• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

EdgeCortix Foresees Barrier Breaking Efficient Next-gen Edge AI Chips

T0@st

News Editor
Joined
Mar 7, 2023
Messages
2,077 (3.18/day)
Location
South East, UK
EdgeCortix, the Japan-based fabless semiconductor company focused on energy-efficient AI processing, predicts that 2024 is set to be a watershed moment for Edge AI. Through its predictions for the year, EdgeCortix believes that Edge AI landscape will be transformed during this exciting year for the industry. Next-gen AI chips, hybrid edge-cloud architectures, software supremacy and the rise of new generative-AI applications "at the edge," will revolutionize the world of business as we know it.

1. Next-Gen efficient Edge AI Chips will break barriers:
Prepare for a hardware uprising! EdgeCortix foresees next-gen energy-efficient AI chips that not only break the barriers of processing power but redefine them. These chips are not just powerful; they are customized for multi-modal generative AI and efficient language models, enabling cutting-edge AI capabilities at low power for a whole new spectrum of applications.




2. Hybrid Edge-Cloud Architectures will emerge, built for speed:
In 2024, it's all about the optimal balance. EdgeCortix anticipates a boom in hybrid edge-cloud architectures that seamlessly integrate edge devices with cloud resources. This is not just about efficiency; it's about enhancing multi-modal generative AI and language models at the edge. The outcome? Blazing-fast responsiveness, reduced latency, and a scalability surge for potent Edge AI applications.

3. Software will eclipse hardware at the Edge:
The Edge is a diverse and fragmented place with many technologies and historic corporate investments. To unify this heterogeneous landscape, software is the answer. EdgeCortix believes that software-driven hardware solutions are the key to enable edge AI capabilities on existing hardware systems. Businesses can then use their current hardware and gain new edge AI benefits.


4. The Edge will come alive with GenAI:
The future is clear, companies will have to embrace GenAI solutions where their customers and employees are active. Tailoring the user experience with anticipatory content to match a user's habits or tastes, and offering information to boost employees' efficiency. These new solutions will have to cope with the lack of power or conventional hardware found in today's data centers. EdgeCortix imagines a new wave of hardware and software solutions will be unleashed to satisfy these end-customer's expectations.

5. Edge AI will open the door to the unimaginable:
Change is the only constant and AI is the driving force of change. In 2023, AI was everywhere, and we at EdgeCortix believe that this trend will not slowdown in 2024. We anticipate that this year will witness a plethora of innovative applications in domains that are crucial for humanity, such as robotics, indoor-farming, primary education, healthcare development, security, communications and remote medical access, as well as in unexpected areas where generative AI can spice things up, such as fashion, music and media. We are excited to see how businesses, governments, technologists and consumers will harness the power of AI and edge AI to enhance our collective lives.

"AI is a catalyst for transformation, and that's what drives us at EdgeCortix," said Sakyasingha Dasgupta, CEO and Founder of EdgeCortix. "We are crafting our environmentally sustainable edge AI solutions with the future in mind, so that our customers and partners can effectively leverage our software and hardware solutions now and, in the years to come."

"AI is always evolving especially across the heterogeneous edge ecosystem, and that's a shared vision for us and EdgeCortix, who we are investing in for a strategic partnership," said Mohammed Dogar, Vice President, Head of Global Business Development & Ecosystem at Renesas Electronics Corporation. "We understand the critical role of software and hardware synergy and the emergence of Generative AI at the edge in 2024, and we are excited to collaborate in various ways with EdgeCortix to take on the challenge."

EdgeCortix's 2024 predictions paint a picture of an Edge AI landscape that's bursting with potential. Hold on tight as hardware and software innovations merge and transform industries, delight users, and open new horizons at the frontier of artificial intelligence. The future isn't just knocking; it's smashing down the doors as we dive into this new era.

About EdgeCortix:
Pioneering the future of the connected intelligent edge, EdgeCortix was founded in 2019 with R&D headquarters in Tokyo, Japan as a fabless semiconductor company focused on energy-efficient AI processing. Taking a software-first approach, EdgeCortix patented its "hardware and software co-exploration," system, using it to design an artificial intelligence specific runtime reconfigurable processor from the ground up. Shipping its software and hardware products to customers globally, the company is geared towards positively disrupting the rapidly growing edge AI hardware space across defense, aerospace, smart cities, industry 4.0, autonomous vehicles and robotics. www.edgecortix.com

View at TechPowerUp Main Site | Source
 
Joined
Oct 6, 2021
Messages
1,605 (1.37/day)
The summary of the text is "we are good; look at us. throw your money at us" and no concrete data presented.
 
Joined
Jun 29, 2023
Messages
107 (0.20/day)
Missing 'crypto' ... otherwise I would have had a full bingo of buzzwords.
 
Joined
Oct 27, 2009
Messages
1,188 (0.21/day)
Location
Republic of Texas
System Name [H]arbringer
Processor 4x 61XX ES @3.5Ghz (48cores)
Motherboard SM GL
Cooling 3x xspc rx360, rx240, 4x DT G34 snipers, D5 pump.
Memory 16x gskill DDR3 1600 cas6 2gb
Video Card(s) blah bigadv folder no gfx needed
Storage 32GB Sammy SSD
Display(s) headless
Case Xigmatek Elysium (whats left of it)
Audio Device(s) yawn
Power Supply Antec 1200w HCP
Software Ubuntu 10.10
Benchmark Scores http://valid.canardpc.com/show_oc.php?id=1780855 http://www.hwbot.org/submission/2158678 http://ww
1706067177438.png



1706067252285.png


Sooo if 1 DNAIP gets you 6.5Tops/3.3Tflops...
They are using 6-8 cores for <10w depending on how they round and how good/bad scaling is.

That is good for 12nm, but I don't think it is going to beat the edge gpus they claim to beat.

1706067536195.png

Neat but definitely behind custom solutions like tenstorrent, But does come in at a lower tdp.
Software support will be paramount with any of these solutions.
 
Top