cuda中thread id

 ////////////////////////////////////////////////////////////////////////////
 //
 // 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.
 //
 ////////////////////////////////////////////////////////////////////////////

 //
 // This sample illustrates the usage of CUDA events for both GPU timing and
 // overlapping CPU and GPU execution.  Events are inserted into a stream
 // of CUDA calls.  Since CUDA stream calls are asynchronous, the CPU can
 // perform computations while GPU is executing (including DMA memcopies
 // between the host and device).  CPU can query CUDA events to determine
 // whether GPU has completed tasks.
 //

 // includes, system
 #include <stdio.h>

 // includes CUDA Runtime
 #include <cuda_runtime.h>

 // includes, project
 #include <helper_cuda.h>
 #include <helper_functions.h> // helper utility functions 

 __global__ void increment_kernel(int *g_data, int inc_value)
 {
     int idx = blockIdx.x * blockDim.x + threadIdx.x;// thread id 计算分三级:thread, block .grid .
     g_data[idx] = g_data[idx] + inc_value; //每一个线程,把对应的操作数增加一个常数
 }

 bool correct_output(int *data, const int n, const int x)
 {
     for (int i = ; i < n; i++)
         if (data[i] != x)
         {
             printf("Error! data[%d] = %d, ref = %d\n", i, data[i], x);
             return false;
         }

     return true;
 }

 int main(int argc, char *argv[])
 {
     int devID;
     cudaDeviceProp deviceProps;

     printf("[%s] - Starting...\n", argv[]);

     // This will pick the best possible CUDA capable device
     devID = findCudaDevice(argc, (const char **)argv);

     // get device name
     checkCudaErrors(cudaGetDeviceProperties(&deviceProps, devID));
     printf("CUDA device [%s]\n", deviceProps.name);

     int n =  *  * ;
     int nbytes = n * sizeof(int);
     int value = ;

     // allocate host memory
     int *a = ;
     checkCudaErrors(cudaMallocHost((void **)&a, nbytes));
     memset(a, , nbytes);

     // allocate device memory
     int *d_a=;
     checkCudaErrors(cudaMalloc((void **)&d_a, nbytes));
     checkCudaErrors(cudaMemset(d_a, , nbytes));

     // set kernel launch configuration
     dim3 threads = dim3(, );//每个block1024个threads，一维
     dim3 blocks  = dim3(n / threads.x, );//block数量，

     // create cuda event handles
     cudaEvent_t start, stop;//运算计时
     checkCudaErrors(cudaEventCreate(&start));
     checkCudaErrors(cudaEventCreate(&stop));

     StopWatchInterface *timer = NULL;
     sdkCreateTimer(&timer);
     sdkResetTimer(&timer);

     checkCudaErrors(cudaDeviceSynchronize());
     float gpu_time = 0.0f;
     printf("a=%d\t%d\t%d\t%d\t%d\t%d\t%d\t%d\t%d\t\n",a[n--],a[n--],a[n--],a[n--],a[n--],a[n--],a[n--],a[n--],a[n--]);
     // asynchronously issue work to the GPU (all to stream 0)
     sdkStartTimer(&timer);
     cudaEventRecord(start, );
     cudaMemcpyAsync(d_a, a, nbytes, cudaMemcpyHostToDevice, );//把host中变量a复制到device中的变量d_a
     increment_kernel<<<blocks, threads, , >>>(d_a, value);//device执行
     cudaMemcpyAsync(a, d_a, nbytes, cudaMemcpyDeviceToHost, );//device结果复制到host
     cudaEventRecord(stop, );
     sdkStopTimer(&timer);

     // have CPU do some work while waiting for stage 1 to finish
     unsigned long int counter=;

     while (cudaEventQuery(stop) == cudaErrorNotReady)
     {
         counter++;
     }

     checkCudaErrors(cudaEventElapsedTime(&gpu_time, start, stop));

     // print the cpu and gpu times
     printf("time spent executing by the GPU: %.2f\n", gpu_time);
     printf("time spent by CPU in CUDA calls: %.2f\n", sdkGetTimerValue(&timer));
     printf("CPU executed %lu iterations while waiting for GPU to finish\n", counter);
     printf("a=%d\t%d\t%d\t%d\t%d\t%d\t%d\t%d\t%d\t\n",a[n--],a[n--],a[n--],a[n--],a[n--],a[n--],a[n--],a[],a[]);

     // check the output for correctness
     bool bFinalResults = correct_output(a, n, value);

     // release resources
     checkCudaErrors(cudaEventDestroy(start));
     checkCudaErrors(cudaEventDestroy(stop));
     checkCudaErrors(cudaFreeHost(a));
     checkCudaErrors(cudaFree(d_a));

     exit(bFinalResults ? EXIT_SUCCESS : EXIT_FAILURE);
 }

一个grid包含多个blocks，这些blocks的组织方式可以是一维，二维或者三维。任何一个block包含有多个Threads，这些Threads的组织方式也可以是一维，二维或者三维。举例来讲：比如上图中，任何一个block中有10个Thread，那么，Block(0,0)的第一个Thread的ThreadIdx是0，Block(1,0)的第一个Thread的ThreadIdx是11；Block(2,0)的第一个Thread的ThreadIdx是21，......，依此类推，