3686400 (49.3%) | 0 (0.0%) | 0 (0.0%) | 0 (0.0%) | 0 (0.0%) |[0m
- [0;32m| profile stream EU | work_cyc | ld_ratio | ld_param_ratio | mv_ratio | mv_linebuffer_ratio | st_ratio |[0m
- [0;32m| teng | 15534772 | 2125313(13.7%) | 2090049(13.5%) | 6013711(38.7%) | 143718(0.9%) | 5161980(33.2%) |[0m
- [0;32m| breakdown of mv_ratio in profile stream EU | teng | all_eus with mv-cmds |[0m
- [0;32m| total_cyc_num | 6013711(100.0%) | 6013711(100.0%) |[0m
- [0;32m| mv,affine,unpack_lsb | 2325432(38.7%) | 2325432(38.7%) |[0m
- [0;32m| weight0_mode,convNxM,mode23,nopad | 729952(12.1%) | 729952(12.1%) |[0m
- [0;32m| teng_binary_mul | 634426(10.5%) | 634426(10.5%) |[0m
- [0;32m| mv,subtensor | 427299(7.1%) | 427299(7.1%) |[0m
- [0;32m| teng_binary_add | 317213(5.3%) | 317213(5.3%) |[0m
- [0;32m| dequant | 317188(5.3%) | 317188(5.3%) |[0m
- [0;32m| mv,concat_c | 296713(4.9%) | 296713(4.9%) |[0m
- [0;32m| mv_patch | 262377(4.4%) | 262377(4.4%) |[0m
- [0;32m| weight0_mode,convNxM,mode20,nopad | 214922(3.6%) | 214922(3.6%) |[0m
- [0;32m| mv,depth2space | 211328(3.5%) | 211328(3.5%) |[0m
- [0;32m| mv,upsample | 121582(2.0%) | 121582(2.0%) |[0m
- [0;32m| mv,padding_ch | 105049(1.7%) | 105049(1.7%) |[0m
- [0;32m| const | 28323(0.5%) | 28323(0.5%) |[0m
- [0;32m| mv,padding | 21678(0.4%) | 21678(0.4%) |[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 | 7776901 | 16969628 | 45.0% | 47.140 | 102.870 |[0m
- [0;32m| teng | 15534772 | 16969628 | 91.0% | 47.140 | 51.500 |[0m
- [0;32m| breakdown of cmds_num for each op | cmds_num | percentage |[0m
- [0;32m| mv,affine,unpack_lsb | 1676 | 30.53% |[0m
- [0;32m| weight0_mode,mode23 | 1310 | 23.86% |[0m
- [0;32m| weight0_mode,mode23,nopad | 318 | 5.79% |[0m
- [0;32m| weight0_mode,convNxM,mode23,nopad | 296 | 5.39% |[0m
- [0;32m| pool,weight0_mode,mode20,conv_align,subtensor | 288 | 5.25% |[0m
- [0;32m| weight0_mode,mode20 | 204 | 3.72% |[0m
- [0;32m| mv,subtensor | 185 | 3.37% |[0m
- [0;32m| revert_split | 170 | 3.10% |[0m
- [0;32m| weight0_mode,convNxM,mode26,nopad | 154 | 2.81% |[0m
- [0;32m| weight0_mode,convNxM,mode20,nopad | 144 | 2.62% |[0m
- [0;32m| const | 135 | 2.46% |[0m
- [0;32m| mv,concat_c | 133 | 2.42% |[0m
- [0;32m| weight0_mode,mode20,nopad | 120 | 2.19% |[0m
- [0;32m| pool,weight0_mode,mode20,subtensor | 96 | 1.75% |[0m
- [0;32m| teng_binary_mul | 77 | 1.40% |[0m
- [0;32m| dequant | 34 | 0.62% |[0m
- [0;32m| teng_binary_add | 34 | 0.62% |[0m
- [0;32m| mv,depth2space | 32 | 0.58% |[0m
- [0;32m| mv_patch | 30 | 0.55% |[0m
- [0;32m| mv,upsample | 27 | 0.49% |[0m
- [0;32m| yuv42xto444,yuv2bgr0 | 11 | 0.20% |[0m
- [0;32m| mv,padding_ch | 10 | 0.18% |[0m
- [0;32m| mv,padding | 6 | 0.11% |[0m
- [0;32m| total_num | 5490 | 100% |[0m
- [34m11:00:35 [I]final_check: FINAL_CHECK: output op_1728:mul check successed![0m
- [34m11:00:35 [I]final_check: FINAL_CHECK: output op_1110 check successed![0m
- [34m11:00:35 [I]final_check: FINAL_CHECK: output op_1111 check successed![0m
- [34m11:00:35 [I]final_check: FINAL_CHECK: output op_1112 check successed![0m
- [34m11:00:35 [I]final_check: FINAL_CHECK: output op_1468 check successed![0m
- [34m11:00:35 [I]final_check: FINAL_CHECK: output op_1470 check successed![0m
- [34m11:00:35 [I]final_check: FINAL_CHECK: output op_1472 check successed![0m
|