add gaussianBlur example

.gitignore

@@ -1 +1,2 @@
-.vscode/
+.vscode/
+/build

CMakeLists.txt

@@ -10,7 +10,7 @@ SET(EXECUTABLE_OUTPUT_PATH "${PROJECT_BINARY_DIR}/bin")
 
 #Find OpenCV
 find_package(OpenCV REQUIRED)
-include_directories(${OpenCV_INCLUDE_DIRS})
+
 link_directories(${OpenCV_LIBRARY_DIRS})
 if(NOT OpenCV_FOUND)
     message(ERROR " OpenCV not found!")
@@ -29,6 +29,7 @@ if (CUDA_FOUND)
 	add_subdirectory(chapter08)
 	add_subdirectory(chapter09)
 	add_subdirectory(chapter10)
+	add_subdirectory(test)
 else()
 	message("CUDA not found!")
 endif()

test/CMakeLists.txt

@@ -0,0 +1,23 @@
+CMAKE_MINIMUM_REQUIRED(VERSION 3.1)
+
+
+CUDA_ADD_EXECUTABLE(add add.cu)
+SET_PROPERTY(TARGET add PROPERTY FOLDER test)
+
+
+
+CUDA_ADD_EXECUTABLE(helloWorld helloWorld.cu)
+SET_PROPERTY(TARGET helloWorld PROPERTY FOLDER test)
+
+include_directories(${OpenCV_INCLUDE_DIRS})
+message(${OpenCV_INCLUDE_DIRS})
+
+include_directories(.)
+
+CUDA_ADD_EXECUTABLE(gaussianblur gaussianblur.cu)
+
+TARGET_LINK_LIBRARIES(gaussianblur
+ ${OpenCV_LIBS})
+
+SET_PROPERTY(TARGET gaussianblur PROPERTY FOLDER test)
+

test/add.cu

@@ -0,0 +1,226 @@
+/**
+* Copyright 1993-2015 NVIDIA Corporation.  All rights reserved.
+*
+* Please refer to the NVIDIA end user license agreement (EULA) associated
+* with this source code for terms and conditions that govern your use of
+* this software. Any use, reproduction, disclosure, or distribution of
+* this software and related documentation outside the terms of the EULA
+* is strictly prohibited.
+*
+*/
+
+/**
+* Vector addition: C = A + B.
+*
+* This sample is a very basic sample that implements element by element
+* vector addition. It is the same as the sample illustrating Chapter 2
+* of the programming guide with some additions like error checking.
+*/
+
+#include <stdio.h>
+
+// For the CUDA runtime routines (prefixed with "cuda_")
+#include <cuda_runtime.h>
+
+//#include <helper_cuda.h>
+/**
+* CUDA Kernel Device code
+*
+* Computes the vector addition of A and B into C. The 3 vectors have the same
+* number of elements numElements.
+*/
+__global__ void
+vectorAdd(const float *A, const float *B, float *C, int numElements)
+{
+	int i = blockDim.x * blockIdx.x + threadIdx.x;
+
+	if (i < numElements)
+	{
+		C[i] = A[i] + B[i];
+	}
+}
+#include <time.h>
+#include <iostream>
+#include <windows.h>
+/**
+* Host main routine
+*/
+int
+main(void)
+{
+
+	LARGE_INTEGER t1, t2, tc;
+	QueryPerformanceFrequency(&tc);
+	long i;
+
+	// Error code to check return values for CUDA calls
+	cudaError_t err = cudaSuccess;
+
+	// Print the vector length to be used, and compute its size
+	int numElements = 2 << 20;
+	size_t size = numElements * sizeof(float);
+	printf("[Vector addition of %d elements]\n", numElements);
+
+	// Allocate the host input vector A
+	float *h_A = (float *)malloc(size);
+
+	// Allocate the host input vector B
+	float *h_B = (float *)malloc(size);
+
+	// Allocate the host output vector C
+	float *h_C = (float *)malloc(size);
+
+	// Verify that allocations succeeded
+	if (h_A == NULL || h_B == NULL || h_C == NULL)
+	{
+		fprintf(stderr, "Failed to allocate host vectors!\n");
+		exit(EXIT_FAILURE);
+	}
+
+	// Initialize the host input vectors
+	for (int i = 0; i < numElements; ++i)
+	{
+		h_A[i] = rand() / (float)RAND_MAX;
+		h_B[i] = rand() / (float)RAND_MAX;
+	}
+
+	// Allocate the device input vector A
+	float *d_A = NULL;
+	err = cudaMalloc((void **)&d_A, size);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to allocate device vector A (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	// Allocate the device input vector B
+	float *d_B = NULL;
+	err = cudaMalloc((void **)&d_B, size);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to allocate device vector B (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	// Allocate the device output vector C
+	float *d_C = NULL;
+	err = cudaMalloc((void **)&d_C, size);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to allocate device vector C (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	// Copy the host input vectors A and B in host memory to the device input vectors in
+	// device memory
+	printf("Copy input data from the host memory to the CUDA device\n");
+	err = cudaMemcpy(d_A, h_A, size, cudaMemcpyHostToDevice);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to copy vector A from host to device (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	err = cudaMemcpy(d_B, h_B, size, cudaMemcpyHostToDevice);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to copy vector B from host to device (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	// Launch the Vector Add CUDA Kernel
+	int threadsPerBlock = 256;
+	int blocksPerGrid = (numElements + threadsPerBlock - 1) / threadsPerBlock;
+	printf("CUDA kernel launch with %d blocks of %d threads\n", blocksPerGrid, threadsPerBlock);
+
+	QueryPerformanceCounter(&t1);
+	vectorAdd << <blocksPerGrid, threadsPerBlock >> >(d_A, d_B, d_C, numElements);
+	err = cudaGetLastError();
+	QueryPerformanceCounter(&t2);
+	std::cout << "gpu cost: " << (t2.QuadPart - t1.QuadPart)*1.0 / tc.QuadPart << std::endl;
+	double gpuTime = (t2.QuadPart - t1.QuadPart)*1.0;
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to launch vectorAdd kernel (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	// Copy the device result vector in device memory to the host result vector
+	// in host memory.
+	printf("Copy output data from the CUDA device to the host memory\n");
+	err = cudaMemcpy(h_C, d_C, size, cudaMemcpyDeviceToHost);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to copy vector C from device to host (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+
+
+	// Verify that the result vector is correct
+	for (int i = 0; i < numElements; ++i)
+	{
+		if (fabs(h_A[i] + h_B[i] - h_C[i]) > 1e-10)
+		{
+			fprintf(stderr, "Result verification failed at element %d!\n", i);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	printf("Test PASSED\n");
+
+
+	QueryPerformanceCounter(&t1);
+	for (int i = 0; i < numElements; ++i)
+	{
+		h_C[i] = h_A[i] + h_B[i];
+	}
+
+	QueryPerformanceCounter(&t2);
+	std::cout << "cpu cost: " << (t2.QuadPart - t1.QuadPart)*1.0 / tc.QuadPart << std::endl;
+	double cpuTime = (t2.QuadPart - t1.QuadPart)*1.0;
+
+	std::cout << "���ٱ�: " << cpuTime / gpuTime << std::endl;
+
+
+	// Free device global memory
+	err = cudaFree(d_A);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to free device vector A (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	err = cudaFree(d_B);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to free device vector B (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	err = cudaFree(d_C);
+
+	if (err != cudaSuccess)
+	{
+		fprintf(stderr, "Failed to free device vector C (error code %s)!\n", cudaGetErrorString(err));
+		exit(EXIT_FAILURE);
+	}
+
+	// Free host memory
+	free(h_A);
+	free(h_B);
+	free(h_C);
+
+	printf("Done\n");
+	return 0;
+}
+