12
Aug, 24
12 Aug, 24

Weebit ReRAM Foundry Developments Presented at FMS

At the recent FMS: the Future of Memory and Storage event in Santa Clara, I took part in the session on Emerging Memories, during which I shared some of the recent progress Weebit has made with various foundries towards making our technology available via their IP portfolios.

 

Above: The author (second from left) on the Emerging Memories Session at FMS 2024

 

FMS is the most important non-volatile memory (NVM) conference, usually attracting ~6,000 participants from across the memory industry. During the show, major memory companies release their newest products and technological achievements. This year, FMS changed its branding from the ‘Flash Memory Summit’ to ’the Future of Memory and Storage,’ recognizing the fact that the NVM market is no longer flash-only. It covers emerging technologies such as ReRAM (RRAM) and MRAM, which are now taking more significant market share, especially as embedded Flash hits a scaling wall.

One application area where ReRAM is gaining traction is automotive, where it brings high-temperature reliability, immunity to electromagnetic interference, high endurance, fast switching speed, longevity and security. Many automotive applications like autonomous vehicles and Advanced Driver Assistance Systems (ADAS) are also part of the AI revolution which is rapidly changing the world. The focus from an NVM perspective is on increased capacity, energy efficiency, and performance. But that must be married with cost efficiency – an NVM for AI, supporting large densities, must be cheap enough to manufacture and mass produce. ReRAM is an ideal fit.

 

Weebit ReRAM: The Latest Foundry Developments

One of Weebit’s important recent developments is the tape-out of a demonstration chip integrating Weebit’s embedded ReRAM module in DB HiTek’s 130nm BCD process. We announced this milestone recently with DB HiTek – a tier-one foundry in South Korea. DB HiTek’s 130nm BCD process is ideal for analog, mixed-signal and high-voltage designs. We’re seeing interest from their customers in a variety of applications including smart power management integrated circuits (PMICs), where integrating the PMIC with a controller on one die can lead to significant advantages in terms of performance, security, power and cost.

We’re now showing publicly for the first time performance data of our ReRAM technology implemented on GlobalFoundries 22FDX® wafers including endurance and retention data. These are the first such ReRAM results.

Pre-qualification results show Weebit’s ReRAM stack is stable at 105 degrees Celsius up to 10K cycles endurance. We’re also demonstrating very good data retention, maintaining pre- and post-cycling for a long time at high temperatures (150°C). These are impressive results for our first set of wafers, and we are continuing to collect data as our characterization and qualification activities continue.

 

Above: cycling and data retention results of Weebit ReRAM on GlobalFoundries 22FDX® wafers

 

Another recent development is our partnership with Efabless Corporation, focused on providing Efabless chipIgnite customers access to Weebit ReRAM IP into designs manufactured using SkyWater’s 130nm CMOS (S130) process. chipIgnite lets customers, including academics, researchers, startups and groups within large OEMs, quickly and cost-effectively develop and test new designs. If they like the design, they can license our product for commercial production with SkyWater.

 

The Weebit ReRAM module has already been fully qualified in SkyWater Technology’s 130nm CMOS (S130) process at temperatures of up to 125 degrees Celsius—the temperature specified for Grade-1 automotive applications. We’ve also already showed ReRAM results on SkyWater S130 under extended automotive conditions with extremely high 100K endurance cycles at very high temp of 150 degrees Celsius.

 

You can see here the slides from my recent FMS presentation.

 

 

Want to read some more?

Why Weebit’s IP Licensing Model Matters

When people think of semiconductor companies, they often picture vast factories filled with billion-dollar equipment. But Weebit Nano operates in a very different way. If

Enabling ‘Few-Shot Learning’
AI with ReRAM

AI training happens in the cloud because it’s compute-intensive and highly parallel. It requires massive datasets, specialized hardware, and weeks of runtime. Inference, by contrast,

The Road to AEC-Q100 Qualification

When it comes to cars, safety and reliability are paramount. That’s why almost every single part of a car must meet standards and regulations designed