jonathan rossCEO and Founder of Groq, said, “The hard work of our talented teams, focused on solving increasingly complex machine learning needs, has driven Groq to innovate. We started knowing that software was limited by hardware, so we built a new processor architecture. to advance software for machine learning workloads. We are delighted to receive Frost & Sullivan’s Technology Innovation Leadership Award as proof of our accomplishments thus far.
Frost & Sullivan notes that the accelerating change in AI and machine learning models and the legacy need to custom code each new model iteration presents a significant challenge, as the industry based on custom coding has to struggling to keep up with the latest technologies. Additionally, the increasing complexity resulting from scaling hardware with multiple processor cores, on-chip, modules, and threads presents significant hurdles. Because simplifying development and delivering real-time results are critical steps for vendors, Groq is well-positioned to address these complexities.
“With nearly seven times the computational density per transistor, Frost & Sullivan recognizes how Groq’s approach leverages a unique combination of easy-to-program systems that enables speed of development and delivers low latency and massive throughput in a single computing core that scales in a near-linear fashion across multiple chips,” said Sushrutha Sadashiva, industry analyst at Frost & Sullivan. “GroqChip™ fits into data centers and is dedicated to IA, where it can work independently or as an integrated solution to help accelerate parts of a system that take advantage of the TSP architecture,” added Samantha FisherBest Practices Research Analyst at Frost & Sullivan.
To that end, the company delivers differentiated features (e.g., sub-millimeter low latency and predictable performance) and outperforms traditional tactics in critical areas, such as performance, power, and accuracy.
Groq’s customer, Argonne National Laboratory, experienced Groq’s performance first-hand. argon computer scientist Tom Brett said, “Using the Groq platform at Argonne, we were able to accelerate our efforts to identify promising COVID-19 drug candidates from large numbers of small molecules. The system’s AI capabilities allowed us to make many more inferences per second, reducing the time needed for each search from days to minutes.”
The innovative Groq tech stack results from the startup’s focus on talent density. Groq recently expanded its talent and solutions portfolio by acquiring Maxeler Technologies. This combines Maxeler’s expertise in data flow solutions with the Groq TSP architecture, helping customers build a cohesive AI strategy in a high performance computing environment.
The latest technical information on Groq solutions will be presented by Groq Chief Architect and Fellow Dennis Abts at the 2022 International Symposium on Computer Architecture (ISCA) based on their accepted paper, “A Software-defined Tensor Streaming Multiprocessor for Large-scale Machine Learning”. ”
Groq is an embedded systems accelerator company specializing in machine learning solutions that generate real-time results for AI and HPC workloads. The startup has developed the innovative, deterministic Tensor Streaming Processor architecture with a single core and a single compiler capable of accurately predicting the performance and computation time of workloads. The startup offers low latency, accuracy, and scalability to its customers. Groq lifted $367 million to date, with Series C funding co-led by D1 Capital and Tiger Global Management. For more information, visit groq.com.
Groq Media Relations Contact: