TasTroy77
Founding Member
It would be like Rolex deciding to use an inferior plastic part rather than high grade 904L steel.
Qualcomm and snapdragon have been discussed before also.
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Qualcomm and snapdragon have been discussed before also.
Fact Finder
Top 20
Stolen from around a Forbes Magazine pay wall a little bit about what Qualcomm’s Snapdragon offers for EV’s:
“Qualcomm has claimed a combination of two SoCs and one AI accelerator can achieve 400 TOPS at just 65-70W power consumption.”
I think they can give you an actual flat battery and limited range 5 year or 20,000 hour warranty for any system provided it is installed in accordance with the Manufacturers specifications and serviced by an authorised BMW Service provider within a driving range of 250 kilometres or less.
My opinion only DYOR
FF
AKIDA BALLISTA
Rise from the ashes
Regular
Global Chinese Financial Forum
I recall this event but didn't remember seeing this pdf published or most likely read it and forgot about it.
This
I recall this event but didn't remember seeing this pdf published or most likely read it and forgot about it.
ThisSpace Cadet
Regular
https://www.tcs.com/embedded-devices-intelligent-systems
Don't think there is any doubt TCS are into Akida. When the shankles are taken off we may find we are everywhere imo.
SC
Rise from the ashes
Regular
There are about 15 jobs advertised for SiFive in Cambridge.
From a quick scan, none of them mention NNs or Akida, but this introductory paragraph appears at the top of all job requirements:
https://www.sifive.com/careers-uk
About SiFive
As the pioneers who introduced RISC-V to the world, SiFive is transforming the future of compute by bringing the limitless potential of RISC-V to the highest performance and most data-intensive applications in the world. SiFive’s unrivaled compute platforms have enabled leading technology companies around the world to innovate, optimize, and deliver the most advanced solutions of tomorrow across every market segment of chip design, including artificial intelligence, machine learning, automotive, datacenter, mobile, and consumer. With SiFive, the future of RISC-V has no limits.... and who can forget:
https://brainchip.com/brainchip-sifive-partner-deploy-ai-ml-at-edge/
BrainChip And SiFive Partner To Deploy AI/ML Technology At The Edge
Laguna Hills, Calif. – April 5, 2022 – BrainChip Holdings Ltd (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), the world’s first commercial producer of ultra-low power neuromorphic AI chips and IP, and SiFive, Inc., the founder and leader of RISC-V computing, have combined their respective technologies to offer chip designers optimized AI/ML compute at the edge.... or this translation provided by @Fact Finder 6 weeks ago:
BrainChip + SiFive
True but SiFive could be a giant and rising together isn't a problem and makes communicating to the market more powerful. Also the quicker we leave the ASX the better. Intel is getting as close as they can to SiFive since their t/o offer rejected and each day that goes by the takeover price...
thestockexchange.com.au
SiFive and BrainChip collaborate to achieve IP compatibility With increasing attention to RISC-V
Published at 11:30 on May 09, 2022[Sally Ward-Foxton，EE Times]
SiFive and BrainChip have announced that they will collaborate to demonstrate compatibility in SoC (System on Chip) design for embedded AI (artificial intelligence) of their IPs. We have already demonstrated how BrainChip's Neuromorphic Processing Unit (NPU) IP (Intellectual Property) works in conjunction with SiFive's RISC-V host processor IP.
SiFive licence the IP for their RISC-v host processor:-
https://www.sifive.com/blog/introduction-to-the-sifive-intelligence-x280
Introduction To The SiFive Intelligence X280
SiFive is the market leader in RISC-V Vector processors with the flagship SiFive vector processor, the SiFive Intelligence X280, leading the charge as a clear favorite with customers, with solutions being designed into a broad range of applications ranging from computer vision, mobile ISP, Edge AI, to datacenter AI.
With a specific emphasis on AI/ML compute, the X280 features the powerful combination of the RISC-V Vector (512-bit vector length) and the SiFive Intelligence Extensions, tightly integrated with an 8-stage dual-issue in-order scalar pipeline.
Akida IP "works in conjunction with SiFive's RISC-V host processor".
So there's a better than even chance that the SiFive Cambridge team will be messin' about in
Last edited:
Proga
Regular
I may have posted this before. 6 weeks old
Argo AI, the driverless startup backed by Ford Motor Co. and Volkswagen AG, has started testing self-driving vehicles in Miami and Austin, Texas, without a human behind the wheel.
While the cars aren’t the first fully driverless vehicles on the road, the tests may be the toughest so far for the technology. Argo Chief Executive Officer Bryan Salesky said in an interview the company is the first to put cars on the road in major cities during rush hour with no safety driver inside.
www.bloomberg.com
Argo AI, the driverless startup backed by Ford Motor Co. and Volkswagen AG, has started testing self-driving vehicles in Miami and Austin, Texas, without a human behind the wheel.
While the cars aren’t the first fully driverless vehicles on the road, the tests may be the toughest so far for the technology. Argo Chief Executive Officer Bryan Salesky said in an interview the company is the first to put cars on the road in major cities during rush hour with no safety driver inside.
Ford-Backed Argo Starts Testing Self-Driving Cars in Miami and Austin
www.bloomberg.com
Sirod69
bavarian girl ;-)
Neuromorphic Chip Market Research Report: Cagr Status, Industry Growth, Trends, Analysis And Forecasts To 2030 - Designer Women
Neuromorphic Chip Market Report Coverage: Key Growth Factors & Challenges, Segmentation & Re
www.designerwomen.co.uk
Major Key players profiled in the report include:
Applied Brain Research
BrainChip Holdings
General Vision
HRL Laboratories
HP Development Company
IBM Corporation
Intel Corporation
Lockheed Martin Corporation
Qualcomm Technologies
Samsung Electronics …
we are on the second place!!!
Sirod69
bavarian girl ;-)
and another one
www.designerwomen.co.uk
The immense players shrouded in the market report are:
Global Neuromorphic Chip Market Positive Demand and Development Approaches through 2022-2028 - Designer Women
Market Research Place has spread another report named Global Neuromorphic Chip Market, which joins a
www.designerwomen.co.uk
The immense players shrouded in the market report are:
- Applied Brain Research
- BrainChip Holdings
- General Vision
- HRL Laboratories
- HP Development Company
- IBM Corporation
- Intel Corporation
- Lockheed Martin Corporation
- Qualcomm Technologies
- Samsung Electronics
Rise from the ashes
Regular
Neuromorphic Chip Market Research Report: Cagr Status, Industry Growth, Trends, Analysis And Forecasts To 2030 - Designer Women
Neuromorphic Chip Market Report Coverage: Key Growth Factors & Challenges, Segmentation & Re
Major Key players profiled in the report include:
Applied Brain Research
BrainChip Holdings
General Vision
HRL Laboratories
HP Development Company
IBM Corporation
Intel Corporation
Lockheed Martin Corporation
Qualcomm Technologies
Samsung Electronics …
we are on the second place!!!
It's in alphabetical order.
Sirod69
bavarian girl ;-)
Rise from the ashes
Regular
Krustor
Regular
This of course is the only reason we are not ranked as number 1
Rise from the ashes
Regular
That is indeed correctThis of course is the only reason we are not ranked as number 1
cosors
👀
I like the comparison with Grand Seiko better. They are simply better and fit better with our understatement of not putting our money where our mouth is
Off topic and no advertising, I just like them a lot better and they do everything better than Rolex. Just my opinion...
mh, many better s
The comparison is also very interesting when you compare the technology of their Spring Drive with Nviso and Akida vs ICs.
Believe in visions and be persistent
It took them decades to develop their own IC that was energy efficient enough or gave them the technology that made this drive possible in the first place.
https://grandseikogs9club.com/chronicle-9/history-spring-drive/
https://www.ablogtowatch.com/history-seiko-spring-drive-movement/
Last edited:
D
Deleted member 118
Guest
Implementing edge AI: Look before you leap - Embedded.com
Companies looking to adopt edge AI often find it to be a difficult challenge, but what makes it so difficult, and what solutions exist to solve this
Implementing edge AI: Look before you leap
June 28, 2022 Douglas FairbairnAs the need for artificial intelligence grows more common and technology needs become more sophisticated, companies looking to adopt edge AI into their products often find it to be a difficult challenge. But what makes it so difficult, and what solutions exist to solve this problem?
Perhaps the single biggest issue that companies face in implementing edge AI is that most companies don’t have the resources in house to develop these sophisticated fast-changing technologies. Lack of trained personnel and little familiarity with design flow often leads to delayed timelines and excess expense to train team members. In addition, there are so many choices, it is impossible for engineers to explore each option. And since every application is different, it may not be appropriate to replicate solutions based on past implementations. However, by asking a few key questions and finding the right partner to take your project from ideation to silicon, any enterprise can develop a roadmap to successfully deploy edge AI in their devices.
Defining Use Cases And Feasibility
ADVERTISEMENT
SCROLL DOWN TO CONTINUE READING
It is important to define use cases before exploring implementation options. The first question any business should ask is: What would the customer find truly useful? After pinpointing the functionality the customer wants, your team needs to set development and production cost goals along with the acceptable time to market.
Now comes the challenging part – making technology-related decisions. Is it possible to implement that functionality within the cost, time, power and space tradeoffs you’re dealing with? Working with an experienced partner/consultant or drawing on internal experience is critical at this stage. You won’t have perfect data on which to base your decision, so actual experience is essential in making these judgements.
Technology Choice
There are several choices a team can make to implement the customer’s desired functionality in the product. Depending on your available resources and development time, here are some of the choices a team might consider:
ADVERTISING
- Software only on the existing embedded processor – This may require very carefully coded models in order to achieve the desired performance. Functionality may be limited, but it is generally the lowest cost solution if it works. Because this is a software-only solution, upgrades or bug fixes are more easily addressed.
- Upgrade/replace the existing processor – This can be a great solution if you can make it work and preserve existing code base, and like the solution above, is software-only and can be easily fixed or upgraded. However, this can often start a project down a slippery path that requires extensive power and performance evaluation. Companies may be better off adding a neural network (NN) or similar accelerator.
- Add a fixed neural network accelerator – This is an optimum choice if there is a good match with the needs of the application, as evaluation and design may not be too difficult. It could very well provide excellent power/performance tradeoffs at a very reasonable cost.
- FPGA – This solution is flexible and upgradable, but typically comes with high cost and high power for the final product. Rarely is this a good choice for “edge” products.
- Dedicated SoC – Often this is the optimum choice for high volume, low cost and low power products where use cases are clearly defined.
It can be difficult to evaluate the right choice without expertise from trained professionals in the edge AI chip space. Evaluation of each option can often take a long time and require extensive knowledge. For example, evaluating a fixed accelerator versus an FPGA implementation can require engineers with different skill sets. With so many vendors and solutions making conflicting claims, making basic decisions can be overwhelming for most enterprises.
One of the most important steps one can take is to find the right partner who can help evaluate the technology tradeoffs and take the company from the initial research and evaluation stage to the design and implementation of the solution. Also, don’t get hung up on finding the solution with the “optimum” power/performance. If you can identify a solution that will work and has adequate software and technical support, that is likely your best choice. Don’t get caught chasing specs.
Building The Solution
Once functionality and technology have been chosen, the next step is implementation. Often the focus is on the implementation of a neural network model, however businesses also have to deal with the implementation of logic (software/hardware) to handle the pipeline from sensor to final output, requiring unique algorithms at each step.
Questions that might come up include:
- What kind of signal conditioning/filtering do I need before passing the data to a NN accelerator?
- Which NN model should I use? Is there an existing model for my technology selection? Which version of which model is best in my application?
- How do I train my model? Where do I get my data and what biases are built into that data? What volume of data do I need?
- What is the cost and availability of the processing power for training models? Do we train in the cloud or on local servers?
- What level of accuracy is adequate? Is it better to have false positives or false negatives?
- What post processing is required and can I handle that workload?
With so many vendors voicing conflicting claims, it is important for businesses looking to implement edge AI not to focus on finding the “best TOPS” or the “fastest” solution, as these are elusive goals. The best way to answer many of these questions of functionality, technology choice and implementation is to partner with a person or organization that has “been there, done that.” Someone with the experience to quickly evaluate potential use cases, technical solutions and vendor offerings to help you narrow your choices as quickly and accurately as possible. Focus on vendors that have the most complete solution, with both the engine to implement, but also models, algorithms, and even existing data to help you in your unique use case and create a solid proof of concept.
|
Rise from the ashes
Regular
Couldn't find the Vorago thread so may as well drop this here.
www.nasa.gov
CAPSTONE Launches to Test New Orbit for NASA’s Artemis Moon Missions - NASA
NASA’s CubeSat designed to test a unique lunar orbit is safely in space and on the first leg of its journey to the Moon. The spacecraft is heading toward an
www.nasa.gov
Dhm
Regular
Hi @Rocket577 I was all set to email Douglas Fairbiarn but just realised he is batting for our team. Go MegaChips! And go Brainchip. He could have dropped a sly Brainchip hint, but I’m happy with his support.Implementing edge AI: Look before you leap - Embedded.com
Companies looking to adopt edge AI often find it to be a difficult challenge, but what makes it so difficult, and what solutions exist to solve thiswww.embedded.com
Implementing edge AI: Look before you leap
June 28, 2022 Douglas Fairbairn
As the need for artificial intelligence grows more common and technology needs become more sophisticated, companies looking to adopt edge AI into their products often find it to be a difficult challenge. But what makes it so difficult, and what solutions exist to solve this problem?
Perhaps the single biggest issue that companies face in implementing edge AI is that most companies don’t have the resources in house to develop these sophisticated fast-changing technologies. Lack of trained personnel and little familiarity with design flow often leads to delayed timelines and excess expense to train team members. In addition, there are so many choices, it is impossible for engineers to explore each option. And since every application is different, it may not be appropriate to replicate solutions based on past implementations. However, by asking a few key questions and finding the right partner to take your project from ideation to silicon, any enterprise can develop a roadmap to successfully deploy edge AI in their devices.
Defining Use Cases And Feasibility
ADVERTISEMENT
SCROLL DOWN TO CONTINUE READING
It is important to define use cases before exploring implementation options. The first question any business should ask is: What would the customer find truly useful? After pinpointing the functionality the customer wants, your team needs to set development and production cost goals along with the acceptable time to market.
Now comes the challenging part – making technology-related decisions. Is it possible to implement that functionality within the cost, time, power and space tradeoffs you’re dealing with? Working with an experienced partner/consultant or drawing on internal experience is critical at this stage. You won’t have perfect data on which to base your decision, so actual experience is essential in making these judgements.
Technology Choice
There are several choices a team can make to implement the customer’s desired functionality in the product. Depending on your available resources and development time, here are some of the choices a team might consider:
ADVERTISING
How To Evaluate The Right Choice
- Software only on the existing embedded processor – This may require very carefully coded models in order to achieve the desired performance. Functionality may be limited, but it is generally the lowest cost solution if it works. Because this is a software-only solution, upgrades or bug fixes are more easily addressed.
- Upgrade/replace the existing processor – This can be a great solution if you can make it work and preserve existing code base, and like the solution above, is software-only and can be easily fixed or upgraded. However, this can often start a project down a slippery path that requires extensive power and performance evaluation. Companies may be better off adding a neural network (NN) or similar accelerator.
- Add a fixed neural network accelerator – This is an optimum choice if there is a good match with the needs of the application, as evaluation and design may not be too difficult. It could very well provide excellent power/performance tradeoffs at a very reasonable cost.
- FPGA – This solution is flexible and upgradable, but typically comes with high cost and high power for the final product. Rarely is this a good choice for “edge” products.
- Dedicated SoC – Often this is the optimum choice for high volume, low cost and low power products where use cases are clearly defined.
It can be difficult to evaluate the right choice without expertise from trained professionals in the edge AI chip space. Evaluation of each option can often take a long time and require extensive knowledge. For example, evaluating a fixed accelerator versus an FPGA implementation can require engineers with different skill sets. With so many vendors and solutions making conflicting claims, making basic decisions can be overwhelming for most enterprises.
One of the most important steps one can take is to find the right partner who can help evaluate the technology tradeoffs and take the company from the initial research and evaluation stage to the design and implementation of the solution. Also, don’t get hung up on finding the solution with the “optimum” power/performance. If you can identify a solution that will work and has adequate software and technical support, that is likely your best choice. Don’t get caught chasing specs.
Building The Solution
Once functionality and technology have been chosen, the next step is implementation. Often the focus is on the implementation of a neural network model, however businesses also have to deal with the implementation of logic (software/hardware) to handle the pipeline from sensor to final output, requiring unique algorithms at each step.
Questions that might come up include:
Final Words Of Advice
- What kind of signal conditioning/filtering do I need before passing the data to a NN accelerator?
- Which NN model should I use? Is there an existing model for my technology selection? Which version of which model is best in my application?
- How do I train my model? Where do I get my data and what biases are built into that data? What volume of data do I need?
- What is the cost and availability of the processing power for training models? Do we train in the cloud or on local servers?
- What level of accuracy is adequate? Is it better to have false positives or false negatives?
- What post processing is required and can I handle that workload?
With so many vendors voicing conflicting claims, it is important for businesses looking to implement edge AI not to focus on finding the “best TOPS” or the “fastest” solution, as these are elusive goals. The best way to answer many of these questions of functionality, technology choice and implementation is to partner with a person or organization that has “been there, done that.” Someone with the experience to quickly evaluate potential use cases, technical solutions and vendor offerings to help you narrow your choices as quickly and accurately as possible. Focus on vendors that have the most complete solution, with both the engine to implement, but also models, algorithms, and even existing data to help you in your unique use case and create a solid proof of concept.
For those following my golfing around Scotland, The Machrie course on Islay is a must do, especially if it is followed by a visit to Laphroaig distillary.
Similar threads
