Silicon Slip-Ups: The Ten Most Common Errors Processor Suppliers Make (Number Four Will Amaze You!)
For over 30 years, BDTI has provided
engineering, evaluation and advisory services to processor suppliers and
companies that use processors in products. The company has seen a lot,
including some classic mistakes. (You know, things like: the chip has an
accelerator, but no easy way to program it… or you can only program it
using an obscure proprietary framework. Or it has an ISP that only works
with one image sensor. Or the development tools promise a lot but fall
far short. Or the device drivers don’t work. Or the documentation is
deficient.) In this top-rated talk, Phil Lapsley, Co-founder and Vice President of
BDTI, presents a fun and fast-paced review of some of the most common
processor provider errors, ones seen repeatedly at BDTI. If you’re a
processor provider, you’ll learn things you can do to avoid these
goofs—and if you’re a processor user, you’ll learn about things to watch
for when selecting your next processor!
Deploying Large Models on the Edge: Success Stories and Challenges
In this talk, Dr. Vinesh Sukumar, Senior
Director of Product Management at Qualcomm Technologies, explains and
demonstrates how Qualcomm has been successful in deploying large
generative AI and multimodal models on the edge for a variety of use
cases in consumer and enterprise markets. He examines key challenges
that must be overcome before large models at the edge can reach their
full commercial potential. He also highlights how Qualcomm is addressing
these challenges through upgraded processor hardware, improved
developer tools and a comprehensive library of fully optimized AI models
in the Qualcomm AI Hub.
INFERENCE ACCELERATION APPROACHES
How Machine Learning Solutions Enable Vision Transformers at the Edge
AI at the edge has been transforming over
the last few years, with newer use cases running more efficiently and
securely. Most edge AI workloads were initially run on CPUs, but machine
learning accelerators have gradually been integrated into SoCs,
providing more efficient solutions. At the same time, ChatGPT has driven
a sudden surge in interest in transformer-based models, which are
primarily deployed using cloud resources. Soon, many transformer-based
models will be modified to run effectively on edge devices. In this
presentation, Stephen Su, Senior Segment Marketing Manager at Arm,
explains the role of transformer-based models in vision applications and
the challenges of implementing transformer models at the edge. Next, he
introduces the latest Arm machine learning solution and how it enables
the deployment of transformer-based vision networks at the edge.
Finally, he shares an example implementation of a transformer-based
embedded vision use case and uses this to contrast such solutions with
those based on traditional CNN networks.
How Digital Compute-in-memory Delivers Fast and Energy-efficient Computer Vision
As artificial intelligence inference
transitions from cloud environments to edge locations, computer vision
applications achieve heightened responsiveness, reliability and privacy.
This migration, however, introduces the challenge of operating within
the stringent confines of resource constraints typical at the edge,
including small form factors, low energy budgets and diminished memory
and computational capacities. Axelera AI addresses these challenges
through an innovative approach of performing digital computations within
memory itself. This technique facilitates the realization of
high-performance, energy-efficient and cost-effective computer vision
capabilities at the thin and thick edge, extending the frontier of what
is achievable with current technologies. In this talk, Bram Verhoef,
Head of Machine Learning at Axelera AI, unveils his company’s pioneering
chip technology and demonstrates its capacity to deliver exceptional
frames-per-second performance across a range of standard computer vision
networks typical of applications in security, surveillance and the
industrial sector. This shows that advanced computer vision can be
accessible and efficient, even at the very edge of our technological
ecosystem.
About This E-Mail
LETTERS AND COMMENTS TO THE EDITOR: Letters and comments can
be directed to the editor, Brian Dipert, at insights@edge-ai-vision.com.
PASS IT ON...Feel free to forward this newsletter to your
colleagues. If this newsletter was forwarded to you and you
would like to receive it regularly, click here
to register.
Edge AI and Vision Alliance, 1646 N California Blvd, Suite 360, Walnut Creek, California, 94596, United States, +1 925.954.1411
