Skip to main content

PROJECTED MEMRISTOR: A nanoscale device for cognitive computing

Periodic Reporting for period 3 - PROJESTOR (PROJECTED MEMRISTOR: A nanoscale device for cognitive computing)

Reporting period: 2019-07-01 to 2020-12-31

As complementary metal–oxide–semiconductor (CMOS) scaling reaches its technological limits, a radical departure from traditional von Neumann systems, which involve separate processing and memory units, is needed in order to extend the performance of today’s computers substantially. In-memory computing is a promising approach in which nanoscale memory devices, organized in a computational memory unit, are used for both processing and memory. The essential idea is to exploit the physical attributes and state dynamics of these memory devices to compute in place without the need to shuttle the data back and forth between the memory and processing units. The critical element in these novel computing systems is a very-high-density, low-power, variable-state, programmable non-volatile memory device. The overall objective of PROJESTOR is to explore such a memory device as well as to investigate ways in which we can use such memory devices for computational purposes.
The first part of the project aims at developing memory devices for in-memory computing. The goal is to explore the concept of projected memory devices and in particular projected phase-change memory devices where the read and write operations are decoupled by exploiting the nonlinear electrical transport in amorphous phase change materials.
As part of this study, we explored various phase-change materials and projection materials. The most important invention in this front was that of single elemental phase-change materials. We showed how the simplest material imaginable, a single element (in this case, antimony), can become a valid alternative when confined in extremely small volumes. This work appeared on the cover of Nature Materials (August 2018 issue) [1]. We also developed the most comprehensive understanding of resistance drift in phase-change materials, the key attribute that we are trying to counter through the concept of projection. This work was published in Advanced Electronics Materials [2]. We also explored semiconducting projection materials such as poly-silicon with mixed results.

In the second part of the project, we explore in-memory computing. We showed several applications where we could exploit the physical attributes and state dynamics of phase-change memory devices to perform computation in place. In one application, we showed how we could perform compressed sensing and recovery. This work was published in IEEE Transactions on Electron Devices [3]. We also demonstrated yet another application where we exploit the crystallization dynamics of phase-change memory devices to solve an unsupervised learning algorithm entirely in the memory [4]. A significant challenge for computational memory is the lack of precision associated with it. We proposed a new concept called mixed precision in-memory computing to address this. We used this concept to solve systems of linear equations and this work appeared in Nature Electronics [5]. The mixed-precision in-memory computing concept was also extended to tackle the challenging problem of training deep neural networks [6]. We also developed a multi-PCM device architecture to counter some of the short comings of in-memory computing [7]. We wrote a comprehensive tutorial on the various computational applications of PCM devices which appeared in the Journal of Applied Physics [8]. Most recently, we showed that with projected phase-change memory devices we can achieve scalar multiplication with an equivalent precision of 8 bit fixed point arithmetic consuming less than 10fJ of energy [9].

[1] Salinga et al., “Monatomic phase change memory”, Nature Materials, 17, 681-685, 2018
[2] Le Gallo et al., “Collective Structural Relaxation in Phase-Change
Memory Devices”, Adv. Electr. Materials, 1700627, 2018
[3] Le Gallo et al., “Compressed Sensing With Approximate Message Passing Using In-Memory Computing”, IEEE Trans. Electr. Dev., 65(10), 2018
[4] Sebastian et al., “Temporal correlation detection using
computational phase-change memory”, 8: 1115, Nature Communications, 2017
[5] Le Gallo et al., “Mixed-precision in-memory computing”, 1, 246-253, Nature Electronics, 2018
[6] Nandakumar et al., arXiv preprint arXiv:1712.01192 2017
[7] Boybat et al., “Neuromorphic computing with multi-memristive
synapses”, Nature Communications, 9:2514, 2018
[8] Sebastian et al, “Tutorial: Brain-inspired computing using phase-change memory devices”, J. Appl. Phys., 124, 111101, 2018
[9] Giannopoulos et al., “8-bit Precision In-Memory Multiplication with
Projected Phase-Change Memory”, Proc. IEDM, 2018
During the course of the project, we made some significant progress beyond the state of the art in both the development of new memory devices as well as their application in computing.

In the memory device front, the exploration of singe elemental phase-change materials is a paradigm shift in this field given that up to now, much of the effort was on fine tuning the material composition. With our work we have shown that, it is essential to focus on nanoscale size effects instead. Currently, we are exploring projected PCM devices with single elemental phase-change materials.

In the computing front, we developed numerous applications for in-memory computing from compressed sensing and temporal correlation detection to solving systems of linear equations and deep learning. We also showed that we can achieve in-memory scalar operations with projected PCM devices with an equivalent precision of 8-bit fixed point arithmetic and consuming less than 10fJ. This is the first time such high precision is reported using in-memory computing.

Going forward, there will be a renewed focus on the computing front, in particular the circuits and algorithmic aspects. We are also exploring newer applications for in-memory computing such as hyperdimensional computing. We are also simultaneously optimizing the projected PCM devices. Towards the end of the project, we expect to have developed a wide range of algorithms for in-memory computing and we also expect to demonstrate some of them using projected PCM devices.
In memory scalar multiplication using projected PCM
Temporal correlation detection using computational phase-change memory
Single elemental phase change memory using Antimony