立方体纹理贴图

▶ 源代码。用纹理方法把元素按原顺序从 CUDA3D 数组中取出来，求个相反数放入全局内存，输出。

 #include <stdio.h>

 #include "cuda_runtime.h"

 #include "device_launch_parameters.h"

 #include <helper_functions.h>

 #include <helper_cuda.h>

 #define MIN_EPSILON_ERROR 5e-3f

 texture<float, cudaTextureTypeCubemap> tex;

 __global__ void transformKernel(float *g_odata, int width)

 {

     unsigned int x = blockIdx.x*blockDim.x + threadIdx.x;

     unsigned int y = blockIdx.y*blockDim.y + threadIdx.y;

     float u = ((x + 0.5f) / (float)width) * .f - .f;// [0, width-1] 间隔 1 的坐标变换为 [-1+1/width,1-1/width] 间隔 1/width 的坐标

     float v = ((y + 0.5f) / (float)width) * .f - .f;

     float cx, cy, cz;

     for (unsigned int face = ; face < ; face++)

     {

         if (face == )// x 正层

         {

             cx = ;

             cy = -v;

             cz = -u;

         }

         else if (face == )// x 负层

         {

             cx = -;

             cy = -v;

             cz = u;

         }

         else if (face == )// y 正层

         {

             cx = u;

             cy = ;

             cz = v;

         }

         else if (face == )// y 负层

         {

             cx = u;

             cy = -;

             cz = -v;

         }

         else if (face == )// z 正层

         {

             cx = u;

             cy = -v;

             cz = ;

         }

         else if (face == )// z 负层

         {

             cx = -u;

             cy = -v;

             cz = -;

         }

         g_odata[face*width*width + y*width + x] = - texCubemap(tex, cx, cy, cz);// 纹理数据读取到全局内存中输出

     }

 }

 int main(int argc, char** argv)

 {

     unsigned int width = , num_faces = , num_layers = ;

     unsigned int cubemap_size = width * width * num_faces;

     unsigned int size = cubemap_size * num_layers * sizeof(float);

     float *h_data = (float *)malloc(size);

     float *h_data_ref = (float *)malloc(size);  // 理论输出

     float *d_data = NULL;

     cudaMalloc((void **)&d_data, size);

     for (int i = ; i < (int)(cubemap_size * num_layers); i++)

         h_data[i] = (float)i;

     for (unsigned int layer = ; layer < num_layers; layer++)

     {

         for (int i = ; i < (int)(cubemap_size); i++)

             h_data_ref[layer*cubemap_size + i] = -h_data[layer*cubemap_size + i] + layer;

     }

     printf("\n\t\Input data.n\t");

     for (int i = ; i < width * num_faces * num_layers; i++)

     {

         printf("%2.1f ", h_data[i]);

         if ((i + ) % width == )

             printf("\n\t");

         if ((i + ) % (width *width) == )

             printf("\n\t");

     }

     printf("\n\tIdeal output data\n\t");

     for (int i = ; i < width * num_faces * num_layers; i++)

     {

         printf("%2.1f ", h_data_ref[i]);

         if ((i + ) % width == )

             printf("\n\t");

         if ((i + ) % (width *width) == )

             printf("\n\t");

     }

     // 设置 CUDA 3D 数组参数和数据拷贝

     cudaChannelFormatDesc channelDesc = cudaCreateChannelDesc(, , , , cudaChannelFormatKindFloat);

     cudaArray *cu_3darray;

     cudaMalloc3DArray(&cu_3darray, &channelDesc, make_cudaExtent(width, width, num_faces), cudaArrayCubemap);

     cudaMemcpy3DParms myparms = {  };

     myparms.srcPos = make_cudaPos(, , );

     myparms.dstPos = make_cudaPos(, , );

     myparms.srcPtr = make_cudaPitchedPtr(h_data, width * sizeof(float), width, width);

     myparms.dstArray = cu_3darray;

     myparms.extent = make_cudaExtent(width, width, num_faces);

     myparms.kind = cudaMemcpyHostToDevice;

     cudaMemcpy3D(&myparms);

     // 设置纹理参数并绑定

     tex.addressMode[] = cudaAddressModeWrap;

     tex.addressMode[] = cudaAddressModeWrap;

     tex.filterMode = cudaFilterModeLinear;

     tex.normalized = true;

     cudaBindTextureToArray(tex, cu_3darray, channelDesc);

     dim3 dimBlock(, , );

     dim3 dimGrid(width / dimBlock.x, width / dimBlock.y, );

     printf("\n\tCubemap data of %d * %d * %d: Grid size is %d x %d, each block has 8 x 8 threads.\n", width, width, num_layers, dimGrid.x, dimGrid.y);

     transformKernel << < dimGrid, dimBlock >> >(d_data, width);// 预跑

     cudaDeviceSynchronize();

     StopWatchInterface *timer = NULL;// 新的计时工具

     sdkCreateTimer(&timer);

     sdkStartTimer(&timer);

     transformKernel << < dimGrid, dimBlock,  >> >(d_data, width);

     cudaDeviceSynchronize();

     sdkStopTimer(&timer);

     printf("\n\Time: %.3f msec, %.2f Mtexlookups/sec\n", sdkGetTimerValue(&timer), (cubemap_size / (sdkGetTimerValue(&timer) / 1000.0f) / 1e6));

     sdkDeleteTimer(&timer);

     // 返回计算结果并检验

     memset(h_data, , size);

     cudaMemcpy(h_data, d_data, size, cudaMemcpyDeviceToHost);

     if (checkCmdLineFlag(argc, (const char **)argv, "regression"))

         sdkWriteFile<float>("./data/regression.dat", h_data, width * width, 0.0f, false);

     else

         printf("Comparing kernel output to expected data return %d\n", compareData(h_data, h_data_ref, cubemap_size, MIN_EPSILON_ERROR, 0.0f));

     printf("\n\tActual output data\n\t");

     for (int i = ; i < width * num_faces * num_layers; i++)

     {

         printf("%2.1f ", h_data[i]);

         if ((i + ) % width == )

             printf("\n\t");

         if ((i + ) % (width * width) == )

             printf("\n\t");

     }

     free(h_data);

     free(h_data_ref);

     cudaFree(d_data);

     cudaFreeArray(cu_3darray);

     getchar();

     return ;

 }

▶ 输出结果

    Input data.n    0.0 1.0 2.0 3.0 4.0 5.0 6.0 7.0 8.0 9.0 10.0 11.0 12.0 13.0 14.0 15.0 16.0 17.0 18.0 19.0 20.0 21.0 22.0 23.0 24.0 25.0 26.0 27.0 28.0 29.0 30.0 31.0 32.0 33.0 34.0 35.0 36.0 37.0 38.0 39.0 40.0 41.0 42.0 43.0 44.0 45.0 46.0 47.0 48.0 49.0 50.0 51.0 52.0 53.0 54.0 55.0 56.0 57.0 58.0 59.0 60.0 61.0 62.0 63.0

    64.0 65.0 66.0 67.0 68.0 69.0 70.0 71.0 72.0 73.0 74.0 75.0 76.0 77.0 78.0 79.0 80.0 81.0 82.0 83.0 84.0 85.0 86.0 87.0 88.0 89.0 90.0 91.0 92.0 93.0 94.0 95.0 96.0 97.0 98.0 99.0 100.0 101.0 102.0 103.0 104.0 105.0 106.0 107.0 108.0 109.0 110.0 111.0 112.0 113.0 114.0 115.0 116.0 117.0 118.0 119.0 120.0 121.0 122.0 123.0 124.0 125.0 126.0 127.0

    128.0 129.0 130.0 131.0 132.0 133.0 134.0 135.0 136.0 137.0 138.0 139.0 140.0 141.0 142.0 143.0 144.0 145.0 146.0 147.0 148.0 149.0 150.0 151.0 152.0 153.0 154.0 155.0 156.0 157.0 158.0 159.0 160.0 161.0 162.0 163.0 164.0 165.0 166.0 167.0 168.0 169.0 170.0 171.0 172.0 173.0 174.0 175.0 176.0 177.0 178.0 179.0 180.0 181.0 182.0 183.0 184.0 185.0 186.0 187.0 188.0 189.0 190.0 191.0

    192.0 193.0 194.0 195.0 196.0 197.0 198.0 199.0 200.0 201.0 202.0 203.0 204.0 205.0 206.0 207.0 208.0 209.0 210.0 211.0 212.0 213.0 214.0 215.0 216.0 217.0 218.0 219.0 220.0 221.0 222.0 223.0 224.0 225.0 226.0 227.0 228.0 229.0 230.0 231.0 232.0 233.0 234.0 235.0 236.0 237.0 238.0 239.0 240.0 241.0 242.0 243.0 244.0 245.0 246.0 247.0 248.0 249.0 250.0 251.0 252.0 253.0 254.0 255.0

    256.0 257.0 258.0 259.0 260.0 261.0 262.0 263.0 264.0 265.0 266.0 267.0 268.0 269.0 270.0 271.0 272.0 273.0 274.0 275.0 276.0 277.0 278.0 279.0 280.0 281.0 282.0 283.0 284.0 285.0 286.0 287.0 288.0 289.0 290.0 291.0 292.0 293.0 294.0 295.0 296.0 297.0 298.0 299.0 300.0 301.0 302.0 303.0 304.0 305.0 306.0 307.0 308.0 309.0 310.0 311.0 312.0 313.0 314.0 315.0 316.0 317.0 318.0 319.0

    320.0 321.0 322.0 323.0 324.0 325.0 326.0 327.0 328.0 329.0 330.0 331.0 332.0 333.0 334.0 335.0 336.0 337.0 338.0 339.0 340.0 341.0 342.0 343.0 344.0 345.0 346.0 347.0 348.0 349.0 350.0 351.0 352.0 353.0 354.0 355.0 356.0 357.0 358.0 359.0 360.0 361.0 362.0 363.0 364.0 365.0 366.0 367.0 368.0 369.0 370.0 371.0 372.0 373.0 374.0 375.0 376.0 377.0 378.0 379.0 380.0 381.0 382.0 383.0

    Ideal output data

    0.0 -1.0 -2.0 -3.0 -4.0 -5.0 -6.0 -7.0 -8.0 -9.0 -10.0 -11.0 -12.0 -13.0 -14.0 -15.0 -16.0 -17.0 -18.0 -19.0 -20.0 -21.0 -22.0 -23.0 -24.0 -25.0 -26.0 -27.0 -28.0 -29.0 -30.0 -31.0 -32.0 -33.0 -34.0 -35.0 -36.0 -37.0 -38.0 -39.0 -40.0 -41.0 -42.0 -43.0 -44.0 -45.0 -46.0 -47.0 -48.0 -49.0 -50.0 -51.0 -52.0 -53.0 -54.0 -55.0 -56.0 -57.0 -58.0 -59.0 -60.0 -61.0 -62.0 -63.0

    -64.0 -65.0 -66.0 -67.0 -68.0 -69.0 -70.0 -71.0 -72.0 -73.0 -74.0 -75.0 -76.0 -77.0 -78.0 -79.0 -80.0 -81.0 -82.0 -83.0 -84.0 -85.0 -86.0 -87.0 -88.0 -89.0 -90.0 -91.0 -92.0 -93.0 -94.0 -95.0 -96.0 -97.0 -98.0 -99.0 -100.0 -101.0 -102.0 -103.0 -104.0 -105.0 -106.0 -107.0 -108.0 -109.0 -110.0 -111.0 -112.0 -113.0 -114.0 -115.0 -116.0 -117.0 -118.0 -119.0 -120.0 -121.0 -122.0 -123.0 -124.0 -125.0 -126.0 -127.0

    -128.0 -129.0 -130.0 -131.0 -132.0 -133.0 -134.0 -135.0 -136.0 -137.0 -138.0 -139.0 -140.0 -141.0 -142.0 -143.0 -144.0 -145.0 -146.0 -147.0 -148.0 -149.0 -150.0 -151.0 -152.0 -153.0 -154.0 -155.0 -156.0 -157.0 -158.0 -159.0 -160.0 -161.0 -162.0 -163.0 -164.0 -165.0 -166.0 -167.0 -168.0 -169.0 -170.0 -171.0 -172.0 -173.0 -174.0 -175.0 -176.0 -177.0 -178.0 -179.0 -180.0 -181.0 -182.0 -183.0 -184.0 -185.0 -186.0 -187.0 -188.0 -189.0 -190.0 -191.0

    -192.0 -193.0 -194.0 -195.0 -196.0 -197.0 -198.0 -199.0 -200.0 -201.0 -202.0 -203.0 -204.0 -205.0 -206.0 -207.0 -208.0 -209.0 -210.0 -211.0 -212.0 -213.0 -214.0 -215.0 -216.0 -217.0 -218.0 -219.0 -220.0 -221.0 -222.0 -223.0 -224.0 -225.0 -226.0 -227.0 -228.0 -229.0 -230.0 -231.0 -232.0 -233.0 -234.0 -235.0 -236.0 -237.0 -238.0 -239.0 -240.0 -241.0 -242.0 -243.0 -244.0 -245.0 -246.0 -247.0 -248.0 -249.0 -250.0 -251.0 -252.0 -253.0 -254.0 -255.0

    -256.0 -257.0 -258.0 -259.0 -260.0 -261.0 -262.0 -263.0 -264.0 -265.0 -266.0 -267.0 -268.0 -269.0 -270.0 -271.0 -272.0 -273.0 -274.0 -275.0 -276.0 -277.0 -278.0 -279.0 -280.0 -281.0 -282.0 -283.0 -284.0 -285.0 -286.0 -287.0 -288.0 -289.0 -290.0 -291.0 -292.0 -293.0 -294.0 -295.0 -296.0 -297.0 -298.0 -299.0 -300.0 -301.0 -302.0 -303.0 -304.0 -305.0 -306.0 -307.0 -308.0 -309.0 -310.0 -311.0 -312.0 -313.0 -314.0 -315.0 -316.0 -317.0 -318.0 -319.0

    -320.0 -321.0 -322.0 -323.0 -324.0 -325.0 -326.0 -327.0 -328.0 -329.0 -330.0 -331.0 -332.0 -333.0 -334.0 -335.0 -336.0 -337.0 -338.0 -339.0 -340.0 -341.0 -342.0 -343.0 -344.0 -345.0 -346.0 -347.0 -348.0 -349.0 -350.0 -351.0 -352.0 -353.0 -354.0 -355.0 -356.0 -357.0 -358.0 -359.0 -360.0 -361.0 -362.0 -363.0 -364.0 -365.0 -366.0 -367.0 -368.0 -369.0 -370.0 -371.0 -372.0 -373.0 -374.0 -375.0 -376.0 -377.0 -378.0 -379.0 -380.0 -381.0 -382.0 -383.0

    Cubemap data of  *  * : Grid size is  x , each block has  x  threads.

Time: 0.098 msec, 249.50 Mtexlookups/sec

Comparing kernel output to expected data return 

    Actual output data

    -0.0 -1.0 -2.0 -3.0 -4.0 -5.0 -6.0 -7.0 -8.0 -9.0 -10.0 -11.0 -12.0 -13.0 -14.0 -15.0 -16.0 -17.0 -18.0 -19.0 -20.0 -21.0 -22.0 -23.0 -24.0 -25.0 -26.0 -27.0 -28.0 -29.0 -30.0 -31.0 -32.0 -33.0 -34.0 -35.0 -36.0 -37.0 -38.0 -39.0 -40.0 -41.0 -42.0 -43.0 -44.0 -45.0 -46.0 -47.0 -48.0 -49.0 -50.0 -51.0 -52.0 -53.0 -54.0 -55.0 -56.0 -57.0 -58.0 -59.0 -60.0 -61.0 -62.0 -63.0

    -64.0 -65.0 -66.0 -67.0 -68.0 -69.0 -70.0 -71.0 -72.0 -73.0 -74.0 -75.0 -76.0 -77.0 -78.0 -79.0 -80.0 -81.0 -82.0 -83.0 -84.0 -85.0 -86.0 -87.0 -88.0 -89.0 -90.0 -91.0 -92.0 -93.0 -94.0 -95.0 -96.0 -97.0 -98.0 -99.0 -100.0 -101.0 -102.0 -103.0 -104.0 -105.0 -106.0 -107.0 -108.0 -109.0 -110.0 -111.0 -112.0 -113.0 -114.0 -115.0 -116.0 -117.0 -118.0 -119.0 -120.0 -121.0 -122.0 -123.0 -124.0 -125.0 -126.0 -127.0

    -128.0 -129.0 -130.0 -131.0 -132.0 -133.0 -134.0 -135.0 -136.0 -137.0 -138.0 -139.0 -140.0 -141.0 -142.0 -143.0 -144.0 -145.0 -146.0 -147.0 -148.0 -149.0 -150.0 -151.0 -152.0 -153.0 -154.0 -155.0 -156.0 -157.0 -158.0 -159.0 -160.0 -161.0 -162.0 -163.0 -164.0 -165.0 -166.0 -167.0 -168.0 -169.0 -170.0 -171.0 -172.0 -173.0 -174.0 -175.0 -176.0 -177.0 -178.0 -179.0 -180.0 -181.0 -182.0 -183.0 -184.0 -185.0 -186.0 -187.0 -188.0 -189.0 -190.0 -191.0

    -192.0 -193.0 -194.0 -195.0 -196.0 -197.0 -198.0 -199.0 -200.0 -201.0 -202.0 -203.0 -204.0 -205.0 -206.0 -207.0 -208.0 -209.0 -210.0 -211.0 -212.0 -213.0 -214.0 -215.0 -216.0 -217.0 -218.0 -219.0 -220.0 -221.0 -222.0 -223.0 -224.0 -225.0 -226.0 -227.0 -228.0 -229.0 -230.0 -231.0 -232.0 -233.0 -234.0 -235.0 -236.0 -237.0 -238.0 -239.0 -240.0 -241.0 -242.0 -243.0 -244.0 -245.0 -246.0 -247.0 -248.0 -249.0 -250.0 -251.0 -252.0 -253.0 -254.0 -255.0

    -256.0 -257.0 -258.0 -259.0 -260.0 -261.0 -262.0 -263.0 -264.0 -265.0 -266.0 -267.0 -268.0 -269.0 -270.0 -271.0 -272.0 -273.0 -274.0 -275.0 -276.0 -277.0 -278.0 -279.0 -280.0 -281.0 -282.0 -283.0 -284.0 -285.0 -286.0 -287.0 -288.0 -289.0 -290.0 -291.0 -292.0 -293.0 -294.0 -295.0 -296.0 -297.0 -298.0 -299.0 -300.0 -301.0 -302.0 -303.0 -304.0 -305.0 -306.0 -307.0 -308.0 -309.0 -310.0 -311.0 -312.0 -313.0 -314.0 -315.0 -316.0 -317.0 -318.0 -319.0

    -320.0 -321.0 -322.0 -323.0 -324.0 -325.0 -326.0 -327.0 -328.0 -329.0 -330.0 -331.0 -332.0 -333.0 -334.0 -335.0 -336.0 -337.0 -338.0 -339.0 -340.0 -341.0 -342.0 -343.0 -344.0 -345.0 -346.0 -347.0 -348.0 -349.0 -350.0 -351.0 -352.0 -353.0 -354.0 -355.0 -356.0 -357.0 -358.0 -359.0 -360.0 -361.0 -362.0 -363.0 -364.0 -365.0 -366.0 -367.0 -368.0 -369.0 -370.0 -371.0 -372.0 -373.0 -374.0 -375.0 -376.0 -377.0 -378.0 -379.0 -380.0 -381.0 -382.0 -383.0

▶ 涨姿势

● helper_time.h 中新定义的计时函数

 // 关键步骤

 StopWatchInterface *timer = NULL;

 sdkCreateTimer(&timer);

 sdkStartTimer(&timer);

 sdkStopTimer(&timer);

 sdkGetTimerValue(&timer);

 sdkDeleteTimer(&timer);

 // helper_time.h

 class StopWatchInterface

 {

     public:

         StopWatchInterface() {};

         virtual ~StopWatchInterface() {};

     public:

         virtual void start() = ;

         virtual void stop() = ;

         virtual void reset() = ;

         virtual float getTime() = ;// 获取计时（计时器不停）

         virtual float getAverageTime() = ;

 };

 inline bool sdkCreateTimer(StopWatchInterface **timer_interface)

 {

 #if defined(WIN32) || defined(_WIN32) || defined(WIN64) || defined(_WIN64)

     *timer_interface = (StopWatchInterface *)new StopWatchWin();

 #else

     *timer_interface = (StopWatchInterface *)new StopWatchLinux();

 #endif

     return (*timer_interface != NULL) ? true : false;

 }

 inline bool sdkDeleteTimer(StopWatchInterface **timer_interface)

 {

     if (*timer_interface)

     {

         delete *timer_interface;

         *timer_interface = NULL;

     }

     return true;

 }

 inline bool sdkStartTimer(StopWatchInterface **timer_interface)

 {

     if (*timer_interface)

         (*timer_interface)->start();

     return true;

 }

 inline bool sdkStopTimer(StopWatchInterface **timer_interface)

 {

     if (*timer_interface)

         (*timer_interface)->stop();

     return true;

 }

 inline float sdkGetTimerValue(StopWatchInterface **timer_interface)

 {

     if (*timer_interface)

         return (*timer_interface)->getTime();

     else

         return 0.0f;

 }

● 立方体纹理贴图。六个面分别为 x = 1 正面、x = -1 轴负面、y = 1 正面、y = -1 负面、z = 1 正面、x = -1 负面，对应前、后、右、左、上、下。按照线性下标 [0, width * width * 6 - 1] 顺序访问时，各元素存储位置如下图所示（width == 2 为例）。

　　　　

0_Simple__simpleCubemapTexture的更多相关文章

随机推荐

  1. Spring AOP关于cglib动态代理

    一: Spring AOP的默认代理方式是jdk动态代理,还有另外一种代理方式是cglib代理,简单说前者基于接口,后者基于继承,基本思路是将被代理对象的类作为父类,然后创建子类来进行方法的调用,调用 ...

  2. [UE4]虚幻4的智能指针

    虚幻自己实现了一套智能指针系统,为了跨平台. 指针: 占用8个字节,4个字节的Object指针,4字节的引用计数控制器的指针, 引用计数控制器需要12字节, 一个C++的Object指针4字节,一个共 ...

  3. 杭电 KazaQ's Socks

    KazaQ wears socks everyday. At the beginning, he has n pairs of socks numbered from 1 to n in his cl ...

  4. 使用Visual Studio Code开发Asp.Net Core WebApi学习笔记（三）-- Logger

    本篇是在上一篇的基础上添加日志功能,并记录NLog在Asp.Net Core里的使用方法. 第一部分:默认Logger支持 一.project.json添加日志包引用,并在cmd窗口使用 dotnet ...

  5. lsof-查看进程句柄

    root@root:~# lsof COMMAND PID TID USER FD TYPE DEVICE SIZE/OFF NODE NAME systemd root cwd DIR , / sy ...

  6. day26 python学习 对象的接口，封装，私用属性 property

    # 抽象类和接口类 #** #不崇尚接口类 #python本身支持多继承,没有接口专用的语法.但是我知道接口的概念 # 接口类:# 是规范子类的一个模板,只要接口类中定义的,就应该在子类中实现# 接口 ...

  7. baidu手机浏览器安卓4.5版公布：由于快，所以爱

    watermark/2/text/aHR0cDovL2Jsb2cuY3Nkbi5uZXQvdTAxNDUyMzk4OA==/font/5a6L5L2T/fontsize/400/fill/I0JBQk ...

  8. Centos7 通过SSH使用密钥实现免密登录

    Public Key认证的主要魅力在于认证时承诺不必提供密码就能够同远程系统建立连接. Public Key认证的基础在于一对密钥,public key和private key,public key对 ...

  9. 【转】每天一个linux命令（39）：grep 命令

    原文网址:http://www.cnblogs.com/peida/archive/2012/12/17/2821195.html Linux系统中grep命令是一种强大的文本搜索工具,它能使用正则表 ...

  10. Anaconda 使用（解决python包管理与环境管理）

    Anaconda完全入门指南(对python环境和原理,讲的比较透彻):https://www.jianshu.com/p/eaee1fadc1e9 用pip一个一个安装第三方库费时费力,还需要考虑兼 ...