SiMa.ai is the first startup to participate and achieve winning results in the industry’s most popular MLPerf image benchmark: ResNet-50, enabling scaling of ML at the embedded edge.
SiMa.ai, the machine learning company delivering solutions for the embedded edge, topped the industry leader in its debut MLPerf Benchmark performance in the Closed Edge Power category. The company’s Machine Learning System-on-Chip (MLSoC™) platform earned top inference achievements in all aspects of the ResNet-50 benchmark, beating the industry leader on both performance (frames per second) and power. These MLPerf results demonstrate that the MLSoC Platform follows through on its promise of an Any, 10x, Pushbutton solution for effortless ML deployment.
“We started SiMa.ai to lead the machine learning industry and we are excited about the acknowledgement that we have come out on top against all major players at the edge,” said Krishna Rangasayee, CEO and founder, SiMa.ai. “While it is exciting that we won at MLPerf in performance and power over the incumbent leader, what is super rewarding is that we are delighting customers globally with a ‘Any, 10x, Pushbutton’ experience that in real life applications far exceeds any other alternative which remains our focus – doing ML software right for our customers.”
Established by industry leaders in 2018, the foundation for MLCommons® aims to accelerate machine learning innovation. The MLPerf™ inference benchmarks are released bi-annually and define a fully standardized way of measuring performance and power for a variety of ML applications, enabling end users to easily sort out company claims, and provide industry-standard metrics. Since inception, the benchmarks have evolved to encompass data sets and best practices, playing a critical role for industry adoption and research.
“SiMa.ai’s achievement of working silicon on their first fab run was impressive, and now they’re already beating incumbents on both latency and energy on MLPerf benchmarks,” said Kurt Keutzer, Professor at UC Berkeley, an esteemed American scientist and pioneer of Deep Learning at the edge. “SiMa.ai has truly established themselves as the startup to watch at the edge,” he continued.
SiMa.ai’s MLSoC hardware combined with its Palette™ software delivers a purpose-built platform with push button results, enabling effortless ML deployment and scaling at the embedded edge while achieving 10x better performance at the lowest power. With this methodology, SiMa.ai is able to achieve dramatic results without needing to employ a massive team while delivering results in minutes versus competitor technology that requires months. This is SiMa.ai’s first time participating in an MLCommons competition, and this event illustrates how SiMa.ai is poised to disrupt the industry with AI in the form of ML which will move into everything that surrounds us, making the world safer and smarter.
“I am impressed with the low power consumption SiMa.ai demonstrated in the MLPerf image classification benchmark,” said Karl Freund, Founder and Principal Analyst at Cambrian-AI Research. “SiMa.ai is truly changing the game and how we think of ML adoptions and scaling at the embedded edge.”
Visit AITechPark for cutting-edge Tech Trends around AI, ML, Cybersecurity, along with AITech News, and timely updates from industry professionals!
