MAX78000
Artificial Intelligence Microcontroller with Ultra-Low-Power Convolutional Neural Network Accelerator
A New Breed of AI Micro Built to Enable Neural Networks to Execute at Ultra-Low Power
Top
Overview
Features and Benefits
- Dual-Core Ultra-Low-Power Microcontroller
- Arm Cortex-M4 Processor with FPU up to 100MHz
- 512KB Flash and 128KB SRAM
- Optimized Performance with 16KB Instruction Cache
- Optional Error Correction Code (ECC-SEC-DED) for SRAM
- 32-Bit RISC-V Coprocessor up to 60MHz
- Up to 52 General-Purpose I/O Pins
- 12-Bit Parallel Camera Interface
- One I2S Master/Slave for Digital Audio Interface
- Neural Network Accelerator
- Highly Optimized for Deep Convolutional Neural Networks
- 442k 8-Bit Weight Capacity with 1,2,4,8-Bit Weights
- Programmable Input Image Size up to 1024 x 1024 pixels
- Programmable Network Depth up to 64 Layers
- Programmable per Layer Network Channel Widths up to 1024 Channels
- 1 and 2 Dimensional Convolution Processing
- Streaming Mode
- Flexibility to Support Other Network Types, Including MLP and Recurrent Neural Networks
- Power Management Maximizes Operating Time for Battery Applications
- Integrated Single-Inductor Multiple-Output (SIMO) Switch-Mode Power Supply (SMPS)
- 2.0V to 3.6V SIMO Supply Voltage Range
- Dynamic Voltage Scaling Minimizes Active Core Power Consumption
- 22.2µA/MHz While Loop Execution at 3.0V from Cache (CM4 Only)
- Selectable SRAM Retention in Low-Power Modes with Real-Time Clock (RTC) Enabled
- Security and Integrity
- Available Secure Boot
- AES 128/192/256 Hardware Acceleration Engine
- True Random Number Generator (TRNG) Seed Generator
Product Details
Artificial intelligence (AI) requires extreme computational horsepower, but Maxim is cutting the power cord from AI insights. The MAX78000 is a new breed of AI microcontroller built to enable neural networks to execute at ultra-low power and live at the edge of the IoT. This product combines the most energy-efficient AI processing with Maxim's proven ultra-low power microcontrollers. Our hardware-based convolutional neural network (CNN) accelerator enables battery-powered applications to execute AI inferences while spending only microjoules of energy.
The MAX78000 is an advanced system-on-chip featuring an Arm® Cortex®-M4 with FPU CPU for efficient system control with an ultra-low-power deep neural network accelerator. The CNN engine has a weight storage memory of 442KB, and can support 1-, 2-, 4-, and 8-bit weights (supporting networks of up to 3.5 million weights). The CNN weight memory is SRAM-based, so AI network updates can be made on the fly. The CNN engine also has 512KB of data memory. The CNN architecture is highly flexible, allowing networks to be trained in conventional toolsets like PyTorch® and TensorFlow®, then converted for execution on the MAX78000 using tools provided by Maxim.
In addition to the memory in the CNN engine, the MAX78000 has large on-chip system memory for the microcontroller core, with 512KB flash and up to 128KB SRAM. Multiple high-speed and low-power communications interfaces are supported, including I2S and a parallel camera interface (PCIF).
The device is available in a 81-pin CTBGA (8mm x 8mm, 0.8mm pitch) package.
Applications
- Audio Processing: Multi-Keyword Recognition, Sound Classification, Noise Cancellation
- Facial Recognition
- Object Detection and Classification
- Time-Series Data Processing: Heart Rate/Health Signal Analysis, Multi-Sensor Analysis, Predictive Maintenance
Product Categories
Markets and Technologies
Product Lifecycle
Production
At least one model within this product family is in production and available for purchase. The product is appropriate for new designs but newer alternatives may exist.
Evaluation Kits (2)
Documentation & Resources
-
MAX78000 Reliability Data10/10/2022PDF116K
-
UG-7456: MAX78000 User Guide7/22/2021PDF6M
-
Elevate Surveillance with Cameras that See, Sense and Think9/15/2022PDF5 M
-
Visual Identification AI at The Edge: Facial Recognition4/27/2023 -
Getting started with the MAXREFDES178 Cube Camera11/30/2022 -
Session 2 - AI at the Edge: A Practical Introduction to Maxim Integrated’s MAX78000 AI Accelerator11/30/2022 -
AI Face Identification11/30/2022 -
Introduction to the MAX78000 Ultra-low Power ARM Cortex M4F with Convolutional Neural Network Accelerator11/30/2022 -
Getting Started with the MAX78000EVKIT11/30/2022 -
Session 1 - AI at the Edge: A Practical Introduction to Maxim Integrated’s MAX78000 AI Accelerator11/30/2022 -
Video Series: Understanding Artificial Intelligence11/29/2022SERIES -
Advanced Computer Vision with MAX78000 and Xailient10/25/2022 -
MAX78000 with AIZip Visual Wake Word model10/25/2022
-
Keywords Spotting Using the MAX7800010/13/2020
-
Hardware Conversion of Convolutional Neural Networks: What Is Machine Learning?—Part 34/1/2023 Analog Dialogue
-
Training Convolutional Neural Networks: What Is Machine Learning?—Part 23/1/2023 Analog Dialogue
-
Introduction to Convolutional Neural Networks: What Is Machine Learning?—Part 12/1/2023 Analog Dialogue
-
Face Identification Using MAX7800011/4/2020
Tools & Simulations
Software Development
Reference Designs (1)
Design Resources
ADI has always placed the highest emphasis on delivering products that meet the maximum levels of quality and reliability. We achieve this by incorporating quality and reliability checks in every scope of product and process design, and in the manufacturing process as well. "Zero defects" for shipped products is always our goal.View our quality and reliability program and certifications for more information.
| Part Number | Material Declaration | Reliability Data | Pin/Package Drawing | CAD Symbols, Footprints & 3D Models |
|---|---|---|---|---|
| MAX78000EXG+ | Material Declaration | Reliability Data | 81-CSP_BGA-8X8X1.17 | |
| Wafer Fabrication Data | MAX78000 Reliability Data |
Support & Discussions
MAX78000 Discussions
RE: MAX78000/MAX78002 Maximum speed of the parallel camera interface
17 week(s) ago in Other ADI Processors
Sample & Buy
Ordering FAQs
See our Ordering FAQs for answers to questions about online orders, payment options and more.
Buy Now Pricing
(**) Displayed Buy Now Price and Price Range is based on small quantity orders.
List Pricing
(*)The 1Ku list pricing shown is for BUDGETARY USE ONLY, shown in United States dollars (FOB USA per unit for the stated volume), and is subject to change. International prices may differ due to local duties, taxes, fees and exchange rates. For volume-specific price or delivery quotes, please contact your local Analog Devices, Inc. authorized distributor. Pricing displayed for Evaluation Boards and Kits is based on 1-piece pricing.
Lead Times
Please see the latest communication from our CCO regarding lead times.
Sampling
Selecting the Sample button above will redirect to the third-party ADI Sample Site. The part selected will carry over to your cart on this site once logged in. Please create a new account there if you have never used the site before. Contact SampleSupport@analog.com with any questions regarding this Sample Site.
Evaluation Boards
Pricing displayed is based on 1-piece.
Up to two boards can be purchased through Analog.com. To order more than two, please purchase through one of our listed distributors.
Pricing displayed is based on 1-piece. The USA list pricing shown is for budgetary use only, shown in United States dollars (FOB USA per unit), and is subject to change. International prices may vary due to local duties, taxes, fees and exchange rates.