NVIDIA AMD Linux GPU Compute December 2018 Suite
1.0.0
System
Test suite extracted from NVIDIA AMD Linux GPU Compute December 2018.
pts/shoc-1.1.0
-opencl -benchmark FFT
Target: OpenCL - Benchmark: FFT SP
pts/shoc-1.1.0
-opencl -benchmark MD5Hash
Target: OpenCL - Benchmark: MD5 Hash
pts/shoc-1.1.0
-opencl -benchmark DeviceMemory
Target: OpenCL - Benchmark: Texture Read Bandwidth
pts/cl-mem-1.0.1
COPY
Benchmark: Copy
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/resnet.py --layers 50 -b 64 --precision fp16
Test: ResNet-50, FP16
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/resnet.py --layers 50 -b 64 --precision fp32
Test: ResNet-50, FP32
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/alexnet.py -b 256 --precision fp16
Test: AlexNet, FP16
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/alexnet.py -b 256 --precision fp32
Test: AlexNet, FP32
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/googlenet.py --precision fp16
Test: Googlenet, FP16
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/inception_v4.py -b 32 --precision fp16
Test: Inception v4, FP16
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/vgg.py --layers 16 -b 32 --precision fp16
Test: VGG-16, FP16
pts/ngc-tensorflow-1.0.0
/workspace/nvidia-examples/cnn/vgg.py --layers 16 -b 32 --precision fp32
Test: VGG-16, FP32