BRN Discussion Ongoing

[JB49]

Good interview with Renesas engineers.
They talk about a neuromorphic unit at 33 minutes. But they say they are working with Edge Cortix in this case. Bit of a shame - with all of the good news floating around, it would of been great to come across a random podcast where they confirm they are using Akida.

They also talk about having an ecosystem of partners for AI. When you go to the Renesas website, they have a large list of Partners. Brainchip arent on that list from what I could see. But then again neither is Edge Cortix.

Renesas Preferred Partners: Collaborating for Enhanced Solutions

Renesas preferred partners are system solution providers working with Renesas and its customers in their domains of expertise.

www.renesas.com

 

[Diogenese]

I’m still excited about what Akida1000 can do. Gen 2 with TENNs must be impressive. How good is this?

3U VPX SNAP Card

bascomhunter.com

APPLICATION​

A single SNAP Card, deployed on an airborne ISR platform, occupying only one 3U VPX slot, could deploy up to five complex machine learning algorithms across each of its onboard processors to perform the following missions simultaneously.

– Automated Target Recognition (ATR) on full motion video feeds and imagery (to include 4k and higher)​

– Real-time detection and identification of threat radars and their acquisition/operating modes​

– Detection of FISINT (Foreign Instrumentation Signature Intelligence) and/or hacking across the airframe’s 1553 communications bus​

– Perform communications analysis to include speech-to-text and foreign language translation of intercepted communications​

– Fuse multiple infrared cameras (e.g., SWIR, MWIR, LWIR) to provide a combined infrared operating picture on the ground Multi-user, simultaneous modulation/demodulation​

View attachment 74421

Hi SG,

Let's just reprise the Bascom Hunter SNAP card:

https://bascomhunter.com/products-s...c-processors/asic-solutions/3u-vpx-snap-card/

Bascom Hunter’s SNAP Card (Spiking Neuromorphic Advanced Processor) is a high-performance 3U OpenVPX AI/ML processor built for rugged, mission-critical environments. The card is SOSA-aligned, HOST-compatible, and conduction cooled. It combines a Xilinx UltraScale+ RFSoC FPGA with five BrainChipAKD1000 spiking neuromorphic processors to achieve the best of both signal processing and neuromorphic computing – featuring a total of 6million neurons and 50 billion synapses across the card. Unlike traditional machine learning accelerators such as GPUs or TPUs, neuromorphic processors are designed to mimic the biological efficiency of the human brain, allowing the SNAP Card to run multiple ML models in parallel at exceptionally low power — just 1W per model — without sacrificing speed or accuracy while the FPGA enhances input/output operations and performs any desired signal processing tasks. This combination in a rugged, interoperable, and military-hardened package makes Bascom Hunter’s SNAP Card the ideal solution for the concurrent and parallel processing of real-time, multi-modal, and multi sensor data on autonomous, unattended, denied, or otherwise battery constrained military systems.

A single SNAP Card, deployed on an airborne ISR platform, occupying only one 3U VPX slot, could deploy up to five complex machine learning algorithms across each of its onboard processors to perform the following missions simultaneously.

– Automated Target Recognition (ATR) on full motion video feeds and imagery (to include 4k and higher)

– Real-time detection and identification of threat radars and their acquisition/operating modes

– Detection of FISINT (Foreign Instrumentation Signature Intelligence) and/or hacking across the airframe’s 1553 communications bus

– Perform communications analysis to include speech-to-text and foreign language translation of intercepted communications

– Fuse multiple infrared cameras (e.g., SWIR, MWIR, LWIR) to provide a combined infrared operating picture on the ground Multi-user, simultaneous modulation/demodulation.

The 5 dedicated Akida chips running specific models feed 5 separate processors.

A. Target recognition
B. Threat radar detection
C. Cybresecurity
D. Intercepted speech analysis and translation
E. Multi-IR camera analysis

These are Akida 1 chips.

There's a fair chance that the Akida 2 version is well into the development phase.

 

[Space Cadet]

Hi SG,

Let's just reprise the Bascom Hunter SNAP card:

https://bascomhunter.com/products-s...c-processors/asic-solutions/3u-vpx-snap-card/

Bascom Hunter’s SNAP Card (Spiking Neuromorphic Advanced Processor) is a high-performance 3U OpenVPX AI/ML processor built for rugged, mission-critical environments. The card is SOSA-aligned, HOST-compatible, and conduction cooled. It combines a Xilinx UltraScale+ RFSoC FPGA with five BrainChipAKD1000 spiking neuromorphic processors to achieve the best of both signal processing and neuromorphic computing – featuring a total of 6million neurons and 50 billion synapses across the card. Unlike traditional machine learning accelerators such as GPUs or TPUs, neuromorphic processors are designed to mimic the biological efficiency of the human brain, allowing the SNAP Card to run multiple ML models in parallel at exceptionally low power — just 1W per model — without sacrificing speed or accuracy while the FPGA enhances input/output operations and performs any desired signal processing tasks. This combination in a rugged, interoperable, and military-hardened package makes Bascom Hunter’s SNAP Card the ideal solution for the concurrent and parallel processing of real-time, multi-modal, and multi sensor data on autonomous, unattended, denied, or otherwise battery constrained military systems.

A single SNAP Card, deployed on an airborne ISR platform, occupying only one 3U VPX slot, could deploy up to five complex machine learning algorithms across each of its onboard processors to perform the following missions simultaneously.

– Automated Target Recognition (ATR) on full motion video feeds and imagery (to include 4k and higher)

– Real-time detection and identification of threat radars and their acquisition/operating modes

– Detection of FISINT (Foreign Instrumentation Signature Intelligence) and/or hacking across the airframe’s 1553 communications bus

– Perform communications analysis to include speech-to-text and foreign language translation of intercepted communications

– Fuse multiple infrared cameras (e.g., SWIR, MWIR, LWIR) to provide a combined infrared operating picture on the ground Multi-user, simultaneous modulation/demodulation.


View attachment 74869
The 5 dedicated Akida chips running specific models feed 5 separate processors.

A. Target recognition
B. Threat radar detection
C. Cybresecurity
D. Intercepted speech analysis and translation
E. Multi-IR camera analysis

These are Akida 1 chips.

There's a fair chance that the Akida 2 version is well into the development phase.

Analysis from my peewee tech brain is: That's Impressive!

SC

 

[Diogenese]

Good interview with Renesas engineers.
They talk about a neuromorphic unit at 33 minutes. But they say they are working with Edge Cortix in this case. Bit of a shame - with all of the good news floating around, it would of been great to come across a random podcast where they confirm they are using Akida.

They also talk about having an ecosystem of partners for AI. When you go to the Renesas website, they have a large list of Partners. Brainchip arent on that list from what I could see. But then again neither is Edge Cortix.

Renesas Preferred Partners: Collaborating for Enhanced Solutions

Renesas preferred partners are system solution providers working with Renesas and its customers in their domains of expertise.

www.renesas.com

"We have our own DRP, engine to accelerate AI workload - we are looking at other AI acceleration hardware to support that. ... working with our partners ... ecosystem partners ... "

 

[Boab]

Hi SG,

Let's just reprise the Bascom Hunter SNAP card:

https://bascomhunter.com/products-s...c-processors/asic-solutions/3u-vpx-snap-card/

Bascom Hunter’s SNAP Card (Spiking Neuromorphic Advanced Processor) is a high-performance 3U OpenVPX AI/ML processor built for rugged, mission-critical environments. The card is SOSA-aligned, HOST-compatible, and conduction cooled. It combines a Xilinx UltraScale+ RFSoC FPGA with five BrainChipAKD1000 spiking neuromorphic processors to achieve the best of both signal processing and neuromorphic computing – featuring a total of 6million neurons and 50 billion synapses across the card. Unlike traditional machine learning accelerators such as GPUs or TPUs, neuromorphic processors are designed to mimic the biological efficiency of the human brain, allowing the SNAP Card to run multiple ML models in parallel at exceptionally low power — just 1W per model — without sacrificing speed or accuracy while the FPGA enhances input/output operations and performs any desired signal processing tasks. This combination in a rugged, interoperable, and military-hardened package makes Bascom Hunter’s SNAP Card the ideal solution for the concurrent and parallel processing of real-time, multi-modal, and multi sensor data on autonomous, unattended, denied, or otherwise battery constrained military systems.

A single SNAP Card, deployed on an airborne ISR platform, occupying only one 3U VPX slot, could deploy up to five complex machine learning algorithms across each of its onboard processors to perform the following missions simultaneously.

– Automated Target Recognition (ATR) on full motion video feeds and imagery (to include 4k and higher)

– Real-time detection and identification of threat radars and their acquisition/operating modes

– Detection of FISINT (Foreign Instrumentation Signature Intelligence) and/or hacking across the airframe’s 1553 communications bus

– Perform communications analysis to include speech-to-text and foreign language translation of intercepted communications

– Fuse multiple infrared cameras (e.g., SWIR, MWIR, LWIR) to provide a combined infrared operating picture on the ground Multi-user, simultaneous modulation/demodulation.


View attachment 74869
The 5 dedicated Akida chips running specific models feed 5 separate processors.

A. Target recognition
B. Threat radar detection
C. Cybresecurity
D. Intercepted speech analysis and translation
E. Multi-IR camera analysis

These are Akida 1 chips.

There's a fair chance that the Akida 2 version is well into the development phase.

Looking at the second gen Akida is it feasible to think all of the above A - E could be handles simultaneously??

 

[JB49]

"We have our own DRP, engine to accelerate AI workload - we are looking at other AI acceleration hardware to support that. ... working with our partners ... ecosystem partners ... "

All i could think while listening to this entire video was that a lot of the problems, hurdles and innovations they seek are solved by Akida 2.0.

 

[Pom down under]

Happy now and cheers everyone to a great next couple of weeks

 

[Diogenese]

Looking at the second gen Akida is it feasible to think all of the above A - E could be handles simultaneously??

View attachment 74876

Hi Boab,

That's not the idea. It's about the number of nodes included in the silicon SoC. From memory, E can have up to 4 nodes, S can have up to 8 nodes and P can have 8 to 128 nodes.

So the E would be much cheaper than the P because they can make more per wafer.

 

[Diogenese]

Looking at the second gen Akida is it feasible to think all of the above A - E could be handles simultaneously??

View attachment 74876

Sorry, got the wrong end of the stick - I think that in a military application separate chips are preferred so you don't lose all functions if one chip fails. There will also be redundancy.

 

[Boab]

Sorry, got the wrong end of the stick - I think that in a military application separate ships are preferred so you don't lose all functions if one chip fails. There will also be redundancy.

Thanks for that. My thinking came about because of it's ability to multi pass processing.

Appreciate your help/thoughts.

 

[Diogenese]

Thanks for that. My thinking came about because of it's ability to multi pass processing.

Appreciate your help/thoughts.

You are right of course. Akida can multitask. We've seen to face recognition and key word spotting together on Akida 1.

 

[Dijon101]

Bit of technical analysis if you subscribe to that sort of thing.

3 green days in a row, with higher highs and higher lows signifies a trend reversal.

Not saying we will have another green day Monday, but we should see a more positive macro outlook in regards to our share price.

I.e we should be richer in 2025

 

[supersonic001]

Magnus Östberg on LinkedIn: #neuromorphic #mercedesbenz #digitalisation #smartcities #innovation | 10 comments

Hyper-personalisation through AR/VR, solar paint and #neuromorphic computing are just some of the next-gen technologies that will shape the future of mobility.… | 10 comments on LinkedIn

www.linkedin.com

I might have missed Anil’s Like from 3 weeks ago 🫢

 

[Pom down under]

Bit of technical analysis if you subscribe to that sort of thing.

3 green days in a row, with higher highs and higher lows signifies a trend reversal.

Not saying we will have another green day Monday, but we should see a more positive macro outlook in regards to our share price.

I.e we should be richer in 2025

I’m lucky I’m in the green, but everyone who is in the red still deserve to start seeing some profit into 2025 after an extremely turbulent last few years, as it’s sure has been a bumpy ride

 

[Space Cadet]

6 months old but nice.

https://www.linkedin.com/posts/jere...sharing-the-activity-7220049594758377472-7kj9

SC

 

[manny100]

Hi SG,

Let's just reprise the Bascom Hunter SNAP card:

https://bascomhunter.com/products-s...c-processors/asic-solutions/3u-vpx-snap-card/

Bascom Hunter’s SNAP Card (Spiking Neuromorphic Advanced Processor) is a high-performance 3U OpenVPX AI/ML processor built for rugged, mission-critical environments. The card is SOSA-aligned, HOST-compatible, and conduction cooled. It combines a Xilinx UltraScale+ RFSoC FPGA with five BrainChipAKD1000 spiking neuromorphic processors to achieve the best of both signal processing and neuromorphic computing – featuring a total of 6million neurons and 50 billion synapses across the card. Unlike traditional machine learning accelerators such as GPUs or TPUs, neuromorphic processors are designed to mimic the biological efficiency of the human brain, allowing the SNAP Card to run multiple ML models in parallel at exceptionally low power — just 1W per model — without sacrificing speed or accuracy while the FPGA enhances input/output operations and performs any desired signal processing tasks. This combination in a rugged, interoperable, and military-hardened package makes Bascom Hunter’s SNAP Card the ideal solution for the concurrent and parallel processing of real-time, multi-modal, and multi sensor data on autonomous, unattended, denied, or otherwise battery constrained military systems.

A single SNAP Card, deployed on an airborne ISR platform, occupying only one 3U VPX slot, could deploy up to five complex machine learning algorithms across each of its onboard processors to perform the following missions simultaneously.

– Automated Target Recognition (ATR) on full motion video feeds and imagery (to include 4k and higher)

– Real-time detection and identification of threat radars and their acquisition/operating modes

– Detection of FISINT (Foreign Instrumentation Signature Intelligence) and/or hacking across the airframe’s 1553 communications bus

– Perform communications analysis to include speech-to-text and foreign language translation of intercepted communications

– Fuse multiple infrared cameras (e.g., SWIR, MWIR, LWIR) to provide a combined infrared operating picture on the ground Multi-user, simultaneous modulation/demodulation.


View attachment 74869
The 5 dedicated Akida chips running specific models feed 5 separate processors.

A. Target recognition
B. Threat radar detection
C. Cybresecurity
D. Intercepted speech analysis and translation
E. Multi-IR camera analysis

These are Akida 1 chips.

There's a fair chance that the Akida 2 version is well into the development phase.

This is what Bascom Hunter say they about Neuromorphic.
We fit into all 3 deployments. The 3rd one below is for future focused customers combining Neuromorphic and photonic. Interesting as photonics perform calculations at the speed of light. Could be huge.
" Bascom Hunter produces three types of Neuromorphic Processors. The first is the deployment of a neural network into an FPGA. Doing this allows us to take existing COTS hardware and help customers bring existing (or proposed) neural networks into this hardware, speeding up the computation and lowering the power requirements. The second is the deployment of a neural network into custom hardware – typically based on a 3rd party ASIC processor. We can take ASICs produced by the vendor of your choice and put it into a platform and mission specific form factor. For example, into VPX or small-sat form factors. The third type of Neuromorphic processor is intended for our future focused customers looking to engage on cutting edge photonic based neuromorphic processors."

Neuromorphic Processors

bascomhunter.com

 

[TheDrooben]

Bit of technical analysis if you subscribe to that sort of thing.

3 green days in a row, with higher highs and higher lows signifies a trend reversal.

Not saying we will have another green day Monday, but we should see a more positive macro outlook in regards to our share price.

I.e we should be richer in 2025

One for our top TA analysts @Fullmoonfever and @Ethinvestor who over on the TA thread are always insightful when looking at how the SP is tracking as far as TA goes. I know a lot of people here don't follow the TA side of things but IMO it is always helpful to understand the way people trade so they can themselves understand why the SP does what it does.........Larry is always trying to learn......and yes @DingoBorat .....gaps are part of that

 

[Diogenese]

This is what Bascom Hunter say they about Neuromorphic.
We fit into all 3 deployments. The 3rd one below is for future focused customers combining Neuromorphic and photonic. Interesting as photonics perform calculations at the speed of light. Could be huge.
" Bascom Hunter produces three types of Neuromorphic Processors. The first is the deployment of a neural network into an FPGA. Doing this allows us to take existing COTS hardware and help customers bring existing (or proposed) neural networks into this hardware, speeding up the computation and lowering the power requirements. The second is the deployment of a neural network into custom hardware – typically based on a 3rd party ASIC processor. We can take ASICs produced by the vendor of your choice and put it into a platform and mission specific form factor. For example, into VPX or small-sat form factors. The third type of Neuromorphic processor is intended for our future focused customers looking to engage on cutting edge photonic based neuromorphic processors."

Neuromorphic Processors

bascomhunter.com

BRN are developing a FPGA, ostensibly for cloud-based customer testing, but once you've got a FPGA, you can use it where you wish.

Akida 1 is an ASIC.

A photonic Akida would need to be designe from the ground up.

 

[DingoBorat]

One for our top TA analysts @Fullmoonfever and @Ethinvestor who over on the TA thread are always insightful when looking at how the SP is tracking as far as TA goes. I know a lot of people here don't follow the TA side of things but IMO it is always helpful to understand the way people trade so they can themselves understand why the SP does what it does.........Larry is always trying to learn......and yes @DingoBorat .....gaps are part of that

View attachment 74902

According to Tom and Jerry (who seems quite chipper lately, so must be happy with the shares he's accumulated, after months of down ramping)..

There are 3 major gaps upwards now.

At 45 cents, $1.595 and $1.91.

Now, as I have always contended, all gaps must be closed, no exception.

The 45 cent gap, could easily be closed on current demand and momentum.

The other 2, will of course need IP deals.

 

[TheDrooben]

According to Tom and Jerry (who seems quite chipper lately, so must be happy with the shares he's accumulated, after months of down ramping)..

There are 3 major gaps upwards now.

At 45 cents, $1.595 and $1.91.

Now, as I have always contended, all gaps must be closed, no exception.

The 45 cent gap, could easily be closed on current demand and momentum.

The other 2, will of course need IP deals.