## 2019 [Memory devices and applications for in-memory computing](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5270/10.1038_s41565-020-0655-z.pdf) Abu Sebastian

![ll](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5289/sram-reram.PNG 'l')

febr 2021 [HiPEAC21 - Keynote by Evangelos Eleftheriou: "In-memory Computing for AI Applications"](https://www.youtube.com/watch?v=30K5i8bdiyg)


## 2014 K.Ando [Spin-transfer torque magnetoresistive random-access memory technologies for normally off computing (invited)](https://aip.scitation.org/doi/full/10.1063/1.4869828?TRACKPRESS=BARDI)

> We can eliminate this meaningless energy loss by utilizing the non-volatile function of advanced spin-transfer torque magnetoresistive random-access memory (STT-MRAM) technology and create a new type of computer, i.e., normally off computers.


## 2015 wong [Memory leads the way to better computing](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5265/wong2015.pdf)
> H.-S. Philip Wong and Sayeef Salahuddin
> New non-volatile memory devices store information using different physical mechanisms from those
> employed in today’s memories and could achieve substantial improvements in computing performance
> and energy efficiency



## 2015 kent [A new spin on magnetic memories](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/5264/kent2015.pdf)
> Andrew D. Kent and Daniel C. Worledge
> Solid-state memory devices with all-electrical read and write operations might lead to faster, cheaper
> information storage



## 201x [Computing-in-Memory with Spintronics](http://www.ee.umn.edu/users/sachin/conf/date18.pdf) Shubham Jain, et al, Kaushik Roy

3 ARCHITECTURES

## ++++ [An MRAM-based Deep In-Memory Architecture for Deep Neural Networks](http://shanbhag.ece.illinois.edu/publications/ADP_ISCAS_MRAM_2019.pdf) Ameya D. Patil

> We further quantify accuracy drop due to analog computation and MTJ process variations for LeNet-300-100 on MNIST dataset and a 9-layer
> CNN on CIFAR-10 dataset and find it to be within $0.5%$ and $1%$, respectively.


- [IMFlexCom: Energy Efficient In-Memory Flexible Computing Using Dual-Mode SOT-MRAM](https://dl.acm.org/doi/pdf/10.1145/3223047) FARHANA PARVEEN

## 2020 [Spintronic devices for energy-efficient data storage and energy harvesting](https://www.nature.com/articles/s43246-020-0022-5) Jorge Puebla




## Tom Coughlin

https://www.forbes.com/sites/tomcoughlin/2020/06/04/advances-enable-36b-emerging-memory-market-by-2030/?sh=3182661f474f

- **2016!!!** not realized? [Crossing **the Chasm to New** Solid-State Storage Architectures](https://ieeexplore.ieee.org/document/7353293?denied=)

> This article explores the current state of solid-state memory, including what is publicly known about the **Intel/Micron XPoint memory and the future consumer devices and technologies that nonvolatile memory will make possible**.

> STT-RAM or other spin-based MRAM technologies could be very attractive nonvolatile candidates to replace SRAM, and possibly DRAM, **because of their high read and write performance as well as high endurance**. The spin-based MRAM devices are also generally configured with a crossbar memory architecture with word- and bit-line memory-cell selection.

- https://www.forbes.com/sites/tomcoughlin/2019/12/16/mram-in-perspective/?sh=636bfdb93cbe

2019 [EMERGING MEMORIES RAMP UP](https://tomcoughlin.com/wp-content/uploads/2019/06/2019-Emerging-Memory-Report-brochure.pdf)
https://tomcoughlin.com/wp-content/uploads/2019/06/

- [2017 Roadmap Mass Data Storage TWG](https://tomcoughlin.com/wp-content/uploads/2019/06/Digital-Storage-Technology-Roadmaps-and-Implications-for-Cloud-Computing-iNEMI-061317r.pdf)