1. SIMD processor based implementation of recursive filtering equations
2. Scans as primitive parallel operations
3. Solving linear recurrences with loop raking
4. J. Bradbury S. Merity C. Xiong and R. Socher. 2016. Quasi-Recurrent Neural Networks. ArXiv e-prints (Nov. 2016). arXiv:1611.01576 J. Bradbury S. Merity C. Xiong and R. Socher. 2016. Quasi-Recurrent Neural Networks. ArXiv e-prints (Nov. 2016). arXiv:1611.01576
5. Ian Buck. 2015. Nvidia's next-gen Pascal GPU architecture to provide 10x speedup for deep learning apps. (2015). Ian Buck. 2015. Nvidia's next-gen Pascal GPU architecture to provide 10x speedup for deep learning apps. (2015).