EVK2 1 1
EVK2 1 1
EVK2 3 1
EVK2 3 1
EVK2 2
EVK2 2

SPU-001 Co-Processor Specification

  • 1 MB on-chip SRAM (10 MB effective with sparsity)
  • 22nm process
  • Packaging: Bare die, WLCSP
  • Sub-mW for speech, audio, and 1-D data
  • SPI interface

Included Demo Applications

  • AI Noise Reduction
  • Always-on Keyword Detection

Host for SPU001-EVK

  • Tympan Host for EVK2
    • Host processor Cortex-M7 at 600 MHz with FPU
    • 2x onboard MEMS Microphones
    • 3.5mm Audio jacks for input/output
    • Micro SD card reader
  • ADI MAX78000FTHR Host for EVK3
    • Host processor dual-core Cortex-M4 with FPU
    • 3.5mm Audio jacks for input/output
    • Micro SD card reader

Welcome

If you just received your evaluation kit (EVK):

Read the Quick Start Guide

If you just received your evaluation board (EVB):

Read about the Schematics and Pinouts in Application Notes

To test Femtosense’s AI Models:

Read the Algorithm Guide and download the latest Release Package.

To integrate SPU-001 into a new design:

Read the Integration Guide and download the 

To develop custom AI models for SPU:

Check out End-to-end Algorithm Development Example

Welcome

  • If you just received your evaluation kit (EVK):
    Read the Quick Start Guide

  • If you just received your evaluation board (EVB):
    Read about the Schematics and Pinouts in Application Notes

  • To test Femtosense’s AI Models:
    Read the Algorithm Guide and download the latest Release Package.

  • To integrate SPU-001 into a new design:
    Read the Integration Guide and download the 

  • To develop custom AI models for SPU:
    Check out End-to-end Algorithm Development Example

Release Packages

  • EVK2

    2.1

    Apr 29, 2024

    *Model Update | improved AINR (2ms, 8ms), new English / Korean SLU demo
    *Firmware Update | PDM mic support, GUI for SLU, XPROG_P files
    *Compatibility | across EVK2 host  

  • EVK2

    2.0

    Mar 22, 2024

    *Compatibility Release for EVK2v2 (Mass Production SPU-001)
    *Available Models | AINR (2ms, 8ms), WWD (Alexa, GSC)
     

  • EVK3

    1.1

    Dec 28, 2023

    *Model Update | improved AINR (2ms, 8ms), new WWD (GSC)
    *Firmware Update | universal firmware for multiple (up to 3) models
     

  • EVK2

    1.0.7

    Dec 28, 2023

    *Model Update| improved AINR (2ms, 8ms), new WWD (Alexa)
     

  • EVK2

    1.0.6

    Oct 25, 2023

    *Model Update | super-low-latency 2ms AINR, new WWD (GSC)
    *Firmware Update | faster loading times, static power measurement support 

  • EVK3

    1.0.1

    Oct 25, 2023

    *Initial release | 8ms AINR (power-optimized), 2ms (super-low-latency) AINR 

  • EVK2

    1.0.5

    Aug 15, 2023

    *Model Release | power-optimized 8ms AINR, improved WWD models
    *Firmware Update | Add power-optimized firmware 

  • EVK2

    1.0.4

    May 04, 2023

    *Firmware update | Add additional error codes and improve reliability of program file reading 

  • EVK2

    1.0.3

    Apr 10, 2023

    *Model update | Add AI noise reduction model AINRGP11604081 

  • EVK2

    1.0.2

    Mar 25, 2023

    *Initial release 

Models & Firmware Releases

2.1 — *Model Update | improved AINR (2ms, 8ms), new English / Korean SLU demo
*Firmware Update | PDM mic support, GUI for SLU, XPROG_P files
*Compatibility | across EVK2 host  

2.0 — *Compatibility Release for EVK2v2 (Mass Production SPU-001)
*Available Models | AINR (2ms, 8ms), WWD (Alexa, GSC)
 

1.1 — *Model Update | improved AINR (2ms, 8ms), new WWD (GSC)
*Firmware Update | universal firmware for multiple (up to 3) models
 

1.0.7 — *Model Update| improved AINR (2ms, 8ms), new WWD (Alexa)
 

1.0.6 — *Model Update | super-low-latency 2ms AINR, new WWD (GSC)
*Firmware Update | faster loading times, static power measurement support 

1.0.1 — *Initial release | 8ms AINR (power-optimized), 2ms (super-low-latency) AINR 

1.0.5 — *Model Release | power-optimized 8ms AINR, improved WWD models
*Firmware Update | Add power-optimized firmware 

1.0.4 — *Firmware update | Add additional error codes and improve reliability of program file reading 

1.0.3 — *Model update | Add AI noise reduction model AINRGP11604081 

1.0.2 — *Initial release 

Technical Documentation

Example 1

Jun 17, 2024

Example 2

Jun 17, 2024

Algorithms Guide

Apr 29, 2024

Integration Guide

Apr 29, 2024

Design 1

Jun 17, 2024

Software and Compiler Resources

fmot
PyTorch frontend and tools
femtoflow
Tensorflow frontend and tools
femtocrux
Core compiler to simulate and deploy models
femtodriverpub
Driver utilities for FS hardware

Get updates

Be the first to know about new products and features

Notice
This website stores cookies on your computer. These cookies, as specified in our Privacy Policy, are used to collect information about how you interact with our website. We use this information in order to improve and customize your browsing experiences.

Use the “Accept” button to consent to the use of such technologies. Use the “Reject” button to continue without accepting.

Privacy Preferences

We and selected third parties use cookies or similar technologies to store cookies on your computer for technical purposes and, with your consent, for other purposes such as website analytics.

Allow All
Manage Consent Preferences
  • Strictly necessary cookies
    Always Active

    These trackers are used for activities that are strictly necessary to operate or deliver the service you requested from us and, therefore, do not require you to consent.

  • Analytical / performance cookies

    These trackers help us to measure traffic and analyze your behavior with the goal of improving our service.
    Cookies Details

Save