You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I used the attached file multi_gpu_test (text file format) multi_gpu_test.txt
following multi-gpu example Tensorflow 2.3.0 from Tensoflow api documentation , to test it . I have the following system parameters:
Windows 10
2 RTX 2080 Ti GPUS
tensorflow version 2.3.0
CUDA Version 10.1 with CUDNN 7.6.5
The second file attached includes the log file from the command window prompt that shows the problem :
2020-09-24 18:27:41.164048: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.165324: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.167037: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.167141: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.167768: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.168299: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.465828: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudnn64_7.dll
2020-09-24 18:27:42.555004: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2020-09-24 18:27:42.555249: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2020-09-24 18:27:42.557047: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2020-09-24 18:27:42.558144: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
[I 18:28:46.435 NotebookApp] Starting buffering
I am not sure what the problem is and how to figure a solution - Thank you for your help,
The sample code attached was pulled directly from the Tensorflow documentation site to demonstrate the consept of the multi_gpu operation -
George Jubran
I used the attached file multi_gpu_test (text file format)
multi_gpu_test.txt
following multi-gpu example Tensorflow 2.3.0 from Tensoflow api documentation , to test it . I have the following system parameters:
Windows 10
2 RTX 2080 Ti GPUS
tensorflow version 2.3.0
CUDA Version 10.1 with CUDNN 7.6.5
The second file attached includes the log file from the command window prompt that shows the problem :
2020-09-24 18:27:41.164048: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.165324: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.167037: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.167141: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.167768: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.168299: E tensorflow/stream_executor/cuda/cuda_blas.cc:225] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED
2020-09-24 18:27:41.465828: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudnn64_7.dll
2020-09-24 18:27:42.555004: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2020-09-24 18:27:42.555249: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2020-09-24 18:27:42.557047: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
2020-09-24 18:27:42.558144: E tensorflow/stream_executor/cuda/cuda_dnn.cc:328] Could not create cudnn handle: CUDNN_STATUS_ALLOC_FAILED
[I 18:28:46.435 NotebookApp] Starting buffering
I am not sure what the problem is and how to figure a solution - Thank you for your help,
The sample code attached was pulled directly from the Tensorflow documentation site to demonstrate the consept of the multi_gpu operation -
George Jubran
log_file_from_command_promt_jupyter_notebook.txt
The text was updated successfully, but these errors were encountered: