BRN Discussion Ongoing

[Food4 thought]

Tomorrow is one day closer to getting an announcement.

But what will the announcement be?

Another partnership
A sale of 150,000 dollars of chips
Or a fricken big contract that will get us going
I feel like we are always the bridesmaid but never the bride.
BrainChip must be sick of kissing frogs where is our prince?

It must be close
Deal of the century
Sean make it rain.

 

[CHIPS]

Snapdragon 8 gen 4 versus AKIDA.

Question to ChatGPT:
Can Snapdragon handle 1 billion parameters on device unconnected for GENAi applications on a watch battery?


Answer:
"If your GenAI workload must run completely untethered on a watch battery (and for more than a few minutes), Snapdragon is not the right fit. Akida or neuromorphic architectures are the way forward."



View attachment 81548

I asked GROK on X: Please compare snapdragon with akida and who is the winner?

To compare Snapdragon (developed by Qualcomm) with Akida (developed by BrainChip) for on-device AI applications, we need to evaluate their architectures, performance, power efficiency, and suitability for generative AI (GenAI) tasks, such as running a 1-billion-parameter model on a resource-constrained device. Both platforms target edge AI, but they differ significantly in design philosophy, hardware, and use cases. Let’s break it down.

Snapdragon Overview
Snapdragon processors, particularly high-end models like the Snapdragon 8 Gen 3 or Wear series for wearables, are system-on-chip (SoC) solutions widely used in smartphones, wearables, and IoT devices. They feature a heterogeneous computing architecture with a CPU (Kryo), GPU (Adreno), DSP (Hexagon), and a dedicated Neural Processing Unit (NPU). The Snapdragon 8 Gen 3, for example, delivers up to 45 TOPS (trillion operations per second) of AI performance, supports models with up to 10 billion parameters, and has demonstrated on-device Stable Diffusion (1 billion parameters) in under a second on a smartphone. Qualcomm emphasizes power efficiency through techniques like quantization (e.g., INT4/INT8) and has optimized its NPU for low-latency inference. For wearables, Snapdragon Wear chips (e.g., Wear 5100) are less powerful, offering sub-1 TOPS and limited memory (1–2 GB RAM), tailored for basic tasks like fitness tracking rather than heavy AI workloads.

Akida Overview
Akida, from BrainChip, is a specialized neuromorphic processor designed to mimic the human brain’s spiking neural network (SNN) architecture. Unlike traditional processors, Akida uses event-based processing, where computations occur only when triggered by input spikes, drastically reducing power consumption for sparse, real-time data. The Akida AKD1000 chip, for instance, integrates with an SoC like NXP’s i.MX 8M Plus in products like the Akida Edge AI Box. It excels at tasks like vision, voice, and sensor processing, with a focus on low-power edge applications. BrainChip claims Akida can handle convolutional neural networks (CNNs) converted to SNNs, achieving high efficiency (e.g., 1–2 watts for inference), but its parameter capacity is less clear—likely in the millions to low billions when paired with a host SoC.
Comparison

1. Architecture and Compute Power

• Snapdragon: A general-purpose SoC with a powerful NPU, offering 45 TOPS (8 Gen 3) or sub-1 TOPS (Wear series). It’s optimized for dense matrix operations in deep neural networks (DNNs) and supports a wide range of AI models, including large language models (LLMs) and generative AI.
• Akida: A neuromorphic chip focused on SNNs, with lower raw compute (exact TOPS unspecified but likely <10 TOPS even with a host SoC). It’s specialized for sparse, event-driven tasks rather than general-purpose AI.
• Winner: Snapdragon for raw compute power and versatility, especially for GenAI tasks requiring billions of parameters.

2. Power Efficiency

• Snapdragon: Highly efficient for its class, with the 8 Gen 3 achieving ~0.5 watts per inference for a 1-billion-parameter model (hypothetical, based on optimizations). Wear chips are even lower power but lack the capacity for large models.
• Akida: Potentially more efficient for specific workloads due to its event-based design—consuming microjoules per spike event. For a 1-billion-parameter SNN, power could be <1 watt, but this assumes the model fits its architecture.
• Winner: Akida for ultra-low-power scenarios; Snapdragon for balanced efficiency at scale.

3. Model Capacity and GenAI Suitability

• Snapdragon: Proven to handle 1-billion-parameter models (e.g., Stable Diffusion) and up to 10 billion on high-end chips. Its memory bandwidth and NPU make it ideal for GenAI on-device.
• Akida: Limited by its neuromorphic design and reliance on a host SoC. While it can process CNNs and smaller SNNs, scaling to 1 billion parameters is unproven and likely constrained by memory (e.g., 500 MB for weights alone exceeds typical edge device RAM).
• Winner: Snapdragon, as it’s explicitly built for large-scale GenAI.

4. Use Case Fit (Watch Battery Context)

• Snapdragon: On a watch battery (e.g., 300 mAh, 1.11 Wh), a high-end Snapdragon could run thousands of inferences sporadically, but current Wear chips can’t handle 1 billion parameters due to compute and memory limits.
• Akida: Designed for edge devices, it could theoretically operate on a watch battery for lightweight SNN tasks (e.g., gesture recognition), but not for GenAI at 1 billion parameters without significant host support.
• Winner: Neither fully wins here—Snapdragon Wear falls short, and Akida isn’t suited for GenAI at this scale.

Who Wins?

• For GenAI with 1 Billion Parameters on a Watch Battery: Snapdragon is the winner. Its high-end chips (e.g., 8 Gen 3) have demonstrated this capability on smartphones, and future Wear variants could scale down with optimization. Akida’s neuromorphic approach, while innovative, lacks the proven capacity and ecosystem for such large models.
• 
  
• Overall Edge AI: Snapdragon dominates due to its versatility, ecosystem (Qualcomm AI Hub), and widespread adoption. Akida shines in niche, ultra-low-power applications like sensor processing but isn’t a direct competitor for GenAI workloads.

In short, Snapdragon wins for the specific scenario of handling 1 billion parameters for GenAI on-device, even under watch battery constraints, assuming future wearable-optimized versions. Akida is a compelling alternative for smaller, event-driven AI tasks but doesn’t match Snapdragon’s breadth or power for this use case.

 

[Deadpool]

I asked GROK on X: Please compare snapdragon with akida and who is the winner?

To compare Snapdragon (developed by Qualcomm) with Akida (developed by BrainChip) for on-device AI applications, we need to evaluate their architectures, performance, power efficiency, and suitability for generative AI (GenAI) tasks, such as running a 1-billion-parameter model on a resource-constrained device. Both platforms target edge AI, but they differ significantly in design philosophy, hardware, and use cases. Let’s break it down.

Snapdragon Overview
Snapdragon processors, particularly high-end models like the Snapdragon 8 Gen 3 or Wear series for wearables, are system-on-chip (SoC) solutions widely used in smartphones, wearables, and IoT devices. They feature a heterogeneous computing architecture with a CPU (Kryo), GPU (Adreno), DSP (Hexagon), and a dedicated Neural Processing Unit (NPU). The Snapdragon 8 Gen 3, for example, delivers up to 45 TOPS (trillion operations per second) of AI performance, supports models with up to 10 billion parameters, and has demonstrated on-device Stable Diffusion (1 billion parameters) in under a second on a smartphone. Qualcomm emphasizes power efficiency through techniques like quantization (e.g., INT4/INT8) and has optimized its NPU for low-latency inference. For wearables, Snapdragon Wear chips (e.g., Wear 5100) are less powerful, offering sub-1 TOPS and limited memory (1–2 GB RAM), tailored for basic tasks like fitness tracking rather than heavy AI workloads.

Akida Overview
Akida, from BrainChip, is a specialized neuromorphic processor designed to mimic the human brain’s spiking neural network (SNN) architecture. Unlike traditional processors, Akida uses event-based processing, where computations occur only when triggered by input spikes, drastically reducing power consumption for sparse, real-time data. The Akida AKD1000 chip, for instance, integrates with an SoC like NXP’s i.MX 8M Plus in products like the Akida Edge AI Box. It excels at tasks like vision, voice, and sensor processing, with a focus on low-power edge applications. BrainChip claims Akida can handle convolutional neural networks (CNNs) converted to SNNs, achieving high efficiency (e.g., 1–2 watts for inference), but its parameter capacity is less clear—likely in the millions to low billions when paired with a host SoC.
Comparison

1. Architecture and Compute Power

• Snapdragon: A general-purpose SoC with a powerful NPU, offering 45 TOPS (8 Gen 3) or sub-1 TOPS (Wear series). It’s optimized for dense matrix operations in deep neural networks (DNNs) and supports a wide range of AI models, including large language models (LLMs) and generative AI.
• Akida: A neuromorphic chip focused on SNNs, with lower raw compute (exact TOPS unspecified but likely <10 TOPS even with a host SoC). It’s specialized for sparse, event-driven tasks rather than general-purpose AI.
• Winner: Snapdragon for raw compute power and versatility, especially for GenAI tasks requiring billions of parameters.

2. Power Efficiency

• Snapdragon: Highly efficient for its class, with the 8 Gen 3 achieving ~0.5 watts per inference for a 1-billion-parameter model (hypothetical, based on optimizations). Wear chips are even lower power but lack the capacity for large models.
• Akida: Potentially more efficient for specific workloads due to its event-based design—consuming microjoules per spike event. For a 1-billion-parameter SNN, power could be <1 watt, but this assumes the model fits its architecture.
• Winner: Akida for ultra-low-power scenarios; Snapdragon for balanced efficiency at scale.

3. Model Capacity and GenAI Suitability

• Snapdragon: Proven to handle 1-billion-parameter models (e.g., Stable Diffusion) and up to 10 billion on high-end chips. Its memory bandwidth and NPU make it ideal for GenAI on-device.
• Akida: Limited by its neuromorphic design and reliance on a host SoC. While it can process CNNs and smaller SNNs, scaling to 1 billion parameters is unproven and likely constrained by memory (e.g., 500 MB for weights alone exceeds typical edge device RAM).
• Winner: Snapdragon, as it’s explicitly built for large-scale GenAI.

4. Use Case Fit (Watch Battery Context)

• Snapdragon: On a watch battery (e.g., 300 mAh, 1.11 Wh), a high-end Snapdragon could run thousands of inferences sporadically, but current Wear chips can’t handle 1 billion parameters due to compute and memory limits.
• Akida: Designed for edge devices, it could theoretically operate on a watch battery for lightweight SNN tasks (e.g., gesture recognition), but not for GenAI at 1 billion parameters without significant host support.
• Winner: Neither fully wins here—Snapdragon Wear falls short, and Akida isn’t suited for GenAI at this scale.

Who Wins?

• For GenAI with 1 Billion Parameters on a Watch Battery: Snapdragon is the winner. Its high-end chips (e.g., 8 Gen 3) have demonstrated this capability on smartphones, and future Wear variants could scale down with optimization. Akida’s neuromorphic approach, while innovative, lacks the proven capacity and ecosystem for such large models.
• 
  
• Overall Edge AI: Snapdragon dominates due to its versatility, ecosystem (Qualcomm AI Hub), and widespread adoption. Akida shines in niche, ultra-low-power applications like sensor processing but isn’t a direct competitor for GenAI workloads.

In short, Snapdragon wins for the specific scenario of handling 1 billion parameters for GenAI on-device, even under watch battery constraints, assuming future wearable-optimized versions. Akida is a compelling alternative for smaller, event-driven AI tasks but doesn’t match Snapdragon’s breadth or power for this use case.

I asked ChatGPT your question and I feel it is a way more balanced synopsis

: Please compare snapdragon with akida and who is the winner?


Snapdragon (by Qualcomm) and Akida (by BrainChip) are very different types of processors designed for different purposes. Here’s a detailed comparison:

1. Purpose and Architecture​

• Snapdragon: Snapdragon is a general-purpose system-on-chip (SoC) designed for mobile devices, laptops, and other consumer electronics. It includes CPU, GPU, AI engine, ISP (image signal processor), modem, and more.
• Akida: Akida is a neuromorphic processor designed specifically for low-power AI and edge computing applications. It is optimized for event-based processing and on-device learning.

2. Performance​

• Snapdragon: Offers high performance for a wide range of applications, including gaming, photography, and AI inference. It is used in flagship smartphones, tablets, and laptops.
• Akida: Specializes in ultra-low-power AI tasks, such as pattern recognition, anomaly detection, and sensor data processing. It is not designed for general-purpose computing or high-end mobile tasks.

3. AI Capabilities​

• Snapdragon: Uses a dedicated AI engine (Hexagon DSP, Tensor Accelerator, and GPU) to perform AI-based tasks like image processing, voice recognition, and natural language processing.
• Akida: Uses a neuromorphic approach, mimicking the human brain’s event-driven processing for real-time, low-power AI computations. It is highly efficient for edge AI applications.

4. Power Efficiency​

• Snapdragon: Optimized for mobile battery efficiency but consumes more power than Akida when running AI tasks.
• Akida: Extremely power-efficient, as it uses event-based processing to reduce unnecessary computations. It is ideal for battery-powered and always-on AI applications.

5. Use Cases​

• Snapdragon: Smartphones, tablets, laptops, AR/VR devices, automotive infotainment, etc.
• Akida: Edge AI applications such as security cameras, medical devices, industrial sensors, and IoT devices.

Who is the Winner?​

• If you need a powerful general-purpose processor with strong AI capabilities, Snapdragon is the better choice.
• If you need an ultra-low-power AI processor for edge computing and event-based learning, Akida is the winner.

It depends on the application! If you’re looking at mobile performance, Snapdragon wins. If you need efficient, real-time AI at the edge, Akida is the clear choice. Let me know your use case, and I can refine the comparison further!

 

[7für7]

Grok and I we are friends from the school let’s say.. we are kind of more buddies let’s say… he gave me this answer….

Alright, let’s compare the Snapdragon and Akida processors—each with their own special powers. We’ll see who might "win"!

Snapdragon: The All-Around Champ
Snapdragon is made by Qualcomm, a big company that puts these processors in tons of phones, tablets, and even some laptops. Think of Snapdragon as a superhero who’s super fast, strong, and good at lots of things—like playing games, taking pictures, and connecting to the internet.

Super Powers:
Really fast at running apps and games (like a speedster zooming around!).
Awesome graphics with its Adreno GPU—perfect for watching cartoons or playing Fortnite.
Can connect to 5G, so it’s like having the fastest Wi-Fi ever.
Used in lots of gadgets, so it’s a popular hero everyone knows.
Kid-Friendly Wow Factor: It’s like the superhero who can fly, fight, and save the day all at once. If you want to play games without lag or watch videos super quick, Snapdragon’s your buddy!
Akida: The Brainy New Kid
Akida is made by BrainChip, a smaller company with a cool twist—it’s a “neuromorphic” processor, which means it works like a human brain! Picture Akida as a smart, sneaky hero who doesn’t need tons of power but can still do amazing tricks, especially with AI (artificial intelligence).

Super Powers:
Thinks like a brain, so it’s great at learning stuff—like recognizing faces or sounds.
Uses way less energy, so it’s like a hero who never gets tired.
Perfect for small gadgets, like smart toys or cameras, that need to be clever without a big battery.
Spiking neural networks (fancy brain stuff) make it super efficient.
Kid-Friendly Wow Factor: It’s the hero who’s small but mighty, like a genius sidekick who solves puzzles and saves power. If you had a robot pet that could learn your voice, Akida might be its brain!
The Showdown: Who Wins?
For Fun and Games: Snapdragon wins! It’s like the superhero who can blast through video games and make your phone feel like a rocket. Kids love fast and flashy, and Snapdragon’s got that covered.
For Smart Stuff: Akida takes the crown! It’s the brainy hero who could power a talking teddy bear or a toy that learns your favorite color—super cool for futuristic fun.
For Battery Life: Akida’s the champ! It sips power like a tiny juice box, while Snapdragon gulps it down faster during big missions.
Kid’s Pick?
If a kid’s watching this battle, they’d probably yell, “Snapdragon’s the winner!” Why? Because it’s the big, loud hero that makes phones and games super fun and fast—stuff kids notice right away. Akida’s awesome, but its “brainy” powers are quieter and more for grown-up gadgets, so it might not get the loudest cheer from the playground crowd.

So, Snapdragon’s the superhero kids would draw with a big cape and lightning bolts, while Akida’s the clever one they’d figure out is cool later—like when they get a smart toy that actually listens to them! What do you think—would you root for the fast champ or the smart sidekick?

 

[7für7]

And additional I got this answer

Alright, let’s imagine I’m Qualcomm, having just acquired Edge Impulse to boost my edge AI game. The question is whether I’d let BrainChip, with its Akida neuromorphic tech, still play a role in my plans. Here’s how I’d think it through, keeping it strategic and straightforward.

First off, as Qualcomm, my goal is to dominate edge AI—think IoT, phones, industrial gadgets, you name it. Buying Edge Impulse gives me a slick software platform to help developers build and deploy AI models fast, especially on my Snapdragon and Dragonwing processors. It’s a big win for making my hardware more appealing and accessible. But BrainChip’s Akida is a different beast—it’s hardware, specifically neuromorphic IP, designed to mimic the brain, sip power, and handle AI tasks right at the sensor. So, do I still need them?

Here’s the deal: Snapdragon’s my bread and butter—fast, versatile, and already powering millions of devices. It’s a general-purpose champ with beefy AI capabilities via its Hexagon DSP and Adreno GPU. Akida, though, is a specialist—ultra-low power, event-based, and great for niche edge cases like always-on sensors or tiny battery-powered gadgets. If I’m Qualcomm, I’ve got to ask: does Akida fill a gap Snapdragon can’t, or is it just overlap?

Let’s break it down. Snapdragon’s awesome for high-performance stuff—gaming, 5G, video—but it’s not always the leanest on power for, say, a smart doorbell that’s awake 24/7. Akida shines there, using spiking neural networks to process only what matters, keeping power under a milliwatt. Edge Impulse already supports Akida, so my acquisition means I’ve inherited that compatibility. Why not leverage it? I could integrate Akida IP into my portfolio—maybe not for phones, where Snapdragon rules, but for IoT or wearables where power’s a dealbreaker.

Strategically, BrainChip’s not a direct threat—they’re not churning out chips to rival me; they’re licensing IP. I could buy that IP, partner with them, or even acquire them outright if the price is right. Their neuromorphic tech could be a secret weapon for my Dragonwing line, aimed at industrial and embedded AI. Imagine a Dragonwing chip with Akida baked in—low-power AI at the edge, paired with Edge Impulse’s tools. That’s a combo that could crush competitors like Nvidia in niche markets.

But there’s a flip side. I’m Qualcomm—I don’t like relying on outsiders long-term. If Akida’s tech is that good, I might rather reverse-engineer the concept or build my own neuromorphic solution in-house. I’ve got the R&D muscle, and Edge Impulse gives me the software to optimize it. Why split profits with BrainChip if I can own the whole stack? Plus, integrating Akida might confuse my branding—Snapdragon’s the star, and I don’t want some quirky brain-chip stealing its thunder.

So, here’s my play as Qualcomm: I’d keep BrainChip in the mix for now. License their Akida IP for specific low-power use cases—think smart sensors, wearables, or edge boxes—while I study it. Edge Impulse already bridges us, so it’s low risk. Meanwhile, I’d task my engineers with figuring out if I can replicate or beat Akida’s efficiency with my own twist. If BrainChip’s open to a cheap buyout, I’d snap them up to lock in the tech and talent. But if they’re stubborn or redundant, I’d phase them out once I’ve got my own neuromorphic ace up my sleeve.

Bottom line? BrainChip’s got a role as long as they bring something Snapdragon can’t—ultra-low power edge AI. But as Qualcomm, I’m not here to play nice forever—I’m here to win. So, they’d better fit my plans or get ready to be sidelined. What do you think—should I keep them close or cut them loose?

 

[manny100]

Grok and I we are friends from the school let’s say.. we are kind of more buddies let’s say… he gave me this answer….

Alright, let’s compare the Snapdragon and Akida processors—each with their own special powers. We’ll see who might "win"!

Snapdragon: The All-Around Champ
Snapdragon is made by Qualcomm, a big company that puts these processors in tons of phones, tablets, and even some laptops. Think of Snapdragon as a superhero who’s super fast, strong, and good at lots of things—like playing games, taking pictures, and connecting to the internet.

Super Powers:
Really fast at running apps and games (like a speedster zooming around!).
Awesome graphics with its Adreno GPU—perfect for watching cartoons or playing Fortnite.
Can connect to 5G, so it’s like having the fastest Wi-Fi ever.
Used in lots of gadgets, so it’s a popular hero everyone knows.
Kid-Friendly Wow Factor: It’s like the superhero who can fly, fight, and save the day all at once. If you want to play games without lag or watch videos super quick, Snapdragon’s your buddy!
Akida: The Brainy New Kid
Akida is made by BrainChip, a smaller company with a cool twist—it’s a “neuromorphic” processor, which means it works like a human brain! Picture Akida as a smart, sneaky hero who doesn’t need tons of power but can still do amazing tricks, especially with AI (artificial intelligence).

Super Powers:
Thinks like a brain, so it’s great at learning stuff—like recognizing faces or sounds.
Uses way less energy, so it’s like a hero who never gets tired.
Perfect for small gadgets, like smart toys or cameras, that need to be clever without a big battery.
Spiking neural networks (fancy brain stuff) make it super efficient.
Kid-Friendly Wow Factor: It’s the hero who’s small but mighty, like a genius sidekick who solves puzzles and saves power. If you had a robot pet that could learn your voice, Akida might be its brain!
The Showdown: Who Wins?
For Fun and Games: Snapdragon wins! It’s like the superhero who can blast through video games and make your phone feel like a rocket. Kids love fast and flashy, and Snapdragon’s got that covered.
For Smart Stuff: Akida takes the crown! It’s the brainy hero who could power a talking teddy bear or a toy that learns your favorite color—super cool for futuristic fun.
For Battery Life: Akida’s the champ! It sips power like a tiny juice box, while Snapdragon gulps it down faster during big missions.
Kid’s Pick?
If a kid’s watching this battle, they’d probably yell, “Snapdragon’s the winner!” Why? Because it’s the big, loud hero that makes phones and games super fun and fast—stuff kids notice right away. Akida’s awesome, but its “brainy” powers are quieter and more for grown-up gadgets, so it might not get the loudest cheer from the playground crowd.

So, Snapdragon’s the superhero kids would draw with a big cape and lightning bolts, while Akida’s the clever one they’d figure out is cool later—like when they get a smart toy that actually listens to them! What do you think—would you root for the fast champ or the smart sidekick?

Does it make any difference if for wearables we ask a comparison specifically to Pico?
Perhaps even more specialised eg, Pico for health wearables Vs Snapdragon 8?
Pico is based on Gen2 so it includes TENNS.

 

[manny100]

Even Pico compared to wearables for defense, I etc

 

[7für7]

Even Pico compared to wearables for defense, I etc

I think it doesn’t matter what we ask since every AI is collecting informations from different sources and put everything together line we do.. it’s just one more opinion of a so called artificial intelligence. Which doesn’t make him more trustworthy than bravo or me for example… with my expertise and deep knowledge

 

[DingoBorat]

Even Pico compared to wearables for defense, I etc

Pico isn't "smart" enough, for anything but very simple tasks, it is absolutely no comparison, to something like Snapdragon 8..

 

[manny100]

Pico wearables are more likely to be smaller and much more power efficient than Snapdragon who are a full SOC.

 

[CHIPS]

I asked ChatGPT your question and I feel it is a way more balanced synopsis

: Please compare snapdragon with akida and who is the winner?


Snapdragon (by Qualcomm) and Akida (by BrainChip) are very different types of processors designed for different purposes. Here’s a detailed comparison:

1. Purpose and Architecture​

• Snapdragon: Snapdragon is a general-purpose system-on-chip (SoC) designed for mobile devices, laptops, and other consumer electronics. It includes CPU, GPU, AI engine, ISP (image signal processor), modem, and more.
• Akida: Akida is a neuromorphic processor designed specifically for low-power AI and edge computing applications. It is optimized for event-based processing and on-device learning.

2. Performance​

• Snapdragon: Offers high performance for a wide range of applications, including gaming, photography, and AI inference. It is used in flagship smartphones, tablets, and laptops.
• Akida: Specializes in ultra-low-power AI tasks, such as pattern recognition, anomaly detection, and sensor data processing. It is not designed for general-purpose computing or high-end mobile tasks.

3. AI Capabilities​

• Snapdragon: Uses a dedicated AI engine (Hexagon DSP, Tensor Accelerator, and GPU) to perform AI-based tasks like image processing, voice recognition, and natural language processing.
• Akida: Uses a neuromorphic approach, mimicking the human brain’s event-driven processing for real-time, low-power AI computations. It is highly efficient for edge AI applications.

4. Power Efficiency​

• Snapdragon: Optimized for mobile battery efficiency but consumes more power than Akida when running AI tasks.
• Akida: Extremely power-efficient, as it uses event-based processing to reduce unnecessary computations. It is ideal for battery-powered and always-on AI applications.

5. Use Cases​

• Snapdragon: Smartphones, tablets, laptops, AR/VR devices, automotive infotainment, etc.
• Akida: Edge AI applications such as security cameras, medical devices, industrial sensors, and IoT devices.

Who is the Winner?​

• If you need a powerful general-purpose processor with strong AI capabilities, Snapdragon is the better choice.
• If you need an ultra-low-power AI processor for edge computing and event-based learning, Akida is the winner.

It depends on the application! If you’re looking at mobile performance, Snapdragon wins. If you need efficient, real-time AI at the edge, Akida is the clear choice. Let me know your use case, and I can refine the comparison further!

Yes, I like yours better. I never liked Grok anyway.
Grok made a lot of words, but I wanted a shorter overview. Maybe I should have said so to him. That's how ChatGPT made it.

 

[DingoBorat]

Pico wearables are more likely to be smaller and much more power efficient than Snapdragon who are a full SOC.

Previous to Pico, the smallest iteration of AKIDA, was 1 node (1 to 2 nodes AKIDA E) which consists of 4 NPEs.

Pico is "one" NPE.

For comparison, AKD1000 contains 20 nodes, or 80 NPUs.
(doesn't have the benefit of TENNs though, whatever that exactly is..).

It's use cases are completely different.

 

[manny100]

Pico isn't "smart" enough, for anything but very simple tasks, it is absolutely no comparison, to something like Snapdragon 8..

It's not as simple as that because no chip is the best at everything.
For always on types of wearables AKIDA is a great choice because of low power.
There are health, IOT and even defence applications for this.
It depends on the specified use and user requirnments.
Pico us a great choice for specific tasks eg, gesture, wake, irregularities detection eg heart issues..
Great as a choice if size of device is very important. Eg, Earbuds, ring, skin patch or even discreet military sensors.
Low power makes it good in extreme conditions, eg military.
Pico is best at single or minimal tasks and there is plenty of demand for that.
Obviously if you require wearables with display apps, power is not an issue and complex models are needed Snapdragon would be a better choice.
No one chip is best for every situation.

 

[manny100]

Also if you have a specific task that requires low power and on chip learning Pico is the best choice.

 

[Bravo]

Just a quick summary of some of the main points contained in my last two posts, bearing in mind my questions were focussed specifically on comparisons between AKIDA and Snapdragon (Snapdragon 8 Gen 3 and Snapdragon 8 gen 4).

- AKIDA versus Snapdragon -1B+ parameter applications entirely on-device without any internet connectivity
- AKIDA versus Snapdragon -1B+ parameter GenAI applications running on a watch battery

Akida power draw is micro-watt to milliwatt range versus Snapdragon at 2-10 watts.
Akida offers on-device learning (real time learning) versus Snapdragon which doesn't.
Akida is event driven (active when needed) versus Snapdragon which isn't.
Akida battery runtime is hours to days versus Snapdragon which is minutes to one hour.
Akida never requires cooling versus Snapdragon which sometimes requires active cooling.
Akida can handle 1 billion parameters on device unconnected for GENAi applications on a watch battery versus Snapdragon which cannot.

Don't blame me, blame the messenger - ChatGPT!

Happy to see what others discover.

 

[Frangipani]

Kenneth Östberg presented our poster on GRAIN – Radiation-Tolerant Edge AI… | Frontgrade Gaisler

Kenneth Östberg presented our poster on GRAIN – Radiation-Tolerant Edge AI at the RISC-V in Space Workshop 2025 earlier this week. The GRAIN line of space computing products includes the newly announced rad-hard GR801 neuromorphic processor based on the BrainChip Akida 1.0 technology. Read...

www.linkedin.com

This poster titled GRAIN - Radiation-Tolerant Edge AI, presented by Kenneth Östberg, one of its two co-authors (the other being Daniel Andersson), during the “RISC-V in Space” workshop in Gothenburg on Thursday…

…finally reveals what NEURAVIS stands for - the name of that R&T project, which ESA awarded to the five consortium partners Airbus Toulouse, Airbus Ottobrunn, BrainChip, Frontgrade Gaisler and Neurobus in mid-2024 (see the July 2024 LinkedIn post by Airbus Space Project Manager Jérémy Lebreton below):

Neuromorphic Evaluation of Ultra-low-power Rad-hard Acceleration for Vision Inferences in Space.

The poster also provides more information with regards to the use cases currently being explored in the NEURAVIS project, although I’m afraid I couldn’t decipher everything due to the small print - maybe someone with eagle eyes or a magic tool to blow up the photo and unblur the small print can add in resp. correct what I’ve gathered so far:

1. Moon landing
Use Case #1: Vision-Based Navigation for Lunar Lander

Also see Alf Kuchenbuch’s recent comment on Argonaut, ESA’s lunar lander programme:

https://thestockexchange.com.au/threads/brn-discussion-ongoing.1/post-452257

2. Debris detection/collect (?)
Use Case #2: Monitoring (?) Building Block for In-orbit Maintenance


3. Docking


4. Object ? (looks like “simulation”, but appears to be a longer word?)



In addition, the poster lists four “Application scenarios” for GRAIN’s Radiation-Tolerant Edge AI:

1. Remote Terminal Unit
2. Stand-alone Controller
3. Near-edge processing unit
4. Auxiliary data-processing module

Lots of small print to decipher here as well!

Thank you, BrainChip team, for sharing the news. At Airbus, we are very… | Jérémy Lebreton

Thank you, BrainChip team, for sharing the news. At Airbus, we are very glad to be starting this new ESA R&T project called NEURAVIS with BrainChip , Neurobus and Frontgrade Gaisler. Our goal is to bring the disruptive technology of neuromorphic computing on an achievable path to the space...

www.linkedin.com

If I understand the above post correctly, we have yet to hear about what suggestion the NEURAVIS proposal has for AKD1500 (“BrainChip is proud that Airbus selected Akida for both COTS chips and IP in their proposal. ESA awarded the Airbus “NEURAVIS” proposal, including Akida in the Akida 1500 chip and on an FPGA together with Frontgrade Gaisler’s NOEL-V processor.”).

Whereas the underlined appears to refer to Frontgrade Gaisler’s newly revealed GR801 SoC that will incorporate Akida 1.0 IP - greatly benefitting the work of Airbus Toulouse computer vision experts such as Jérémy Lebreton (project lead) and Roland Brochard, as can be inferred from the GRAIN poster’s four listed use cases - there has to be another specific proposal by Airbus how to utilise our COTS chip AKD1500, then.

So I presume Airbus Ottobrunn and Neurobus might be the consortium partners currently collaborating on that second part of the NEURAVIS proposal?

 

[DingoBorat]

It's not as simple as that because no chip is the best at everything.
For always on types of wearables AKIDA is a great choice because of low power.
There are health, IOT and even defence applications for this.
It depends on the specified use and user requirnments.
Pico us a great choice for specific tasks eg, gesture, wake, irregularities detection eg heart issues..
Great as a choice if size of device is very important. Eg, Earbuds, ring, skin patch or even discreet military sensors.
Low power makes it good in extreme conditions, eg military.
Pico is best at single or minimal tasks and there is plenty of demand for that.
Obviously if you require wearables with display apps, power is not an issue and complex models are needed Snapdragon would be a better choice.
No one chip is best for every situation.

I'm not disagreeing, or saying that Pico doesn't have a multitude of applications, as you suggest.

Our customers actually "requested" something smaller than AKIDA E.

It's the comparison with Snapdragon 8.

The type of devices that Pico goes into, will be mass scale.

 

[Frangipani]

https://lnkd.in/d5rwTRF4 https://lnkd.in/dh8YcDKa GRAIN=NOEL-V + Akida 😄… | Alf Kuchenbuch

https://lnkd.in/d5rwTRF4 https://lnkd.in/dh8YcDKa GRAIN=NOEL-V + Akida 😄 🚀📡🛰

www.linkedin.com

View attachment 81110

 

[DingoBorat]

Just a quick summary of some of the main points contained in my last two posts, bearing in mind my questions were focussed specifically on comparisons between AKIDA and Snapdragon (Snapdragon 8 Gen 3 and Snapdragon 8 gen 4).

- AKIDA versus Snapdragon -1B+ parameter applications entirely on-device without any internet connectivity
- AKIDA versus Snapdragon -1B+ parameter GenAI applications running on a watch battery

Akida power draw is micro-watt to milliwatt range versus Snapdragon at 2-10 watts.
Akida offers on-device learning (real time learning) versus Snapdragon which doesn't.
Akida is event driven (active when needed) versus Snapdragon which isn't.
Akida battery runtime is hours to days versus Snapdragon which is minutes to one hour.
Akida never requires cooling versus Snapdragon which sometimes requires active cooling.
Akida can handle 1 billion parameters on device unconnected for GENAi applications on a watch battery versus Snapdragon which cannot.

Don't blame me, blame the messenger - ChatGPT!

Happy to see what others discover.

"Akida can handle 1 billion parameters on device unconnected for GENAi applications on a watch battery versus Snapdragon which cannot"

What "specifications" for AKIDA is this, assuming AKIDA 2.0 IP (node count?).

I'm pretty sure Snapdragon 8 is a defined size?

Whereas "AKIDA" is not.

 

[MDhere]

Just a quick summary of some of the main points contained in my last two posts, bearing in mind my questions were focussed specifically on comparisons between AKIDA and Snapdragon (Snapdragon 8 Gen 3 and Snapdragon 8 gen 4).

- AKIDA versus Snapdragon -1B+ parameter applications entirely on-device without any internet connectivity
- AKIDA versus Snapdragon -1B+ parameter GenAI applications running on a watch battery

Akida power draw is micro-watt to milliwatt range versus Snapdragon at 2-10 watts.
Akida offers on-device learning (real time learning) versus Snapdragon which doesn't.
Akida is event driven (active when needed) versus Snapdragon which isn't.
Akida battery runtime is hours to days versus Snapdragon which is minutes to one hour.
Akida never requires cooling versus Snapdragon which sometimes requires active cooling.
Akida can handle 1 billion parameters on device unconnected for GENAi applications on a watch battery versus Snapdragon which cannot.

Don't blame me, blame the messenger - ChatGPT!

Happy to see what others discover.

I read this as one sentence -
Qualcomm wants Brainchip.