BRN Discussion Ongoing

Part of an early Aug article.

Be exceptionally great if, given we work with Renesas, are part of ARMs fold and proven up Akida with the M85 that Gen 2 is part of the below plans...bold :unsure:



R-Car-S5​

The company is working on a fifth generation R-Car system on chip (SoC) for automotive designs for 2027 with a chiplet architecture. The fourth generation R-Car S4 is sampling but not yet in production.

“Well, when we be able to have Gen-5 SoC? We can’t really say at this moment, but then it might be as early as 2027. And if it’s after that, it probably will be pushed out by two or three years. That’s how we imagine the pace will be as we prepare,” said Shibata.

“I don’t want to say too much, but then, of course, higher computation capability is one differentiation from G4 and G5, Gen-5, and, of course, that’s easy to understand. But then in addition to that, I think there are some other changes that we want to implement. For example, using chiplets, we’re hoping that we’d be able to seek more flexibility in responding to the needs of our customers.”

“Another factor, for example, the past was like SoC versus MCU. From next generation, we want to have a crossover device. So high compute and the more traditional MCU, something in between is something that we’d like to have, and so that we’d be able to have a true, seamless situation.”

This is behind the drive to the high end ARM M85 core with AI acceleration.

“I guess it’s really those two factors, in other words, higher flexibility device and more scalability. We want to make a step further scalability than what we have been doing in the past.
 
  • Like
  • Fire
  • Love
Reactions: 21 users

Diogenese

Top 20
Part of an early Aug article.

Be exceptionally great if, given we work with Renesas, are part of ARMs fold and proven up Akida with the M85 that Gen 2 is part of the below plans...bold :unsure:



R-Car-S5​

The company is working on a fifth generation R-Car system on chip (SoC) for automotive designs for 2027 with a chiplet architecture. The fourth generation R-Car S4 is sampling but not yet in production.

“Well, when we be able to have Gen-5 SoC? We can’t really say at this moment, but then it might be as early as 2027. And if it’s after that, it probably will be pushed out by two or three years. That’s how we imagine the pace will be as we prepare,” said Shibata.

“I don’t want to say too much, but then, of course, higher computation capability is one differentiation from G4 and G5, Gen-5, and, of course, that’s easy to understand. But then in addition to that, I think there are some other changes that we want to implement. For example, using chiplets, we’re hoping that we’d be able to seek more flexibility in responding to the needs of our customers.”

“Another factor, for example, the past was like SoC versus MCU. From next generation, we want to have a crossover device. So high compute and the more traditional MCU, something in between is something that we’d like to have, and so that we’d be able to have a true, seamless situation.”

This is behind the drive to the high end ARM M85 core with AI acceleration.

“I guess it’s really those two factors, in other words, higher flexibility device and more scalability. We want to make a step further scalability than what we have been doing in the past.
I always thought chiplets were the endy bits at the bottom of a bag of Smith's Crisps.
 
  • Haha
  • Like
Reactions: 19 users
Perhaps the departure of our Head of Sales was planned, as he already has a VP position with Untether AI.

View attachment 45013
View attachment 45014


Perhaps it was planned, to the mutual benefit of both companies?
I have heard Brainchip mention how its "untethered from the cloud..." numerous times......
Definitely looks like some bad blood between CS and BrainChip..
Going by the fact of no spiel about BrainChip or AKIDA after his position and time spent, like he does for Syntiant and his new employer..

Looks like a bit of sour grapes..

Always felt like he was a bit of a recruitment from the "dark side" coming from Syntiant..
Even though he dissed them and basically said they had nothing, compared to AKIDA..

Now, he still sings Syntiant's praise, but nothing for BrainChip..

Just a snake in the grass, glad he's gone..

20230920_224012.jpg
 
  • Like
  • Fire
  • Wow
Reactions: 21 users
Definitely looks like some bad blood between CS and BrainChip..
Going by the fact of no spiel about BrainChip or AKIDA after his position and time spent, like he does for Syntiant and his new employer..

Looks like a bit of sour grapes..

Always felt like he was a bit of a recruitment from the "dark side" coming from Syntiant..
Even though he dissed them and basically said they had nothing, compared to AKIDA..

Now, he still sings Syntiant's praise, but nothing for BrainChip..

Just a snake in the grass, glad he's gone..

View attachment 45068
Given our watertight customer NDAs :cautious:trust we also have the same level for staff as he walks out with I would expect, a fair bit of BRN Intel :mad:
 
  • Like
  • Thinking
  • Sad
Reactions: 10 users
Given our watertight customer NDAs :cautious:trust we also have the same level for staff as he walks out with I would expect, a fair bit of BRN Intel :mad:
There's always a 6 to 12 month "exclusion period" of dealing with previous customers, in just basic sales roles..

Pretty hard to enforce, but you have to actually have something better..
 
  • Like
Reactions: 10 users

McHale

Regular
To change the subject just for a minute....

My Brisbane Lions, after my bagging of around 6/7 players who were playing like 1st year players in the AFL finally stood up and started
playing as they "normally do" from around, round 12 onwards, well here we are, I believe we will bet Carlton and meet Greater Western
Sydney (GWS) in the Grand Final...I think Collingwood will meet GWS who are peaking at just the right time and cause a big upset.

Maybe Brainchip is a better long term bet !! Love my Akida 1.0, 1.5, 2.0 and beyond...go Peter and team ❤️❤️
Go the mighty Brisbane Lions
 
  • Like
Reactions: 4 users

Cartagena

Regular
Definitely looks like some bad blood between CS and BrainChip..
Going by the fact of no spiel about BrainChip or AKIDA after his position and time spent, like he does for Syntiant and his new employer..

Looks like a bit of sour grapes..

Always felt like he was a bit of a recruitment from the "dark side" coming from Syntiant..
Even though he dissed them and basically said they had nothing, compared to AKIDA..

Now, he still sings Syntiant's praise, but nothing for BrainChip..

Just a snake in the grass, glad he's gone..

View attachment 45068
Agree. He actually does look like a snake, you're not wrong mate..
Fullmoon, I'm sure BRN would have covered themselves in that eventuality of staff leaving and any breach of the terms of confidentiality agreements or IP secrets would be met with legal action. Well I hope so
 
Last edited:
  • Like
Reactions: 8 users
Those that bought more a few days ago, are you still topping up? Asking for my wife... and our marriage.
Yes bought more today.

This more recent harsh move down is nothing to do with the company fundamentals.

Looking forward to the “leaving the ASX200” selling completing and the SP normalising.

Quite interesting the big bargain hunters swooping in at the end of the day to buy up what they can and what they know is too low a price also, the surge up at end of day happened yesterday and today!

Glad I am on the mark and buying the bargains like some other insto’s.

Don’t forget the buyers there last Friday that lapped up tens of millions of shares sold just at 29.5 cents by the close - they are very happy to be in at that higher level in bulk….the last few days is just more bargain stocktake sale shopping.
 
Last edited:
  • Like
  • Haha
Reactions: 22 users
Loihi is a test chip, the amount of silicon it occupies would be too big to be commercially viable and AFAICT Intel have never tried to commercialise it. If Intel intend to embed nueromorpic processing in the PCs that they brand then I reckon they must have come knocking on our door.
Awesome, that’s what I want to hear.

Akida Inside! 😉 Hoping….
 
Last edited:
  • Like
  • Fire
  • Wow
Reactions: 12 users

Kachoo

Regular
Once upon a time a little boy was born, one a little smarter than the average. Over time this little boy grew up to be a very clever man who worked for some very high tech companies and even delved in inventing new technology. Let’s call this person PVM. Well PVM moved to the land down under and flew under the radar whilst he developed a new invention. He then started a new company on the ASX and being the founder was blessed with a motsa (shit load for our German friends) of shares in the new company. He then got a team around him while he progressed his invention. In the early part of growth out of the few staff one of the key roles recruited was a patent lawyer followed by a second which at one stage represented about 4% of the available staff. Now did the remaining staff all work out, no but when does that happen in real life.
Now as the invention gained the attention of those tech nerds around the world. Yip has that resulted in huge sales no. Are those tech nerds saying anything negative or producing evidence that it doesn’t work- no. Is there lots of buzz around the broader tech concept- yes.

So why tell this story. Well for a govt worker with a high percentage of their life savings invested in a singular share portfolio should I be worried- yes. Am I - no. Why- my job is to observe and analyse everything from body language to oral and written documents. Whilst I may not possess the photographic memory of a more prestigious poster of the past, I tend to focus of the bits that don’t gel.

Now if I was the inventor of something I didn’t believe in or I knew was a bit dodgy I would be over time dropping my substantial holdings to take advantage of what based on my inside knowledge is my good fortune of a high share price and some obviously inexperience company who dropped the company name which saw the SP rise to $2.34.

Secondly if I missed that opportunity to reduce my holdings on that jump, I would be singing the techs praises from the highest mountain with the largest loud hailer possible.

So PVM has sold some shares. Yip true but let’s see why. That’s right he donated some shares to a cause he had personal affinity with and gained nothing from the transfer.

Is PVM panicking and doing everything to raise the SP . No he has continued in the same calm manner since the companies inception. Does this help the share price- no but have the company mislead us or the market or did they call out lumpy sales and the inability to inform the market. Does this calm methodical manner offer me comfort- yes. Does it help my bank balance- no- well not in short term but if it is aligned with a long term well informed and achievable strategic plan then SP growth is not only inevitable it should be sustained.

So whilst I would like a lot more information, messaging and evidence of sales, I would also like world peace, food in every child’s bellies and a roof over every head.

I am comfortable with holding and whilst I have only recently returned to being in the red I spent many more years in the red in the early days and back then I was actually more nervous than today even though my holdings today are substantially more.
This is a very rational post that people need to think about.

PVDM went from having a 300 plus million dollars to 30 million. That is quite the cut to take considering where he could be today if he cashed out.

He is not crying just moving ahead with work. This product is cutting edge and customers need to know how to use it and maximize it's benifits and understanding.

Look MB has not stopped on the Neuromorphic front they have hired staff and continue to innovate in that direction.

The Breakdown in the SP imo is below what is fair value for BRN IMO. That said the MB spike was well above value clearly. That MB spike is what management said was inflated not what the SP is at today but the down ramper twist the the words to benifit there maximum adgenda.

People are scared worried yes some think that if I sell now I will buy more at 10 cents cause it's going there right? Well we don't know that and thinking this could leave you out of shares quick.

My 2 thoughts why the SP is here.

Clearly Shorter won and beat out the longs on from 2 years ago.

1. Why is there such a drop well instos needed to sell and balance books. Shorters naked short a little to get a cheaper cover. Add in the terrified retailers and you overwhelm the sell side dropping prices.

2. How far will this go we don't know. But believe me if a larger player sees value he will buy up shares quite quick before you have a chance to place your order.

If this is a hostile takeover the buyer kills the price accumulate shares the when they feel they have the board buy the throat they will come in with an offer and buy out the rest of the share. I'm not sure if this is what's happening but if I was to do such a move the timing is ripe.

We know that retail is not patient and handling loses for us is harder then for some instos or companies.

Neuromorphic computing is just blooming and will continue to do so.

Has there been a competitor that's come out publicly to challenge Akida and it's performance I have not seen one. This would mean the product does what it is suppose to.

The only negative comments I have heard over time is.
A. Akida 1000 failed commercially we have good enough solutions.

If this was true 100 % of our partners and trusted parties would have left.

B. Revenue is non existent. This is true but we did generate marginal revenues from Renesas and Megachips royalties are due in time.

C. People in the development industry love and promote Akida ISL, Edge Impulse, ARM and TATA. If Akida is the a key solution to product inovation a company would not give away their secrets.

Personally I don't know what the company has happening and what's in the pipes but they have move forth and hired staff to meet work loads. You don not go from 20 odD people to almost 100 in about 3 year with nothing to go with.

Why would we have sales in Japan Korea Isreal, France Germany and USA if we had little to offer customers. IMO

Time will see how we play out. But if I was the Board and I knew that the SP would be crushed I'd have done the CR in July and moved one they did not. Why?
 
  • Like
  • Fire
  • Love
Reactions: 51 users

Diogenese

Top 20
Loihi is a test chip, the amount of silicon it occupies would be too big to be commercially viable and AFAICT Intel have never tried to commercialise it. If Intel intend to embed nueromorpic processing in the PCs that they brand then I reckon they must have come knocking on our door.
Hi jtardif999,

I've been down the Meteor Lake rabbit hole and the news is not good if the press speculation is correct.


Inside Meteor Lake: Intel’s radical new Core chip is optimized for the future (msn.com)



The NPU is one part of that. Intel’s NPU includes a pair of neural compute engines, each with two VLIW Shade DSPs inside, with inference engines capable of up to eight instructions per cycle. Even for consumers used to parsing the number of cores per chip, base clocks, and turbo clocks, this won’t make a lot of sense. What Intel is trying to convey is that AI requires a ton of multiply-accumulate (MAC) instructions per cycle, and that those engines can perform 2,048 MAC calculations each.
...
Intel’s secret sauce, though, isn’t just the AI NPU, but how the CPU, GPU, and NPU can all help assist each other. Take the following example. Running 20 iterations of Stable Diffusion, Intel tried various combinations: performing all of the calculations on the CPU, all on the GPU, all on the NPU, and a combination of all three. Performing them all on the NPU took 20.7 seconds and 10 total watts, the most efficient use. But performing them all on the GPU and NPU finished the task in 11.3 seconds, consuming 30W.

Akida does not do "instructions per cycle".
Akida does not do lots of MACs.
Akida does not use Watts.
 
  • Like
  • Fire
  • Love
Reactions: 38 users

jtardif999

Regular
Hi jtardif999,

I've been down the Meteor Lake rabbit hole and the news is not good if the press speculation is correct.


Inside Meteor Lake: Intel’s radical new Core chip is optimized for the future (msn.com)



The NPU is one part of that. Intel’s NPU includes a pair of neural compute engines, each with two VLIW Shade DSPs inside, with inference engines capable of up to eight instructions per cycle. Even for consumers used to parsing the number of cores per chip, base clocks, and turbo clocks, this won’t make a lot of sense. What Intel is trying to convey is that AI requires a ton of multiply-accumulate (MAC) instructions per cycle, and that those engines can perform 2,048 MAC calculations each.
...
Intel’s secret sauce, though, isn’t just the AI NPU, but how the CPU, GPU, and NPU can all help assist each other. Take the following example. Running 20 iterations of Stable Diffusion, Intel tried various combinations: performing all of the calculations on the CPU, all on the GPU, all on the NPU, and a combination of all three. Performing them all on the NPU took 20.7 seconds and 10 total watts, the most efficient use. But performing them all on the GPU and NPU finished the task in 11.3 seconds, consuming 30W.

Akida does not do "instructions per cycle".
Akida does not do lots of MACs.
Akida does not use Watts.
Indeed.. my comment was around if they did want to embed Neuromorphic - based on the above, sounds like not.
 
  • Like
Reactions: 3 users

Frangipani

Regular
There's some IFS and BUTs here. Lets start with Intel Foundry Services ...
… and leave aside any Baseless Unfounded Theories for the time being? 🤭

Just an observation on my part, which may or may not be of any significance:
I’ve been wondering (especially after Colleen Vitolo’s comment “Great job Todd and Rob!” that @Dhm had spotted on Sept 8: https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-359269) whether there was any particular reason why Tony Dawe did not comment on the fact that the entity under number 17 in Fact Finder’s list of corporate and academic engagements reads “Intel” rather than “Intel Foundry Services (IFS)”?

E9E45949-A64F-4491-9708-290B61A0F739.jpeg


It may just seem a technicality, as of course Intel is the company behind IFS and Brainchip even uses the (old, pre-2020) Intel logo on their partnership website (whereas recent Brainchip presentations have been using the IFS logo instead), but my point is “Intel” being listed could suggest to readers that there is more collaboration with Brainchip than just the foundry business, which, however, is the only technology partnership between Brainchip and Intel that has so far been officially announced. So in a list of relationships that have been publicly acknowledged to date, I’d personally expect to find “IFS” rather than “Intel”.

I was actually going to point this out to @Fact Finder himself, after he had reposted that compilation of companies and universities in his recent article questioning NVIDIA’s long-term survival, but I noticed he has since changed the name from “Intel” to “Intel Foundries”. Maybe he is willing to shed some light on the reason for his editing? His own proofreading or someone else’s? If so, was that someone else by any chance a Brainchip employee?

So the question is: Does the fact that neither Rob Telson nor his colleagues in the US found it necessary to correct the entity’s name under number 17 on the list (initially at least) indicate there is further collaboration with Intel, not only through the foundry business alone (however, overlooking the fact that no public announcement has so far been made) or do they simply not bother to differentiate between Intel Foundry Services and Intel? 🤔
 
  • Like
  • Love
  • Fire
Reactions: 14 users

Frangipani

Regular
Yes, it’s very interesting if Sean has keep his cards very close (glued?) to his chest.
A interesting part from the news report discussion between the reporters was the lady mentioned the word “foundry” linked to intels new AI chip in the PC to be hopefully rolled out in mid Dec 23.
So if intel mentioned it’s from the foundry then why would it be it’s own IP etc in their AI chip?

Yes, the lady said just foundry and not Intel foundry services so just stating as it was mentioned. Yes same thing really in reference to intel in this manner during their discussion

The below press release dated June 21st may provide an answer to your question:



“Intel leaders told analysts and investors during a webinar Wednesday that its transition to a new internal foundry model will be a key enabler to achieving its stated cost savings goal of more than $8-10 billion exiting 2025. In this new operating model, Intel’s internal product groups move to a foundry-style relationship with the company’s manufacturing group. As a result, company execs say they are projecting a broad class of increased efficiencies that will be reflected in greater profitability as Intel pursues its long-term ambition to achieve non-GAAP gross margins of 60%.

The Background:

Intel is embarking on the most significant business transformation in its 55-year history. With IDM 2.0, Intel set out to regain process technology leadership, expand the use of third-party foundry capacity and build a world-class foundry business with a significant expansion of Intel’s manufacturing capacity. With these efforts well on track,
Intel now is making a fundamental shift in how its product business units work with technology development and manufacturing to ensure long-term growth while achieving efficiencies and cost savings.

In this new “internal foundry” model, Intel’s product business units will engage with the company’s manufacturing group in a similar arm’s-length fashion that fabless semiconductor companies engage with external foundries.
 
  • Like
  • Fire
Reactions: 16 users
I'm loving Sean's level of enthusiasm here:


"As a leader in Edge AI, we see just how ubiquitous the technology will be and will highlight how we are driving AI into a plethora of use cases that weren’t possible before.”
 
  • Like
  • Love
  • Fire
Reactions: 51 users

FlipDollar

Never dog the boys
That's my issue with the forum and the reason all of my friends left months ago already.
As soon as someone does not agree, logical thinking just stops, and you get called a lier, downramper, stupid, thrown gifs at you ladididi dadidi.
A product, the only one you have, 3 years into commercialization that doesn't sell and even gets called not robust enough by its own company is a failure. End and over.

I can name you an example for a lie regarding this topic.
When the technology was ready for licensing, they said that revenue growth would outgrow expenses. They said that there will be a lot of ip licensing going forward, or other phrases liked it'd become the defacto standard.
Regarding the second gen, there was only an outdated timeline available.
I don't recall when it was, but I think it was some months maybe even only some weeks before the last AGM someone dropped that the "AKD1000 never intended to be a revenue stream"
Now that's a lie with consequences that we can all witness right now.
Can't wait for people making excuses like "he was only talking about physical chips and not IP" or whatever people will come up with.
I agree - it’s sickening some days reading grown adults fanboying over specific posters long winded monologues too.

The echo chamber is alive and well and a balance of opinion is too hard for many on here.
 
  • Like
  • Love
  • Haha
Reactions: 13 users

AARONASX

Holding onto what I've got
 
Last edited:
  • Like
  • Fire
  • Love
Reactions: 30 users

AARONASX

Holding onto what I've got
[
 
  • Like
  • Fire
  • Love
Reactions: 32 users
  • Like
  • Fire
  • Love
Reactions: 23 users
Top Bottom