• Skip to main content
  • Skip to secondary menu
  • Skip to footer

Technologies.org

Technology Trends: Follow the Money

  • Technology Events 2026-2027
  • Sponsored Post
  • Technology Markets
  • About
    • GDPR
  • Contact

Spin Memory Unveils New Method of Designing Memory to Shake Up $100B Chip Market

August 12, 2020 By admin

Spin Memory, Inc. (Spin Memory), the leading developer of MRAM technologies, today announced a new solution that will significantly improve the capabilities of existing and emerging memory technologies: the Universal Selector. As the cost of semiconductor scaling and innovation continues to rise, the industry has struggled to make major advances in scaling and performance — which limits advancements in areas such as AI and IoT.

Spin Memory’s new Universal Selector creatively solves this problem with a novel approach to how transistors are designed and built into memory chips. It is a completely new way of designing dynamic random-access memory (DRAM), magnetoresistive random-access memory (MRAM), Resistive RAM (ReRAM) and other emerging memory technologies — which encompasses more than $100 billion in semiconductor products. The Universal Selector allows on-chip memory to achieve higher levels of performance, reliability and density than ever before, which will boost innovation to levels above that anticipated by Moore’s Law.

The innovation enables new layouts, smaller cell footprints and improved densities in DRAM, MRAM and ReRAM products — bringing about higher levels of performance, reliability and density than ever before. Additionally, the Universal Selector is the first true industry solution to the DRAM problem of row hammer disturbs, while simultaneously reducing Soft Error Rates (SER) and leakage. Spin Memory is currently working with NASA on the applicability of this technology to develop low SER and row hammer-immune DRAM solutions.

“Row hammer is one of the leading issues in DRAM reliability and security, and has long been a frustrating plague on the memory industry. As DRAM’s longstanding major disturb problem, row hammering is only becoming more of a problem as cells shrink,” said Charlie Slayman, IRPS 2020 technical program chair. “Spin Memory’s Universal Selector offers a novel way to design vertical cell transistors and has been presented to the JEDEC task group evaluating solutions to the row hammering problem.”

Spin Memory’s Universal Selector is a selective, vertical epitaxial cell transistor whose channel has a low enough doping concentration that it operates in full depletion. The fully depleted cell transistor along with other unique process and device features leads to a crucial architectural change, allowing the channel to be completely electrically isolated from the silicon substrate. This completely eliminates the possibility of any trapped or migrating electrons causing row hammer, making this design row hammer-immune.

Beyond solving the row hammer disturb problem, the Universal Selector improves DRAM array density by 20% – 35% through its 4F2 (4F2) DRAM bitcell configuration. For emerging memories such as MRAM, ReRAM and PCRAM, the Universal Selector enables manufacturers to create 1T1R memory bitcells of 6F2 – 10F2 (6F2 – 10F2), enabling manufacturers to embed up to five times more memory in the same area footprint with minimal additional wafer processing costs. This drastically improved memory density will fulfill the demands of cutting-edge applications — allowing artificial intelligence, virtual reality, edge computing and more to reach new technological heights.

“Today’s most innovative and demanding technologies need more advanced memory to keep up with computing demands. Speed and reliability are necessary for complex applications running at the edge, such as autonomous vehicles or health wearables — where accurate and real-time decisions could make the difference between life and death,” said Tom Sparkman, CEO of Spin Memory. “Our latest breakthrough innovation allows for exciting new advancements and capabilities for these technologies — in addition to pushing MRAM into the mainstream market.”

Beyond the density improvements for DRAM and all emerging memories, Spin Memory’s new Universal Selector will bring MRAM to a new level of SRAM-like performance. Combined with the company’s other MRAM IPs and innovations, including the PSC, Spin Memory is overcoming all the limitations of MRAM to offer a next-generation nonvolatile memory solution for the industry. The emerging hyper-dense, high-performance MRAM will offer a new memory option that overcomes many of the limitations of legacy SRAM solutions for on-chip memory.

Additionally, this new way of building transistors allows for smaller memory cells while utilizing materials and processes that already exist in standard silicon manufacturing processes. This empowers any developer of non-Flash memories to take advantage of the Universal Selector quickly and easily. This breakthrough allows for drastically improved density for almost every memory technology on the market without requiring an investment in specialized hardware or resources.

Spin Memory will share additional technical details on this new technology and solution at the virtual 31st Magnetic Recording Conference on Thursday, August 20 at 10:40 a.m. PDT. Dr. Kadriye Deniz Bozdag, Spin Memory’s manager of MRAM testing, will give an online presentation on the Universal Selector’s full functions and capabilities. Anyone interested in signing up for the event and watching the presentation online can register here.

About Spin Memory
Spin Memory, Inc. is the pre-eminent MRAM IP supplier. Through collaboration with industry leaders, Spin Memory is transforming the semiconductor industry by solving memory challenges vital for AI, ADAS, 5G, IoT and more. Spin Memory’s disruptive STT-MRAM technologies and products provide SRAM-like speed and endurance that can replace SRAM and ultimately DRAM in both embedded and stand-alone applications. For more information, please visit www.spinmemory.com.

Filed Under: Tech

Footer

Recent Posts

  • AltSql: An Embedded Database Engine That Syncs Devices and Gateways Without Conflicts
  • VPN Works: Uses Linux Network Namespaces to Isolate and Log Every Connection From an Agent
  • Precomputing: Materializes Dashboard Answers With SQLite Triggers as Data Arrives
  • Preconfiguration: Generates Reproducible Setup Across Multiple Cloud Platforms From One Spec
  • BareProxy: A Go Reverse Proxy That Makes Routing Decisions Explainable
  • AI Infrastructure Moves Beyond GPUs as Billions Flow Into Interconnects, Cloud, Robotics and Agent Systems
  • Supermicro Is Now Shipping NVIDIA Vera Rubin NVL72 Racks, With 1,152-GPU Scalable Units Ready to Order
  • Synopsys and TSMC Certify A14 Design Flows and Roll Out Agentic AI Chip Design Tools
  • Bird.com Secures $450M in Debt Financing and Opens Its Messaging Network to AI Agents
  • Meta AI Glasses Become the First Consumer Device to Record Dolby Atmos Audio

Media Partners

  • Market Analysis
  • BareProxy.com
  • App Coding
Screening Startup and Product Ideas After a Brainstorm: Four Questions, Money First
An AI Lab Is Paying Up Front for Atlas Energy’s (AESI) Generators as Agentic AI Multiplies Token Demand
Oracle’s Force Majeure Notice on Project Jupiter Shows Where AI Data Center Risk Is Landing
AI Infrastructure Credit Costs Rise as CoreWeave-Tied Bonds Price at 9.25% and China Chipmaker Profits Jump 620%
OpenAI and Anthropic Cut AI Model Prices as $1.75B in Funding Flows to Data, Security and Infrastructure
Semiconductor Revenue Hits Record $425B in Q2 2026, but Omdia’s $500B Q3 Forecast Implies Growth Halves
AI Extinction Warnings Went Global in Six Days. Nothing in the Technology Changed.
Anthropic Walks Away From $6 Billion Decart Acquisition: The Deal Was About Inference Cost, Not World Models
VR Status Report 2026: Quest Sales Keep Falling While Smart Glasses Take the Money
The Case That the US Can Grow Out of $40 Trillion in Debt: Three Conditions the Clinton Surpluses Actually Met
BareProxy 0.1 Alpha Adds Plan, Apply and Rollback
Introducing BareProxy, the Web Server and Reverse Proxy That Explains Itself
BareProxy Serves Hugo and Other Static Sites Straight From a Folder
How BareProxy Plan Shows What a Config Change Will Do Before It Goes Live
One Record per Request: How BareProxy Tracing Works
BareProxy Modules: Eight Add-Ons Around a Bare Core
Why BareProxy Routes on the Same Path It Forwards
About
Config Reference
Contact
Screening App Ideas Before You Write Code: Four Questions, Starting With Who Pays
AltSql: Gives IoT Devices a 15 KB Database That Keeps Working When the Link Drops
BareProxy: A Small Go Web Server and Reverse Proxy That Explains Every Routing Decision
Precomputing: Keeps Dashboard Answers Ready in a SQLite File as the Data Arrives
Preconfiguration: Writes Coding Agent Setup Files From One Spec and Tests Them on a Clean Machine
VPN Works: Gives Each AI Agent Its Own Network and a Record of Every Connection
Cloudflare Worker Previews Setup: Which Bindings Isolate Per Branch and Which You Configure Yourself
Nine Apps Worth Coding, and the Hard Part Buried in Each One
Application Performance Optimization: Where Most Teams Waste Their Time
AI App Builders by Use Case: Lovable, Bolt.new, Replit Agent, Softr, FlutterFlow and v0

Media Partners

  • AltSql.com
  • Technology Conferences
  • API Coding
AltSql Is a Native Hybrid of Key-Value and SQL, From the Sensor to the Gateway
AltSql Core and AltSql DB Are Now Open Source Under the Apache License 2.0
Introduction
AltSql DB 0.3 Adds Secondary Indexes and Statement Savepoints: A Lookup on a Million Rows Ran 198 Times Faster Than a Full Scan
How It Works
AltSql DB 0.2: SQL and Direct Calls Wrote Byte-Identical Files Over 100,000 Random Steps
AltSql DB Keeps a Whole Fleet in One File and Reads by Key 5 Times Faster Than SQLite Through SQL
AltSql Core and Six Prototypes Built Around It
AltSql Ask Puts One SQL Question to 500 Simulated Machines and Brings Back Only the Answers
Machine Monitoring Case Study: Overheat Alarm Handled on the Sensor While Wi-Fi Was Down
Cloudflare Connect 2026, October 19–21, Moscone West, San Francisco
JNUC 2026, September 23–25, Kansas City Convention Center, Kansas City
Startup World Cup Grand Finale 2026, November 4–6, Hilton San Francisco Union Square, San Francisco
FYUZ 2026, November 3–5, The Westin Seattle, Seattle
ONUG AI Networking Summit 2026, October 28–29, Penn District, New York
Networking Field Day 2026, October 6–9, San Jose
Nova Future Summit 2026, September 28–30, Napa
Breakbulk Americas 2026, September 22–23, George R. Brown Convention Center, Houston
Gartner CIO & IT Executive Conference 2026, September 21–23, Sheraton São Paulo WTC Hotel, São Paulo
ITC Vegas 2026, September 29–October 1, Mandalay Bay, Las Vegas
Audit an API Field's Completeness Before You Build a Feature on It
Caching a Third-Party API Response in a Cloudflare Pages Function
Fetching a Remote JSON API at Build Time in Hugo with resources.GetRemote
GBIF's API Returns CC BY-NC Images by Default, Which Breaks Commercial Use
Querying USAspending for Federal Contract Awards With a POST Search and No API Key
Reading the Launch Library API for Rocket Launch Schedules Without a Key
API Monetization Models: How Companies Actually Charge for Access
API Testing Strategies: What to Test and When
AI Platforms for Designing APIs in 2026: Spec Editors, SDK Generators, MCP Builders and AI Gateways Reviewed
Every Accident in Your API Becomes a Contract

Copyright © 2026 Technologies.org

Media Partners: Market Analysis · Market Research · Referently · Photography