Mythic launches power-sipping AI chip

Edge-focused AI chip consumes one-tenth the power of a desktop GPU

Semiconductor startup Mythic has launched an artificial intelligence (AI) processor that it says will deliver the computing capabilities of a GPU for a tenth of the power.

The M1076 Mythic AMP chip targets edge computing AI applications with power and footprint limitations. Like other edge-based AI processors, the Mythic CPU runs a neural network to handle a process called inferencing. This takes new input, such as a video signal from a camera in a manufacturing plant, and runs it through a trained AI model designed to recognize specific things — like an object on a production line.

The difference lies in how the chip processes data in its neural network. It uses a combination of analog circuitry and in-memory computing to save power. Rather than storing its data in slower memory that the chip must access when needed, it uses multiple memory arrays that handle the computing themselves using their memory elements as tunable resistors. 

This allows the chip to compute neural network inputs and outputs as voltages and currents. The memory arrays function as nodes in the neural network graph and can operate in parallel.

The unique chip architecture enables the company to fit more AI computing horsepower into a single chip, it says. The M1076 delivers up to 25 trillion operations per second (TOPS) using a 3-watt power draw. It's available as a single chip, a PCIe M2 card for low-footprint applications, and a PCIe card with up to 16 chips. The latter can deliver 400 TOPS for just 75 watts of power.

Related Resource

The AI-powered supply chain

Better demand forecasting and operational excellence

An airplane flying over a city - The AI-powered supply chain - whitepaper from DataRobotDownload now

To run neural networks trained by popular AI packages such as PyTorch, developers will need to retrain them to run on the chip's Analog Compute Engine (ACE) and then compile them for the chip's architecture.

Mythic says the chip will work well in video processing applications, including object detection and depth estimation, making it suitable for industrial machine vision, surveillance cameras, and augmented reality applications.

The company raised $70 million in series C funding in May, led by BlackRock and Hewlett Packard Pathfinder, bringing its total funding to $165.2 million.

Featured Resources

B2B under quarantine

Key B2C e-commerce features B2B need to adopt to survive

Download now

The top three IT pains of the new reality and how to solve them

Driving more resiliency with unified operations and service management

Download now

The five essentials from your endpoint security partner

Empower your MSP business to operate efficiently

Download now

How fashion retailers are redesigning their digital future

Fashion retail guide

Download now

Recommended

Preparing for AI-enabled cyber attacks
Whitepaper

Preparing for AI-enabled cyber attacks

22 Jul 2021
Unilabs to deploy Ibex’s AI-assisted cancer diagnostic platform across Europe
artificial intelligence (AI)

Unilabs to deploy Ibex’s AI-assisted cancer diagnostic platform across Europe

21 Jul 2021
US creates AI data-sharing task force
artificial intelligence (AI)

US creates AI data-sharing task force

11 Jun 2021
ISG and Cognigy partner on automated conversational AI
artificial intelligence (AI)

ISG and Cognigy partner on automated conversational AI

10 Jun 2021

Most Popular

Salesforce's $28bn Slack acquisition: What's next for workplace collaboration?
collaboration

Salesforce's $28bn Slack acquisition: What's next for workplace collaboration?

22 Jul 2021
Samsung Galaxy S21 5G review: A rose-tinted experience
Mobile Phones

Samsung Galaxy S21 5G review: A rose-tinted experience

14 Jul 2021
One third of cyber security pros report experiencing workplace harassment
Careers & training

One third of cyber security pros report experiencing workplace harassment

22 Jul 2021