Dashboard

Featured nodes

Roots

  • Public root

Templates

  • Test template
  • iCorps template
  • Guanyu's Latex template
  • Ivar's latex template
  • Family Tree template
  • Latex template
  • Router template

Trees

  • Public trees

Orphans

  • Browse orphan nodes
Related nodes

Parents4

  • NVM Computing - startups
  • Analog Computing
  • SURVEY of ML accelerators
  • Flash Memory

Siblings23
  • Sort by title
  • Sort by date

  • analog AI at IBM
  • AI accelerators - history
  • Optical Computing
  • Hardware AI on memristors
  • tinyML - commercial companies
  • Analog devices - pros and cons
  • Plumerai and XMOS
  • Mythic AI
  • SURVEY of ML accelerators
  • AIStorm
  • Syntiant AI
  • Two better than one
  • Analog Architectures for ML
  • 2015 - now - Strukov's group
  • Memory Issues For AI Edge Chips
  • Floating Gate Flash vs All other memories
  • Google TPU
  • FlexLogix
  • NAND XIP Flash
  • SRAM/DRAM basics
  • Gyrfalcon
  • Aspinity ML core
  • Lattice Semiconductor

Children1
  • Sort by title
  • Sort by date

  • AI Hardware in 2021
Knowenβ
  • Help
    • Welcome to Knowen!
    • Edit test node (no login required)
    • Create new test node (no login required)
  • Not logged in
    • Sign in
    • Sign up
5Privacy
  • Edit node

Mythic AI

Created over 5 years ago, updated about 2 months ago

https://www.mythic-ai.com/category/artificial-intelligence/

https://www.mythic-ai.com/the-era-of-analog-compute-has-arrived/

  • PDF of main points - medium , poor print 2018 - Hot Chips - PRESENTATION

  • video Building the Future of AI Hardware Part 1 - CogX 2019
    39:30 mythic- matrix multiplication with flash in-memory

https://patents.justia.com/search?q=Mythic

NEWS - https://semiengineering.com/tag/mythic-ai/

A Closer Look at Machine Learning Chip Maker Mythic Apr 16th, 2018

Mythic AI Accelerator Targets High-End Edge With 35 TOPS By Sally Ward-Foxton 11.19.2020

the product - M1108 ANALOG MATRIX PROCESSOR

Dave Fick

presentation at Berkeley - 2019 Analog Compute-in-Memory at Mythic
a course - Hardware for Machine Learning

2017 Analog In-Memory Subthreshold Deep Neural Network Accelerator as well as pdf

MYTHIC MULTIPLIES IN A FLASH

Analog In-Memory Computing Eliminates DRAM Read/Write Cycles By Mike Demler (August 27, 2018)

  • Codasip Bk3, Codasip Studio - RESULT Reusable programmable domain-specific core with custom instructions

Parents

  • NVM Computing - startups
  • Analog Computing
  • SURVEY of ML accelerators
  • Flash Memory

Children

  • AI Hardware in 2021

Contact us or leave feedback

© KTree Inc. 2026