2021-02-22 - Sally Ward-Foxton

Similarity Search Engine Accelerate AI Inference

Splitting out the search portion from an AI model means it can be hardware-accelerated to dramatically reduce latency...

2020-11-16 - Sally Ward-Foxton

Homegrown CNN Accelerator Moves AI to the Edge

Maxim plans to combine its new CNN accelerator with its other IP for a range of AI-enabled application-specific SoCs...

2020-09-18 - Sally Ward-Foxton

AI Accelerators Promise Power Efficient for Near-Edge Computing

Qualcomm’s Cloud AI 100 silicon will ship next year on three different cards, each…

2020-09-17 - Sally Ward-Foxton

Co-optimized HW/SW Accelerator for AI Recommendation Models

Hardware-software solution uses sparsity to accelerate AI recommendation models that are typically memory-bound...

2020-01-21 - Anne-Françoise Pelé

France’s Most Promising Startups

France, under La French Tech 120 program, has unveiled the identity of the 123 high-potential startups that will benefit from…

2019-12-19 - Sally Ward-Foxton

AI Chip Ups the Ante, uses FD-SOI

GreenWaves tweaks architecture, uses FD-SOI to cut power by 5x

2019-12-16 - Sally Ward-Foxton

AWS Rolls Out Inferentia Chip

Amazon makes Inferentia chip available for customer machine-learning workloads.

2019-12-11 - Sally Ward-Foxton

AI: There’s More to Chip Performance Than TOPS

What is the best measure of inference performance?

2019-11-18 - Sally Ward-Foxton

Graphcore’s AI Chips Used in Microsoft’s Azure Cloud

Modest performance improvements on BERT, more dramatic on ResNext.

2019-11-08 - Sally Ward-Foxton

Nvidia Reveals World’s Smallest AI ‘Supercomputer’

The board delivers 1.4 TOPS/W for drones and small robots.