API tools faq
paste
mahmoodn

nsys_out_rnnt

mahmoodn
Nov 3rd, 2022
177
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 5.13 KB | None | 0 0
raw download clone embed print report
  1. &&&& RUNNING RNN-T_Harness # /work/./build/bin/harness_rnnt
  2. I1103 19:58:43.096913 866 main_rnnt.cc:2903] Found 1 GPUs
  3. [I] Starting creating QSL.
  4. [I] Finished creating QSL.
  5. [I] Starting creating SUT.
  6. [I] Set to device 0
  7. Dali pipeline creating..
  8. Dali pipeline created
  9. [I] Creating stream 0/1
  10. [I] [TRT] [MemUsageChange] Init CUDA: CPU +531, GPU +0, now: CPU 966, GPU 2541 (MiB)
  11. [I] [TRT] Loaded engine size: 81 MiB
  12. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1239, GPU +348, now: CPU 2388, GPU 2891 (MiB)
  13. [I] [TRT] [MemUsageChange] Init cuDNN: CPU +178, GPU +56, now: CPU 2566, GPU 2947 (MiB)
  14. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +0, now: CPU 0, GPU 0 (MiB)
  15. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1, GPU +8, now: CPU 2593, GPU 3007 (MiB)
  16. [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 2593, GPU 3015 (MiB)
  17. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +232, now: CPU 0, GPU 232 (MiB)
  18. [I] Created RnntEncoder runner: encoder
  19. [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 2593, GPU 3249 (MiB)
  20. [I] [TRT] Loaded engine size: 3 MiB
  21. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 2599, GPU 3257 (MiB)
  22. [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +10, now: CPU 2599, GPU 3267 (MiB)
  23. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +0, now: CPU 0, GPU 232 (MiB)
  24. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 2599, GPU 3271 (MiB)
  25. [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 2599, GPU 3279 (MiB)
  26. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +1, now: CPU 0, GPU 233 (MiB)
  27. [I] Created RnntDecoder runner: decoder
  28. [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 2600, GPU 3279 (MiB)
  29. [I] [TRT] Loaded engine size: 1 MiB
  30. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +1, now: CPU 0, GPU 234 (MiB)
  31. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  32. [I] Created RnntJointFc1 runner: fc1_a
  33. [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 2600, GPU 3279 (MiB)
  34. [I] [TRT] Loaded engine size: 0 MiB
  35. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1, GPU +8, now: CPU 2601, GPU 3287 (MiB)
  36. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  37. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1, GPU +8, now: CPU 2601, GPU 3287 (MiB)
  38. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  39. [I] Created RnntJointFc1 runner: fc1_b
  40. [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 2600, GPU 3287 (MiB)
  41. [I] [TRT] Loaded engine size: 0 MiB
  42. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1, GPU +8, now: CPU 2601, GPU 3295 (MiB)
  43. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  44. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +1, GPU +8, now: CPU 2601, GPU 3295 (MiB)
  45. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  46. [I] Created RnntJointBackend runner: joint_backend
  47. [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 2600, GPU 3295 (MiB)
  48. [I] [TRT] Loaded engine size: 0 MiB
  49. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 2601, GPU 3303 (MiB)
  50. [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +10, now: CPU 2601, GPU 3313 (MiB)
  51. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  52. [I] [TRT] [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +8, now: CPU 2601, GPU 3305 (MiB)
  53. [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +8, now: CPU 2601, GPU 3313 (MiB)
  54. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  55. [I] Created RnntIsel runner: isel
  56. [I] [TRT] [MemUsageChange] Init CUDA: CPU +0, GPU +0, now: CPU 2601, GPU 3313 (MiB)
  57. [I] [TRT] Loaded engine size: 0 MiB
  58. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +0, now: CPU 0, GPU 234 (MiB)
  59. [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +2, now: CPU 0, GPU 236 (MiB)
  60. [I] Created RnntIgather runner: igather
  61. [I] Instantiated RnntEngineContainer runner
  62. cudaMemcpy blocking
  63. cudaMemcpy blocking
  64. [I] Instantiated RnntTensorContainer host memory
  65. Stream::Stream sampleSize: 61440
  66. Stream::Stream singleSampleSize: 480
  67. Stream::Stream fullseqSampleSize: 61440
  68. Stream::Stream mBatchSize: 16
  69. [I] Finished creating SUT.
  70. [I] Starting warming up SUT.
  71. [I] Finished warming up SUT.
  72. [I] Starting running actual test.
  73. Generating '/tmp/nsys-report-ecc6.qdstrm'
  74. [1/1] [========================100%] nsys_rnnt.nsys-rep
  75. Generated:
  76. /work/nsys_rnnt.nsys-rep
  77.  
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!