MRAM-Info is a news hub and knowledge center born out of keen interest in MRAM memory technologies.
MRAM is a next-generation memory technology, based on electron spin rather then its charge. Often referred to as the "holy-grail of memory", MRAM is fast, high-density and non-volatile and can replace all kinds of memories used today in a single chip.
In October 2018 Intel revealed that it is developing embedded MRAM - and that the company has successfully integrated embedded MRAM into its 22nm FinFET CMOS technology on full 300mm wafers.
Now Intel gave more details on its embedded STT-MRAM, and said that the technology is ready for high-volume manufacturing. Intel said it has used a "write-verify-write" scheme and a two-stage current sensing technique to create 7Mb perpendicular STT-MRAM arrays in its 22FFL FinFET process.
Everspin Technologies announced that it started to ship pre-production customer samples of its 28 nm 1Gb STT-MRAM chips in December 2018. Everspin already announced that it started to sample these new 1Gb STT-MRAM chips in November 2018.
In November 2017 Everspin announced it will delay its 1Gb STT-MRAM chips as its focus has shifted to its 256 Mb STT-MRAM chips. It is great, tough, to see Everspin progressing with its larger MRAM chip and we hope that mass production will begin, as planned, in the middle of 2019.
Researchers from Japan's Tohoku University developed a 128 Mb STT-MRAM device that features a write speed of 14 nm, the world's fastest STT-MRAM chip at a density over 100 Mb.
To achieve this high speed, the researchers developed MTJs that are integrated with CMOS, which also significantly reduces the power-consumption of the memory device.
2018 is soon over - and this was another year of MRAM progress - new MRAM chips are entering production, new MRAM-enhanced devices are released and we are seeing the first adoption of embedded MRAM solutions.
Here are the top 10 stories posted on MRAM-Info in 2018, ranked by popularity (i.e. how many people read the story):
In June 2017 it was reported that Taiwan Semiconductor Manufacturing Company (TSMC) will start producing embedded MRAM in 2018 using a 22 nm process. In what may bet he first adoption of TSMC's eMRAM technology, AI accelerator startup Gyrfalcon Technology announced the commercial availability of its LightSpeeur 2802M, AI ASIC that include TSMC's eMRAM.
The 2802M ASIC has 40MB of eMRAM memory, which can support large AI models or multiple AI models within a single chip. Applications include image classification, voice identification, voice commands, facial recognition, pattern recognition and more.
Market analyst firm Yole Developpement presents its latest next-generation memory forecasts in an interesting new article. The company says that following more than 15 years of development, PCM is finally taking off in stand-alone applications due to strong support from Intel and Micron.
STT-MRAM is expected to lead the embedded memory race as many foundries are rushing to add MRAM support and expertise to their product lines. STT-MRAM is promising for enterprise storage SCM.
Researchers at Belgium-based research institute Imec presented the first power-performance area comparison between SRAM and STT-MRAM last-level cache at the 5 nm node.
The analysis, based on design-technology co-optimization and silicon verified models, reveals that STT-MRAM meets the performance requirements for last-level caches in the high-performance computing domain. For larger memory densities, STT-MRAM was found to offer significant energy gains compared to SRAM.