hand 3
hand 3

SPU-001 is Here!

The SPU-001 is now in mass production. It is tiny enough to fit into the smallest devices and efficient enough to last all day running powerful AI applications on-device in real time!

Get in touch to order SPU-001 hardware, evaluation kits, software tooling, or production-grade AI models!

Inquiry

SPU-001 Integration

wlcsp bare die new1
wlcsp bare die new1

Co-Processor

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

Hardware IP

SoC Integration

  • 512 kB on-chip SRAM per SPU-001 core (5 MB effective with sparsity)
  • Memory is shareable
  • 22nm process | can be ported to any process node
  • Available in fractional or multi-core configurations
  • AXI interface
coredesign gif 2
coredesign gif 2
4-core Configuration

SPU-001 Evaluation

evb
evb

Evaluation Board (EVB)

PCB Board with SPU-001 WLCSP for integrating with external host systems

  • Full access to SPU pins on PMOD header
  • 16 Mb onboard SPI Flash
  • 1.8-3.3V operation
  • Headers for easy power measurement
evk2
evk2

Evaluation Kit 2 (EVK2)

EVB + Tympan open source hearing aid platform and Tympan connector board

  • Host processor Cortex-M7 with FPU
  • 2x onboard MEMS microphones
  • 3.5mm audio jacks for input/output
  • Micro SD card reader
evk3 black gray
evk3 black gray

Evaluation Kit 3 (EVK3)

EVB + Analog Devices MAX78000FTHR board and PCB connector board

  • Host processor dual-core Cortex-M4 with FPU
  • 3.5mm Audio jacks for input/output
  • Micro SD card reader

Software Development Kit

flow 20231
flow 20231

Our Software Development Kit (SDK) allows developers to get started with minimal barriers. The SDK provides advanced sparse optimization tools, a hardware simulator, and the Femtocrux compiler.

Deploy models to the SPU with or without fine-tuning. Achieve high efficiency for dense models, and even higher efficiency for sparse models.

Optimize

Optimize models with sparsity regularization and quantization aware training. 

Simulate

Simulate energy, latency, throughput, and footprint of your model on the SPU.

Deploy

Use the Femtocrux compiler to deploy to the SPU for verification, testing, and production.

Available Ready-to-Deploy Models

AI Noise Cancellation

  • Real-time Face-to-Face
  • Next-gen Hearing-aid
  • Conference / Phone calls
  • Extreme Noise

AI Voice Interface

  • Wakeword Detection
  • Local Commands¬†
  • Sentence Intent Understanding
  • Voice Cleanup

Get updates

Be the first to know about new products and features