API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Jun 19th, 2019
90
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 7.46 KB | None | 0 0
raw download clone embed print report
  1. # nvcc batchmatmul.cu -lcublas -o batchmatmul.out && ./batchmatmul.out
  2. error code = 0
  3. Time : 0.0 ms
  4. Memcpy status: 77
  5. batchmatmul.out: batchmatmul.cu:84: int main(int, char**): Assertion `status == cudaSuccess' failed.
  6. Aborted (core dumped)
  7.  
  8. # nvidia-smi
  9. Sat Jun 8 02:37:50 2019
  10. +-----------------------------------------------------------------------------+
  11. | NVIDIA-SMI 410.72 Driver Version: 410.72 CUDA Version: 10.0 |
  12. |-------------------------------+----------------------+----------------------+
  13. | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
  14. | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
  15. |===============================+======================+======================|
  16. | 0 Tesla V100-SXM2... On | 00000000:06:00.0 Off | 0 |
  17. | N/A 37C P0 45W / 300W | 0MiB / 16130MiB | 0% Default |
  18. +-------------------------------+----------------------+----------------------+
  19. | 1 Tesla V100-SXM2... On | 00000000:07:00.0 Off | 0 |
  20. | N/A 39C P0 47W / 300W | 0MiB / 16130MiB | 0% Default |
  21. +-------------------------------+----------------------+----------------------+
  22. | 2 Tesla V100-SXM2... On | 00000000:0A:00.0 Off | 0 |
  23. | N/A 40C P0 48W / 300W | 0MiB / 16130MiB | 0% Default |
  24. +-------------------------------+----------------------+----------------------+
  25. | 3 Tesla V100-SXM2... On | 00000000:0B:00.0 Off | 0 |
  26. | N/A 37C P0 45W / 300W | 0MiB / 16130MiB | 0% Default |
  27. +-------------------------------+----------------------+----------------------+
  28. | 4 Tesla V100-SXM2... On | 00000000:85:00.0 Off | 0 |
  29. | N/A 40C P0 45W / 300W | 0MiB / 16130MiB | 0% Default |
  30. +-------------------------------+----------------------+----------------------+
  31. | 5 Tesla V100-SXM2... On | 00000000:86:00.0 Off | 0 |
  32. | N/A 40C P0 49W / 300W | 0MiB / 16130MiB | 0% Default |
  33. +-------------------------------+----------------------+----------------------+
  34. | 6 Tesla V100-SXM2... On | 00000000:89:00.0 Off | 0 |
  35. | N/A 41C P0 45W / 300W | 0MiB / 16130MiB | 0% Default |
  36. +-------------------------------+----------------------+----------------------+
  37. | 7 Tesla V100-SXM2... On | 00000000:8A:00.0 Off | 0 |
  38. | N/A 39C P0 46W / 300W | 0MiB / 16130MiB | 0% Default |
  39. +-------------------------------+----------------------+----------------------+
  40.  
  41. +-----------------------------------------------------------------------------+
  42. | Processes: GPU Memory |
  43. | GPU PID Type Process name Usage |
  44. |=============================================================================|
  45. | No running processes found |
  46. +-----------------------------------------------------------------------------+
  47.  
  48. # nvcc --version
  49. nvcc: NVIDIA (R) Cuda compiler driver
  50. Copyright (c) 2005-2018 NVIDIA Corporation
  51. Built on Sat_Aug_25_21:08:01_CDT_2018
  52. Cuda compilation tools, release 10.0, V10.0.130
  53.  
  54.  
  55. # cuda-memcheck batchmatmul.out | head -50
  56. ========= CUDA-MEMCHECK
  57. ========= Program hit cudaErrorInvalidDeviceFunction (error 8) due to "invalid device function" on CUDA API call to cudaFuncSetAttribute.
  58. ========= Saved host backtrace up to driver entry point at error
  59. ========= Host Frame:/usr/lib/x86_64-linux-gnu/libcuda.so.1 [0x357283]
  60. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x79a03c]
  61. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c2ab]
  62. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c610]
  63. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 (cublasCreate_v2 + 0x1ce7) [0x14b337]
  64. ========= Host Frame:batchmatmul.out [0x3e81]
  65. ========= Host Frame:/lib/x86_64-linux-gnu/libc.so.6 (__libc_start_main + 0xf0) [0x20830]
  66. ========= Host Frame:batchmatmul.out [0x3599]
  67. =========
  68. ========= Program hit cudaErrorInvalidDeviceFunction (error 8) due to "invalid device function" on CUDA API call to cudaGetLastError.
  69. ========= Saved host backtrace up to driver entry point at error
  70. ========= Host Frame:/usr/lib/x86_64-linux-gnu/libcuda.so.1 [0x357283]
  71. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x79deb3]
  72. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c2b8]
  73. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c610]
  74. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 (cublasCreate_v2 + 0x1ce7) [0x14b337]
  75. ========= Host Frame:batchmatmul.out [0x3e81]
  76. ========= Host Frame:/lib/x86_64-linux-gnu/libc.so.6 (__libc_start_main + 0xf0) [0x20830]
  77. ========= Host Frame:batchmatmul.out [0x3599]
  78. =========
  79. ========= Program hit cudaErrorInvalidDeviceFunction (error 8) due to "invalid device function" on CUDA API call to cudaFuncSetAttribute.
  80. ========= Saved host backtrace up to driver entry point at error
  81. ========= Host Frame:/usr/lib/x86_64-linux-gnu/libcuda.so.1 [0x357283]
  82. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x79a03c]
  83. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c2ab]
  84. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c610]
  85. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 (cublasCreate_v2 + 0x1ce7) [0x14b337]
  86. ========= Host Frame:batchmatmul.out [0x3e81]
  87. ========= Host Frame:/lib/x86_64-linux-gnu/libc.so.6 (__libc_start_main + 0xf0) [0x20830]
  88. ========= Host Frame:batchmatmul.out [0x3599]
  89. =========
  90. ========= Program hit cudaErrorInvalidDeviceFunction (error 8) due to "invalid device function" on CUDA API call to cudaGetLastError.
  91. ========= Saved host backtrace up to driver entry point at error
  92. ========= Host Frame:/usr/lib/x86_64-linux-gnu/libcuda.so.1 [0x357283]
  93. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x79deb3]
  94. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c2b8]
  95. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c610]
  96. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 (cublasCreate_v2 + 0x1ce7) [0x14b337]
  97. ========= Host Frame:batchmatmul.out [0x3e81]
  98. ========= Host Frame:/lib/x86_64-linux-gnu/libc.so.6 (__libc_start_main + 0xf0) [0x20830]
  99. ========= Host Frame:batchmatmul.out [0x3599]
  100. =========
  101. ========= Program hit cudaErrorInvalidDeviceFunction (error 8) due to "invalid device function" on CUDA API call to cudaFuncSetAttribute.
  102. ========= Saved host backtrace up to driver entry point at error
  103. ========= Host Frame:/usr/lib/x86_64-linux-gnu/libcuda.so.1 [0x357283]
  104. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x79a03c]
  105. ========= Host Frame:/usr/local/cuda-10.0/targets/x86_64-linux/lib/libcublas.so.10.0 [0x72c2ab]
  106. ...
  107. ...
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
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!