search

jiazhihao / TASO

The Tensor Algebra SuperOptimizer for Deep Learning
Apache License 2.0
692 stars 90 forks source link

run example failed #86

Open MingliSun opened 3 years ago

MingliSun commented 3 years ago

I build TASO on ubuntu18.04(on cuda) and python version is 3.8.6 and GCC is 7.5.0 And this is my nvidia-smi output:

+-----------------------------------------------------------------------------+ | NVIDIA-SMI 440.100 Driver Version: 440.100 CUDA Version: 10.2 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | |===============================+======================+======================| | 0 GeForce 920M Off | 00000000:01:00.0 N/A | N/A | | N/A 56C P0 N/A / N/A | 478MiB / 2004MiB | N/A Default | +-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+ | Processes: GPU Memory | | GPU PID Type Process name Usage | |=============================================================================| | 0 Not Supported | +-----------------------------------------------------------------------------+

An error occured when I run item in examples: Cuda failure: 2 /home/sun/gitDownload/taso/src/cudnn/ops_cudnn.cu:29 Aborting... I looked up in docs.nvidia.com and

cudaErrorMemoryAllocation = 2

means that

The API call failed because it was unable to allocate enough memory to perform the requested operation so it's my GPU problem or not? should I change another computer to run it?

Thanks

gcunhase commented 2 years ago

Also facing the same issue. Is this repo still active?

Pegessi commented 1 year ago

Maybe you should give more info about this failure.