Ceva-NeuPro-Nano - NPU IP for Embedded ML

From Ceva, Inc.

Contact Vendor

Ask Volt AI questions about this IP

Quickly find out if this is the right IP for you with our semiconductor-trained AI assistant, Volt.

Description

Ceva-NeuPro-Nano is a highly efficient and self-sufficient Edge NPU designed for Embedded ML applications.

This Edge NPU, which is the smallest of Ceva-NeuPro's NPU product family, delivers the optimal balance of ultra-low power and high performance in a small area to efficiently execute Embedded ML workloads across AIoT product categories, including Hearables, Wearables, Home Audio, Smart Home, Smart Factory, and more. Ranging from 10 GOPS up to 200 GOPS per core, Ceva-NeuPro-Nano is designed to enable always-on audio, voice, vision, and sensing use cases in battery-operated devices across a wide array of end markets. Ceva-NeuPro-Nano makes the possibilities enabled by Embedded ML into realities for low cost, energy efficient AIoT devices.

Learn more about Ceva-Neupro-Nano salution>

Deliverables

Soft IP

Synthesizable RTL
Verilog integration testbench
Sample synthesis script and constraints
Sample simulation script
Datasheet
Hardware user guide
Hardware implementation guide
Standard EDA tool flow scripts and support files
Verification test bench and test vectors

Features

Fully programmable to efficiently execute Neural Networks, feature extraction, signal processing, audio and control code
Scalable performance to meet a wide range of use cases, with MAC configurations up to 64 int8 (native 128 of 4×8) MACs per cycle
Two NPU configurations to address a wide variety of use cases are available: (1) Ceva-NPN32 with 32 4×8, 32 8×8, 16 16×8, 8 16×16, 4 32×32 MAC operations per cycle (2) Ceva-NPN64 with 128 4×8, 64 8×8, 32 16×8, 16 16×16, 4 32×32 MAC operations per cycle and 2x performance acceleration using 50% weight sparsity (Sparsity Acceleration)
Future proof architecture that supports the most advanced ML data types and operators, including 4-bit to 32-bit integer support and native transformer computation
Ultimate ML performance for all use cases, with Sparsity Acceleration, acceleration of non-linear activation types, and fast quantization – up to 5 times acceleration of internal re-quantizing tasks
Powerful microcontroller and DSP capabilities with a Coremark/MHz score of 6.0
Ultra-low memory requirements achieved with Ceva-NetSqueeze™, yielding up to 80% memory footprint reduction through direct processing of compressed model weights without the need for an intermediate decompression stage. NetSqueeze solves a key bottleneck inhibiting the broad adoption of AIoT processors today
Ultra-low energy achieved through innovative energy optimizations, including dynamic voltage and frequency scaling support tunable for the use-case, and dramatic energy and bandwidth reduction by distilling computations using weight-sparsity acceleration
Complete, simple to use Ceva-NeuPro-Studio AI SDK, optimized to work seamlessly with leading, open-source AI inference frameworks, such as LiteRT for Microcontrollers and µTVM
Model Zoo of pre-trained and optimized machine learning models covering Embedded ML audio, voice, vision and sensing use cases
Comprehensive portfolio of optimized runtime libraries and off-the-shelf application-specific software

Tech Specs

Class	Value
Categories	Processor > AI Processor
Maturity	In Production
Availability	All Countries & Regions

Image Gallery

Ceva-NeuPro-Nano - NPU IP for Embedded ML

Applications

Automotive
Consumer IoT
Industrial Automation

Ceva-NeuPro-Nano - NPU IP for Embedded ML

Ask Volt AI questions about this IP

Sign Up for Silicon Hub

Welcome to Silicon Hub

Switch to a Buyer Account

Create a Buyer Account