search

ryujaehun / pytorch-gpu-benchmark

Using the famous cnn model in Pytorch, we run benchmarks on various gpu.
MIT License
226 stars 85 forks source link

GTX 2080 Ti Performance [Windows 10] #17

Closed arstropica closed 3 years ago

arstropica commented 3 years ago

I am trying to troubleshoot my 2080 Ti performance on Windows 10 WSL2. Below is: output from the system config method, output from the pytorch collect_env script, and a chart comparison of the average Float Model Train Benchmark result.

Also, the test did not complete successfully. The script crashed my WSL ubuntu session during the half precision test. Any pointers as to what to do next would be appreciated! Thanks.

system_configs

uname_result(system='Linux', node='TROPICALRENDER', release='5.4.72-microsoft-standard-WSL2', version='#1 SMP Wed Oct 28 23:40:43 UTC 2020', machine='x86_64', processor='x86_64')
                     scpufreq(current=3600.0100000000016, min=0.0, max=0.0)
                    cpu_count: 16
                    memory_available: 32396013568
gpu_configs

Number of GPUs on current device : 1
CUDA Version : 11.0
Cudnn Version : 8005
Device Name : GeForce RTX 2080 Ti
Collecting environment information...
PyTorch version: 1.7.1+cu110
Is debug build: False
CUDA used to build PyTorch: 11.0
ROCM used to build PyTorch: N/A

OS: Ubuntu 20.04.2 LTS (x86_64)
GCC version: (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0
Clang version: Could not collect
CMake version: Could not collect

Python version: 3.8 (64-bit runtime)
Is CUDA available: True
CUDA runtime version: Could not collect
GPU models and configuration: GPU 0: GeForce RTX 2080 Ti
Nvidia driver version: Could not collect
cuDNN version: Probably one of the following:
/usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudnn.so.8
/usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudnn_adv_infer.so.8
/usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudnn_adv_train.so.8
/usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudnn_cnn_infer.so.8
/usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudnn_cnn_train.so.8
/usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudnn_ops_infer.so.8
/usr/local/cuda-11.0/targets/x86_64-linux/lib/libcudnn_ops_train.so.8
HIP runtime version: N/A
MIOpen runtime version: N/A

Versions of relevant libraries:
[pip3] numpy==1.20.1
[pip3] torch==1.7.1+cu110
[pip3] torchaudio==0.7.2
[pip3] torchfile==0.1.0
[pip3] torchvision==0.8.2+cu110
[conda] blas                      1.0                         mkl  
[conda] cudatoolkit               11.0.221             h6bb024c_0  
[conda] mkl                       2020.2                      256  
[conda] mkl-service               2.3.0            py38he904b0f_0  
[conda] mkl_fft                   1.3.0            py38h54f3939_0  
[conda] mkl_random                1.1.1            py38h0573a6f_0  
[conda] numpy                     1.19.2           py38h54aff64_0  
[conda] numpy-base                1.19.2           py38hfa32c7d_0  
[conda] pytorch                   1.7.1           py3.8_cuda11.0.221_cudnn8.0.5_0    pytorch
[conda] torchaudio                0.7.2                      py38    pytorch
[conda] torchvision               0.8.2                py38_cu110    pytorch

image

ryujaehun commented 3 years ago

Sorry, I'm lately check I often experience performance degradation in windows systems. I don't know what is the reason. https://github.com/pytorch/pytorch/issues/22083 gives some information.