SiMa.ai Surpasses the Industry ML Leader Again in the MLPerf™ Closed Edge ResNet50 Benchmark SiMa.ai achieves groundbreaking performance and power results with a 20 percent improvement since its first submission in April 2023

Press Releases

SAN JOSE, Calif. – September 11, 2023 – SiMa.ai, the machine learning company delivering solutions for the embedded edge, today announced the results of its second MLPerf submission, outperforming industry ML leader, NVIDIA’s Orin NX and AGX Orin in the Closed Edge power category in the MLCommons® ML Perf 3.1 benchmark. SiMa.ai participated in the MLPerf ™ Inference 3.1 closed, edge, power division of this benchmarking process, focusing on the image classification benchmark Resnet50. Since the company’s prior submission in April 2023, SiMa.ai achieved a 20 percent improvement in its results for Single Stream Resnet50 for performance and power[1], while exhibiting up to 85 percent greater Resnet50 MultiStream efficiency compared to NVIDIA[2]. With frames per second per watt as the defacto performance standard for edge AI and ML, these results demonstrate SiMa.ai’s pushbutton approach drives continued leadership in unrivaled power efficiency that does not compromise performance.

“Outperforming the industry leader not only once, but again for a second time is great validation for our technology. Our team at SiMa.ai will persistently pursue performance per watt leadership and new standards in ease of use for the embedded edge market as part of our core DNA,” said Krishna Rangasayee, CEO and founder, SiMa.ai. “We are proud of the SiMa.ai team’s leadership in the latest MLPerf benchmark and excited to extend these latest improvements to our customers’ real-world needs and use cases.”

SiMa.ai’s purpose-built MLSoC and Palette software enable customers to effortlessly build, test, fine tune and deploy a wide variety of highly optimized applications for embedded edge. SiMa’s hardware and software first set a new industry standard in embedded edge power efficiency in the MLPerf April 2023 submission, and the company was consistent in the technology used in this latest August 2023 round. SiMa.ai was able to achieve a 20% improvement in performance / watt without any hardware changes through continuous performance improvement in their pushbutton tools. SiMa.ai has a strong software roadmap that not only includes significant new features, but also further improvements in performance that will enable customers to future proof their production deployments.

SiMa.ai’s accomplishments in the MLPerf benchmarks showcase its consistent pursuit of innovation and growth. As the company advances its technology, it remains focused on delivering solutions that are cutting-edge, performant, sustainable and efficient.

To learn more about how SiMa.ai can help your organization, for more information or to schedule a demo with someone from our team, visit our website at www.sima.ai or drop us a line at developer.mlsoc@sima.ai.

About SiMa.ai

SiMa.ai is a Machine Learning company delivering the industry’s first software-centric, purpose-built MLSoC platform. We enable Effortless ML deployment and scaling at the embedded edge by allowing customers to address any computer vision problem while achieving up to 10x better performance at the lowest power. Initially focused on computer vision applications, SiMa.ai is led by technologists and business veterans backed by a set of top investors committed to helping customers bring ML on their platforms.

Contact:
Jordan Beadle
SBS Comms for SiMa.ai
sima@sbscomms.com

© Copyright 2023 SiMa Technologies, Inc. SiMa.ai logo and other designated brands included herein are trademarks in the United States and other countries.

Notices And Disclaimers

[1] Verified MLPerf™ score of v3.1 Inference Closed Power ResNet50. Results taken from https://mlcommons.org/en/inference-edge-31/ on Sept 11, 2023. Results 3.1-0131 to 3.0-0104. The MLPerf™ name and logo are trademarks of MLCommons Association in the United States and other countries. All rights reserved. Unauthorized use strictly prohibited. See www.mlcommons.org for more information.

[2] Verified MLPerf™ score of v3.1 Inference Closed Power ResNet50. Results taken from https://mlcommons.org/en/inference-edge-31/ on Sept 11, 2023. Results 3.1-0131, 3.1-0115. The MLPerf™ name and logo are trademarks of MLCommons Association in the United States and other countries. All rights reserved. Unauthorized use strictly prohibited. See www.mlcommons.org for more information.