CUDA编程（一）：QT中编写cuda代码

可以下载一下demo:https://pan.baidu.com/s/1mUsb0iIOA5tnX7MOSpcHMQ  j8j2

1.pro文件配置（在已有工程的配置的内容下，添加以下内容）

#在已有的工程上添加以下内容
####cuda库########
LIBS += -L"/usr/local/lib" \
    -L"/usr/local/cuda/lib64" \
    -lcudart \
    -lcufft

DEPENDPATH += .

#你所编写的cuda文件#######
OTHER_FILES += bilinear.cu

CUDA_SOURCES += bilinear.cu



CUDA_SDK = "/usr/local/cuda-8.0/"   # Path to cuda SDK install
CUDA_DIR = "/usr/local/cuda-8.0/"            # Path to cuda toolkit install
#####系统类型，计算能力###########
SYSTEM_NAME = linux         # Depending on your system either 'Win32', 'x64', or 'Win64'
SYSTEM_TYPE = 64            # '32' or '64', depending on your system
CUDA_ARCH = sm_21           # Type of CUDA architecture, for example 'compute_10', 'compute_11', 'sm_10'
NVCC_OPTIONS = --use_fast_math


INCLUDEPATH += $$CUDA_DIR/include
QMAKE_LIBDIR += $$CUDA_DIR/lib64/

CUDA_OBJECTS_DIR = ./

CUDA_LIBS = cudart cufft
CUDA_INC = $$join(INCLUDEPATH,'" -I"','-I"','"')
NVCC_LIBS = $$join(CUDA_LIBS,' -l','-l', '')

CONFIG(debug, debug|release) {
    # Debug mode
    cuda_d.input = CUDA_SOURCES
    cuda_d.output = $$CUDA_OBJECTS_DIR/${QMAKE_FILE_BASE}_cuda.o
    cuda_d.commands = $$CUDA_DIR/bin/nvcc -D_DEBUG $$NVCC_OPTIONS $$CUDA_INC $$NVCC_LIBS --machine $$SYSTEM_TYPE -arch=$$CUDA_ARCH -c -o ${QMAKE_FILE_OUT} ${QMAKE_FILE_NAME}
    cuda_d.dependency_type = TYPE_C
    QMAKE_EXTRA_COMPILERS += cuda_d
}
else {
    # Release mode
    cuda.input = CUDA_SOURCES
    cuda.output = $$CUDA_OBJECTS_DIR/${QMAKE_FILE_BASE}_cuda.o
    cuda.commands = $$CUDA_DIR/bin/nvcc $$NVCC_OPTIONS $$CUDA_INC $$NVCC_LIBS --machine $$SYSTEM_TYPE -arch=$$CUDA_ARCH -O3 -c -o ${QMAKE_FILE_OUT} ${QMAKE_FILE_NAME}
    cuda.dependency_type = TYPE_C
    QMAKE_EXTRA_COMPILERS += cuda
}

 

2.main.cpp

#include<stdio.h>
#include "bilinear.h"
int main(void)
{
   showhello();
   while(1);
}
//nvcc -arch sm_20

3.cuda文件：bilinear.cu

#include "bilinear.h"

extern "C"
__global__ void hellofromGPU(void)
{
    printf("GPU:hello sunyi\n");
}

void showhello(void)
{
    hellofromGPU <<<1,10>>>();
    cudaDeviceSynchronize();

}

4.头文件

#ifndef BILINEAR_H
#define BILINEAR_H
#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <stdio.h>
#include "malloc.h"
#define  WIDTH 11

#define  HEIGHT 10
#define  X_INTER 3
#define  Y_INTER 3
#define  BLOCK_SIZE 8

void showhello(void);
#endif // BINLINEARINTERPOLATIONCUDA_H