andr01d-1

#include <iostream>
#include <vector>
#include <cuda_runtime.h>

// reduce0 kernel: Sums elements using interleaved shared memory addressing
__global__ void reduce0(int *g_idata, int *g_odata) {
    extern __shared__ int sdata[];
    unsigned int tid = threadIdx.x;
    unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
    

andr01d-1

#include <Eigen/Core>
#include <Eigen/Geometry>

#include <iostream>

/*Eigen::Quaterniond multiply(Eigen::Quaterniond a, Eigen::Quaterniond b) {
    a.normalize();
    b.normalize();
    Eigen::Quaterniond c = Eigen::Quaterniond::Identity();
    c.w() = a.w() * b.w() - a.vec().transpose() * b.vec();