wilzy123
Founding Member
FF , has Brainchip got one of our chips involved with assisting a NASA rockettravel to the moon ?
Yep, whatever FF says... bank on it.
Not financial advice. DYOR.
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Yep, whatever FF says... bank on it.
Not financial advice. DYOR.
FJ-215
Regular
Petrol or electric?Have you heard of this thing called a chainsaw?
FJ-215
Regular
AusEire
Founding Member.
You still owe me a beerOk mate thanks for that.
I might have to buy a pair of specs to straighten the lines next time and if that fails I’ll just ask you to confirm if I’m ever not sure
Flick me a message when you’re back in Perth, the home of Brainchip’s HQ (fk you @AusEire ) and we can grab a beer or two
Stay safe mate and enjoy the island!
wilzy123
Founding Member
Fact Finder
Top 20
Hi @Frank ZappaFF , has Brainchip got one of our chips involved with assisting a NASA rocket
What we have on this question or should I say the closest we have is a statement made Professor Iliadis at Democratis University of Thrace that NASA was using AKIDA for navigation in space to a university newspaper after the deal for his spiking neural network cyber security algorithm was licensed to Brainchip.
My opinion only DYOR
FF
AKIDA BALLISTA
alwaysgreen
Top 20
Purely based on his name, I reckon Professor Iliadis also enjoys a little chicken gyros cooked on a spit
wilzy123
Founding Member
Sounds legit.Purely based on his name, I reckon Professor Iliadis also enjoys a little chicken gyros cooked on a spit
Fact Finder
Top 20
Petrol but I was talking to an SES fellow using an electric I have decided they are the go.
FJ-215
Regular
In order to benchmark NNs, you would need to start with a standardized heterogeneous model library for each of image and sound.Just on benchmarking & a bit of understanding....would appear we're no orphans
The Sounds Of The AI Benchmark War: Crickets
Karl Freund
Contributor
Founder and Principal Analyst, Cambrian-AI Research LLC
Follow
Apr 6, 2022,01:00pm EDT
NVIDIA once again dominated a near-empty field of AI competitors in MLPerf Inference V2.0. Let’s explore why other chip companies don’t want to play.
Industry standard benchmarks have been an important feature of the IT landscape for decades, with SPEC, TPC, and other organizations offering benchmark suites to help buyers understand what chips and systems are best for which workloads.
The AI benchmark organization MLCommons has done a great job collaborating across dozens of member companies to define a broad suite of training and inference benchmarks that represent the bulk of AI applications in the data center and the edge.
Where is everyone Else?
While the number of contributors (NVIDIA, Qualcomm and system vendors) increased dramatically, and performance improved by up to 50%, the number of chip architectures being tested dropped to two: performance-leader NVIDIA and efficiency-leader Qualcomm. Intel demurred this time around, while AWS, Google, AMD, Intel Habana, Graphcore, Cerebras, SambaNova, Groq, Alibaba and Bidu decided to skip the fun with their own chips.
I’ve spoken to a few customers about their experience running inference on these novel platforms, and in general the results are promising. So why not publish and provide a public tabulation of which chips are good at which problems? There are several reasons:
- The top reason is the lack of a good ROI. These benchmarks take a lot of engineering effort to run because most platforms will not run them well without optimizations. The effort could be better spent working with a live customer to close the deal.
- Performing those optimizations will produce a better product, but publishing the results can risky. You don’t want to be slower than NVIDIA. Frankly we suspect everyone is slower than NVIDIA on a chip-to-chip basis. So one would have to find a different way to interpret the results, as Qualcomm has done by touting energy efficiency. But,...
- Even if you have an angle, the arguments you make can easily be blunted. For example, a more energy-efficient chip sounds good, but if it is significantly slower, then a buyer may have to purchase more accelerators, reducing or even reversing the supposed advantage.
- Apples to apples comparisons are next to impossible, even in a well managed benchmark effort like MLPerf. Pricing, for example, is not considered. Nor is ease of software porting and optimization. And not everyone needs or can afford a Ferrari anyway.
- Did we mention that NVIDIA is hard to beat? Yeah, THAT. We count over 5000 results in the MLPerf Inference spreadsheet, with over 95% of them run on NVIDIA. The GPU leader simply overwhelms any startup that wants to pick a few cells and hope for the best.
So, what we end up with NVIDIA showing how much better they are than they were last year. While NVIDIA did not publish any “Hopper” benchmarks, preferring to await the AI Training regatta in six months, their engineers did publish results for the latest edge SOC, the Jetson Orin, besting its predecessor by 2 to 5X.
View attachment 22170
So, what is the outlook for MLCommons?
I believe that MLCommons provides an extremely valuable service to the industry and will continue to do so. All AI chip vendors use the suite of inference and training benchmarks to help determine performance bottlenecks and to refine their software optimizations. End users can run these open source benchmarks themselves to determine which platform best meets their needs.
As for participation, I suspect Intel will rejoin the fray to tout their Sapphire Rapids CPU, which has significant AI acceleration on board, and hopefully their new Ponte Vecchio GPU now being installed at the DOE ARNL labs. And I expect more contributions from Graphcore as well, at least in training.
That being said, I doubt that others such as AMD and AWS will step up any time soon, but the Chinese vendors might see an opportunity to show off their silicon.
But let’s acknowledge that NVIDIA is just plain hard to beat; great engineers under a great leader can do, well, great things. Also, Qualcomm has amazing energy efficiency born from over a decade of smart phone chip development and research.
Regardless of the size of the public party, however, everyone will continue to benefit from the rich set of apps and data sets that MLCommons has helped the community develop. These are real applications that cover the waterfront of AI use cases, which in and of itself is a great value to the industry.
So already there is a problem because Akida libraries are different form other libraries, being optimized for digital SNN, and then Akida can run 1-bit to 4-bit weights and activations. Very recently other companies have emerged claiming 1-bit to 8-bit, but higher bit counts are common.
So if the benchmarking is done against a model library designed for an 8-bit NN, this will not show Akida at its best.
So you need to benchmark for each of 1-bit, 2-bits, 4-bits, and 8-bits ... 32-bits ... [In CNN, the more bits, the greater the accuracy].
Then you need to identify the benchmark parameters, eg, fps, power per inference, accuracy.
Then it is further complicated by new sensor technologies like DVS (Prophesee) where Akida is incomparable, and other tasks like nViso's facial recognition. .
But we have had some benchmarking figures released recently:
[courtesy of @uiux ]
In the left chart, the orange bars illustrate the performance of Akida/GPU/CPU against the best performance model against which they were tested, while the gray bars show the average performance of each tested on 5 models. Now, assuming that each was tested against the same 5 models (otherwise the comparison is meaningless) Akida has been run against 8-bit plus models, requiring quantization before being used on Akida, unless the models were adapted for Akida before testing.
The effect of Akida's quantization is illustrated by the memory requirements shown in this chart:
So, really, it's a bit like comparing lemons with diamonds.
Last edited:
Deadpool
Did someone say KFC
Terroni2105
Founding Member
Brainchip job advertised on LinkedIn, IP Verification Engineer in Hyderabad India.
not sure what this line may mean for us:
www.linkedin.com
not sure what this line may mean for us:
- The role would include functional verification of the IP solution of Siemens/Synopsys/Cadence.
LinkedIn Login, Sign in | LinkedIn
Login to LinkedIn to keep in touch with people you know, share ideas, and build your career.
Earlyrelease
Regular
Perth WA Chippers.
As per one of my last posts the Perth Xmas drinks.
I have booked for 40 people at Samuals Bar (base of Hilton Hotel, Mill Street Perth) It is from 4-7pm on Friday evening 25 November. This is an opportunity to catch up put a face to a TSE name, have a laugh, realize that we are all mom and dads (mostly) who kid ourselves we are Warren Buffet's, but hell its better than talking about our normal 9-5 grind. So come along. The BRN office staff are aware and may or may not attend for a quick hello depending on what break though they have had or if the market was red that day. If you could just PM if you are attending so I can add extra numbers if I have to but also so I can add new members to a local list for any future events.
Stay safe, stay strong and hold long.
As per one of my last posts the Perth Xmas drinks.
I have booked for 40 people at Samuals Bar (base of Hilton Hotel, Mill Street Perth) It is from 4-7pm on Friday evening 25 November. This is an opportunity to catch up put a face to a TSE name, have a laugh, realize that we are all mom and dads (mostly) who kid ourselves we are Warren Buffet's, but hell its better than talking about our normal 9-5 grind. So come along. The BRN office staff are aware and may or may not attend for a quick hello depending on what break though they have had or if the market was red that day. If you could just PM if you are attending so I can add extra numbers if I have to but also so I can add new members to a local list for any future events.
Stay safe, stay strong and hold long.
alwaysgreen
Top 20
We need a fellow verification engineer to assist. @chapman89 ?Brainchip job advertised on LinkedIn, IP Verification Engineer in Hyderabad India.
not sure what this line may mean for us:
- The role would include functional verification of the IP solution of Siemens/Synopsys/Cadence.
LinkedIn Login, Sign in | LinkedIn
Login to LinkedIn to keep in touch with people you know, share ideas, and build your career.
In all seriousness, surely that is confirmation that Siemens is working with us. Great find!
It's not clear what the metric to use for benchmarking would be.
Even if you say the best metric is inferences per watt, the other systems have taken many many watts just to be trained. Do you include these watts? Possibly not if you can use the model in many chips.
i.e. the akida based chip will be doing a different job in a very different way: Akida will pick up anomalies that others can't because they haven't been trained on those particular cases.
Without a metric there can be no benchmarking.
stockduck
Regular
What comes in my mind is a new technic called "iSensoric" when you search for siemens....they talk about intelligent sensors but nothing special that could leed to our IP.We need a fellow verification engineer to assist. @chapman89 ?
In all seriousness, surely that is confirmation that Siemens is working with us. Great find!
Just my opinion, do your own research.
Boab
I wish I could paint like Vincent
Perhaps we are already working with Siemens via Nviso?We need a fellow verification engineer to assist. @chapman89 ?
In all seriousness, surely that is confirmation that Siemens is working with us. Great find!
Just had a flick through this EE Times, on page 35 features MuMurtry Speirling electric car that broke the Goodwood Hill Climb in West Sussex UK. A friend of my sister actually worked on it, I've just sent him the copy of this and mentioned that Akida is on page 19 and is in the Mercedes EQXX and that he should mention it to the tech guys on the team, he said he would. McMurtrys house is about a mile from the village where my sister lives, on the end of the Cotswolds.
Similar threads
