Articles from Untether AI

Untether AI®, a leader in energy-centric AI inference acceleration, is teaming up with AI Platform Alliance members Ampere® Computing, NETINT, ZoneMinder, AVC Group, and ASA Computers to introduce the Intelligent Video Recording (IVR) solution at ISC West 2025, the premier security industry tradeshow. This groundbreaking AI-powered system sets a new benchmark in video surveillance, delivering up to 8x better AI camera efficiency while operating in an eco-friendly server consuming under 600 watts.

Untether AI®, a leader in energy-centric AI inference acceleration today introduced a breakthrough in AI model support and developer velocity for users of the imAIgine® Software Development Kit (SDK). Using a breakthrough generative compiler technology, the upcoming release the imAIgine SDK will support 4 times more AI models than the previous releases. Additionally, for new neural networks users may architect, the generative compiler creates new kernels for these layers automatically, reducing development time to just minutes, increasing developer velocity by orders of magnitude.

Untether AI®, a leader in energy-efficient AI inference acceleration, today announced its partnership with Vertical Data, recognized for its cutting-edge infrastructure solutions that enhance computing capabilities at the source of data generation. This collaboration aims to advance modular and portable data center solutions, enabling faster, more secure, and highly efficient AI-driven computing.

Untether AI®, the leader in energy-centric AI inference acceleration, today announced broad availability of its highly anticipated speedAI 240 Slim AI inference accelerator cards. Recently receiving top marks in the MLPerf benchmark for AI inference, speedAI 240 Slim cards provide customers the performance, energy efficiency, AI model support, and scalability they need for a broad range of applications from regional clouds to the edge. J-squared and Ola-Krutrim are among customers who have already deployed speedAI®.

Untether AI®, the leader in energy-centric AI acceleration technology, is at the forefront of transforming agriculture with edge-optimized solutions that address critical challenges like labor shortages and inefficient resource use. As AI reshapes the farming practices, Untether AI is delivering cutting-edge solutions that significantly improve productivity and sustainability, ensuring the future of agriculture.

Untether AI®, the leader in energy-centric AI inference acceleration, is proud to announce its partnership with Ampere by joining the AI Platform Alliance (AIPA), a collaborative organization focused on advancing the future of AI solutions through a diverse ecosystem of industry leaders. As part of this partnership, Untether AI will showcase its groundbreaking AI acceleration technology alongside founding member Ampere Computing at Yotta 2024, one of the premier events for AI and edge computing.

Untether AI®, the leader in energy-centric AI inference acceleration, today announced its world-leading verified submission to the MLPerf® Inference benchmarks, version 4.1. The speedAI®240 Preview accelerator card submission demonstrated the highest throughput of any single PCIe card in Datacenter and Edge categories for the image classification benchmark, ResNet-50[1]. The speedAI240 Slim submission exhibited greater than 3X the energy efficiency of other accelerators in the Datacenter Closed Power category [2], 6X the energy efficiency in the Edge Closed category [3], and 3X lower latency in the Edge Closed category [4].

Untether AI®, the leader in energy-centric AI inference acceleration, today announced its partnership with Ola-Krutrim to provide AI acceleration solutions for its India datacenters. This multi-faceted partnership includes today’s performance demonstration with speedAI-based acceleration solutions and co-development of Untether AI’s next generation datacenter solutions, which will be used for inference deployment and fine-tuning of Krutrim’s generative AI models. Untether AI was selected by Krutrim because its energy-efficient At-Memory compute is ideally suited for the high-performance, high-scalability required for the Indian market.

Untether AI®, the leader in energy-centric AI inference acceleration, today announced the availability of early access (EA) of its imAIgine® Software Development Kit (SDK) supporting the speedAI® inference acceleration solutions.

Untether AI®, the leader in energy-centric AI inference acceleration, today announced that it has received the ISO 9001:2015 certification of its Quality Management System. A key milestone in Untether AI’s commitment to quality, this certification recognizes its internal quality systems for the runAI® and speedAI® AI inference acceleration devices, cards, and the associated imAIgine® Software Development Kit (SDK).

Untether AI, the leader in energy-centric AI inference acceleration, today announced a collaboration with Arm to develop best-in-class solutions optimized for next-generation automotive applications. As part of this collaboration, Untether AI will enable its inference acceleration technology to be implemented alongside the latest-generation Automotive Enhanced (AE) technology from Arm, to create solutions that address performance, power, safety, and security requirements for advanced Driver Assistance Systems (ADAS) and autonomous vehicle (AV) applications.

Untether AI®, the leader in energy-centric AI acceleration technology, in partnership with J-Squared Technologies, renowned for their ruggedized computer systems, today announced the availability of an AI-powered object detection solution at the AUSA Global Force Symposium and Exhibition in Huntsville, AL. This technology showcases the integration of Untether AI's tsunAImi® tsn200 inference accelerator card within J-Squared Technologies rugged Vanguard 2U rackmount server, showcasing counter-drone detection for both commercial applications and defense sectors.

Untether AI, the leader in energy-centric AI inference acceleration, today announced that it has joined the Scalable Open Architecture for Embedded Edge (SOAFEE) Special Interest Group (SIG). The SOAFEE SIG is focused on delivering an architecture for automotive applications with associated reference implementations to help advance the deployment of software-defined vehicles (SDV). Untether AI’s joining the organization represents the company's ongoing commitment to the automotive marketplace. Untether AI’s expertise in AI inference acceleration for advanced driver-assistance systems (ADAS) and autonomous vehicle (AV) applications will be invaluable for furthering the organization's goals.

Untether AI®, the leader in energy-centric AI acceleration technology, today announced Board of Directors and senior leadership appointments as it enters a new phase of growth. Chris Walker, previously President of Untether AI, has been appointed as CEO. Dr. Amir Salek, former head of Silicon for Google Technical Infrastructure and Google Cloud and current Senior Managing Director at Cerberus Capital Management, L.P. (“Cerberus”), has joined Untether AI’s Board of Directors and as a Senior Technical Advisor to the company. In addition, these appointments come amid an unprecedented explosion of machine learning and generative AI use cases, and as Untether AI’s next-generation AI inference accelerator, the speedAI® family, is in fabrication and on track to sample in the first half of this year.

Untether AI®, the leader in energy-centric AI inference acceleration, today announced that it has joined Universal Chiplet Interconnect Express™ (UCIe™) Consortium, the industry organization that has developed an open specification that defines the interconnect between chiplets within a package. As the leader in energy-centric AI acceleration, Untether AI sees heterogeneous compute with die-to-die interconnect as the next logical step for energy-centric compute architectures.

Untether AI®, the leader in energy-centric AI acceleration technology, is pleased to participate and present at the upcoming Super Computing Conference, November 13 - 17, 2023. The company will demonstrate its at-memory compute architecture which solves the data movement bottleneck that costs energy and performance in traditional CPUs and GPUs, resulting in high-performance, low-latency neural network inference acceleration without sacrificing accuracy.

Today, Untether AI®, the leader in energy-centric AI acceleration technology, announced it has appointed Avnet as its distribution partner in Israel. The distribution partnership will support Untether AI to meet the growing demand for the company’s products in the burgeoning AI inference acceleration space.

AI Hardware and Edge AI Summit-- Today, Untether AIⓇ, the leader in energy-centric AI acceleration technology, announced the shipment of its tsunAImiⓇ tsn200 accelerator card powered by the runAIⓇ 200 device. By leveraging at-memory computation, Untether AI breaks through the barriers of traditional von Neumann architectures, offering industry-leading compute density with power and price efficiency.

Today, Untether AI®, the leader in energy-centric AI acceleration technology, announced it has appointed Chris Walker, former Corporate Vice President and General Manager at Intel Corporation, as President. After leading the silicon giant’s mobile business unit through multiple years of growth and fostering the company’s client AI work, Walker joins Untether AI to lead its commercial efforts at a time when demand for efficient AI compute is rapidly accelerating.

Today, Untether AI®, the leader in energy-centric AI semiconductor technology, announced it has been selected as the winner of the “AI Hardware Innovation Award” in the prestigious international AI Breakthrough Awards program conducted by AI Breakthrough. The company received the award for its high-performing AI semiconductor architecture that significantly reduces power consumption in AI workloads.

Untether AI®, the leader in energy-centric AI inference acceleration, today announced that it has joined MLCommons®, an AI industry engineering consortium created to accelerate machine learning innovation. Untether AI has long recognized and worked with the group’s widely acknowledged MLPerf benchmarks. With its membership, Untether AI is excited to contribute to MLCommons’ work in sharing state-of-the-art datasets and best practices for ML development. MLCommons’ MLPerf benchmarks provide the industry a fair and balanced accounting of the strengths and weaknesses of AI compute architectures. These benchmarks, widely embraced by ML developers, represent a variety of artificial intelligence workloads, from recommendation engines and vision networks to transformers. Untether AI’s energy-centric AI acceleration solution supports these types of neural network architectures.

Untether AI® is pleased to participate at the upcoming TSMC Technology Symposium, April 26, 2023. The company will highlight its groundbreaking energy-centric AI inference acceleration, which provides improved accuracy and efficiency for diverse neural networks such as vision, natural language processing, and recommendation engines.

Untether AI®, the leader in at-memory computation for artificial intelligence (AI) workloads, today announced the availability of the imAIgine® Software Development Kit (SDK) version 22.12. The imAIgine SDK provides an automated path to running neural networks on Untether AI’s runAI™ devices and tsunAImi® accelerator cards, with push-button quantization, optimization, physical allocation, and multi-chip partitioning. This release dramatically improves the speed in which developers can create and deploy neural networks or high-performance compute workloads, saving months of development time.

Untether AITM, the leader in at-memory computation for artificial intelligence (AI) workloads, today announced at the HOT CHIPS 2022 conference its next-generation architecture for accelerating AI inference workloads called speedAI devices, with an internal codename “Boqueria.” At 30 TeraFlops per watt (TFlops/W) and 2 PetaFlops of performance, the speedAI architecture sets a new standard for energy efficiency and compute density.

Untether AI, the pioneers of at-memory computation for artificial intelligence (AI) inference acceleration, today announced the appointments of Renxin Xia as Vice President of Hardware Engineering and Annette van’t Spyker as Vice President of Human Resources. Both new executives will report to CEO Arun Iyengar. Mr. Xia comes to Untether AI with significant experience in high-performance semiconductor design, RISC-V processors and electronic design automation tools. He is responsible for the engineering of Untether AI’s industry-leading AI inference acceleration devices and system level solutions. Ms. van’t Spyker brings extensive global talent management and acquisition experience across multiple industries and is leading Untether AI’s worldwide people resources. These new additions bring meaningful leadership experience and will fuel the company’s continued growth.

Untether AITM, the leader in at-memory computation for artificial intelligence (AI) inference acceleration, today announced a collaboration with General Motors, supported by the Government of Ontario through the Ontario Vehicle Innovation Network (OVIN), to accelerate the development of next-generation artificial intelligence perception systems for autonomous vehicles.

Untether AI co-founder Raymond Chik was honored by the Association of Chinese Canadian Entrepreneurs (ACCE) during a gala dinner hosted by the ACCE in Toronto on April 23, 2022. In 2018, Dr. Chik, Dr. Martin Snelgrove, and Darrick Wiebe founded Untether AI. This year the ACCE honored that founding and the progress Untether AI has made as the pioneers of at-memory computation for artificial intelligence (AI) inference acceleration by awarding him and the company Startup of the Year.

Untether AI is pleased to present at the upcoming AI Hardware Summit hosted by Kisaco Research, September 13 - 15, 2021. The company will highlight its groundbreaking at-memory compute architecture for neural net inference that eliminates the data-movement bottleneck that costs energy and hampers performance in traditional architectures.

Untether AITM, the leader in at-memory computation and AI inference acceleration, today announced an oversubscribed $125 million funding round led by an affiliate of Tracker Capital Management, LLC (“Tracker Capital”), a stage-agnostic venture capital investor that principally invests in high-potential technology growth companies. Tracker Capital was founded by Stephen A. Feinberg who is also Co-Founder and Co-CEO of Cerberus Capital Management. The round was co-led by Intel Capital, Intel Corporation’s global investment organization, and included participation from new investor Canada Pension Plan Investment Board (“CPP Investments”) and existing investor Radical Ventures.