Saturday, August 17, 2019

Gaussian blur/filter


Resources:
OpenCL:

$clinfo

 [1] 2D Gauss+SIPL https://www.eriksmistad.no/gaussian-blur-using-opencl-and-the-built-in-images-textures/


[2] Gaussian blur  https://github.com/mnmnc/gaussian_blur_opencl
$locate CL/cl.h
$sudo apt install ocl-icd-opencl-dev
$g++ main.cpp lodepng.cpp -lOpenCL -std=c++11 -o gb -I /usr/include





Cuda:
[1] Compile by Cuda 8 https://github.com/yanji84/cuda-blur
$nvcc -c -arch=sm_20 blur.cu -I /usr/local/cuda-8.0/samples/common/inc/
$g++ main.cpp reference_cal.cpp util.cpp -I /usr/local/cuda-8.0/samples/common/inc/ `pkg-config --cflags --libs opencv` -lcuda  -I /usr/local/cuda-8.0/targets/x86_64-linux/include/ blur.o  -std=c++11 -L /usr/local/cuda-8.0/targets/x86_64-linux/lib/ -lcudart


[2] Gaussian kd-tree https://melhorum.blogspot.com/search?q=Gaussian

Cuda Makefile:
all: program

program: cudacode.o
    g++ -o program -L/usr/local/cuda/lib64 -lcuda -lcudart main.cpp  cudacode.o 

cudacode.o:
    nvcc -c -arch=sm_20 cudacode.cu 

clean: rm -rf *o program
 
Cuda Tutorials:
[1] Hello https://cuda-tutorial.readthedocs.io/en/latest/tutorials/tutorial01/
[2] Summary http://www.icl.utk.edu/~mgates3/docs/cuda.html
[1] locate convolutionSeparable #example from cuda
[2] Samples https://docs.nvidia.com/cuda/cuda-samples/index.html#cuda-separable-convolution
[3] Compiling https://devblogs.nvidia.com/easy-introduction-cuda-c-and-c/
[4] Find Cuda https://github.com/dusty-nv/jetson-utils/tree/master/cuda
[5] Image to GL https://github.com/zchee/cuda-sample/tree/master/3_Imaging/simpleCUDA2GL
[6] Image processing http://developer.download.nvidia.com/compute/DevZone/C/html/Image_Processing.html

References:


No comments:

Ubuntu Forware port 80

  #!/bin/bash iptables -t nat -A PREROUTING -i eth0 -p tcp --dport 80 -j REDIRECT --to-port 8069 iptables -t nat -A PREROUTING -i eth0 -p tc...