Canada's semiconductor industry is gaining momentum, but challenges remain. In a recent EE Times | Electronic Engineering Times article by Gary Hilson, our CEO Chris Walker shares his insights on the country's efforts to bolster its chip sector: "What is needed is a virtuous cycle that will both propel and perpetuate leadership in the sector," says Walker. Consistent funding and fostering a vibrant ecosystem where "people move around and ideas flow" should be the emphasis. At Untether AI, we're committed to driving innovation and contributing to a thriving tech ecosystem, right here in Canada. Learn more about the industry's response to recent funding announcements at https://lnkd.in/gWqSgKAP. Marie-Josée Turgeon, C2MI Gordon Harling, CMC Microsystems Stephane Tremblay, IBM Bromont . . . #cdntech #ai #inference #acceleration #semiconductor #investment #funding
Untether AI
Semiconductor Manufacturing
Toronto, Ontario 7,616 followers
Accelerating the Future of AI
About us
Untether AI delivers energy-centric AI inference acceleration from the edge to the cloud, supporting any type of neural network model. Founded in 2018 with a mission to break AI out of data centers and make it available all the way to the network edge, we’ve developed a unique at-memory architecture for deep learning that places the processing next to the memory – minimizing data movement and power consumption. Using our hardware, enterprises become untethered from the data center, free to run AI workloads nearly anywhere. Other AI inference accelerator companies make promises; Untether AI makes products.
- Website
-
https://www.untether.ai
External link for Untether AI
- Industry
- Semiconductor Manufacturing
- Company size
- 51-200 employees
- Headquarters
- Toronto, Ontario
- Type
- Privately Held
- Founded
- 2018
- Specialties
- Artificial Intelligence, Machine Learning, Inference Acceleration, Semiconductor, Energy Efficiency, Sustainability, HPC, Edge Computing, and Cloud Computing
Locations
-
Primary
Toronto, Ontario M5V 2H2, CA
-
Silicon Valley, US
-
San Jose, US
Employees at Untether AI
Updates
-
We're honored to be listed in the Lazard VGB AI Infra 40, highlighting leaders in AI infrastructure innovation. Lazard's report highlights the critical need for energy-efficient AI solutions. Our energy-centric AI inference acceleration addresses this challenge head-on. We're honored to be recognized alongside fellow pioneers in this transformative field, further fueling our commitment to high-performance, sustainable AI computing.
The Lazard VGB AI Infra 40 list showcases a selection of some of the most exciting growth-stage AI infrastructure companies we have identified through hundreds of discussions with CEOs and investors. Read on for the full list and to learn more about key market themes: https://lnkd.in/efm6KZBh
-
At Untether AI, we're always thinking about the future of AI and its impact. A recent blog on AI's environmental footprint caught our attention, particularly this insight from our own Senior Director of Product, Philip Lewer: "Models are built expressly for the purpose of inference, and thus run substantially more frequently in inference mode than training mode — in essence train once, run everywhere." This highlights a crucial aspect of AI's energy consumption that's often overlooked. While training gets a lot of attention, inference could be the most significant factor in AI's carbon footprint. Interested in learning more about AI's environmental impact and potential solutions? Check out the full blog post from Hugging Face at https://lnkd.in/g8c4u_G2 and visit our website to learn more about our sustainable AI inference acceleration solutions. . . . . #ai #inference #responsibleai #sustainability #environmental #energyefficiency #modeltraining #carbonfootprint
-
Untether AI is thrilled to be named to the EE Times | Electronic Engineering Times' Silicon 100 for the 4th consecutive year! This prestigious list recognizes the top emerging companies shaping the future of technology. Our at-memory computing architecture continues to push the boundaries of AI inference, from edge devices to data centers. With our runAI® and speedAI® ICs, tsunAImi® accelerator cards, and recent collaboration with Arm on automotive AI, we're accelerating innovation across industries. Thank you to our incredible team and partners for making this recognition possible. We're honored to be in such great company on the Silicon 100 and excited to keep driving AI performance forward. Read EE Times' complete 2024 revision of the annual list at https://lnkd.in/gwuSJ2fQ. . . . #ai #silicon100 #eetimes #cdntech #autotech #fintech #visionai #agtech #government #aerospace #defense #inference #acceleration
-
-
NOW AVAILABLE Untether AI has released early access to our imAIgine® Software Development Kit (SDK), updated to include everything users need to easily deploy their models on our revolutionary speedAI family of inference acceleration solutions. Key features of this release include: ✅ Push-button flow for easy model deployment 💡 Power-user options for low-level optimizations 📊 Comprehensive analysis tools with virtual hardware view Explore the transformative potential of speedAI and the imAIgine SDK. Gain early access and start developing now at https://lnkd.in/giehnf_3. More information on our early access release can be found at https://lnkd.in/g92p-rGS. . . . #AIInference #MachineLearning #EdgeComputing #imAIgine #speedAI #SDK #PCIe #EarlyAccessProgram #Hardware
-
-
In a rapidly evolving automotive landscape, the demand for advanced computing power in vehicles continues to grow. Chiplets and the Universal Chiplet Interconnect Express (UCIe) standard are two of the revolutionary components driving the future of autonomous vehicle development. Did you know? 💡 Today's vehicles require AI processing that rivals data centers 💡 Chiplets are becoming the new norm in automotive computing 💡 The UCIe standard is paving the way for seamless technology integration (ultimately ushering in the era of delivering self-driving vehicles to the masses) Dive deeper into the future of automotive computing in our recently contributed blog post: https://lnkd.in/gmfvezfi.
-
-
A report by Moor Insights & Strategy highlights Untether AI's innovative at-memory compute architecture as a standout solution for AI inference. Our speedAI® family combines high performance, low latency, and energy efficiency— crucial factors in the growing inference market and why "MI&S is so bullish about the prospects of Untether AI." See our analysis of the report in our latest blog post: https://lnkd.in/g9NcDwp8
-
-
The $2B earmarked for AI infrastructure in Canada is a crucial step, but we must prioritize domestic development to truly advance our AI capabilities. Our VP of Product, Bob Beachler, weighs in on the importance of fostering home-grown innovation in AI compute in the latest tech newsletter by The Peak. Read more at https://lnkd.in/g6MniA7V.
-
-
Thanks for the warm welcome, UXL Foundation! Untether AI is proud to contribute to efforts aimed at building a multi-architecture, multi-vendor software ecosystem for accelerated computing. We support initiatives that unify heterogeneous compute environments through open standards and expand open-source projects in this space.
We are excited to announce two new contributor members to the #UXLFoundation: Inspire Semiconductor, Inc. and Untether AI! These two processor companies work in the AI field, and we can't wait to see how their contributions will advance UXL projects. https://bit.ly/4cqtxfa
-
-
Our VP of Product, Bob Beachler, recently joined Amelia Dalton on her weekly #FishFry podcast via EE Journal. Tune in to hear more about our unique approach to AI inference acceleration, our collaboration with Arm for autonomous vehicles, and Bob's insights on the future of AI-driven devices. 🐟 🎧 Listen now! https://lnkd.in/eiUWqBfN
-