Groq TSP blows away single chip record at 1 PetaOp/s

Groq believes its TSP architecture on silicon is many times faster than chips on the market today. It is currently being tested by customers. (Groq)

Start-up Groq announced a new processor architecture capable of 1 quadrillion operations per second on a single chip when implemented, marking a record. That’s a 1 followed by 15 zeroes.

The Mountain View, California, company said Thursday that its new Tensor Streaming Processor (TSP) supports up to 250 trillion floating point operations per second (FLOPS).

It is designed for deep learning inference processing requirements of computer vision, machine learning and artificial intelligence workloads, all of which are part of edge computing and IoT applications, especially those involving safety and a high degree of accuracy.

Free Daily Newsletter

Interesting read? Subscribe to FierceElectronics!

The electronics industry remains in flux as constant innovation fuels market trends. FierceElectronics subscribers rely on our suite of newsletters as their must-read source for the latest news, developments and predictions impacting their world. Sign up today to get electronics news and updates delivered to your inbox and read on the go.

Jonathan Ross, co-founder of Groq, said the architecture is many multiples faster than anything else available for inference work in terms of low latency and inferences per second. While top GPU companies have talked about 1 PetaOp/s (one peta operations per second) coming in a few years, Groq has already announced it and shipped samples to customers, he added in a statement.

Samples of silicon running the architecture have been tested by customers who have reported the top performance, Ross said. Those customers are running both x86 and non-x86 systems. A key feature of TSP is that software is used to implement execution planning instead of using valuable silicon real estate for dynamic instruction execution.

As a result, Groq claimed its architecture for TSP chips is less complex than traditional architectures for CPUs, GPUs and Field Programmable Gate Arrays.

Grog has posted a whitepaper describing the Tensor Streaming architecture.

The company is showing the architecture at Supercomputing Denver Nov. 17-21.

RELATED: IBM challenges Google’s quantum superiority claim

Suggested Articles

Two economic studies on expanding tech jobs to dozens of heartland places in the U.S. provoke a discussion on good work, good life.

The revived Toys R Us toy store will be smaller than the huge box stores of the past and utilize sensors to monitor consumer behavior.

Integration of Symantec business expected to help with security software sales