BRN Discussion Ongoing

Hi DB,

I can see your soldering iron is a bit rusty.

As you say, a gate array is an prefab IC with bunches of different logic gates and registers with selectable interconnexions.

The Programmable part means that the user can choose the interconnexions. Once upon a time, you only got one shot at proramming the interconnexions, so it was permanently programmed which was usually done on a programming device before the gate array was installed on a circuit board (eg, fusable links).

Field programmability means that the gate array interconnexions can be chosen when the FPGA is installed.

So for example, there may be a mesh network similar to that used in Akida interconnecting the gates and registers where the interconnexions are controlled by a CPU.

US2016342722A1 METHOD AND DEVICE FOR PROGRAMMING A FPGA

View attachment 75689

A method of programming a FPGA, wherein the FPGA comprises an array of macrocells, each comprising at least a configurable hardware block and a configurable interconnection network, the method comprises the steps of: providing a high-level configuration file containing: first data defining a set of macrocells and their relative positions; second data defining a configuration of the hardware blocks of the macrocells; and third data defining interconnections between the macrocells; wherein said high-level configuration file contains neither data defining an absolute position of the macrocells within the FPGA, nor local routing information fully defining a configuration of their interconnection networks; converting said high-level configuration file into a bitstream file; and uploading the bitstream file into the FPGA. A semiconductor chip comprising a FPGA and a device configured for programming the FPGA are provided.


Because the layout is not optimized as in an ASIC, the performance will be significntly below that of an ASIC, but still better than a software simulation.
Ah yes, of course!
Now I understand, completely..


No wonder Anastasi won't return "my" calls 😔...


Screenshot_20250110-195251_Firefox.jpg
 
Last edited:
  • Haha
  • Wow
Reactions: 11 users

MDhere

Top 20
I disagree that a NASDAQ listing, is a "total fantasy" Tech 😛...

It is, while we are unprofitable.

But with strong profits down the track (hopefully within the next 2 to 5 years, the sooner the better) I think a NASDAQ listing, would then become a certainty.
well my thinking is similar, when it hits $3.50 aud it may decide to half the number of shares doubling the aud price to $7 then going to the Nasdaq at the qualifying price about $4 usd, that's thoughts of how it will eventually move into the nasdaq otherwise I would expect attempt of takeover offer would need to be at least $7. of course that's my opinion and its conservative at that. Happy friday night people :)
 
  • Like
  • Love
  • Fire
Reactions: 17 users
well my thinking is similar, when it hits $3.50 aud it may decide to half the number of shares doubling the aud price to $7 then going to the Nasdaq at the qualifying price about $4 usd, that's thoughts of how it will eventually move into the nasdaq otherwise I would expect attempt of takeover offer would need to be at least $7. of course that's my opinion and its conservative at that. Happy friday night people :)
I disagree that they will consolidate to list..
I'm pretty sure the "qualifying price" isn't set in stone and isn't determinate, depending on other factors..

There just wouldn't be the required liquidity, with such large holdings and only 1 billion shares on issue.

But anyway, it's all just meaningless conjecture, at this point..
 
  • Like
  • Love
Reactions: 8 users
From RTX

Our RF systems use higher-power microelectronics, increased processing power and software-defined apertures to achieve next-generation capabilities for radar, electronic warfare, communications and multifunction radio frequency applications.
We’re advancing electro-optical/infrared and other systems such as space-based multispectral sensors and electro-optical distributed aperture systems variants.
We are providing increased capability against advanced threats and countermeasures by enhancing high-bandwidth digital waveform generation, AI-enabled intelligent signal processing and advanced neuromorphic processing.
Our acoustic systems enable advanced mine-hunting and undersea networking capabilities through high sensitivity, directionality, multiple access and multi-mod active and passive capabilities for sonar, communications and navigation.
Our missile seekers counter a wide range of advanced threats through advanced processing and algorithms, all while achieving low size, weight, power and cost.

Link:
https://www.rtx.com/who-we-are/we-are-rtx/transformative-technologies

SC
 
  • Like
  • Fire
  • Love
Reactions: 31 users

7für7

Top 20
You really have to be lacking in understanding not to get it. If you read between the lines – or rather, you don’t even need to read between the lines – just listen carefully and understand. It becomes clear that these BrainChip podcasts from CES reveal groundbreaking developments in AI technology. Whether it’s Akida’s role in the next generation of AI, on the edge, and other technologies or for example the last podcast, Bill Eichen from DeGirum highlighting the synergies between our technologies and what will come (faster now) – it’s undeniable that BrainChip is playing a key role in the future of AI.
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 36 users
Good afternoon back in Australia,

I'm sure others read my posts, so wherever you are in the world, gidday !

I have just listened to the first podcast hosted by Steve Brightfield, what a relaxed professional, I loved it, he's not a journalist, he's
a veteran technology professional, having been in the industry for 35 plus years, it shows !

This next point is important, this is the positive effect Sean has had since coming on board, he has targeted (in my opinion) top class,
mature executive type staff, surrounding himself with guns, not to dissimilar to what Peter and Anil did in the early years, surrounding
themselves with top class PHD Scientists and Electrical Engineers.

Steve has brought his old mate Bill on board, they met as young blokes (35 years ago) so the trust and friendship is solid, that's
what I'm talking about, those types of relationships open up DOORS !

Listen carefully to what Bill says, within 5 minutes of logging into Degirum, Brainchip software is ready to give you benchmarks for
what you are looking for.

"Your team (Brainchip) is available to support us ASAP, you're in California, we're in Silicon Valley"

"A lot of people are trying it" (Brainchip, that is)

Are we getting any traction ?

Do we have the attention of a number of "major players" ?

Is the general tech industry finally starting to get a handle on Edge AI, and more specifically Spiking Neural Networks ?

Is/Was CES 2025 all about AI and weeding out the hype and getting down to the "Real Disruptors" who are the "Real Deal"?

Forget the current share price, Bottsie is having a field day, buying and selling to itself, do you think all our partners and current
engagements give a S... about the day to day bullshit, they are engaged with a company that has the goods, and the ones who
have the "real investment dollars" are getting to know it, faster and faster as this "evolutionary game" plays out !!

Talk about the Nasdaq is a total fantasy for us, in my opinion it will only happen in a take over scenario plays out and the name
Brainchip will sadly be a distant memory, sorry, but that's how I see it over the next 5 years.

More to come..........have a top weekend.......Tech.
How many podcasts has there been so far at this years ces?
 

Esq.111

Fascinatingly Intuitive.
  • Thinking
  • Like
Reactions: 3 users
Still one more day to go? Or maybe the company had decided not to release them all at once which I found strange last year.
 
  • Like
  • Thinking
Reactions: 3 users

7für7

Top 20
What I find truly remarkable is that Nintendo didn’t take the opportunity to officially showcase their Switch 2 at CES. Considering it’s the most important tech trade show, it would have been a great moment—especially regarding the technology inside, even if it primarily belongs to the gaming sector. Aside from an allegedly 3D-printed version (which also seems questionable), there was nothing to see.

 
  • Like
Reactions: 4 users
Nearly 4 years and still pending. I guess the medical trials take a very long time to conduct?

 
  • Like
  • Fire
  • Thinking
Reactions: 7 users

Diogenese

Top 20
The AFRL SBIR article says:

The project uses the technology on micro-doppler signature analysis for radar processing, which BrainChip said provides high activity discrimination capabilities.

https://www.aumanufacturing.com.au/brainchips-human-like-ai-wins-it-us-air-force-radar-contract

Doppler is used to detect whhether an object is approaching or receding. Micro-doppler detects relative movement between parts of the object, eg, propellors.

https://www.mathworks.com/help/radar/ug/introduction-to-micro-doppler-effects.html

A moving target introduces a frequency shift in the radar return due to Doppler effect. However, because most targets are not rigid bodies, there are often other vibrations and rotations in different parts of the target in addition to the platform movement. For example, when a helicopter flies, its blades rotate, or when a person walks, their arms swing naturally. These micro scale movements produce additional Doppler shifts, referred to as micro-Doppler effects, which are useful in identifying target features. This example shows two applications where micro-Doppler effects can be helpful. In the first application, micro-Doppler signatures are used to determine the blade speed of a helicopter. In the second application, the micro-Doppler signatures are used to identify a pedestrian in an automotive radar return.

But it's not just RTX:
https://arxiv.org/abs/2312.16419

Radar detection of wake vortex behind the aircraft: the detection range problem​

Jiangkun Gong, Jun Yan, Deyong Kong, Deren Li
In this study, we showcased the detection of the wake vortex produced by a medium aircraft at distances exceeding 10 km using an X-band pulse-Doppler radar. We analyzed radar signals within the range profiles behind a Boeing 737 aircraft on February 7, 2021, within the airspace of the Runway Protection Zone (RPZ) at Tianhe Airport, Wuhan, China. The findings revealed that the wake vortex extended up to 6 km from the aircraft, which is 10 km from the radar, displaying distinct stages characterized by scattering patterns and Doppler signatures. Despite the wake vortex exhibiting a scattering power approximately 10 dB lower than that of the aircraft, its Doppler Signal-to-Clutter Ratio (DSCR) values were only 5 dB lower, indicating a notably strong scattering power within a single radar bin. Additionally, certain radar parameters proved inconsistent in the stable detection and tracking of wake vortex, aligning with our earlier concept of cognitive micro-Doppler radar.
 
  • Like
  • Love
  • Wow
Reactions: 19 users

Slade

Top 20
This is worth watching. It’s Steve Brightfield from BrainChip talking to the Gadget Man at CES today. Starts at around the 8 min mark. Enjoy!
I promise that you will be excited by the end of it.

 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 62 users

Bravo

If ARM was an arm, BRN would be its biceps💪!
  • Haha
  • Like
Reactions: 13 users

Learning

Learning to the Top 🕵‍♂️
This is worth watching. It’s Steve Brightfield from BrainChip talking to the Gadget Man at CES today. Starts at around the 8 min mark. Enjoy!
I promise that you will be excited by the end of it.


Cheer Slade.

That's is some gold nuggets 😀

Not the exact qoute but, I like it.

'We sign more partners, where we can't mention.

Learning 🪴
 
Last edited:
  • Like
  • Love
  • Fire
Reactions: 29 users

Diogenese

Top 20
  • Haha
  • Thinking
Reactions: 6 users

Diogenese

Top 20
.
 
  • Fire
Reactions: 1 users
  • Haha
Reactions: 4 users

7für7

Top 20
-Where do you see brainchip in 5 years from now?

-In every product!


HAHAHHAA TAKE ALL MY MONEY did he really say that? Can someone confirm??

And what about the other new partners who are thrilled about brainchip, he can not name now ? 😂😭

1736516131931.gif
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 21 users
Was trying to understand DeGirum a bit more and found this article by Max Maxfield who we know has written some succinct and positive articles on Akida too.

This article, whilst a couple years old, gives a pretty good insight into what they can do and I believe they have further expanded their offerings. Good partnership imo.



January 12, 2023

DeGirum Has the Best Edge AI Story Ever!​


by Max Maxfield
I sometimes feel like I’m listening to a broken record when a company calls to tell me about the wonders of their new artificial intelligence (AI) processor. I try to say “Ooh” and “Aah” in all the right places, but oftentimes my heart isn’t really in it. Every now and then, however, I do get to hear something that makes me sit up in my seat and exclaim, “WHAT? O-M-G!”
I honestly believe that “WHAT? O-M-G!” is what you are going to say upon reading this column, but before we plunge into the fray with gusto and abandon…
Rarely does a day go by that I’m not exposed to some hot-off-the-press AI-related topic. For example, my chum Joe Farr just emailed me to say that he asked the ChatGPT chatbot, “Could you write a program in C# that acts as a BASIC interpreter?” As Joe informed me, he was surprised by the response, which I’ve summarized as follows:
It proceeded to give me a complete C# program listing. Not a fragment or snippet, but a complete bloody program listing along with an example of it working. You can see the darn thing typing out the code in front of your eyes… in real-time. It’s really frightening to watch.
I’ve documented Joe’s experiments in more detail in a Cool Beans Blog: Using ChatGPT to Write a BASIC Interpreter. As part of that blog, I also made mention of the new American science fiction horror film M3GAN (pronounced “Megan”), the watching of which will also have you sitting up in your seat exclaiming “WHAT? O-M-G!” (I speak from experience).
Returning to the topic in hand, I was just chatting with the cofounders of a company that has only recently emerged from stealth mode. Winston Lee (CEO) and Shashi Chilappagari (CTO) founded DeGirum.ai in 2017, and the company is already offering sample modules featuring their ORCA-NNX (Neural Network Express) device.
“Good Grief, not another AI accelerator,” I hear you muttering under your breath. Trust me, what I’m about to tell you will dispel your cynical attitude and leave you clamoring for more, in which case, you’re welcome. Of course, if you build your own AI accelerators, you may be less enthused by the news I am about to impart, in which case, I’m sorry.
As Winnie-the-Pooh famously said, “For I am a bear of very little brain, and long words bother me.” I also am a bear of little brain, and I feel the same way about long presentations. I like a simple story that I can wrap my brain around, so it can be disconcerting when a company assaults me with a presentation featuring so many slides that I start to fear it will never end. Thus, you can only imagine my surprise and delight when I was presented with DeGirum’s 4-slide offering.
We commenced with Slide #1 as shown below. Shashi made mention of the fact that trying to work out whose AI accelerator was the best is a non-trivial task, not the least that the concept of “best” may vary from model-to-model and application-to-application.
max-0204-01-evaluating-ai-hardware-is-hard-1024x416.jpg

Evaluating AI hardware is hard (Source: DeGirum.ai)
It doesn’t help when some people talk in terms of tera operations per second (TOPS) while others make their claims based on frames per second (FPS). And then there are those who boast of their offering with tall tales of TOPS/Watt, TOPS/$, FPS/Watt, and FPS/Dollar. Just to add to the fun and frivolity, we may not end up talking in terms of real units because cunning marketeers are not averse to “normalizing” (some may say “obfuscating”) their metrics in terms of price, power, or performance.
As Pontius Pilate said (well, warbled) in Jesus Christ Superstar: “And what is ‘truth’? Is truth unchanging law? We both have truths. Are mine the same as yours?” If I didn’t know better, I’d say Pontius had spent too much time perusing data sheets from different AI accelerator vendors.
Even the simplest things can be hard to measure, and the aforementioned terms don’t mean the same for everyone. One AI accelerator’s data sheet may quote twice the TOPS of someone else’s offering, but that doesn’t mean the end application will run twice as fast.
Take TOPS/Watt, for example. Are we just talking about the matrix multiplication unit, or the whole system-on-chip (SoC) power, and are we also taking any DDR memory, PCIe, and other peripherals into account? These nitty-gritty details are rarely made clear in a product sheet.
If we are looking at statistics associated with an accelerator, we may not obtain the same results with different host processors. Even values associated with the accelerator itself can vary from model to model. And, perhaps most importantly, the real application is never running only the AI model. In the case of a visual processing task, for example, the application will also be doing things like decoding, resizing, and otherwise processing a video feed and making decisions and performing actions based on what the model detects.
ResNet-50 is a 50-layer convolutional neural network (48 convolutional layers, one MaxPool layer, and one average pool layer). If someone says “We can run XXX frames per second of a ResNet-50 model” in their AI accelerator datasheet, this doesn’t actually mean much of anything to an end application developer.
And, if you are architecting a new system, there are a bunch of potential hardware restrictions that have to be taken into account. What types and sizes of model can the AI accelerator accommodate? How about input size, precision, and the number of models that can be running at the same time?
As a parting thought before we move on, how would one set about comparing an AI accelerator that is very efficient but limited in what it can run to an accelerator that can run almost anything but is not as efficient. Which is best? How long is a piece of string?
Well, we all know how difficult this stuff can be, but it’s refreshing to hear a vendor saying it out loud. By this time, I was nodding my head and agreeing with everything Shashi and Winston said, at which point they whipped out Slide 2 showing their ORCA-NNX chips on two M.2 modules (one with external DDR and one without).
max-0204-02-degrium-orca-nnx-1024x309.jpg

ORCA-NNX chips presented on M.2 modules with and without DRAM
(Source: DeGirum.ai)

This is when they started to batter me with information pertaining to the ORCA-NNX, which—I now know—supports vision models and speech models (and other models), large models and small models, pruned models and dense models, floating-point models (Float32) and quantized models (Int8), and that’s just the beginning. In addition to DRAM support, along with PCIe and USB interfaces, ORCA-NNX also supports efficient model multiplexing, multi-camera real-time performance, and multi-chip scaling, where the latter means you may run one or two (or more) ORCA-NNX accelerators in an edge device, or even more ORCA-NNX accelerators in an edge server, all without changing the software.
And, speaking of software, we are talking about a fully pipelined AI server stack, simple and convenient Python and C++ SDKs, intuitive APIs for rapid application development, model pipelining and parallelization, support for a wide variety of input data types including (but not limited to) images, camera feeds, audio and video streams, and video files, all coupled with automatic and efficient scaling for multiple devices.
“Hmmm, this all sounds mighty impressive,” I thought, “but what does the ORCA-NNX architecture look like and how does this compare to the competition?” I think Shashi was reading my mind, because this is where we transitioned to Slide #3 as shown below. Well, not exactly as shown below, because I’ve blurred out the company and product names associated with any competitors. The folks at DeGirum say: “When we publish numbers officially, it is our duty to report the conditions in which we measured them or if we have obtained them from other sources,” and they prefer to keep some information on the down-low for the moment. They did reveal that the vertical axis is in terms of FPS, if that helps.
max-0204-03-degirum-application-performance-v2.jpg

Application performance (Source: DeGirum.ai)
From PyTorch we are informed that, “YOLOv5 is a family of compound-scaled object detection models trained on the COCO dataset and including simple functionality for Test Time Augmentation (TTA), model ensembling, hyperparameter evolution, and export to ONNX, CoreML, and TFLite.”
The results from YOLOv5s using single, dual, and quad ORCA-NNX implementations are shown in the three columns on the right. As we see, even a single ORCA-NNX outperforms its nearest competitor.
So, where we are in this column at this moment in time is we’ve been told that (a) it’s very hard to compare different AI accelerators, (b) everyone quotes different numbers, (c) DeGirum’s ORCA-NNX outperforms the competition, and (d) DeGirum marry their powerful hardware with intuitive and easy-to-use software that helps developers to quickly create powerful edge AI applications.
“But these are the same claims everyone makes,” I thought to myself, with a sad (internal) grimace.
“But these are the same claims everyone makes,” said Shashi, with a wry smile.
Not surprisingly, this is a problem the guys and gals at DeGirum encountered very early on. They would meet and greet a new potential customer, explain that they had the best hardware and even better software, and the customer would immediately respond that everyone else was saying exactly the same thing.
This is when Shashi introduced Slide #4 (he did this with something of a flourish and with a silent “Tra-la,” if the truth be told). In order to silence the skeptics, the chaps and chapesses at DeGirum have introduced something they call the DeLight Cloud Platform as shown below:
max-0204-04-degirum-delight-cloud-platform-1024x511.jpg

DeLight Cloud Platform (Source: DeGirum.ai)
And what a delight it is (I’m sorry, I couldn’t help myself). The idea behind the DeLight Cloud Platform is that, rather than simply say “we are the best,” the folks at DeGirum decided to let users prove this for themselves.
As Shashi told me, people want to be able to compare and contrast AI accelerator application performance, but doing this in a rigorous manner means purchasing a bunch of platforms, creating software, porting it to all the platforms, checking that everything is working as planned, and performing an analysis in terms of power, price, and performance to see which one comes out on top. Not surprisingly, however, obtaining the hardware, loading the necessary drivers, installing the full software tool chain, and developing even a simple test application can consume a substantial amount of time and resources.
All of this is addressed by the DeLight Cloud Platform. First, we have the DeGirum Device Farm which includes ORCA-NNX platforms from DeGirum, Edge TPUs from Google, and GPU lines from Nvidia, along with VPUs (a general term for accelerators coming out from Intel), ARM-based SoCs, and others that will be added as their hardware and software becomes more widely available.
Next, we have the DeGirum Model Zoo, which boasts a collection of ready-to-use models. Users can employ DeGirum’s hardware-agnostic APIs to start developing applications on their client-side Windows, Unix/Linux, and Mac hosts. In the not-so-distant future, the folks at DeGirum plan to add a BYOM (“bring your own model”) capability.
All this means users can load a model and instantly start developing a test application. Once they have their application working, they can use the DeLight Cloud Platform to evaluate all of the hardware options.
One of the major pain points in today’s model design, training, and porting processes is that, by the time you try to make your model work on your selected hardware, it may be too late to discover that the model is not, in fact, well suited to that hardware. The folks at DeGirum say they’ve flipped the process around so you can start with the hardware first.
The primary difference between a trained and untrained model are its weights, which means you can evaluate an untrained model’s compatibility, speed, and portability on day one without having to train the little rascal. Once you know your model will work on the selected hardware, you can train it, prune it, quantize it, etc. And, once you’ve developed your real-world application on the DeLight Cloud Platform, you can use the same software to deploy this application onto your edge devices.
The applications for edge AI are essentially limitless, including surveillance, smart homes, smart buildings, smart cities, robotics, industry, medical, manufacturing, agriculture (e.g., AI-equipped drones detecting weeds or fungal outbreaks and applying pesticides and insecticides in small, focused doses—see Are Agricultural Drones Poised to be the Next Big Thing?).
Creating state-of-the-art edge AI accelerators provides tremendous opportunities for small, innovative companies like DeGirum, but only if they can convince users that their technology is worth investigating. As far as I’m concerned, offering the DeLight Cloud Platform is a masterstroke (I’m reminded of the Brilliant! Guinness adverts because I want to exclaim “Brilliant!”). What say you?
 
  • Like
  • Fire
  • Love
Reactions: 26 users
Top Bottom