BRN Discussion Ongoing

Hi Fmf,

I think this bit is particularly interesting, especially the choice of example of a "hardware start-up with a novel way of processing neural networks".

To assist customers with such applications, SiFive developed the new Vector Coprocessor Interface Extension (VCIX, pronounced “Vee-Six”). VCIX allows for tight coupling between the customer’s SoC/accelerator and the X280. For example, consider a hardware AI startup with a novel way of processing neural networks or one that has designed a very large computational engine. Instead of designing a custom sequencer or control unit, they can simply use the X280 as a drop-in replacement. With VCIX, they are given direct connections to the X280. The interface includes direct access into the vector unit and memory units as well as the instruction stream, allowing an external circuit to utilize the vector pipeline as well as directly access the caches and vector register file.

View attachment 25865

VCIX is designed to interface the NN to the SiFive X280.

The VCIX is a high-performance direct-coupling interface to the X280 and its instruction stream. To that end, Asanovic noted that on the X280 with the new VCIX interface, the X280 is capable of sending 1,024 bits over onto the accelerator/external component each cycle and retrieving 512 bits per cycle, every cycle sustained over the VCIX interface. [Per cycle @ 300 MHz, for example].

On the other hand, Google seem reluctant to abandon their in-house MXU and TPU:

Cliff Young, Google TPU Architect, and MLPerf Co-Founder was also part of the SiFive announcement. As we’ve seen from other Google accelerators, their hardware team always looks to eliminate redundant work by utilizing off-the-shelf solutions if it doesn’t add any real value to design it themselves in-house.

For their own TPU accelerators, beyond the inter-chip interconnect and their highly-refined Matrix Multiply Unit (MXU) which utilizes a systolic array, much of everything else is rather generic and not particularly unique to their chip. Young noted that when they started 9 years ago, they essentially built much of this from scratch, saying “scalar and vector technologies are relatively well-understood. Krste is one of the pioneers in the vector computing areas and has built beautiful machines that way. But should Google duplicate what Krste has already been doing? Should we be reinventing the wheel along with the Matrix Multiply and the interconnect we already have? We’d be much happier if the answer was ‘no’. If we can focus on the stuff that we do great and we can also reuse a general-purpose processor with a general-purpose software stack and integrate that into our future accelerators.” Young added, “the promise of VCIX is to get our accelerators and our general-purpose cores closer together; not far apart across something like a PCIe interface with 1000s of cycles of delay but right next to each other with just a few 100s of cycles through the on-chip path and down to 10s of cycles through direct vector register access
.”

Google are still dabbling with analog SNNs:
WO2020077215A1 TEMPORAL CODING IN LEAKY SPIKING NEURAL NETWORKS

View attachment 25866
Spiking neural networks that perform temporal encoding for phase-coherent neural computing are provided. In particular, according to an aspect of the present disclosure, a spiking neural network can include one or more spiking neurons that have an activation layer that uses a double exponential function to model a leaky input that an incoming neuron spike provides to a membrane potential of the spiking neuron*. The use of the double exponential function in the neuron's temporal transfer function creates a better defined maximum in time. This allows very clearly defined state transitions between "now" and the "future step" to happen without loss of phase coherence.

May be time for a little morphic resonance.

Footnote: Wonder if Cliff Young still has those gumboots?
Hey D

Cheers and agree.

Part why I thought to post these few articles I found even though a little dated.

Figured there was potentially some interesting other "between the lines" type info.

Interesting you mentioned Google & analog SNN as was reading an article earlier on Mythic (link below) but also a LinkedIn comment by a Google employee (ex IBM & NVIDIA) about Mythics issue back in Nov.

1672578279328.png



Mythic bet big on analog AI but has run out of cash​

 
  • Like
  • Wow
  • Fire
Reactions: 21 users
Now back mid year, the following came up.

So, when I read the article I could see the VPU relates to Movidius, who Intel acquired some 6 years ago (as per the article).

However, I'd like to know if any chance now or in the future if Akida has potential to be included as the AI accelerator...... be damn nice if was :)

Intel confirms 14th Gen Meteor Lake has ‘Versatile Processing Unit’ for AI/Deep Learning applications​

Published: 30th Jul 2022, 16:52 GMT


Versatile Processing Unit for deep learning and AI inference​

Intel is adding VPU to Meteor Lake and newer.

A new commit to Linux VPU driver today confirms that the company has plans to introduce a new processing unit into consumer 14th Gen Core processors, a Versatile Processing Unit.

METOER-LAKE-VPU-HERO2-1200x443.jpg


The VPU driver is included into the Linux Direct Rendering Manager (DRM), the same way their graphics driver is integrated. The VPU appears 6 years after Intel acquired a company called Movidius, which has been developing their own VPUs. It is not entirely clear if and how Intel plans to incorporate Movidius designs into Meteor Lake, it could be a full-blown SoC-like integration or just a copy of architecture bits needed for Meteor Lake. Obviously after so many years, VPU design should be much more complex.

The confirmation on VPU comes from Kerner.org patches, where the following description is added:



Intel VPU for Meteor Lake, Source: kernel.org

Thus, Intel confirms the new VPU has five components, including CPU to VPU integration unit, memory management, RISC controller, network on chip and the most important part, the Neural Compute Subsystem (NCS) doing the actual work. This VPU unit could be considered Intel’s alternative to NVIDIA’s Tensor Cores, a dedicated chip that is heavily focused on AI algorithms.

Intel Meteor Lake is now officially coming next year, eventually it should become available for mobile and desktop platforms packed with new hybrid architecture featuring Redwood Cove and Crestmont CPU cores and Intel’s newest Xe-LPG graphics architecture.

VideoCardzAlder LakeRaptor LakeMeteor Lake
Intel Mainstream CPU Roadmap (RUMORED)
Desktop Launch DateQ4 2021Q4 2022Q4 2023
CPU NodeIntel 7Intel 7Intel 4
Big Core µArchGolden CoveRaptor CoveRedwood Cove
Small Core µArchGracemontGracemontCrestmont
Graphics µArchXe-LPXe-LPXe-LPG
Max CPU Core Count16 (8C+8c)24 (8C+16c)TBC
Max GPU Core Count96 EU96 EU128-192 EU
Desktop SocketLGA1700LGA1700LGA 1851
Memory SupportDDR4/DDR5-4800DDR4/DDR5-5600DDR5
PCIe GenPCIe 5.0PCIe 5.0PCIe 5.0
Intel Core Series12th Gen Core13th Gen Core14th Gen Core
You're starting to remind me of the Energizer Bunny, mate
Thanks for all your efforts across the board with providing wonderful, interesting research. Hopefully one day get to smash a few drinks with you and listen to some Tom petty and the heartbreakers whilst laughing at the sheer amount of profits BRN have made us, also laugh at some of the WANCA'S post over at shittsville whilst I post a few flame and baiting posts.🤣
 
Last edited:
  • Like
  • Haha
  • Fire
Reactions: 17 users
My son, who has a 5 grand gaming computer, last year bought a Nintendo switch (dads coin) worth about $500, so he could play Mario Cart which he used to play as a youngster and absolutely loves the new Switch.

Most of the big selling Nintendo games including Mario, Pokémon, Animal Crossing, Super Smash Bros., Zelda, Donkey Kong, Tetris, and many more and are only available to play on the Nintendo platform.

As of September 2022, all Nintendo Switch models have sold over 114 million units worldwide, making it Nintendo's best-selling home console while all their most popular games have sold over 20 million units each worldwide.

The Nintendo switch uses Soc Nvidia Tegra X1 platform and uses Arms CPU Quad-core ARM Cortex-A57and 53 and GPU Nvidia GM20B

I seem to recall Rob saying "more of a partner than a competitor" 🧐

Nintendo was to release a new high end Switch using Nvidia (DLSS) Deep learning super sampling, but something happened that we are not privy to, and apparently have now shelved the idea in favour of a new successor to Switch.

Maybe, just maybe this new successor to Switch will have a little sticker on its lid with the words AKIDA inside and be the most powerful user interactive, yet power efficient gaming platform the world has ever seen and those sales statistics above just might look minuscule in comparison.

I will be out of pocket $1000 because my son will want the latest one, but the consolation will be the BRN share price will be rapidly approaching the Stratosphere by then.😃

Of course my opinion only.
Dude...I'd just download an emulator for him on his gaming PC and then find free ROMs or does he want it portable?

I used to use MAME when I had time....maybe I should try make some time again :(


1672578649908.png


1672578830553.png


1672578875941.png
 
  • Like
  • Fire
  • Love
Reactions: 15 users
My son, who has a 5 grand gaming computer, last year bought a Nintendo switch (dads coin) worth about $500, so he could play Mario Cart which he used to play as a youngster and absolutely loves the new Switch.

Most of the big selling Nintendo games including Mario, Pokémon, Animal Crossing, Super Smash Bros., Zelda, Donkey Kong, Tetris, and many more and are only available to play on the Nintendo platform.

As of September 2022, all Nintendo Switch models have sold over 114 million units worldwide, making it Nintendo's best-selling home console while all their most popular games have sold over 20 million units each worldwide.

The Nintendo switch uses Soc Nvidia Tegra X1 platform and uses Arms CPU Quad-core ARM Cortex-A57and 53 and GPU Nvidia GM20B

I seem to recall Rob saying "more of a partner than a competitor" 🧐

Nintendo was to release a new high end Switch using Nvidia (DLSS) Deep learning super sampling, but something happened that we are not privy to, and apparently have now shelved the idea in favour of a new successor to Switch.

Maybe, just maybe this new successor to Switch will have a little sticker on its lid with the words AKIDA inside and be the most powerful user interactive, yet power efficient gaming platform the world has ever seen and those sales statistics above just might look minuscule in comparison.

I will be out of pocket $1000 because my son will want the latest one, but the consolation will be the BRN share price will be rapidly approaching the Stratosphere by then.😃

Of course my opinion only.
Would be a dream for us to be incorporated into Nintendo products
And we definitely have a damn good chance considering our relationship with megachips who as we know have an awesome relationship with Nintendo.
Well I hope you end up being out of pocket a grand in the near future and have to buy a Nintendo product with Akida embedded inside.🤣
 
  • Like
  • Haha
  • Fire
Reactions: 15 users

Learning

Learning to the Top 🕵‍♂️
Thank you.🎆🎉🍾

Screenshot_20230102_001508_LinkedIn.jpg

It's great to be a shareholder 🏖
 
  • Like
  • Love
  • Fire
Reactions: 53 users
  • Thinking
  • Like
Reactions: 2 users
You're starting to remind me of the Energizer Bunny, mate
Thanks for all your efforts across the board with providing wonderful, interesting research. Hopefully one day get to smash a few drinks with you and listen to some Tom petty and the heartbreakers whilst laughing at the sheer amount of profits BRN have made us, also laugh at some of the WANCA'S post over at shittsville whilst I post a few flame and baiting posts.
Cheers mate.

Like your thinking 🔥

Tooo many Red Bulls today haha....nah.....I just had these book marked over past few days and just got time to actually get organised to post them

Hopefully just some additional thought provoking info in there somewhere. I found them interesting.

Bailing soon though...early morn as wanna watch to see if my Green Bay Packers beat the Vikings to keep our playoff hopes alive 🙏🤞
 
  • Like
  • Love
Reactions: 8 users
LoL, years ago I was doing the Acecard thing for Ds lites.
Had to quickly google the Acecard as not heard of.

Interesting.

I was just a sucker for the old arcade games I grew up with in the late 70 / 80s and used the emulators.

I still got my original Commodore 64 in its box / packaging with the old data cassette and floppy drive.

Got the old joysticks, about 100+ discs etc and all still works :D

Between my boys & I, we still have the PS1 to PS5 & Xbox 360 to Xbox X
 
  • Like
  • Love
  • Fire
Reactions: 16 users
Had to quickly google the Acecard as not heard of.

Interesting.

I was just a sucker for the old arcade games I grew up with in the late 70 / 80s and used the emulators.

I still got my original Commodore 64 in its box / packaging with the old data cassette and floppy drive.

Got the old joysticks, about 100+ discs etc and all still works :D

Between my boys & I, we still have the PS1 to PS5 & Xbox 360 to Xbox X
Crazy Kong, frogger, dig dug, space invaders, wonderboy in monsterland, pac man, pengo and many more at 20 cents a game which could last ages if you where half decent.
 
Last edited:
  • Like
  • Fire
Reactions: 10 users
Crazy Kong, frogger, dig dug, space invaders, wonderboy in monsterland, pack man, pengo and many more at 20 cents a game which could last ages if you where half decent.
Absolutely.

Frogger, Dig Dug, Pengo...loved them.

Was also into Defender, Centipede, Golden Axe, Galaga / Galaxian, Dragons Lair, Altered Beast, Moon Patrol...sooo good.

Don't get me wrong, today's games pretty full on, played most of em with the boys as they grew up, COD, Gears etc but something to be said for the originals.

I remember a friends older brother used to use what he called a jiggle stick for us little delinquents haha.

Bent bit of wire you fed up inside the coin return slot through a hole or something in the design, to jiggle the coin in slot wire to clock up free games.

I'll leave it that as clogging up the threads haha
 
  • Like
  • Haha
Reactions: 6 users
Absolutely.

Frogger, Dig Dug, Pengo...loved them.

Was also into Defender, Centipede, Golden Axe, Galaga / Galaxian, Dragons Lair, Altered Beast, Moon Patrol...sooo good.

Don't get me wrong, today's games pretty full on, played most of em with the boys as they grew up, COD, Gears etc but something to be said for the originals.

I remember a friends older brother used to use what he called a jiggle stick for us little delinquents haha.

Bent bit of wire you fed up inside the coin return slot through a hole or something in the design, to jiggle the coin in slot wire to clock up free games.

I'll leave it that as clogging up the threads haha
Haha. Yes we used to use the whipper snipper cord at the end bent it a little to look like the letter J.😂
 
  • Fire
  • Haha
  • Like
Reactions: 3 users
Haha. Yes we use to use the whipper snipper cord at the end bent it a little to look like the letter J.😂
That's the one

Glad we weren't the only delinquents then haha

Used to have to go to the counter every so often to get some 20c coins so they didn't get suss when we had like 99 credits and playing for ages haha
 
  • Haha
  • Like
Reactions: 6 users

Dallas

Regular
 
  • Like
  • Wow
  • Fire
Reactions: 29 users
Another one where I'd love to see us piggybacked on SiFive & Intel into the Horse Creek next year especially given the other articles and strategy that Intel are looking to execute.

Given we are now part of the IFS & have a pre-existing relationship with SiFive, I actually wouldn't be surprised to maybe see us added to the Intel Pathfinder for Risc-V down the track.



Intel, SiFive Demo High-Performance RISC-V Horse Creek Dev Platform On Intel 4 Process​

October 7, 2022 David Schor Cadence, Intel, Intel 4, Intel Foundry Services (IFS), Intel Innovation 2022, RISC-V, SiFive, Synopsys

intel-horse-creek-board-header-wc.png



Last year Intel announced the development of the Horse Creek Platform, a partnership with SiFive for the development of a new high-performance RISC-V development system as part of both the company’s Intel Foundry Services (IFS) and their effort to catalyze the adoption of RISC-V. The boards were said to be a continuation of SiFive’s own HiFive development boards designed to grow the RISC-V ecosystem and accelerate prototyping.

Early this year Intel also announced the IFS Accelerator ecosystem alliance designed to help accelerate chip prototyping and tape-outs through deep collaboration with various semiconductor partners across EDA, IPs, and design services. IFS Accelerator is a comprehensive suite of tools comprising silicon-verified Intel-process-specific optimized IP portfolio (from std cell library, memory, GP I/O, analog, and I/F IPs). Strategically, A large and vibrant ecosystem will be incredibly important for the success of Intel’s foundry strategy and IFS Accelerator is one of a piece of that. The company initially started Accelerator in September of 2021 to assist the automotive industry with transitioning to more advanced nodes, however, it has since broadened its effort into other segments.

It’s worth noting that SiFive is a member of the IFS Accelerator, saying “SiFive will enable IFS customers to create computing platforms featuring RISC-V, optimized for their market applications. Intel’s broad portfolio of IP compliments the SiFive portfolio of performance-driven processor IP such as the SiFive Intelligence and SiFive Performance families of processor IP.”


Horse Creek​

At the recent Intel Innovation 2022 Developer Conference, the company demoed Horse Creek for the first time in public. Horse Creek is a Raspberry Pi-inspired RISC-V software development board. It’s physically quite a bit larger due to a large number of integrated interfaces. For example, there’s 8 GiB of DDR5. PCIe 5.0 slot. SPI Flash contains the U-Boot, and a myriad of other monitoring and debugging interfaces.





Within 18 months, Horse Creek went from an announcement to a fully working A0 stepping chip running Linux. Manufactured on the company’s most advanced Intel 4 process, the die measures just 4 mm by 4 mm and is packaged in a 19 mm x 19 mm BGA package. The chip intends to also demonstrate the interoperability of 3rd-party controllers and IPs along with Intel’s own hard IP PHYs. As such the SoC itself integrates a number of advanced interfaces.



The SoC itself integrates quad-core SiFive P550 RISC-V cores. Each core features private L1 and L2 caches with a shared last-level cache – all operating at 2.2 GHz. At the time of tape out those were the highest-performance RISC-V cores. Note that since SiFive actually announced next-generation P650 cores, surpassing them in performance. The SoC integrates Intel’s own PCIe 5.0 PHY with x8 lanes along with Synopsys PCIe 5 Controller. It also integrates Intel’s DDR5 PHYs supporting 5600 MT/s rates along with Cadence’s memory controller. Other Intel’s own Intel 4 IPs include 2 MiB of shared SRAM (part of their memory compiler), process monitor, caches, Power/Clock/PLLs, electronic fuses, JTAG, and various cell libraries.



Horse Creek boots up Linux, and Intel demonstrated the chip executing a video game (running on the CPUs as there is no GPU) along with various other applications (media player, playback, browser, etc).


Pathfinder for RISC-V​

About a month ago Intel also announced Intel Pathfinder for RISC-V, a rapid prototyping development environment for system integrators. Essentially, it’s a suite of IPs, middleware, open-source, and 3rd party tools along with OS support designed to simplify the exploration of pre-silicon RISC-V-based designs. Intel said it is partnering with commercial and open-source RISC-V IP providers to enable a consistent environment for software development across different RISC-V-based processors. On the commercial side, RISC-V core IPs include those from Andes, Codasip, SiFive, MIPS, and others. Pathfinder includes a number of FPGA platforms for RISC-V chip emulations. The starter edition utilizes the Terasic Developer Kit for Intel Pathfinder while the commercial tools include boards based on the Stratix 10 GX for full chip emulation capabilities.



No availability date for the new Horse Creek Dev boards has been announced yet.
Just something a little more recent on Pathfinder for more background.

Hope we get a berth.

I see Renesas in the mix too.




Intel simplifies access to Pathfinder for RISC-V and adds 14 new partners​

December 8, 2022 Nitin Dahad
Intel Pathfinder for RISC-V merges Starter and Professional editions to ease user transitions, and 14 new ecosystem partners are added.



Intel has simplified access to its Pathfinder for RISC-V initiative by unifying its starter and professional editions and added 14 new ecosystem partners with an array of new features, taking the total number of industry partners to 33.

Designed for SoC architects and system software developers, Intel Pathfinder for RISC-V is a pre-silicon development environment that supports IP selection via testing for compatibility and performance, as well as early-stage software development using Intel FPGA and simulator platforms. Previously users had to select which edition they wanted, but now it has unified its Starter and Professional editions. Intel said this merger into a single product is to ease user transitions; individual users can download the new version with its enhanced features, and commercial developers can use the same version and request custom extensions for vendor-specific capabilities required for their projects.
The new features include:

  • Static kernel debug for users wanting to debug the Linux kernel.
  • Multi-core support via SMP Linux.
  • A new FMC add-on board available in Q1’23 using Intel Stratix 10 GX FPGA development board enabling new I/O interfaces and simplifying connectivity.
  • A new Intel Cyclone 10 GX FPGA development board to be supported in Q1’23, enabling lower cost and additional flexibility.

Intel’s general manager for RISC-V Ventures, Vijay Krishnan, said to embedded.com, “Since the launch of Intel Pathfinder for RISC-V, we have added 14 new ecosystem partners to strengthen the initiative for a total of 33 industry partners. Furthermore, we are starting to see the value of Intel Pathfinder for RISC-V flow downstream from pre-silicon development to silicon. Examples from today’s announcement are the regenerative agriculture solution (using Renesas RISC-V SoC) and the decision of EMASS to sample their silicon BSP with our IDE. PES University in India is using our product to train students, Codasip is incorporating us in their university program, and UC Santa Barbara is driving innovative manycore designs with Intel Pathfinder. So our presence in academia and research is also growing.”

He added, “While we cannot share specific numbers, we are on course to hitting our internal goals for the total number of downloads for 2022. The current momentum gives us great impetus in terms of adding more capabilities and customers in 2023. Maintaining a torrid pace of execution and fostering ecosystem collaboration are key imperatives for Intel Pathfinder for RISC-V.”

Intel’s chief strategy officer and senior vice-president, Saf Yeboah, said, “Intel Pathfinder for RISC-V highlights Intel’s strategic investments in accelerating the adoption of open architectures, with the ultimate goal of creating greater value and choice for end-users.”

Ecosystem partners add new features

Open-source simulator supporting a breadth of RISC-V models

Antmicro and Intel’s cooperation enables easier architectural exploration and pre-silicon development by providing vector instruction-capable RISC-V platform simulation in Renode for Intel Pathfinder in early 2023. Renode is an open-source software development framework with commercial support from Antmicro that allows development, debug and test of multi-node device systems reliably, scalably and effectively. Tim Ansell, a software engineer at Google, said,

“Renode gives you the ability to do a lot of work on real-world objects without ever having to have any hardware. It allows you to have continuous integration systems which run very comprehensive test suites without having to set up bespoke hardware CI systems. This makes it a powerful framework for testing, and in fact it has enabled significantly more insight into product development.”

New floating-point unit for RISC-V cores

CalligoTech has designed posit numeric unit (PNU) IP, a coprocessor for real-number computations using POSITs – a new number system with higher accuracy and better dynamic range, at reduced power. Within the Intel Pathfinder for RISC-V developer environment, the company will enable its PNU with CORE-V CVA6 cores and enhanced RISC-V Compilers (C/C++/gFortran).

Enhanced audio capabilities for hearables, wearables and smart home devices

CEVA announced that its CEVA-BX1 and CEVA-BX2 audio DSP IP will be available with Intel Pathfinder for RISC-V in the Q1’23 timeframe, enabling customers to evaluate best-in-class DSP and audio front-end software IPs from CEVA combined with RISC-V based host platforms.

Bringing RISC-V cores and tools to education institutes

Codasip is collaborating with Intel to enable undergraduate and graduate level courses that will benefit from Codasip RISC-V IP and Intel Pathfinder for RISC-V. The goal is to be integrated into courses at multiple universities in the fall of 2023.

Ultra-low power SoC for AIoT

Embedded A.I. Systems (EMASS) has announced its intent to deliver engineering samples of the edge AI SoC named ECS-DoT in Q1’23. Its board support package (BSP) integrates Intel Pathfinder for RISC-V IDE and combined with the ultra-low power consumption of our SOC, could potentially unlock new capabilities and use cases for customers in the AIoT segment.

Combining RISC-V with neuromorphic accelerators

General Vision has combined its NeuroMem technology with RISC-V host processors and Intel Pathfinder for RISC-V developer tools to enable next generation real time learning pattern recognition featuring low latency and ultra-low power.

RISC-V cores and SoC reference designs for efficient scaling

G S Madhusudan, CEO & co-founder, InCore Semiconductors, said, “As we roll-out a comprehensive range of RISC-V commercial we see a synergistic opportunity to use Intel Pathfinder for RISC-V as the IDE that will enable our customers and SoC design partners to scale efficiently. InCore is keen to grow this collaboration with Intel to take full advantage of the massive customer interest in RISC-V based SOCs by providing a comprehensive, class leading development environment.”

Solution for regenerative agriculture

LATERAL.systems is applying innovative edge solutions utilizing AI-driven predictive analytics in supporting regenerative agriculture to provide farmers rich data insights that enable food safety, optimal crop quality and higher yields. Combining LATERAL’s edge platform application-level capabilities with IOTech middleware, RISC-V silicon and Intel Pathfinder for RISC-V, the company plans to field test its solution targeting the indoor farming community in 2023. IOTech has been working with Intel Pathfinder for RISC-V since its launch.

Renesas is providing customers a new option of RISC-V based MPU with RZ/Five, ideal for use cases such as industrial gateways and controllers. Andes said Intel Pathfinder for RISC-V enables its customers’ software development using open-source tools, FPGA platforms for early SoC development and verification, and easy migration path from FPGA to ASIC via Intel Foundry Services.

RISC-V within the engineering curriculum

PES University, a teaching and research institute in India, has already revamped the computer architecture course within the undergraduate program to be entirely on RISC-V. PES is also partnering with Intel to enable its students to use Intel Pathfinder for RISC-V as a development tool.

RISC-V design services

Prodapt has joined Intel’s ecosystem by actively promoting Intel Pathfinder for RISC-V as a developer tool for its design services customers.

USB controller for Intel Pathfinder for RISC-V

System Level Solutions (SLS) announced support for Intel Pathfinder for RISC-V via its USB host and device controller IP for the Intel Cyclone 10 GX development board, which is a recent addition to the family of Intel FPGA boards supported by Intel Pathfinder for RISC-V. SLS hopes to expand this relationship over time by providing peripheral IP that will accelerate the adoption of RISC-V across FPGA and ASIC designs.

RISC-V reference designs

Tessolve is working to enable its first RISC-V based SOC reference design in early 2023, using Intel Pathfinder for RISC-V as the preferred development environment. Tessolve said it would work with Intel to implement these reference designs to drive cost-effective and rapid scaling of RISC-V based designs.

Exploring CORE-V CVA6 open-source manycore RISC-V architectures

The University of California Santa Barbara is collaborating with Intel within the OpenHW ecosystem on research that will enable octa-core and higher configurations of the open-source CORE-V CVA6 RISC-V cores with Intel Pathfinder for RISC-V. Over time, it expects this work will benefit RISC-V developers across academia, research, and commercial organizations
 
  • Like
  • Fire
  • Love
Reactions: 21 users
  • Like
  • Love
  • Fire
Reactions: 14 users
With the earlier talk of Nintendo, did a quick search and got these post thoughts by a Harvard Digital Innovation and Transformation MBA student.

Trust we may still have some opps in the controllers, eye tracking etc areas if Nintendo are looking at DLSS.

NVIDIA also have a special CES broadcast event on the 3rd.




Nintendo + Nvidia: Applying Machine Learning to Disrupt the Value Chain​

By Jonathan
Student
POSTED OCT 4, 2022

blog-post-pic-1_small-519x200.jpg



Nintendo’s application of machine learning to its handheld gaming device breaks down supply barriers and opens strategic opportunities.

Company Background and Problem Introduction​

Not many can fault Nintendo for lack of innovation – of the 10 best selling video game consoles of all time, five belong to the Japanese giant, with standout mentions going to the Wii (101.6 MM units) as the 7th best-selling console and the Switch (111 MM units) as the 5th best-selling console. However, much of what has made these consoles so attractive for gamers – novel incorporation of full-body motion and full portability – usually comes at the cost of lower graphical fidelity or a sacrifice in frame rates per second (FPS), two attributes that are usually key drivers of console and game title purchases. These non-consequential tradeoffs usually split Nintendo’s addressable market, since many “core” gamers will forgo a lower-resolution adventure with a spunky Italian plumber for a more visually immersive experience that involves shooting life-like bullets at beautifully rendered space aliens.

The graphics comparison starkly favors PlayStation’s machines vs. Nintendo’s in FIFA 2021

The Introduction of Machine Learning​

That might all change with Nintendo’s latest announcement that a new, Nintendo Switch Pro, empowered with an Nvidia-produced DLSS 3.0 graphics card, might be in the works for 2022. DLSS stands for deep learning super sampling, and it allows machines that don’t have the physical space for large graphics cards to produce high-resolution images without taxing visual performance (i.e., FPS) to a crawl. Nvidia achieves this by first training its AI models with high-resolution scans, so the AI knows what a stunning resolution “should” look like. After training the AI, it is calibrated so it can match high-end resolutions with low-end inputs.

Putting it all together, DLSS then samples multiple lower resolution images and uses motion data and feedback from prior frames to reconstruct native quality images. As the AI reconstructs the image, its effectively “filling in the gaps” that exist between the low-quality input and the desired high-quality native output. The best part is DLSS does all of this offline, which frees up the GPU to produce more FPS, rather than visual fidelity. As a KPI, this improves FPS by as much as 50% — a staggering lift that was previously only possible by OEM’s making costly investments in larger and clunkier GPUs.




Here, we can see the algorithm begin to apply texture resolution as it “learns” from the native training stimulus

Flight Simulator — one of Microsoft’s most popular titles — is notorious for being taxing on GPUs and FPS; here, we see DLSS rendering an almost identical presentation while outputting a ~100% increase in FPS

Supply Advantages for Nintendo​

This would provide tremendous strategic opportunity to Nintendo, from both a supply and demand perspective. On the supply side: first, by removing the previous graphical barrier to entry that has plagued Nintendo’s machines for years, it incentivizes game studios to design with Nintendo’s hardware in mind, which would accommodate same day console releases for the Switch (usually, ports to the Switch come months after a title’s original release on other platforms), a key factor in driving unit sales on a given platform. Second, it frees up Nintendo to continue innovating with its hardware design, already one of Nintendo’s core competencies. Third, as consumers clamor for better graphics, it reduces expenditures in the short and long term, as more powerful GPUs are more costly for OEMs to implement.

Tangentially, it would also give Nintendo tighter control over its own vertical integration, as software updates can be remotely applied to the ML-enabled chip by Nvidia, meaning Nintendo would invest less capital and manpower to update its hardware production facilities.

Less restrictions around the hardware frees up software partners to begin designing content with Nintendo consoles in mind, as opposed to having them as an afterthought.

Demand Opportunities for Nintendo​

On the demand side: by boosting the Switch’s ability to render games at a high-resolution, Nintendo can now pursue demanding, competitive-minded “core gamers” that were previously out of reach. While this was previously unheard of, (the garden walls that once separated Xbox players from playing with PlayStation players led to tightly entrenched platform fanatics), as more and more games are being released with platform-agnostic, cross-play functionality (i.e., anyone with a copy of the game can play with anyone else), the choice of which console to buy a game for has become largely a hardware question. As DLSS narrows the performative gap between consoles, we would expect to see more Call of Duty players on a Switch than we’ve seen before. In addition to reaching disparate audiences, DLSS also enables Nintendo to deliver a more compelling value proposition to its current target customers. While all game developers and OEMs would benefit from DLSS, Nintendo is in a better position to extract value because it boasts a wide assortment (arguably, the widest) of highly sought-after console-exclusives. Right now, PlayStation is the largely undisputed paragon of providing fully immersive, beautiful single player experiences. If Nintendo can fully harvest DLSS, it can provide the same immersive experiences boasted by PlayStation’s titles, but because it has more valuable intellectual properties in its portfolio, it can compete at a higher level.
 
  • Like
  • Love
  • Fire
Reactions: 30 users
@Fredsnugget some reason can't quote you possibly because you wrote your reply in my quoted post 😂
That's just the right amount madness to your method 😄 those kids are going to be nicely set up with those parcels in the future. You're a good Dad ♥️
I don't know about the rest of the holders but I'm so damn excited about CES event it's been a longtime coming to finally be able to witness Akida in all its glory embedded into products. A defining time for Peter A J van der Made and Anil Shamrao Mankar.
And to all the others that have made this possible. LoL I could yell with excitement right now.
Unbelievable this actually works 👇

 
Last edited:
  • Like
  • Haha
  • Love
Reactions: 17 users

FlipDollar

Never dog the boys
Happy new year to all the brainiacs here. This year is shaping up nicely to be a good year for us, and if not there's always the next one. One thing is for sure, it will happen and I'm willing to wait. My holding is going nowhere and I've convinced the kids their shares we got them are long term. Hopefully the 50k shares each will set them up. Got them at 6c for them so the only way is up.
I dont contribute much here but appreciate the research many do and read daily.
May health and prosperity follow us all wherever we may be.
Bring on 2023
50k shares is plenty good - what a legend of a dad!
 
  • Like
  • Fire
  • Wow
Reactions: 12 users
  • Like
  • Fire
Reactions: 39 users

Foxdog

Regular
Hey FF, you've often mentioned to have a plan when it comes to an investment in BRN. I'm wondering what this actually looks like (although I know the specific details differ for each individual).
Do you have a target SP in mind at which you'll reduce your holdings by a certain % to fund lifestyle, pay off any debt etc, while keeping the remainder of your portfolio intact until the next SP milestone? For example: when the SP reaches $5 reduce holdings x 30% (to pay off mortgage or buy a yacht) and then hold the remainder until, say $7.50 at which point reduce by another 10-15%.
If so, is there flexibility to adjust for fundamentals i.e. in the above example at $5 would you hold if an upcoming CES promised an announcement of new tech that could see the SP rise in the short term, hoping to skim off 30% at a higher price?

Not seeking investment advice but simply wondering if a plan involves 'targets' and how disciplined one should be if/when those targets are reached.

Of course this assumes that the SP will actually continue to rise 😎

Cheers Fd
 
  • Like
  • Fire
Reactions: 18 users
Top Bottom