Pfthb

Solved: Sorry, it's my fault, I should use atomicAdd(times,1); instead of *times++ in the kernel function.

I call the kernel function like this

dim3 Dg(blockSize, blockSize, blockSize);
dim3 Db(8, 8, 8);
voxelize << < Dg, Db >> > ();
cudaDeviceSynchronize();

But I found that my program only solve the part of the problem, so I use printf() in my global function voxelize () like the following code

__global__ void voxelize()
 printf("the thread blockIdx.x %d, blockIdx.y %d blockIdx.z %dn", blockIdx.x, blockIdx.y, blockIdx.z);
 unsigned int xIndex = blockDim.x * blockIdx.x + threadIdx.x;
 unsigned int yIndex = blockDim.y * blockIdx.y + threadIdx.y;
 unsigned int zIndex = blockDim.z * blockIdx.z + threadIdx.z;
 unsigned int i = zIndex * blockDim.x*blockDim.y+ yIndex * blockDim.x+ xIndex;
 

The output showed only the last part of each dimension runned( that is, the blockIdx.x is always 5, only some of the blockIndex.z are changing from 0 to 5).But I don't understand why, is there anything wrong when I call this kernel function?
My computer is with the GTX1050Ti MaxQ and cuda 10.

After, I passed a pointer to the kernel to monitor the running times.

 int blockSize = ceil(pow(triangles.size() 69664 / 512.0, 1.0 / 3));
 dim3 Dg(blockSize, blockSize, blockSize);
 dim3 Db(8, 8, 8);
 int* times = new int(0);
 int* gpu_times;
 cudaMalloc((void **)&gpu_times, sizeof(int));
 cudaMemcpy(gpu_times, times, sizeof(int), cudaMemcpyHostToDevice);
 voxelize << < Dg, Db >> > (gpu_times);
 cudaDeviceSynchronize();
 cudaMemcpy(times, gpu_times, sizeof(int), cudaMemcpyDeviceToHost);
 std::cout << *times << std::endl;

the kernel is modified as

__global__ void voxelize(int* times)
 (*times)++;
 printf("the thread blockIdx.x %d, blockIdx.y %d blockIdx.z %dn", blockIdx.x, blockIdx.y, blockIdx.z);
 unsigned int xIndex = blockDim.x * blockIdx.x + threadIdx.x;
 unsigned int yIndex = blockDim.y * blockIdx.y + threadIdx.y;
 unsigned int zIndex = blockDim.z * blockIdx.z + threadIdx.z;
 unsigned int i = zIndex * blockDim.x*blockDim.y+ yIndex * blockDim.x+ xIndex;
 

the output is
the output shows it runs 141 times, but in fact, the output should be far more than 69664

sorry, it's my fault, I should use atomicAdd(times,1); instead of *times++.

But why does printf() only output a part of the index as I described before?

For your printf problem

You need to call cudaDeviceSynchronize() (error checking omitted for clarity):

#include <stdio.h>

__global__ void voxelize()
 printf("the thread blockIdx.x %d, blockIdx.y %d blockIdx.z %dn", blockIdx.x, blockIdx.y, blockIdx.z);
 unsigned int xIndex = blockDim.x * blockIdx.x + threadIdx.x;
 unsigned int yIndex = blockDim.y * blockIdx.y + threadIdx.y;
 unsigned int zIndex = blockDim.z * blockIdx.z + threadIdx.z;
 unsigned int i = zIndex * blockDim.x*blockDim.y+ yIndex * blockDim.x+ xIndex;


int main()

 dim3 Dg(5, 5, 5);
 dim3 Db(8, 8, 8);
 voxelize<<<Dg, Db>>>();
 cudaDeviceSynchronize();

 return 0;

This will print something like:

the thread blockIdx.x 2, blockIdx.y 3 blockIdx.z 4
the thread blockIdx.x 2, blockIdx.y 3 blockIdx.z 4
the thread blockIdx.x 2, blockIdx.y 3 blockIdx.z 4
the thread blockIdx.x 2, blockIdx.y 3 blockIdx.z 4
the thread blockIdx.x 2, blockIdx.y 3 blockIdx.z 4
[...]

For you count problem

You can't do that: (*times)++;. You'll have a concurrency problems. You need to use atomic functions.