BRN Discussion Ongoing

[Smoothsailing]

What time is it now in Perth?

3 hours behind Sydney were the AGM will be held at 10am Sydney time

 

[FJ-215]

3 hours behind Sydney were the AGM will be held at 10am Sydney time

11.00AM for the AGM. Tech roadmap is at 10.00am

 

[perceptron]

Hi Manny,

Here's the response I got from Chat GPT4.

Tony Lewis’s upcoming presentation at the Embedded Vision Summit outlines a potentially transformative shift in how language models are deployed at the edge. Here's an analysis of the implications and disruptive potential of this new method:

---

Key Implications of the New Processing Method Using SSMs​

1. Significant Gains in Energy and Compute Efficiency​

• Fewer Multiply-Accumulate Units: State-space models (SSMs) inherently require fewer MAC operations, drastically reducing energy usage and silicon real estate. This is crucial in edge deployments where power budgets are tight.
• Read-Only Architecture: Eliminates the need for dynamic key-value cache mechanisms used in transformers, allowing use of non-volatile or low-power memory types (e.g., MRAM, ReRAM), further slashing power consumption.

2. Latency and Responsiveness​

• Precomputed Input Sequences: SSMs can leverage static structure to enable sub-100 ms time-to-first-token performance. This real-time capability is a major win for voice assistants, AR/VR systems, and mobile apps.

3. Compatibility and Transition Path​

• Distillation from Transformers (e.g., LLaMA): By enabling smooth migration from established transformer models, the SSM approach lowers the barrier to adoption for companies with large pretrained models or investment in transformer-based workflows.

4. Broader Hardware Support​

• The reduced need for large, flexible compute units means SSMs can run efficiently on less powerful MCUs, DSPs, or dedicated edge AI chips—dramatically widening the range of viable deployment targets.

---

Edge Computing Success Potential​

SSMs seem highly promising for edge applications, especially in:

• Battery-powered devices (wearables, IoT sensors)
• Latency-sensitive interfaces (voice/user interaction)
• Bandwidth-constrained environments (offline processing)
• Cost-sensitive products where transformer demands are prohibitive

Their advantages directly address the key blockers for transformer adoption at the edge (power, memory, compute), making SSMs a potentially dominant architecture in this space within 1–3 years.

---

Disruption Potential for NVIDIA and Other Players​

NVIDIA’s ecosystem is largely optimized for transformer-style architectures (e.g., large GPU memory, high-throughput MAC arrays, transformer-optimized CUDA libraries). Here's how this development could affect them:

Challenges for NVIDIA​

• Less dependence on GPUs: If SSMs run efficiently on CPUs, ASICs, or even microcontrollers, edge devices may increasingly bypass NVIDIA’s hardware.
• New AI chip entrants gain ground: Startups or ARM-based players can capitalize on the lighter compute profile to offer cheaper, more efficient edge AI solutions.

Opportunities for NVIDIA​

• Adaptation potential: NVIDIA could pivot by offering cuDNN-like support for SSMs or incorporating them into TensorRT. They may also design more SSM-friendly hardware blocks in future Jetson modules.

Biggest Threat​

• If open-source ecosystems and chip vendors like Apple (Neural Engine), Google (Edge TPU), or Qualcomm fully embrace SSMs ahead of NVIDIA, they could seize a disproportionate share of the edge AI market—especially in consumer devices.

---

Conclusion​

Tony Lewis’s presentation introduces a processing paradigm that could redefine edge AI, making high-performance language models feasible on low-power devices. This is not just an incremental improvement—it opens the door to widespread deployment of real-time LLMs far beyond cloud and high-end hardware. While not an immediate existential threat to NVIDIA, it does present a strategic inflection point that the company—and its competitors—must respond to.

Thanks for posting. There are many use cases for LLM at the edge. Dr Lewis and his team have achieved something worth discussing further. Is today when Dr Lewis releases his raodmap? Thanks in advance.

 

[FJ-215]

Dear Valued BrainChip Shareholder, BrainChip Holdings Ltd is excited to announce that Chief Development Officer Dr. Jonathan Tapson will showcase the company's Technology Roadmap prior to its Annual General Meeting on 6 May. The presentation takes place in the Thomas Keneally Room at the Sydney Harbour Marriott Hotel at 10 a.m. AEST. In the special 35-minute presentation, Dr. Tapson will discuss how the company's AkidaTM technology is providing efficient AI performance at the Edge to better enable intelligent devices and applications. He will highlight expected advancements in the platform's brain-inspired capabilities, highly configurable IP platform and emerging markets for the company's IP. Shareholders wishing to attend the Technology Roadmap presentation in person, especially those who intend to attend both the presentation and the AGM, are advised to register at least 10 minutes prior to the commencement of the Technology Roadmap presentation with representatives of our share registry, Boardroom Limited, who will be positioned outside the Thomas Keneally Room. BrainChip's Technology Roadmap presentation will also be offered live via webcast on the Lumi platform. Those shareholders wishing to attend online can register at https://meetings.lumiconnect.com/300-896-227-913 Sincerely Antonio J. Viana Chairman

 

[Smoothsailing]

11.00AM for the AGM. Tech roadmap is at 10.00am

Thankyou

 

[WhiteDove]

​ Dear Valued BrainChip Shareholder, BrainChip Holdings Ltd is excited to announce that Chief Development Officer Dr. Jonathan Tapson will showcase the company's Technology Roadmap prior to its Annual General Meeting on 6 May. The presentation takes place in the Thomas Keneally Room at the Sydney Harbour Marriott Hotel at 10 a.m. AEST. In the special 35-minute presentation, Dr. Tapson will discuss how the company's AkidaTM technology is providing efficient AI performance at the Edge to better enable intelligent devices and applications. He will highlight expected advancements in the platform's brain-inspired capabilities, highly configurable IP platform and emerging markets for the company's IP. Shareholders wishing to attend the Technology Roadmap presentation in person, especially those who intend to attend both the presentation and the AGM, are advised to register at least 10 minutes prior to the commencement of the Technology Roadmap presentation with representatives of our share registry, Boardroom Limited, who will be positioned outside the Thomas Keneally Room. BrainChip's Technology Roadmap presentation will also be offered live via webcast on the Lumi platform. Those shareholders wishing to attend online can register at https://meetings.lumiconnect.com/300-896-227-913 Sincerely Antonio J. Viana Chairman

Smoke and mirrors or genuine good news?

 

[buena suerte :-)]

Morning all and looking forward to catching up with whoever is going to the AGM today. The wife banned me wearing my west ham top today, but most people should know what I look like so be sure to say hello.

Av a goody Mate

 

[FJ-215]

Smoke and mirrors or genuine good news?

As an investor I think it is a must watch. What I'm hoping to hear is.....

This is where we are, this is how we are improving our current offering. This is what we have planned for the next generation.

 

[HopalongPetrovski]

Anyone know if the Technology Roadmap about to be presented is being recorded?

 

[Bravo]

Good luck everyone!

Make sure your helmet is strapped on nice and tight.

 

[Jacob Kiraz]

Av a goody Mate

I thought it started at 11am the AGM

 

[Bravo]

I should ask Tony Dawe if he can give me the name of this soundtrack. It's fire!

 

[MrNick]

I thought it started at 11am the AGM

Technology Roadmap is now LIVE, as a shareholder you should have a link or at least an invite to watch/listen. This is for an hour prior to AGM.

 

[7für7]

Good luck everyone!

Make sure your helmet is strapped on nice and tight.


View attachment 83798

I wanted to buy this helmet. It was sold out this morning.

 

[supersonic001]

Sneak preview on look ahead for BRN …

From the pre meet session …..

 

[7für7]

The dean tried to make a question and i switch off…

 

[manny100]

There does not seem to many attendees at the Tech meeting.

 

[SERA2g]

Yet again, another question and answer time with brainchip where one shareholder chooses to be selfish by taking up most of the question time with one fucking question.

I suspect we'll see the same again when we get to the AGM.

So frustrating listening to someone turn up unprepared and so self centred.

 

[TheDrooben]

Presentation slides from the roadmap showcase.......

 

[buena suerte :-)]