CUDA 10.1
2080 Ti
latest geforce drivers
I use a program called Starnet++ which normally uses AVX to remove stars from astrophotography images. Someone made a tensorflow.dll that tells the program to use the GPU instead of the CPU. When I run the program, i get this output:
PS E:\Astro\StarNet_Win> .\rgb_starnet++.exe ‘E:\Scope\Targets\Andromeda Galaxy M31\60mm\Andromeda_2.tif’
2020-09-08 21:13:44.886688: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudart64_101.dll
Reading input image… TIFFReadDirectory: Warning, Unknown field with tag 37724 (0x935c) encountered.
Done!
Bits per sample: 16
Samples per pixel: 3
Height: 4500
Width: 4896
Restoring neural network checkpoint… Done!
2020-09-08 21:13:52.020545: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations: AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2020-09-08 21:13:52.053077: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x272b78a5320 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-09-08 21:13:52.053163: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
2020-09-08 21:13:52.058242: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library nvcuda.dll
2020-09-08 21:13:52.080903: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1716] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: GeForce RTX 2080 Ti computeCapability: 7.5
coreClock: 1.62GHz coreCount: 68 deviceMemorySize: 11.00GiB deviceMemoryBandwidth: 573.69GiB/s
2020-09-08 21:13:52.081000: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudart64_101.dll
2020-09-08 21:13:52.085975: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cublas64_10.dll
2020-09-08 21:13:52.089461: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cufft64_10.dll
2020-09-08 21:13:52.091125: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library curand64_10.dll
2020-09-08 21:13:52.095350: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cusolver64_10.dll
2020-09-08 21:13:52.097962: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cusparse64_10.dll
2020-09-08 21:13:52.111342: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudnn64_7.dll
2020-09-08 21:13:52.112290: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1858] Adding visible gpu devices: 0
2020-09-08 21:13:53.511078: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1257] Device interconnect StreamExecutor with strength 1 edge matrix:
2020-09-08 21:13:53.511147: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1263] 0
2020-09-08 21:13:53.512067: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1276] 0: N
2020-09-08 21:13:53.513030: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:39] Overriding allow_growth setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.
2020-09-08 21:13:53.513103: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1402] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 9419 MB memory) → physical GPU (device: 0, name: GeForce RTX 2080 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5)
2020-09-08 21:13:53.519145: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x27285e3e810 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:
2020-09-08 21:13:53.519199: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): GeForce RTX 2080 Ti, Compute Capability 7.5
Total number of tiles: 5467
2020-09-08 21:13:56.732740: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cudnn64_7.dll
2020-09-08 21:13:57.524116: W tensorflow/stream_executor/gpu/redzone_allocator.cc:314] Internal: Invoking GPU asm compilation is supported on Cuda non-Windows platforms only
Relying on driver to perform ptx compilation.
Modify $PATH to customize ptxas location.
This message will be only logged once.
2020-09-08 21:13:57.535013: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library cublas64_10.dll
100% finished
Done!
I am new to CUDA on the dev side and was just wondering why wouldn’t the program see the CUDA cores of my gpu?