MRAM-Info: the MRAM experts

pMTJ STT-MRAM developer Avalanche Technology announced that it has signed an agreement with LinearASICs Inc. to develop companion chiplets to offer a complete portfolio of Space Grade products with SPI and DDR interfaces, based on Avalanche's 1Gb Space Grade MRAM.

Avalanche's 2nd-Gen P-SRAM evaluation kit

LinearASICs will provide standalone serial interface chiplets such as Octal SPI (OSPI), as well as standard memory interface chiplets such as DDR. These chiplets will be available as standalone devices or integrated modules through Avalanche.

Embedded MRAM solutions are now entering the market, as leading foundries Samsung, TSMC and GlobalFoundries are scaling-up and ramping up their solutions.

This has been a slow process, as getting next-generation technologies into large fab is never an easy task, but we are finally seeing these foundries start to offer these technologies to their customers.

Everspin Technologies announced its financial results for Q2 2021. Revenues were $11.85 million, up 15% over Q1 2021 (and similar to Q2 2020), as STT-MRAM revenues jumped 56%. Net profit was $0.25 million, up from a loss of $0.46 million in Q1 2021 (and $1.29 million in Q2 2020).

At the end of Q2 2021, Everspin had $14.2 million in cash and equivalents, down from $15.5 million from the end of Q1 2021. Cash flow from operations was negative at $0.56 million. Looking into the next quarter, Everspin expects revenues to be in the range of $11.7 million to $12.8 million.

Researchers from Northwestern University, in collaboration with researchers from China, Italy and France, developed a new SOT-MRAM device structure that enables deterministic switching without any need for bias magnetic fields.

The new approach, unlike most earlier methods, can be scaled to large wafers with good uniformity, since it doesn't rely on having a structural asymmetry in the device. SOT-MRAM devices based on this structure could be faster and more energy-efficient than current designs.

Orthogonal Spin Transfer MRAM (OST-MRAM) technology developer Spin Memory is shutting down. The company's main investor and founding company, Allied Minds, said in a statement that the main reasons challenges in securing new customers and COVID-19 which "significantly delayed the required testing of its development chip with ARM".

This is a sad ending to Spin Memory, which began its way as Spin Transfer Technologies - a spin-off from NYU that was established together with Allied Minds.

Researchers from Northwestern University developed a new method of building artificial neural networks using MRAM-based stochastic computing units. The researchers say that this design could enable AI devices that are highly energy efficient.

Embedded MRAM technologies are being adopted at major foundries, which enable the use of these technologies for unconventional computing architectures that use the stochasticity of MRAM cells (rather than their nonvolatility), to perform energy-efficient computing operations. MRAM cells exhibit stochastic switching characteristics, which is a challenge for reliable memory devices. But for neural networks, this can be taken advantage of if the MTJs are appropriately designed.

Researchers from Northwestern University and the University of Messina in Italy developed a new MRAM memory device composed of antiferromagnetic materials, which could be beneficial for use in AI systems and cryptocurrency mining.

Antiferromagnetic materials (AFM), offer inherently faster dynamics than ferromagnetic materials (FM), have no macroscopic magnetic poles and can be scaled much better. AFM-based memory cannot be erased with external magnetic fields which could prove to be a major security advantage.