Would be nice to have functionality to allocate matricies with cudaMallocPitch and copied with cudaMemcpy2D, with overloaded access of "[idx]" to be pitch aligned for Matrices passed into a cuda kernel.
-- GitLab Migration Automatic Message -- This bug has been migrated to gitlab.com's GitLab instance and has been closed from further activity. You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.com/libeigen/eigen/issues/1649.