please, I conftoned of a trouble in Cuda 12

[TycheLime]

No description provided.

[TycheLime]

template<int N,typename T>
global void kernel(T* arr) {
for (int i = blockDim.x * blockIdx.x + threadIdx; i < N; i += blockDim.x * gridDim.x) {
arr[i] = i;
}
}

[TycheLime]

the above code can not compile.

[Crown40]

int i = blockDim.x * blockIdx.x + threadIdx =should be altered as>int i = blockDim.x * blockIdx.x + threadIdx.x

template<int N,typename T> global void kernel(T* arr) { for (int i = blockDim.x * blockIdx.x + threadIdx; i < N; i += blockDim.x * gridDim.x) { arr[i] = i; } }