disjoint.cpp

void transpose(disjoint Matrix4& target, const disjoint Matrix4& source)
{
  for (int i = 0; i < 4; ++i) for (int j = 0; j < 4; ++j) target.m[i][j] = source.m[j][i]; 
}

// this is a safe overload
void transpose(Matrix4& target, const Matrix4& source)
{
  Matrix4 temp;
  for (int i = 0; i < 4; ++i) for (int j = 0; j < 4; ++j) temp.m[i][j] = source.m[j][i]; 
  target = temp;
}

void prepare_skinning_data_for_gpu(disjoint Matrix4* cb, const disjoint Matrix4* world_transforms, const disjoint Matrix4* inv_bind_pose, size_t count)
{
    for (size_t i = 0; i < count; ++i)
    {
        mul(cb[i], world_transforms[i], inv_bind_pose[i]);
        
        // TODO: change shader compiler to not need this
        transpose(cb[i], cb[i]);
    }
}

void prepare_skinning_data_for_gpu_2(disjoint Matrix4* cb, const disjoint Matrix4* world_transforms, const disjoint Matrix4* inv_bind_pose, size_t count)
{
    for (size_t i = 0; i < count; ++i)
    {
        // disjoint Matrix4 result; would be correct and not cause the issue in transpose below
        disjoint Matrix4& result = cb[i];

        mul(result, world_transforms[i], inv_bind_pose[i]);
        
        // TODO: change shader compiler to not need this
        transpose(cb[i], result);
    }
}