yolov8njump-exp1.log 29 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201
  1. nohup: ignoring input
  2. [W Context.cpp:69] Warning: torch.set_deterministic is in beta, and its design and functionality may change in the future. (function operator())
  3. [15 08:18:40 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:39] WRN migrate all stand-alone args into a single task
  4. [15 08:18:40 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:159] set task task_0's 0th input model path as /root/axera/axera-quan-hjj/model/yolov8-jump.onnx
  5. [15 08:18:40 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:178] set task task_0's 0th output model path as /root/axera/axera-quan-hjj/joint/yolov8n-jump.joint
  6. [15 08:18:40 <frozen super_pulsar.proto.configuration_super_pulsar_manip>:297] set task task_0's pulsar_conf.output_dir as /root/axera/axera-quan-hjj
  7. /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.)
  8. return torch._C._cuda_getDeviceCount() > 0
  9. [15 08:18:41 <frozen super_pulsar.func_wrappers.wrapper_pulsar_build>:17] planning task task_0
  10. [15 08:18:41 <frozen super_pulsar.func_wrappers.pulsar_build.neuwizard_step>:459] WRN affine_preprocess at QAT model compiling is deprecated, insert enforce_integers at front, please use scale_to_integers instead.
  11. [15 08:18:41 <frozen super_pulsar.func_wrappers.wrapper_pulsar_build>:340] ################## Running task task_0 ##################
  12. [15 08:18:41 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:30] python3 /root/python_modules/super_pulsar/super_pulsar/toolchain_wrappers/wrapper_neuwizard.py --config /tmp/tmpnu8ile81.prototxt
  13. [15 08:18:41 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] [W Context.cpp:69] Warning: torch.set_deterministic is in beta, and its design and functionality may change in the future. (function operator())
  14. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] ONNX Model Version 12 for "/root/axera/axera-quan-hjj/model/yolov8-jump.onnx"
  15. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning load step finished; elapsed time: 0.01s
  16. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step finished; elapsed time: 0.02s
  17. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step finished; elapsed time: 0.00s
  18. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step finished; elapsed time: 0.00s
  19. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "native" finished; elapsed time: 0.26s
  20. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "native_no_bn" finished; elapsed time: 0.00s
  21. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "pretransformed" finished; elapsed time: 0.39s
  22. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning calibrate step finished; elapsed time: 0.00s
  23. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "transformed" finished; elapsed time: 21.33s
  24. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "posttransformed" finished; elapsed time: 0.75s
  25. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "magma" finished; elapsed time: 0.53s
  26. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "magma_validified" finished; elapsed time: 0.11s
  27. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning transform step to "lava_with_rtv" finished; elapsed time: 2.65s
  28. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning dump_joint_model step finished; elapsed time: 0.00s
  29. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning evaluate step finished; elapsed time: 0.00s
  30. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning ir_bit_macs step finished; elapsed time: 0.00s
  31. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning ir_bit_float_params step finished; elapsed time: 0.00s
  32. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Planning ir_bit_quantized_params step finished; elapsed time: 0.00s
  33. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Loading model finished; elapsed time: 0.00s
  34. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "onnx_step_1" finished; elapsed time: 0.01s
  35. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "onnx_step_2" finished; elapsed time: 0.00s
  36. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "onnx" finished; elapsed time: 0.00s
  37. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "native" finished; elapsed time: 0.10s
  38. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "native_no_bn" finished; elapsed time: 0.00s
  39. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "pretransformed" finished; elapsed time: 0.13s
  40. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [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.)
  41. [15 08:19:09 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] return torch._C._cuda_getDeviceCount() > 0
  42. [15 08:21:25 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Calibrating finished; elapsed time: 136.18s
  43. [15 08:21:25 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Recalibrating for op_283_FeatureQuantization_Global_Backward, op_282:cat is missing
  44. [15 08:42:19 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Recalibrating for op_327_FeatureQuantization_Global_Backward, op_326:cat is missing
  45. [15 09:12:23 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Recalibrating for op_349_FeatureQuantization_Global_Backward, op_348:cat is missing
  46. [15 09:44:41 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Recalibrating for op_396_FeatureQuantization_Global_Backward, op_395:cat is missing
  47. [15 10:19:43 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Recalibrating for op_418_FeatureQuantization_Global_Backward, op_417:cat is missing
  48. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "transformed" finished; elapsed time: 9283.48s
  49. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "posttransformed" finished; elapsed time: 0.49s
  50. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "magma" finished; elapsed time: 0.21s
  51. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "magma_validified" finished; elapsed time: 0.03s
  52. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "lava_with_rtv" finished; elapsed time: 1.16s
  53. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Dynamically planning transform step to "lava" finished; elapsed time: 0.01s
  54. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "lava" dynamically finished; elapsed time: 0.02s
  55. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Dynamically planning transform step to "lava_onnx" finished; elapsed time: 0.35s
  56. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "lava_onnx" dynamically finished; elapsed time: 0.47s
  57. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Dynamically planning transform step to "lava_onnx_axe" finished; elapsed time: 0.06s
  58. [15 10:56:11 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Transforming to "lava_onnx_axe" dynamically finished; elapsed time: 0.22s
  59. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [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.)
  60. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 65, 80, 80]) [-1, 65, 6400]
  61. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 65, 40, 40]) [-1, 65, 1600]
  62. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 65, 20, 20]) [-1, 65, 400]
  63. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 65, 80, 80]) [-1, 65, 6400]
  64. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 65, 40, 40]) [-1, 65, 1600]
  65. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 65, 20, 20]) [-1, 65, 400]
  66. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 32, 80, 80]) [-1, 32, 6400]
  67. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 32, 40, 40]) [-1, 32, 1600]
  68. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 32, 20, 20]) [-1, 32, 400]
  69. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 32, 80, 80]) [-1, 32, 6400]
  70. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 32, 40, 40]) [-1, 32, 1600]
  71. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] axe.Transpose torch.Size([1, 32, 20, 20]) [-1, 32, 400]
  72. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Joint model dumpped as "/root/axera/axera-quan-hjj/joint/model.lava_joint"
  73. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Dumping Joint Model finished; elapsed time: 5.84s
  74. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Evaluation is not performed.
  75. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Evaluating finished; elapsed time: 0.00s
  76. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Overview Table of Bit MACs
  77. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] | Domain | native | pretransformed | transformed | posttransformed | magma | lava |
  78. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] |----------|----------|------------------|---------------|-------------------|---------|--------|
  79. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] | Bit MACs | 383G | 368G | 372G | 401G | 378G | 389G |
  80. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Bit MACs measurement for each domain finished; elapsed time: 0.09s
  81. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Overview Table of parameter size
  82. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] | Domain | native | pretransformed | transformed | posttransformed | magma | lava |
  83. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] |----------------------|----------|------------------|---------------|-------------------|---------|--------|
  84. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] | Parameter Size(bits) | 104M | 106M | 107M | 112M | 112M | 140M |
  85. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Float Parameter size measurement for each domain finished; elapsed time: 0.25s
  86. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Overview Table of parameter size
  87. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] | Domain | native | pretransformed | transformed | posttransformed | magma | lava |
  88. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] |----------------------|----------|------------------|---------------|-------------------|---------|--------|
  89. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] | Parameter Size(bits) | 26M | 26M | 27M | 28M | 27M | 29M |
  90. [15 10:56:18 <frozen super_pulsar.toolchain_wrappers.wrapper_neuwizard>:36] DBG [neuwizard] Quantized Parameter size measurement for each domain finished; elapsed time: 0.24s
  91. [15 10:56:22 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:535] DBG working in "/root/tmpr6wfr1xx"
  92. [15 10:56:22 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:227] python3 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
  93. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  94. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] inference_report.log:
  95. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  96. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:-------------------------|:-----------------------------|:-------------|:-------------------|
  97. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  98. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:----------------|-------------:|---------------:|
  99. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  100. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:---------------|:-----------------|:--------------|:--------------|:------------|:--------------|:----------------|:-------------------|:----------------|
  101. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  102. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:-----------------------|:------------------|:------------------|:------------------|:--------------------|
  103. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  104. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:-----------------------|:-----------------|:--------------------|:--------------------|:--------------------|:------------------|:-----------------|:--------------|:-------------|
  105. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  106. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] profile stream EU: ld/st_ratio might include ringbuf/linebuf/feature_swap parts; mv_ratio migth have ringbuf part.
  107. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  108. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:--------------------|-----------:|:---------------|:-----------------|:---------------|:----------------------|:---------------|
  109. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  110. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:---------------------------------------------|:----------------|:-----------------------|
  111. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  112. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:-----------|-----------:|----------:|:--------|-------:|----------:|
  113. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  114. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] inference: 21.2 ms, 47.14 fps
  115. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] qps = fps * batch_size = 47.14
  116. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  117. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] simulated fps is based on DDR_BW: 1.59 GB/s
  118. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  119. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] DDR IO stats:
  120. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] ideal_input_data_size: 4317504 Byte,
  121. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] ideal_output_data_size: 6536000 Byte,
  122. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] extra_mid_io_data_size: 7475200 Byte,
  123. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] total_io_data_size: 18328704 Byte
  124. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  125. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] MAC per inference: 6109250560 MAC@int8
  126. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] MAC utils: 31.25 %
  127. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  128. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] commit_id:
  129. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  130. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] |:----------------------------------------------|-----------:|:-------------|
  131. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  132. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] subgraph num: 6
  133. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] 
  134. [15 11:00:15 <frozen super_pulsar.toolchain_wrappers.wrapper_pulsar_compiler>:250] DBG [pulsar] pulsar.py totally used 232s
  135. [15 11:00:36 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:582] File saved: /root/axera/axera-quan-hjj/joint/yolov8n-jump.joint
  136. [15 11:00:36 <frozen super_pulsar.toolchain_wrappers.wrapper_toolchain>:587] DBG cleared /root/tmpr6wfr1xx
  137. | Pre_alloc OCM | linebuffer(may SWAP later) | ringbuffer | parameter |
  138. | size(ratio of whole OCM) | 0(0.0)% | 0(0.0)% | 112128(5.3)% |
  139. | range | (None, None) | (None, None) | (1985024, 2097152) |
  140. | Pre_alloc DDR | ringbuffer | feature_swap |
  141. | size(M) | 0.00 | 0.00 |
  142. | profile conv | work_cyc | linebuf | warmup_tail | core_idle | io_idle | stride2_idle | standalone_fetch | MAC |
  143. | 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%) |
  144. | profile ideal DDR_IO | min_io_sum | min_params_read | min_inputs_read | min_outputs_write |
  145. | DDR IO size (Byte) | 10853504 (100.0%) | 3907904 (36.0%) | 409600 (3.8%) | 6536000 (60.2%) |
  146. | 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 |
  147. | 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%) |
  148. | profile stream EU | work_cyc | ld_ratio | ld_param_ratio | mv_ratio | mv_linebuffer_ratio | st_ratio |
  149. | teng | 15534772 | 2125313(13.7%) | 2090049(13.5%) | 6013711(38.7%) | 143718(0.9%) | 5161980(33.2%) |
  150. | breakdown of mv_ratio in profile stream EU | teng | all_eus with mv-cmds |
  151. | total_cyc_num | 6013711(100.0%) | 6013711(100.0%) |
  152. | mv,affine,unpack_lsb | 2325432(38.7%) | 2325432(38.7%) |
  153. | weight0_mode,convNxM,mode23,nopad | 729952(12.1%) | 729952(12.1%) |
  154. | teng_binary_mul | 634426(10.5%) | 634426(10.5%) |
  155. | mv,subtensor | 427299(7.1%) | 427299(7.1%) |
  156. | teng_binary_add | 317213(5.3%) | 317213(5.3%) |
  157. | dequant | 317188(5.3%) | 317188(5.3%) |
  158. | mv,concat_c | 296713(4.9%) | 296713(4.9%) |
  159. | mv_patch | 262377(4.4%) | 262377(4.4%) |
  160. | weight0_mode,convNxM,mode20,nopad | 214922(3.6%) | 214922(3.6%) |
  161. | mv,depth2space | 211328(3.5%) | 211328(3.5%) |
  162. | mv,upsample | 121582(2.0%) | 121582(2.0%) |
  163. | mv,padding_ch | 105049(1.7%) | 105049(1.7%) |
  164. | const | 28323(0.5%) | 28323(0.5%) |
  165. | mv,padding | 21678(0.4%) | 21678(0.4%) |
  166. | revert_split | 229(0.0%) | 229(0.0%) |
  167. | EU | work_cyc | tot_cyc | ratio | fps | fps_bnd |
  168. | conv-1core | 7776901 | 16969628 | 45.0% | 47.140 | 102.870 |
  169. | teng | 15534772 | 16969628 | 91.0% | 47.140 | 51.500 |
  170. | breakdown of cmds_num for each op | cmds_num | percentage |
  171. | mv,affine,unpack_lsb | 1676 | 30.53% |
  172. | weight0_mode,mode23 | 1310 | 23.86% |
  173. | weight0_mode,mode23,nopad | 318 | 5.79% |
  174. | weight0_mode,convNxM,mode23,nopad | 296 | 5.39% |
  175. | pool,weight0_mode,mode20,conv_align,subtensor | 288 | 5.25% |
  176. | weight0_mode,mode20 | 204 | 3.72% |
  177. | mv,subtensor | 185 | 3.37% |
  178. | revert_split | 170 | 3.10% |
  179. | weight0_mode,convNxM,mode26,nopad | 154 | 2.81% |
  180. | weight0_mode,convNxM,mode20,nopad | 144 | 2.62% |
  181. | const | 135 | 2.46% |
  182. | mv,concat_c | 133 | 2.42% |
  183. | weight0_mode,mode20,nopad | 120 | 2.19% |
  184. | pool,weight0_mode,mode20,subtensor | 96 | 1.75% |
  185. | teng_binary_mul | 77 | 1.40% |
  186. | dequant | 34 | 0.62% |
  187. | teng_binary_add | 34 | 0.62% |
  188. | mv,depth2space | 32 | 0.58% |
  189. | mv_patch | 30 | 0.55% |
  190. | mv,upsample | 27 | 0.49% |
  191. | yuv42xto444,yuv2bgr0 | 11 | 0.20% |
  192. | mv,padding_ch | 10 | 0.18% |
  193. | mv,padding | 6 | 0.11% |
  194. | total_num | 5490 | 100% |
  195. 11:00:35 [I]final_check: FINAL_CHECK: output op_1728:mul check successed!
  196. 11:00:35 [I]final_check: FINAL_CHECK: output op_1110 check successed!
  197. 11:00:35 [I]final_check: FINAL_CHECK: output op_1111 check successed!
  198. 11:00:35 [I]final_check: FINAL_CHECK: output op_1112 check successed!
  199. 11:00:35 [I]final_check: FINAL_CHECK: output op_1468 check successed!
  200. 11:00:35 [I]final_check: FINAL_CHECK: output op_1470 check successed!
  201. 11:00:35 [I]final_check: FINAL_CHECK: output op_1472 check successed!