4ds Memory Ltd. · ASX:4DS

4ds Memory — Investor Presentation (March 2024)

27 slides from 4ds Memory's investor presentation, Mar 4, 2024

  1. Slide 1: 4DS Australian Open Briefings Presentation

    4DS Memory Limited | ABN 43 145 590 110 Level 2, 50 Kings Park Road, West Perth WA 6005 PO Box 271, West Perth WA 6872 +61 8 6377 8043 | david@4dsmemory.com | www.4dsmemory.com ASX RELEASE 4 March 2024 4DS Australian Open Briefings Presentation 4DS Memory Limited (ASX:4DS) (4DS) (the Company), is pl

  2. Slide 2: Memory for the AI Age

    For personal use only MEMORY FOR THE AI AGE THE MEMORY THAT BREATHES MARCH 2024

  3. Slide 3: Artificial Intelligence

    Artificial Intelligence For personal use only Nvidia Co-founder and CEO Jensen Huang described the emergence of artificial intelligence (AI) as the beginning of a new industrial revolution, emphasising that there’s an ongoing global ‘awakening’ concerning AI technology.1 He also believes that, over

  4. Slide 4: 4DS: The Right Memory for the Right Market at the Right Time

    4DS: The Right Memory for the Right Market at the Right Time For personal use only The New Age of AI Processing is built on decades of research into neuromorphic processing and Neural Net modeling These models require huge amounts of data and are the result of billions of weighted matrix calculation

  5. Slide 5: Generative AI Transforming the Compute Industry

    Generative AI AI refers to a long history Machine learning is in of machine learning everything from your home Transforming the development that has thermostat to your car’s Compute Industry For personal use only evolved over the past antilock braking to your 40 years in the industry Alexa connected

  6. Slide 6: The 4DS Advantages

    The 4DS Advantages For personal use only Persistent Tunable Low Energy Scalable to Any Analog Memory at Retention from per Bit Process Node Programmability DRAM Speeds Seconds to Days 4.7ns write for 1 hour Highest energy For Warm Data and Simple fab By time or voltage read – no refresh optimization

  7. Slide 7: An Overview of Memory Terminology

    An Overview of Memory Terminology For personal use only SRAM DRAM 4DS ReRAM NAND Volatile, provides the fastest Volatile, provides large data Persistent, provides hours of Non-volatile, provides lowest read time, used for immediate storage capabilities with retention with very fast write cost per by

  8. Slide 8: What is PCMO and why is it unique?

    What is PCMO and why is it unique? For personal use only Current is spread across entire interface area Low current densities lead to high cell endurance Top electrode Thin oxide layer FAST Super fast programming Perovskite layer comprised of: Praseodymium One Shot write E Field injects or Calcium r

  9. Slide 9: What is PCMO and why is it unique? continued

    What is PCMO and why is it unique? continued For personal use only _ High O affinity by top electrode creates an oxygen depletion layer at the surface junction (oxygen vacancies in the PCMO lattice) Pulse of electric field pushes oxygen back into PCMO, filling vacancies (very fast response: EPIR) Wh

  10. Slide 10: ReRAM: Two Different Technologies, Two Different Memory Solutions

    ReRAM: Two Different Technologies, Two Different Memory Solutions For personal use only 4DS PCMO OTHERS – Filamentary Area based, lower current density programming, Filament based, high current density, low endurance for high endurance reliable cell Up to 109 Endurance Endurance can be as low as 104

  11. Slide 11: AI is Driven by Deep Neural Nets

    AI is Driven by Deep Neural Nets For personal use only Data Pre-train Prompt Decode Please write a Instruction Generative Result Once upon a time, story about a cat. I1 AI Models R1 there was a cat named Jesse... Dog

  12. Slide 12: Neural Nets are an approach to modeling how the brain builds recognition and recall

    Neural Nets are an approach to modeling how the brain builds recognition and recall For personal use only They are a Digital approximation of the Analog process that Action Post-synaptic neuron Action goes on in the brain potential potential Axon Axon Dendrites Dendrites Pre-synaptic neuron Synapse

  13. Slide 13: The energy cost of AI

    The energy cost of AI: 70-80% of the AI operations are due to the weighted calculations For personal use only Moving the data in and out of the GPU takes 5x the energy of the operation itself, and bottlenecks the speed of the GPU Source: B.Fleischer, VLSI’18.

  14. Slide 14: The energy cost of AI continued

    The energy cost of AI: 70-80% of the AI operations are due to the weighted calculations continued For personal use only The global demand Global electricity demand from data centres, AI, and cryptocrurencies, 2019-2026 for electricity may see a huge surge because of AI processing Low case Base case

  15. Slide 15: A Major Driver for new AI architectures: Moving Memory Close to CPU

    A Major Driver for new AI architectures: Moving Memory Close to Central Processing Unit (CPU) For personal use only In-Memory Computing Conventional Near-memory In-memory is the defining feature computing system computing computing of all emerging AI engines Sources: Mutlu et al., “A modern primer o

  16. Slide 16: SRAM has been the approach for In-Memory Compute, but Running out of Steam

    SRAM has been the approach for In-Memory Compute, but Running out of Steam For personal use only Nvidia’s A100 AI and Memory Wall processor has only 40MB of on-chip memory, an order of magnitude lower than what is required

  17. Slide 17: Golden age of emerging processor architectures and IC growth

    Which is driving a golden age of emerging processor architectures and Integrated Circuit (IC) growth For personal use only Global Semiconductor Market Growth and Forecast Global Semiconductor Market Size (USD Bn) Forecast Source: World Semiconductor Trade Statistics and Mckinsey’s projected yearly g

  18. Slide 18: Golden age of emerging processor architectures and IC growth continued

    Which is driving a golden age of emerging processor architectures and IC growth continued For personal use only Artificial intelligence (AI) chip market revenue Nvidia market capitalisation from 2022 to 2027 Source: ©️ Statistica, 2024 Source: S&P Capital IQ. By The New York Times

  19. Slide 19: A need for a New Memory Solution Exists

    A need for a New Memory Solution Exists For personal use only “Difficult challenges gating development of beyond-CMOS devices include those related to memory technologies, information processing or logic devices, and heterogeneous integration of multi-functional components, a.k.a. More-than-Moore (M

  20. Slide 20: The Speed Advantages of 4DS Memory

    The Speed Advantages of 4DS Memory For personal use only 4DS has demonstrated reliable, robust ReRAM programming with a single 4.7ns write pulse This improves on our previously reported 9.5ns The sub 5 nanosecond speeds are due to Electric Pulse Induced Resistance switching, which enables single sho

  21. Slide 21: Persistence + Speed = Energy Savings

    Persistence + Speed = Energy Savings For personal use only For permanent offline storage, traditional NVM offers the best solution For long persistence data 4DS offers a low energy alternative DRAM needs constant refresh 4DS needs no refresh within its persistence window, and then can be ‘refreshed’

  22. Slide 22: Why Important? Warm Data Applications

    Why Important? Warm Data Applications For personal use only Advanced computing always needs DRAM for constant read and write (Hot Data), but emerging Inference Engines for AI need data at DRAM speeds that doesn’t change over time (Warm Data) Storage Class Memory – data storage that is peripheral to

  23. Slide 23: Why Important? Analog Compute in Memory

    Why Important? Analog Compute in Memory For personal use only Using SRAM is the common way of tackling the bandwidth problem in AI processing SRAM is the fastest memory for such uses However the number of weights is limited by SRAM cell size (6T) and # bits per weight needed A scalable analog altern

  24. Slide 24: Corporate Summary

    Corporate Summary For personal use only ASX Symbol: 4DS 4DS Memory 12 month share price graph Shares on Issue 1,762,834,918 Options on Issue 47,207,184 Cash on hand ~ $10M Share price (1 March 2024) 0.110 Market Cap (at 0.110 share price) $193M Top 5 shareholders own 10.39% (at 1 March 2024) Citicor

  25. Slide 25: Board and Management

    Board and Management For personal use only David McAuliffe Dr Guido Arnout Howard Digby Ting Yen Peter Himes Executive Chairman Non-Executive Director Non-Executive Director Chief Technical Officer Strategic Advisor to the Board Experienced company director 30+ years in commercialising Former senior

  26. Slide 26: 4DS: The Right Memory for the Right Market at the Right Time

    For personal use only 4DS: THE RIGHT MEMORY FOR THE RIGHT MARKET AT THE RIGHT TIME

  27. Slide 27: For More Information

    For personal use only FOR MORE INFORMATION Registered Office USA Office Level 2, 50 Kings Park Road 3155 Skyway Court West Perth WA 6005 Fremont CA 94539 Postal Address Phone +61 6377 8043 PO Box 271 Email info@4dsmemory.com West Perth WA 6872 Web 4DSmemory.com

4DS Memory — Investor Presentation (March 2024) on 6ix