BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
potarto/potatoPerhaps this is a good omen to keep your mouth watering..........
View attachment 45975
Google Pixel 8a allegedly leaks, shows off massive bezels
Images of what appears to be the Google Pixel 8a have leaked. The leak shows a more rounded device with sizeable bezels.www.androidauthority.com
Deadpool
Did someone say KFC
Not technically brn related, but Space Jesus is worried 
finance.yahoo.com
Elon Musk Urges U.S. To Cut Reliance On Asia For Semiconductor Chips — 'Fear Of Running Out Is Causing Every Company To Overorder — Like The Toilet Paper Shortage But At Epic Scale'
Supply chain issues created during the global coronavirus pandemic cost automakers billions of dollars in 2021 and prompted some companies to build domestic manufacturing facilities to solve the problem. "Never seen anything like it," Tesla CEO Elon Musk posted on the platform now known as X...
finance.yahoo.com
cosors
👀
According Mr Karl Popper and me a theory is right or not wrong until it is disproved. So make an effort to disprove.
I stick to a plausible causal chain until it has been disproved.
Simply stating that something is dumb nonsense is not enough for me.
Before you were specific with Lidar and MB. Here you are much too general for me.
Someone once claimed that the world is a sphere. That was considered heresy. We know the rest of the story.
Just as an example of why I think this approach makes more sense than calling others out for their research and dot joining.
Last edited:
cosors
👀
Thank you for your tireless work. Please never let up!
And, I really like your feet. Maybe this will help motivate you.
Satchmo25
Member
Leuven-based Axelera AI brings first products to a… | Leuven MindGate
Axelera AI, a Dutch developer of innovative AI systems with a research department in Leuven, is bringing its first products to market. 'We focus on…
Dhm
Regular
Hi @Diogenese thanks for your stirling efforts explaining this. Rhetorical question coming: why couldn’t our senior management make it abundantly clear we have the solution for Apples problem?
Morning Chippers ,
Another neuromorphic mob with some heavy backers.
Regards ,
Esq.
Another neuromorphic mob with some heavy backers.
Regards ,
Esq.
jtardif999
Regular
Worked with EW years ago; have always thought it would be an eventual likely use case for Akida.Looks like our mates at the US Air Force - AFRL got another $7m in the kitty approved as below.
Hopefully they allocate some to Dev with Akida.
Amendments to H.R. 4365 - Department of Defense Appropriations Act, 2024 - Republican Cloakroom
colors differentiate en blocs black indicates standalone amendment EN BLOC #1 OFFERED BY REP. CALVERT – ADOPTED BY VOICE James (R-MI) – Amendment No. 1 – Increase in Army RDTE account of $15 million with a reduction of $15 million to O&M, Army Buchanan (R-FL) – Amendment No. 2 – Increases and...repcloakroom.house.gov
Washington, September 25, 2023
Amendments to H.R. 4365 – Department of Defense Appropriations Act, 2024
Carey (R-OH) – Amendment No. 116 – Increases and decreases by $7 million for research, development, test and evaluation for the Air Force with the intent that the $7 million will be used for the development of a cognitive EW machine learning/neuromorphic processing device to counter AI-enabled adaptive threats (Air Force RDT&E, Line 162, PE# 0207040F, Multi-Platform Electronic Warfare Equipment)
Schnitzel lover
Regular
This is definitely a possibility that a clarification email exchange between ASX and BRN has occurred.. It’s fairly common..I do agree with your views, but I would like to add another dynamic, maybe just maybe two things are or were at play this week, the ASX didn't accept the way the company's planned announcement was presented or there is a material aspect to the announcement/s that wasn't accepted in the way it was presented for release, personally I'm happy with my earlier view of something within the first 2 weeks of October, time shall tell.
The company could be erring on the side of caution as AKD 2.0 wasn't quite ready for release, and that's a mature and responsible approach also.
Go BrisbaneRegards...Tech
Schnitzel lover
Regular
I’m
in agreement with you Rob.. Surely there’ll be a atleast 1-2 new IP deals before the years out as Chapman eluded to, and that should ward off the wolves atleast for the next AGM..
Mt09
Regular
I reckon we need a cornerstone investor, joint Ann with 2.0 release would be nice!
https://mail.google.com/mail/u/0/?u...78509094314536135|msg-a:r-5258032398876372717 i take this with a grain of salt.
Deadpool
Did someone say KFC
For anyone that has not read the 2023 edge ai technology report, do your self a favour, very informative and entertaining read, and of course BRN gets a Guernsey.
Mt09
Regular
What do you not trust about Gmail?
DingoBorat
Slim
They make a NPU Neural Processing Unit, but aren't touting neuromorphic?.. I think there's a difference @Diogenese?
Kneron Unveils the KL730 AI Chip, Propelling Low-Energy GPT Solutions at Scale | Kneron – Full Stack Edge AI
●Tackling the largest bottleneck in AI adoption - energy costs - the KL730 yields a 3 to 4 times leap in energy efficiency compared to previous Kneron models and versus peers●The KL730 offers base-level compute power starting from 0.35 to 4 effective tera operations per second, supporting the mos...
A lot of talk about use for Chat GPT models, so like in your article Esq, they definitely are trying to "ride" the A.I. wave..
They know where the attention is and they're going for it.
I don't think what they've got is a technical threat to us, but they are competition.
DingoBorat
Slim
They make a NPU Neural Processing Unit, but aren't touting neuromorphic?.. I think there's a difference @Diogenese?
Kneron Unveils the KL730 AI Chip, Propelling Low-Energy GPT Solutions at Scale | Kneron – Full Stack Edge AI
●Tackling the largest bottleneck in AI adoption - energy costs - the KL730 yields a 3 to 4 times leap in energy efficiency compared to previous Kneron models and versus peers●The KL730 offers base-level compute power starting from 0.35 to 4 effective tera operations per second, supporting the mos...www.kneron.com
A lot of talk about use for Chat GPT models, so like in your article Esq, they definitely are trying to "ride" the A.I. wave..
They know where the attention is and they're going for it.
I don't think what they've got is a technical threat to us, but they are competition.
Neural Processor - WikiChip
A neural processor, a neural processing unit (NPU), or simply an AI Accelerator is a specialized circuit that implements all the necessary control and arithmetic logic necessary to execute machine learning algorithms, typically by operating on predictive models such as artificial neural networks...
A neural processor, a neural processing unit (NPU), or simply an AI Accelerator is a specialized circuit that implements all the necessary control and arithmetic logic necessary to execute machine learning algorithms, typically by operating on predictive models such as artificial neural networks (ANNs) or random forests (RFs).
Nothing special, an accelerator..
Stable Genius
Regular
Hi all,
If you’re on this forum you probably already understand the content of this article but it educates on the differences between edge, far edge, cloud etc quite well. BRN not mentioned but it describes the landscape and where the technology is going.
What goes on between the sensor and the data center.
SEPTEMBER 28TH, 2023 - BY: FRANK SCHIRRMEISTER
Recently, I attended the AI HW Summit in Santa Clara and Autosens in Brussels. Artificial intelligence and machine learning (AI/ML) were critical themes for both events, albeit from different angles. While AI/ML as a buzzword is very popular these days in all its good and bad ways, in discussions with customers and prospects, it became clear that we need to be precise in defining what type of AI/ML we are talking about when discussion requirements of networks-on-chips (NoCs).
From sensors to data centers – AI/ML happens everywhere.
Sensors are the starting point of the AI/ML pipeline, and they collect raw data from the environment, which can be anything from temperature readings to images. At Autosens, in the context of automotive, this was all about RGB and thermal cameras, radar, and lidar. On-chip AI processing within sensors is a burgeoning concept where basic data preprocessing happens. For instance, IoT sensors utilize lightweight ML models to filter or process data, reducing the load and the amount of raw data to be transmitted. This local processing helps mitigate latency and preserve bandwidth. As discussed in some panels at Autosens, the automotive design chain needs to make some tough decisions about where computing happens and how to distribute it between zones and central computing as EE architectures evolve.
Edge devices are typically mobile phones, tablets, or other portable gadgets closer to the data source. In my view, cars are yet another device, albeit pretty complex, with its own “sensor to data center on wheels” computing distribution. The execution of AI/ML models on edge devices is crucial for applications that require real-time processing and low latency, like augmented reality (AR) and autonomous vehicles that cannot rely on “always on” connections. These devices deploy models optimized for on-device execution, allowing for quicker responses and enhanced privacy, as data doesn’t always have to reach a central server.
Edge computing is an area where AI/ML may happen without the end user realizing it. The far edge is the infrastructure most distant from the cloud data center and closest to the users. It is suitable for applications requiring more computing resources and power than edge devices but also needs lower latency than cloud solutions. Examples might include advanced analytics models or inference models that are heavy for edge devices but are latency-sensitive, the industry seems to adopt the term “Edge AI” for the computing going on here. Notable examples include facial recognition and real-time traffic updates on semi-autonomous vehicles, connected devices, and smartphones.
Data centers and the cloud are the hubs of computing resources, providing unparalleled processing power and storage. They are ideal for training complex, resource-intensive AI/ML models and managing vast datasets. High-performance computing clusters in data centers can handle intricate tasks like training deep neural networks or running extensive simulations, which are not feasible on edge devices due to resource constraints. Generative AI originally resided here, often requiring unique acceleration, but we already see it moving to the device edge as “On-Device Generative AI,” as shown by Qualcomm.
When considering a comprehensive AI/ML ecosystem, layers of AI/ML are intricately connected, creating a seamless workflow. For example, sensors might collect data and perform initial processing before sending it to edge devices for real-time inference. More detailed analysis takes place at far or near edge computing resources for more detailed analysis, before the data reaches data centers for deep insights and model (re-)training.
Networks-on-Chips (NoCs) as a critical enabler of AI/ML.
The first aspect – connecting AI/ML subsystems – is all about fast data movement, and for that, broad bit width, the ability to broadcast, and virtual channel functionality are critical. Some application domains are unique, as outlined in “Automotive AI Hardware: A New Breed.” In addition, the general bit-width requirements vary significantly between sensors, devices, and edges.
To enable the second aspect, connecting all the bits and pieces on a chip, it is all about the support of the various protocols – I discussed them last month in “Design Complexity In The Golden Age Of Semiconductors.” Tenstorrent’s Jim Kellerdescribed the customer concern regarding de-risking best in a recent joint press releaseregarding Arteris’ FlexNoC and Ncore technology: “The Arteris team and IP solved our on-chip network problems so we can focus on building our next-generation AI and RISC-V CPU products.”
Finally, the industry controversially discusses the connections between chiplets across all application domains. The physical interfaces with competing PHYs (XSR, BOW, OHBI, AIB, and UCIe) and their digital controllers are at the forefront of discussion. In the background, NoCs and “SuperNoCs” across multiple chiplets/chips must support the appropriate protocols. We are currently discussing Arm’s CHI C2C and other proposals. It will require the proverbial village of various companies to make the desired open chiplet ecosystem a reality.
semiengineering.com
Happy Day Light Savings!
If you’re on this forum you probably already understand the content of this article but it educates on the differences between edge, far edge, cloud etc quite well. BRN not mentioned but it describes the landscape and where the technology is going.
Network-On-Chips Enabling Artificial Intelligence/Machine Learning Everywhere
7Shares
What goes on between the sensor and the data center.
SEPTEMBER 28TH, 2023 - BY: FRANK SCHIRRMEISTER
Recently, I attended the AI HW Summit in Santa Clara and Autosens in Brussels. Artificial intelligence and machine learning (AI/ML) were critical themes for both events, albeit from different angles. While AI/ML as a buzzword is very popular these days in all its good and bad ways, in discussions with customers and prospects, it became clear that we need to be precise in defining what type of AI/ML we are talking about when discussion requirements of networks-on-chips (NoCs).
Where is AI/ML happening?
To discuss where the actual processing is happening, I found it helpful to use a chart that shows what is going on between sensors that create the data, the devices we all love and use, the networks transmitting the data, and the data centers where a lot of the “heavy” computing takes place.
From sensors to data centers – AI/ML happens everywhere.
Sensors are the starting point of the AI/ML pipeline, and they collect raw data from the environment, which can be anything from temperature readings to images. At Autosens, in the context of automotive, this was all about RGB and thermal cameras, radar, and lidar. On-chip AI processing within sensors is a burgeoning concept where basic data preprocessing happens. For instance, IoT sensors utilize lightweight ML models to filter or process data, reducing the load and the amount of raw data to be transmitted. This local processing helps mitigate latency and preserve bandwidth. As discussed in some panels at Autosens, the automotive design chain needs to make some tough decisions about where computing happens and how to distribute it between zones and central computing as EE architectures evolve.
Edge devices are typically mobile phones, tablets, or other portable gadgets closer to the data source. In my view, cars are yet another device, albeit pretty complex, with its own “sensor to data center on wheels” computing distribution. The execution of AI/ML models on edge devices is crucial for applications that require real-time processing and low latency, like augmented reality (AR) and autonomous vehicles that cannot rely on “always on” connections. These devices deploy models optimized for on-device execution, allowing for quicker responses and enhanced privacy, as data doesn’t always have to reach a central server.
Edge computing is an area where AI/ML may happen without the end user realizing it. The far edge is the infrastructure most distant from the cloud data center and closest to the users. It is suitable for applications requiring more computing resources and power than edge devices but also needs lower latency than cloud solutions. Examples might include advanced analytics models or inference models that are heavy for edge devices but are latency-sensitive, the industry seems to adopt the term “Edge AI” for the computing going on here. Notable examples include facial recognition and real-time traffic updates on semi-autonomous vehicles, connected devices, and smartphones.
Data centers and the cloud are the hubs of computing resources, providing unparalleled processing power and storage. They are ideal for training complex, resource-intensive AI/ML models and managing vast datasets. High-performance computing clusters in data centers can handle intricate tasks like training deep neural networks or running extensive simulations, which are not feasible on edge devices due to resource constraints. Generative AI originally resided here, often requiring unique acceleration, but we already see it moving to the device edge as “On-Device Generative AI,” as shown by Qualcomm.
When considering a comprehensive AI/ML ecosystem, layers of AI/ML are intricately connected, creating a seamless workflow. For example, sensors might collect data and perform initial processing before sending it to edge devices for real-time inference. More detailed analysis takes place at far or near edge computing resources for more detailed analysis, before the data reaches data centers for deep insights and model (re-)training.
How are NoCs an enabler?
As outlined above, AI/ML is happening everywhere, literally. However, as described, the resource requirements vary widely. NoCs play in three main areas here: (1) connecting the often very regular AI/ML subsystems, (2) de-risking the integration of all the various blocks on chips, and (3) connecting various silicon dies in a chiplet scenario (D2D) or various chips in a chip-to-chip (C2C) environment.
Networks-on-Chips (NoCs) as a critical enabler of AI/ML.
The first aspect – connecting AI/ML subsystems – is all about fast data movement, and for that, broad bit width, the ability to broadcast, and virtual channel functionality are critical. Some application domains are unique, as outlined in “Automotive AI Hardware: A New Breed.” In addition, the general bit-width requirements vary significantly between sensors, devices, and edges.
To enable the second aspect, connecting all the bits and pieces on a chip, it is all about the support of the various protocols – I discussed them last month in “Design Complexity In The Golden Age Of Semiconductors.” Tenstorrent’s Jim Kellerdescribed the customer concern regarding de-risking best in a recent joint press releaseregarding Arteris’ FlexNoC and Ncore technology: “The Arteris team and IP solved our on-chip network problems so we can focus on building our next-generation AI and RISC-V CPU products.”
Finally, the industry controversially discusses the connections between chiplets across all application domains. The physical interfaces with competing PHYs (XSR, BOW, OHBI, AIB, and UCIe) and their digital controllers are at the forefront of discussion. In the background, NoCs and “SuperNoCs” across multiple chiplets/chips must support the appropriate protocols. We are currently discussing Arm’s CHI C2C and other proposals. It will require the proverbial village of various companies to make the desired open chiplet ecosystem a reality.
Where are we heading from here?
AI/ML’s large universe of resource requirements makes it an ideal fuel for what we experience as a semiconductor renaissance today. NoCs will be a crucial enabler within the AI/ML clusters, connecting building blocks on-chip and connecting chiplets carrying AI/ML subsystems. Brave new future, here we come!
Network-on-Chips Enabling Artificial Intelligence/Machine Learning Everywhere
What goes on between the sensor and the data center.
semiengineering.com
Happy Day Light Savings!
Similar threads
