Techinvestor17
Regular
We’re does this slide come from?Got to wonder what the market cap will be if all these chips are a raging success.
View attachment 27557
We’re does this slide come from?Got to wonder what the market cap will be if all these chips are a raging success.
View attachment 27557
You’re a champion Dio
“Perhaps” you may need to check their website and do some reading.Cerence is a software company which delivers software solutions running on all kinds of hardware. You can squeeze out Akida like a lemon it will not fit into software I fear.
Bring on Australia Day Luca !Yes, @Dhm! Prophesee is getting the word out, like upcoming Jan 25th TinyML Presentation!
Go Luca Verre, spread the word of the Brainchip Akida, sitting on the pole (love it @TECH)!
https://www.tinyml.org/event/tinyml-trailblazers-series-tinyml-success-stories-with-luca-verre
View attachment 27625
In archery it's not so good, in bombing, you're spot on.
Holy sheet Dio.When comparing chalk and cheese, are we talking camembert or parmesan?
Perceive's figures are for the YOLO V5 database.
In 2019, the Akida simulator did 30 fps @ 157 mW on MobileNet V1.
View attachment 27636
I don't have the fps/W figures for the Akida 1 SoC performance, so if anyone has those to hand, it would be much appreciated.
The chip simulator seems to have topped out at 80 fps. We know Akida 1 SoC can top 1600 fps (don't recall what database), which is 20 times faster than the simulator, so it wouldn't even get into second gear doing 30 fps.
Back in 2018, Bob Beachler said they expected 1400 frames per second per Watt.
https://www.eejournal.com/article/brainchip-debuts-neuromorphic-chip/
So 30 fps would be 20 mW if there is a linear dependence. And, of course, we were told that the SoC performed better than expected.
But the main thing is that the comparison databases need to be the same as performance varies depending on database.
Perceive relys on compression to achieve extreme sparsity by ignoring the zeros in the multiplier.
US11003736B2 Reduced dot product computation circuit
View attachment 27638
[0003] Some embodiments provide an integrated circuit (IC) for implementing a machine-trained network (e.g., a neural network) that computes dot products of input values and corresponding weight values (among other operations). The IC of some embodiments includes a neural network computation fabric with numerous dot product computation circuits in order to process partial dot products in parallel (e.g., for computing the output of a node of the machine-trained network). In some embodiments, the weight values for each layer of the network are ternary values (e.g., each weight is either zero, a positive value, or the negation of the positive value), with at least a fixed percentage (e.g., 75%) of the weight values being zero. As such, some embodiments reduce the size of the dot product computation circuits by mapping each of a first number (e.g., 144) input values to a second number (e.g., 36) of dot product inputs, such that each dot product input only receives at most one input value with a non-zero corresponding weight value.
1. A method for implementing a machine-trained network that comprises a plurality of processing nodes, the method comprising:
at a particular dot product circuit performing a dot product computation for a particular node of the machine-trained network:
receiving (i) a first plurality of input values that are output values of a set of previous nodes of the machine-trained network and (ii) a set of machine-trained weight values associated with a set of the input values;
selecting, from the first plurality, a second plurality of input values that is a smaller subset of the first plurality of input values, said selecting comprising (i) selecting the input values from the first plurality of input values that are associated with non-zero weight values, and (ii) not selecting a group of input values from the first plurality of input values that are associated with weight values that are equal to zero;
computing a dot product based on (i) the second plurality of input values and (ii) weight values associated with the second plurality of input values.
ASIDE: This isn't relevant to the discussion, but I stumbled across it just now and it shows that we developed a dataset for MagikEye in 2020, which I had not observed before.
View attachment 27637
SHORT ARTICLE ON SOCIONEXT AFTER THEY PUBLICLY LISTED LAST YEAR, SOCIONEXT ARE ONE OF BRN'S CLOSET PARTNERS
Japanese IC designers staged their biggest IPO
Compiled by Liu Zhongyong/Comprehensive External Electricity Tuesday, January 17, 2023 9:20 AM Japanese chip designer Socionext's stock has nearly doubled since its initial public offering in October to become the best performer among recent new listings of similar size or larger, reflecting investors' bullish view of the company's unique business model. Socionext's share price has jumped 82 percent since it went public on October 12 to raise 76.8 billion yen ($602 million), Japan's biggest IPO last year, closing at 6,660 yen on the 16th. According to Bloomberg Rounding, Socionext posted its best performing stock in the first three months of new listings in nearly 20 years. Amid concerns about rising interest rates and high inflation, the IPO market is not in good shape, and Socionext has become a rare leader. SMBC Nikko Securities analyst Takeshi Hanaya reported this month that the company is expected to generate stable revenue and profit growth due to its "unique solutions from system design to production and quality management that meet the unique needs of customers." Socionext develops dedicated consumer, automotive, and industrial chips for customers. It has become a trend for enterprise customers to use dedicated chips, and Faraday, Sechip, and Creative Electronics are all competitors of Socionext. According to reports, in addition to the Japanese factory, Socionext has 60% of its products entrusted to Taiwanese manufacturers, TSMC and UMC are its suppliers, and last year announced a cooperation with TSMC to develop 5nm automotive chips. Socionext was founded in 2015 by the merger of the system-on-chip businesses of Fujitsu Semiconductor and Panasonic. [See original link]
For those that have not watched this before,
As Molly would say,
" Do yourselves a favour "
One of only a few stocks that didn’t go backwards in the technology sector.SHORT ARTICLE ON SOCIONEXT AFTER THEY PUBLICLY LISTED LAST YEAR, SOCIONEXT ARE ONE OF BRN'S CLOSET PARTNERS
Japanese IC designers staged their biggest IPO
Compiled by Liu Zhongyong/Comprehensive External Electricity Tuesday, January 17, 2023 9:20 AM Japanese chip designer Socionext's stock has nearly doubled since its initial public offering in October to become the best performer among recent new listings of similar size or larger, reflecting investors' bullish view of the company's unique business model. Socionext's share price has jumped 82 percent since it went public on October 12 to raise 76.8 billion yen ($602 million), Japan's biggest IPO last year, closing at 6,660 yen on the 16th. According to Bloomberg Rounding, Socionext posted its best performing stock in the first three months of new listings in nearly 20 years. Amid concerns about rising interest rates and high inflation, the IPO market is not in good shape, and Socionext has become a rare leader. SMBC Nikko Securities analyst Takeshi Hanaya reported this month that the company is expected to generate stable revenue and profit growth due to its "unique solutions from system design to production and quality management that meet the unique needs of customers." Socionext develops dedicated consumer, automotive, and industrial chips for customers. It has become a trend for enterprise customers to use dedicated chips, and Faraday, Sechip, and Creative Electronics are all competitors of Socionext. According to reports, in addition to the Japanese factory, Socionext has 60% of its products entrusted to Taiwanese manufacturers, TSMC and UMC are its suppliers, and last year announced a cooperation with TSMC to develop 5nm automotive chips. Socionext was founded in 2015 by the merger of the system-on-chip businesses of Fujitsu Semiconductor and Panasonic. [See original link]
For those that have not watched this before,
As Molly would say,
" Do yourselves a favour "
Hi TeroniI just had a thought - with all the lay offs happening at Google, Microsoft, Meta, Amazon etc there might be some high class people applying for any jobs going at Brainchip
Hi Teroni
I would think that all these companies are pruning the dead wood for the spring, as winter has been long and very cold with no growth.
With the warmth of spring comes new growth and hopefully fruit
Brainchip will bare fruit
I personally can’t wait to taste what the good weather will bring.
Duy-Loan Le
Her 4 criteria for choosing a job.
2023 is a year of the Water Rabbit, starting from January 22nd, 2023 (Chinese New Year), and ending on February 9th, 2024 (Chinese New Year's Eve). The sign of Rabbit is a symbol of longevity, peace, and prosperity in Chinese culture. 2023 is predicted to be a year of hope.Happy Prosperous New Year to all.
Wishing BrainChip Inc and all its Shareholders a Prosperous and Successful year.
Learning
For those that have not watched this before,
As Molly would say,
" Do yourselves a favour "