Groq at ISCA 2022

ISCA Paper 2022

Startup Presents Second Paper on Novel Approach to Large-scale Machine Learning Read the paper In June 2022, Groq presented its second paper in three years,

Why Groq – Michelle Donnelly

Michelle Donnelly

As someone who is customer-obsessed and a “growth hacker,” I’ve joined Groq as Chief Revenue Officer. During my time as a sales and go-to-market leader

Why Groq – Jim Miller

jim miller

My career has taught me that most people will ask for what they know. So when they get something unexpected, and better than what they

Why Groq – Igor Arsovski

Igor Arsovski blog photo

Groq is always hiring for talent density. We value sharing about our culture and talent transparently, so we sat down with Igor Arsovski, Fellow, to

Why Groq – San Mehat

san mehat

I’ve always joked that I was born 10 years too late to participate in the microcomputer revolution of the 1980s and 300 years too early

Responsibility at the Core

Samidh Blog 1

Twenty years ago when I was a graduate student at the MIT Artificial Intelligence Lab, I burned the midnight oil trying to get neural networks


It just got a lot easier to get started with Groq technology with GroqFlow! GroqFlow, our automatic toolflow for mapping machine learning workloads to GroqChip™,

Groq Gives Hope

Groq Cares copy

What else does the team at Groq do besides simplify compute for the world? They give back; as they should. In celebration of Companies that

Come Join Our Elite Team of AI Innovators

Engineer Talent

Artificial Intelligence is exploding. And with it comes amazing new careers in computational engineering, semiconductor development, systems integration and data science. The technology seekers, thinkers

The Shortest Path to Performance

groqnode 1

With over 1,000 attendants and more than 100 speakers, the AI Summit is the industry event for the AI hardware ecosystem. The event offers unique perspectives

ISCA 2020 Conference


We introduce the Tensor Streaming Processor (TSP) architecture, a functionally-sliced microarchitecture with memory units interleaved with vector and matrix deep learning functional units. This architecture

Groq TSP Leads in Inference Performance

LinleyMastheadGroqArticle 1

Today the Linley Group released its latest Microprocessor Report titled “Groq Rocks Neural Networks”, which concludes that Groq’s “TSP stands out in both peak performance