Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
  • AI
  • Tech
  • Cybersecurity
  • Finance
  • DeFi & Blockchain
  • Startups
  • Gaming
Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
Dataconomy
No Result
View All Result

British startup develops bendable microprocessor capable of running ML models for under 1 USD

The Flex-RV chip by Pragmatic Semiconductor offers an ultra-low-cost, flexible microprocessor that can run machine learning models, paving the way for innovations in wearable tech and medical devices

byEmre Çıtak
October 1, 2024
in Artificial Intelligence
Home News Artificial Intelligence

British startup Pragmatic Semiconductor has revealed a 32-bit microprocessor, Flex-RV, that is not only bendable but can also run machine learning models — all for less than a dollar.

The innovative chip, based on the open-standard RISC-V architecture, could transform how we approach flexible electronics, offering a cost-effective solution with numerous practical applications.

Flex-RV’s break from silicon

The Flex-RV achieves its flexibility by using indium gallium zinc oxide (IGZO) instead of conventional silicon. Silicon chips require complex and expensive packaging to protect their brittle structure from breaking under stress. In contrast, IGZO transistors can be printed directly onto plastic substrates at low temperatures, allowing the Flex-RV to bend and twist without damage.

Stay Ahead of the Curve!

Don't miss out on the latest insights, trends, and analysis in the world of data, technology, and startups. Subscribe to our newsletter and get exclusive content delivered straight to your inbox.

During a demonstration, Pragmatic showcased the chip being rolled around a straw while continuing to function, although it still requires careful handling. This flexibility could open doors to a wide range of applications where traditional rigid chips fall short.

While the Flex-RV doesn’t offer blistering performance, with only 12,600 logic gates and a maximum clock speed of 60 kHz (or 0.00006 GHz), it’s not intended for high-performance computing. Instead, the chip focuses on ultra-low power consumption, drawing less than 6 mW of power, and features an integrated machine learning accelerator.

This makes it ideal for applications like disposable medical devices, body-conforming gadgets, soft robotics, and brain-computer interfaces, where flexibility and efficiency matter more than raw power.

Cost efficiency with RISC-V architecture

Pragmatic also avoids the high licensing costs associated with proprietary architectures by utilizing the open-source RISC-V instruction set, further keeping the cost of the chip below one dollar. This approach aligns with the company’s vision of developing affordable, flexible electronics that can be integrated into a wide array of everyday devices.

Testing has shown that the Flex-RV can withstand bending to a 5 mm radius curve, maintaining accuracy despite slight variations in throughput. This marks a significant leap forward from previous flexible chips, which could only be tested while still on their original rigid wafers.

In a broader context, the Flex-RV moves beyond earlier flexible electronics projects like the “Flexduino,” which incorporated rigid components on a flexible PCB. With Flex-RV, even the integrated circuit is flexible, showcasing the future of truly bendable computing devices.

Read more about this massive breakthrough here.


Featured image credit: Pragmatic Semiconductor/YouTube

Tags: Machine Learning

Related Posts

xAI sues former engineer to stop him from joining OpenAI, alleging theft of Grok trade secrets

xAI sues former engineer to stop him from joining OpenAI, alleging theft of Grok trade secrets

September 2, 2025
Psychopathia Machinalis and the path to “Artificial Sanity”

Psychopathia Machinalis and the path to “Artificial Sanity”

September 1, 2025
GPT-4o Mini is fooled by psychology tactics

GPT-4o Mini is fooled by psychology tactics

September 1, 2025
AI reveals what doctors cannot see in coma patients

AI reveals what doctors cannot see in coma patients

September 1, 2025
Asian banks fight fraud with AI, ISO 20022

Asian banks fight fraud with AI, ISO 20022

September 1, 2025
ChatGPT introduces flashcard quizzes for learning

ChatGPT introduces flashcard quizzes for learning

September 1, 2025

LATEST NEWS

xAI sues former engineer to stop him from joining OpenAI, alleging theft of Grok trade secrets

Psychopathia Machinalis and the path to “Artificial Sanity”

GPT-4o Mini is fooled by psychology tactics

AI reveals what doctors cannot see in coma patients

Asian banks fight fraud with AI, ISO 20022

Android 16 Pixel bug silences notifications

Dataconomy

COPYRIGHT © DATACONOMY MEDIA GMBH, ALL RIGHTS RESERVED.

  • About
  • Imprint
  • Contact
  • Legal & Privacy

Follow Us

  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Glossary
    • Whitepapers
  • Newsletter
  • + More
    • Conversations
    • Events
    • About
      • About
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
No Result
View All Result
Subscribe

This website uses cookies. By continuing to use this website you are giving consent to cookies being used. Visit our Privacy Policy.