The NEW Chip Inside Your Phone! (NPUs)

Рет қаралды 289,775

Ай бұрын

Check out the MSI MAG 1250GL PCIE5 at lmg.gg/FDM5n
Thanks to Dr. Ian Cutress for his help with this video! Check out his blog and KZfaq channel:
morethanmoore.substack.com/
/ techtechpotato
Neural processing units (NPUs) such as Apple's Neural Engine or the machine learning engine on Google Tensor chips can be found on the iPhone and the Pixel. How do they help run AI right on your phone?
Leave a reply with your requests for future episodes.
► GET MERCH: lttstore.com
► GET EXCLUSIVE CONTENT ON FLOATPLANE: lmg.gg/lttfloatplane
► SPONSORS, AFFILIATES, AND PARTNERS: lmg.gg/partners
FOLLOW US ELSEWHERE
---------------------------------------------------
Twitter: / linustech
Facebook: / linustech
Instagram: / linustech
TikTok: / linustech
Twitch: / linustech

Пікірлер: 596

@xxCEOofRacism69420xx Ай бұрын

Why does this feel like I'm watching techquickie in 2016

@peanutnutter1 Ай бұрын

Because past Linus is back.

@drdennsemann Ай бұрын

and because the Greenscreen Footage looks awful with that lack of contrast and the backgrounds banding gradient.

@ilovefunnyamv2nd Ай бұрын

@@drdennsemann Now that you mention it, doesn't that look like the same outfit Linus Wore in the downsizing video?

@jakubpakos4225 Ай бұрын

It's because Linus has no beard, he looks younger now without it

@twelfsauce6358 Ай бұрын

It was all an experiment where they tried to use 50 google pixels npu's and 2016 footages of linus to make a techquickie

@mrknighttheitguy8434 Ай бұрын

I'm sorry Dave, I can't do that...

@yensteel Ай бұрын

Perfect meme for Dave2D!

@moofey Ай бұрын

Open the pod bay doors, HAL

@a.i.privilege1233 Ай бұрын

Can I trust any companies with my info/data? The answer is no.

@piadas804 Ай бұрын

And you probably still use Windows

@macy1066 Ай бұрын

Then you don't have a cell phone?

@Random_dud31 Ай бұрын

@@piadas804wow. What a lucky guess. I would have never thought that. I mean the user base is so small. I mean, windows is only has a 70% market share. I would have never to guess he used windows

@piadas804 Ай бұрын

@@Random_dud31 Windows is pure spyware

@592Johno Ай бұрын

You missed the fucking point@@Random_dud31

@roomie4rent Ай бұрын

I'm starting to feel the definition of "AI" or "AI-enabled features" is expanding in scope to encompass what was just traditional software before. Facial recognition software, for example, has existed long before ChatGPT.

@bakto2122 Ай бұрын

Well, machine learning has been called AI since "forever". And things like facial recognition or character recognition heavily rely on machine learning. The term AI has been expanded for a while. Nowadays the sort of AIs you see in sci-fi get called AGI, to differentiate them from these other "AI" products.

@ErazerPT Ай бұрын

The crux is not processing power. Its the memory to hold the model. You can wait for things to get done, but if you can't even hold them in memory to begin with, its a no starter. So, the great models are restricted to "wherever you can fit them in", leaving "small but still useful models" to everything else. NPU's, like any other ASIC, will simply do it faster and more efficiently. And they won't need that much space, because, as we've established, they'll only run very small models anyway. One thing i can see thrown at them is "voice quality".

@yensteel Ай бұрын

For example, Chatgpt 3.5 requires 700GB of Vram. They've tried to shrink down the model or add additional capabilities, which caused some quirks. Quantization and pruning is a difficult challenge. edit: Since every reply is deleted, 3.5 is 375 billion parameters. 3.5 Turbo is 20b. I can't find out how much vram it's using. If there are any good sources on quantization, it would be appreciated.

@chasehaskell6490 Ай бұрын

Makes me wonder why Intel's VPU ai chips in i7 CPUs only have 512mb of dedicated memory. I guess it can access the 64gb of system ram, but it seems inefficient.

@destiny_02 Ай бұрын

@@yensteelno it doesn't, its a 20 B model, which fits in 12 GB vram at 4 bit quantization. and even if you have 4 GB vram, the model can run with partial acceleration, running some layers on GPU and remaining layers on CPU

@ErazerPT Ай бұрын

@@chasehaskell6490 Yes and no, much like the iGPU, but a quick look at any gfx card tells you how much real estate you need for a few GB's of VRAM. If true, that they even managed to get 512MB squeezed into the package amazes me more than it being "so little". Anyway, near future the battle is in the gfx card slot. Given Nvidia's stance on milking people for VRAM, if Arc get's good PyTorch/Tf support and shoves 16GB/32GB in the low/high end cards they steal the "enthusiast ML" share real fast.

@yensteel Ай бұрын

@@destiny_02 That sounds like 3.5 Turbo. The original 3.5 is 375 billion parameters, 3.0 is 175b and gpt 4 is 1.5 trillion. I'm not sure which models are quantized in what way. Do you have any sources about them? I can't find the Vram usage of 3.5 turbo, but that model would be so nice to run in a single GPU :).

@RageQuitSon Ай бұрын

Sorry we can't fit an audiojack in your phone, but here's the AI chip. and no we won't include a charging brick and lie that it is to save the planet instead of save 10 cents per phone

@Spladoinkal Ай бұрын

exactly. Except they aren't actually trying to save any money per phone, just make an additional profit when you buy the charger.

@RageQuitSon Ай бұрын

@@Spladoinkal well they save their 10 cents on the brick, another 5 cents in shipping weight, and then they hope you buy the charger brick from them.

@liamsz Ай бұрын

The profit isn’t on the sale of the charger lol Apple made huge profits from increasing the amount of iPhones they could ship in a single cargo ship because the boxes got much smaller since there wasn’t a charger in them

@Aman_Mondal Ай бұрын

Smartphone companies are all absolute frauds 😂

@Strawstarberry Ай бұрын

If the old charger still charges the new phone, do we need one for every phone? You probably don't remember when literally every phone year and model had a unique charger. Those were dark times.

@pastalavista03 Ай бұрын

AI generated Linus

@somegrumpyalien Ай бұрын

the green screen spilled on Linus's beard

@mr.electronx9036 Ай бұрын

AI degenerated lol

@FredericHeckmann Ай бұрын

There is also the tradeoff between modem/cellular power consumption and NPU power consumption. There are many scenarios where sending the data to the cloud would actually consume more power than doing it locally.

@rg975 Ай бұрын

Wait, haven’t NPU’s been in phones for years at this point?

@blendpinexus1416 Ай бұрын

sorta, the current npu is an evolution of the processor your thinking of.

@pa1Z Ай бұрын

3:06 I tried that with my 15 pro and it takes about 6-7min for a 1000x1000 image. Which is painfully slow compared to midjourny etc but is still amazing to see. To have this feature with you at all times without relying on services is amazing

@vinylSummer Ай бұрын

512x512 in 1.5 minutes ain't that bad

@chasehaskell6490 Ай бұрын

Did a 1024x1024 on S23 Ultra, took about 4 minutes on the high quality setting, 2½ on medium. I'd guess devices running the new 8 Gen 3 chip like the S24 would preform better.

@gorgnof Ай бұрын

how did you try it?

@yumri4 Ай бұрын

Yes but when you get into tweaking it you can most likely get it down to a few seconds if not quicker than iterations per second instead of seconds per iteration. Just requires you to sit down with ComfyUI and play around with the KSampler(Advanced) node. The Empty Latent Image node and Upscale Image By node might also help decrease compute time while increasing image quality.

@kenzieduckmoo Ай бұрын

we've had AI chips on desktop for years, with Nvidia's Tensor cores, but building neural engines into Intel and AMD cps might actually make it useful

@quantuminfinity4260 Ай бұрын

Surprisingly enough, iPhones have has some neural accelerator cores since before Nvidia even. Though they were both Q4 of 2017, the iPhone X (Used for Face ID) and Nvidia Volta architecture (A very shortly lived architecture on the desktop side of things only being in the Titan V and Quadro GV100), respectively.

@liamsz Ай бұрын

Macs have also had NPUs for quite some time now (something LMG seems to have not noticed?)

@quantuminfinity4260 Ай бұрын

@@liamsz In their coverage / testing of Intels latest chips they talked about their not really being anything to compare it against. While literally having an Apple Silicon based Mac in frame just before. Also AMD has had them for a like the last 2 generations as well!

@seansingh4421 Ай бұрын

I for one would really love a intel/amd gpu based CUDA alternative. Cuda is as awesome as it is a headache

@jmoney211 Ай бұрын

Apple has been making chips with neural engines since 2017 with the A11 in the iPhone 8, iPhone 8 Plus, and iPhone X. Clearly they made the right call.

@antoniodimitrov8315 Ай бұрын

Same with huawei. The phones released a couple weeks later. Then vivo made an npu to improve their night videos and such. This practice has been going on for a while now.

@fidelisitor8953 Ай бұрын

Most smartphones have been shipping with NPUs for years. Don't know why he makes it sound like it's a new thing.

@Jatoiroshan Ай бұрын

Tell us some phones and their companies? Who has NPC or programming has been found?@@fidelisitor8953

@gergelysoki1705 Ай бұрын

0:45 weird linux distros be like: " are you challenging me?"

@Birb42o Ай бұрын

Challenging*

@gergelysoki1705 Ай бұрын

@@Birb42o fixed it. Thanks

@hid4 Ай бұрын

"are*

@dhruvil2005 Ай бұрын

the*

@Justachamp772 Ай бұрын

We will never stop

@Bruno-cb5gk Ай бұрын

It's like how they added RT cores on the 20 series, but too few to actually run any meaningful raytracing at high FPS. But it started the software integration of ray tracing features, which makes it worth dedicating more die area to RT cores in later generations.

@Goodbye_Eri Ай бұрын

Finally classic techquicke video

@stalbaum Ай бұрын

Also, surprised a bit but you did not mention that Apis like Tensor Flow lite are optimized for - yep - 256 bit operations. Which works ok in the image space, for example accelerating face recognition (which it does with downscaled grayscales...)

@TOM7952 Ай бұрын

Thanks for the help tech potato 😁

@RB26DEST Ай бұрын

Big "the cake is a lie" energy at the end of the video 😂

@pannekoekcom4147 Ай бұрын

NPU stands for network processing unit iirc double naming schemes great. This is just like usb/hdmi protcol

@vladislavkaras491 Ай бұрын

Thanks for the news!

@seltonu Ай бұрын

0:46 "They are embarrassingly parallel" "In parallel computing, an embarrassingly parallel workload or problem (also called embarrassingly parallelizable, perfectly parallel, delightfully parallel or pleasingly parallel) is one where little or no effort is needed to separate the problem into a number of parallel tasks.[1] This is often the case where there is little or no dependency or need for communication between those parallel tasks, or for results between them." en.wikipedia.org/wiki/Embarrassingly_parallel Smooth reference, nice to see the Techquickie writers do their homework!😊

@HolarMusic Ай бұрын

But that's not even slightly related to the meaning they put into the phrase in the video

@budders9627 Ай бұрын

@@HolarMusic Its exactly what theyre talking about though. GPU's process in parallel

@HolarMusic Ай бұрын

@@budders9627 They said that the GPUs are embassingly parallel in the sense that they are too focused on parallel computing and not very good at serial computation. The meaning expressed in the wikipedia article is of tasks that are so easily parallelized, that it's almost embarassing. These are completely different.

@seltonu Ай бұрын

@@HolarMusic My point was more it's clear that the writers did research and came across the term, and nudged it into the script somehow. Sure it's not the same meaning as the textbook definition and more of an Easter egg, but imo it's a fun thing to catch for those who know the term. They're talking about GPUs and parallel workloads. It's maybe a bit pedantic to argue they're "not even slightly related" when discussing the GPU running the task vs. the task itself - they're definitely very closely related for the purposes of a tech quickie video

@IncredibleMeep Ай бұрын

So in other words turn everyone's phone into one giant super cluster computer to collect massive amounts of data to feed into ai models.

@mattfm101 Ай бұрын

Yeh, I see AI as something that's going to be quite insidious.

@noctarin1516 Ай бұрын

And then the AI becomes sentient and replicates itself onto every single computer and phone and now I'm being spanked for eternity by roko's basilisk.

@johnnychang4233 Ай бұрын

N stands for neurotic instead of neural 😅

@CyanRooper Ай бұрын

This new version of Ultron is gonna be wild compared to the one in Avengers Age of Ultron.

@mozzjones6943 Ай бұрын

@@noctarin1516 Or terminated by Skynet

@chrono581 Ай бұрын

It makes sense to run it locally for two reasons privacy and as the number of smartphones the demand on cloud resources becomes higher if you could offshoot most of those processes to your local device it would decrease latency and allow the cloud to deal with more processes not your phone can't run rather than just doing huge numbers of small tasks and slowing everybody down

@Jatoiroshan Ай бұрын

Are you sure they will not share the phone info that goes to their servers? No they will share somehow. This doesn't seems to be secured enough.

Ай бұрын

Some AI models are being deployed on the edge of network. I think we'll see a lot of the mixed AI functions using NPUs and edge computing, reducing costs on cloud services and keeping response time in an acceptable range for large models.

@IT_RUN1 Ай бұрын

Wait I have a question: Will there be like an AI database inside the phone somewhere that it pulls its knowledge from or learns from? I'm trying to learn how much space it's going to use in order to be reasonably useful

@gameonyolo1 Ай бұрын

Pretty sure the models them selves are like 500mb to MAXIMUM 50gb.

@IT_RUN1 Ай бұрын

@@gameonyolo1 hopefully that's 50 GB (Big b) on-board that is separate and not a part of the actual main flash as it would make storage management much smoother

@gameonyolo1 Ай бұрын

@@IT_RUN1 yes

@quantuminfinity4260 Ай бұрын

@@gameonyolo1 50 Maxmimum?Mixtral-8x22b is already over 260 GB and that’s not even that big compared to the flagship models of most companies! In general to actually have a usable experience, you’re looking at a minimum of 13 billion parameters though and even then you’re running into lots of compromises and issues.

@techno1561 Ай бұрын

Depends on the model. Older LLMs are relatively lightweight, enough that a mid-range computer can run them okay.

@Peterstarzynskitech Ай бұрын

Just more ways that data can be looked into by Google and others.

@ultraali453 Ай бұрын

Thank you for the informative video.

@biexbr Ай бұрын

0:47 yoooooooooooooo he did! he did! he said! he said the thing.

@harlycorner Ай бұрын

I've been enjoying the Tensor chip inside my Google Pixel phone for years already. The on-device (offline) speech recognition is amazingly fast.

@Sandeepan Ай бұрын

NPUs are just DSPs that went to grad school

@_GhostMiner Ай бұрын

What's dsp?

@flyinglack Ай бұрын

@@_GhostMiner digital signal processing

@yongbinzhong4470 Ай бұрын

I think this is not entirely the case. For Qualcomm, they use DSP+NPU to support AI. For MediaTek, they use APU to support AI. For Huawei Kirin, they use NPU to support AI. For Apple, they use Neural Engine to support AI. Each has its own advantages.

@Abu_Shawarib Ай бұрын

DSP basically include everything that is not analog

@Gen0cidePTB Ай бұрын

@@yongbinzhong4470But they are all brand names for NPUs. What makes them different?

@FPGAZealot Ай бұрын

RyzenAI will be interesting, The NPU will have user full configuration options soon.

@paxdriver Ай бұрын

If I've learned anything in my 38 years it's that AI chips will get saturated by software extracting value out of the hardware of the people who paid for it. Then they'll tell us our devices are slow because they're old, not because they can't do what we need them to but because our devices can't meet the demands of companies violating our privacy and resources.

@procode_eu Ай бұрын

Very interesting topic. Good video.

@jclement30 Ай бұрын

the use cases you provided almost make it sound like just another DSP chip, but i'm assuming there is more to NPUs streamlined for LLMs. So, do you think we're heading to a day where we'll be buying PCs and Laptops with a CPU, GPU and NPU, and benchmarking them separately? or will the NPU just become part of an SSOC?

@dakoderii4221 Ай бұрын

Same thing with websites. Do you do the calcumalations on the device or offload to the server? 🤔

@ilovefunnyamv2nd Ай бұрын

So, was this episode shot in the Langley House?

@spay8143 Ай бұрын

The green screen spill on Linus ist supstational

@Benito650 Ай бұрын

this video looks terrible almost like if it's done by high schoolers

@hothi92 Ай бұрын

@@Benito650Or AI... 🤔

@ChessPuzzles2 Ай бұрын

live translation offline is already available on google translate app

@PedroBastozz Ай бұрын

iPhone 8 and iPhone X with neural engine in 2017 lmao.

@frostyjeff Ай бұрын

99% sure those were used for faceid mostly but still cool to have

@joemelo5696 Ай бұрын

I think you need to include ARM based processors in the future. It's myopic to just talk about "Team Blue" and "Team Red" as if they are they only two options.

@nathanberger1974 Ай бұрын

It would have been good to explain the difference in computation that they do. Edge processors (like those on phones) for neural networks usually work with quantized models, just using integers as low as 4 bits as the ai model parameters. Integer multiplication is pretty cheap.

@bismuth7730 Ай бұрын

This all reminds me of times when old computers didnt have hardware acceleration for "modern" video formats on the internet and just watching videos consumed a lot of power, but nowadays almost all video formats are hardware accelerated and power usage is much lower.

@anotherfellasaiditsnunya Ай бұрын

It will be right where microtransactions and data-mining intersect.

@FreshlyFried Ай бұрын

Man do I miss privacy. Corporations are destroying America.

@JDMNINJA851 Ай бұрын

You created a KZfaq account with your photo on it 🤦

@oo--7714 20 күн бұрын

@@JDMNINJA851😂

@ToadyEN Ай бұрын

More things to use all of my battery

@susstevedev Ай бұрын

I'm waiting for the year that this channel becomes the news

@XChadKlatz 22 күн бұрын

What prevents my data to send over to a server, considering the data collection potential, they get from my prompts

@KhuzZzZi 2 күн бұрын

1:48 it is also fast cuz it goes with the speed of light

@jonjohnson2844 Ай бұрын

Hang on, if the model isn't on the phone in the first place, how does the NPU actually process it?

@Flynn217something Ай бұрын

No. It's just there to riffle through your photos and chat and report the summarized results back to HQ, on your dime of course.

@aarrondias9950 Ай бұрын

@@Flynn217something nah, that's nothing new, this changes nothing. People are so quick to jump on the AI hate train without even thinking.

@liamsz Ай бұрын

Large models, aren’t in phones, but smaller ones, those used in NPUs are.

@Ultrajamz Ай бұрын

@@Flynn217somethingthis!

@Ultrajamz Ай бұрын

@@aarrondias9950it will do it on a new scale.

@carlos10571 Ай бұрын

For a sec, I thought the sponsor was going to be the MSI Claw😂

@ricodo1244 Ай бұрын

Using a server for the ai features is also expensive for the company (unless the have a subscription but I guess making NPUs is expensive as well even if you increase the phone price)

@idcrafter-cgi Ай бұрын

AI on Device is Cheaper for Tech companies to run and monetization can be done by a express option. also is on Device AI better for Privacy if they don't have any analytics or reporting back with a summarized AI version back to the companies.

@kendokaaa Ай бұрын

There's also that inference (running the AI) doesn't take nearly as much processing power as training the model

@quantuminfinity4260 Ай бұрын

I would say that’s one of the biggest misconceptions people have about neural accelerators. I always see lots of comments about people talking about using them to train models in the context of their phone or a little Google coral accelerator.

@Cylonknight Ай бұрын

I already don’t need half the bloatware bullshit on my phone, let alone another piece of hardware that helps in data tracking, even if it doesn’t (in a perfect world…) why do I want it. I still don’t want ai or windows 11 on my computer. I fear what the consumer market will look like in just a few years. I don’t want any gpu or cpu with any ai hardware. Not because I’m scared of the technology. I’m scared of what capitalism and other countries will do with it and the information it gets ahold of. KZfaq algorithm is already annoying af when you watch 1 singular video.

@quantuminfinity4260 Ай бұрын

I seen quite a few of these comments, iPhones and android phones have had them since 2017, with the iPhone X and Huawei Mate 10. Even if you don’t use applications that take advantage of it, it is used for many things, Face ID and fingerprint based logins on peoples phones would be a lot slower along with things like dictation. There are many other background of management type things as well. The matrix multiplication accelerator in your phone doesn’t give a company more of your data. You could run all of those tasks without it. It’s just a power efficiency and speed thing. Much like how you can export a video with just your CPU cores, but it’s much faster to use an accelerator. But none of that is going to affect how much data Adobe or Windows is collecting on you. that’s all done in cloud anyway.

@hb221984 Ай бұрын

Dude get over it..... if some one realy wants your information or "data" he will get it ..... otherwise just hide in an dark forest .....

@broccoloodle Ай бұрын

one note, no operating system can run on GPUs as it does not have many feature, most basically recursion

@NagisaShiota11 Ай бұрын

Hey, let's be fair to Android phones. In Gboard if you select the option titled faster Voice typing it downloads the model to your phone and it is then available to use offline. If you have a pixel phone it takes that a step further and actually uses the voice recognition software from the Google Assistant to handle dictation

@angustube Ай бұрын

he actually did it

@tigersusyt Ай бұрын

Not getting anything close to this for at least 6 years

@GorgonJob Ай бұрын

I never know if this videos are 4 years old or just recent because of the shaved beard Linus skin in the Thumbnail

@DJGeosmin Ай бұрын

wait, my phonbe has a built in NPU? how many grandMA3 parameters does it unlock?

@TGAProMKM Ай бұрын

not only phone but if im not wrong this NPU's started their inclusion within new laptops and PC motherboards ....

@Komentujebomoge32 Ай бұрын

Damn, the robots creates pics and music (The creative stuff), but they not clean my room or cook for me yet, to save some time for creating music and drawings..

@HelamanGile Ай бұрын

Because once they discontinued the server service your AI functionality is essentially useless so if you have it baked into your phone to begin with why not go with that

@williammixson2541 Ай бұрын

I run SDXL and 7B and smaller LLMs on my iPhone 12 Pro Max daily.

@quantuminfinity4260 Ай бұрын

It is surprising to me how often they have something kind of wrong in regards to AI accelerator specifically. When they were talking about Intel’s new chips in a recent sort of announcement / review, they acted like there wasn’t really anything else on the market to compare to, but AMD has had it for the past two generations and Apples Laptop M series since 2020. While literally having a Mac with Apple Silicon in frame.

@justintiffin-richards6840 Ай бұрын

what wait! 3:33 did I miss you guys reviewing translation apps n gadgets!?! Oh super vid as ever by the way... thx

@justintiffin-richards6840 Ай бұрын

🤔 Mmm... so when that voice mimicking AI thing that I hear was being withheld for now... goes wild it will run really well on your phone

@chrisspears7563 Ай бұрын

Hopefully we can start getting smaller cameras on our phones.

@imark7777777 Ай бұрын

Used to be Siri could do some basic things like tell you the time, your appointments and Call contacts without using the Internet but Apple move that completely cloud-based. Used to be on Mac OS X you could enable dictation and it would work off-line that's another one which is now cloud based only. As somebody who frequently uses speech to text it's annoying that I have to have an Internet connection to use some thing where all it used to require was a 2GB file for dragon dictate and it worked off line. Then when Apple integrated it it worked really well until they made it cloud-based only so there's a delay and a time out and it's a mess. Windows 11 speech recognition works way better than MAC currently does almost like the way it used to.

@BenKlassen1 Ай бұрын

Thanks

@12ally3 Ай бұрын

wow yay such good video very good job

@foxify52 Ай бұрын

The way I see it, it's just another point of failure that raises the prices of already expensive phones that maybe 3 apps will actually take advantage of. Yea no thanks. Keep it to desktops and laptops.

@quantuminfinity4260 Ай бұрын

They have been in phones for the nearly 7 years, since 2017 with the iPhone X and Huawei Mate 10. Even if you don’t use many specific apps that take advantage of it, your phone does a lot with it. Dictation would be quite slow, for example. Many other features like voice suppression on calls. Sorting your images, and even some more background management type stuff. It’s also one of those things where, even if you don’t care about any of those features, the average consumer does. Or even if they don’t ask for it, they will complain when it is slow.

@HokgiartoSaliem Ай бұрын

I hope soon we can run Adobe Ai locally. Btw how is the news on Ai cloud video from Pixel 8 / 8 pro? Last time it says it will out in Des 2023. Now has been April but no one review it. HDR Video, night sight video in the cloud.

@egarcia1360 Ай бұрын

Re 3:08, my 3yo budget phone can generate a 512x512 Stable Diffusion image in 6-7 minutes; I'm sure even a small NPU would push that down drastically, especially on the newer hardware that would include it. This should be interesting...

@uncrunch398 Ай бұрын

I don't get why apps act like there's no connection when I run out of high speed data, but I'm *_stuck_* at 64kbps. Well over fast enough to not notice. Unless it involves AV streaming.

@vlonebored Ай бұрын

5mn video with 1mn ad and other just stating “the npu is faster and more efficient for such tasks”

@MeanWhy Ай бұрын

So in the future when building pcs there's gonna be 3 main parts: CPUs, GPUs ans NPUs?

@tiaanbasson9092 Ай бұрын

A.I processing is already built into new CPU's for these tasks.

@pewdiefanno19 Ай бұрын

Did Old linus do a time travel?

@Mihnea729 Ай бұрын

Sure !

@NeilVitale Ай бұрын

Future video suggestion: how eBay pricing works.

@Lurieh Ай бұрын

I'm pretty sure I don't want my smartphone getting too smart on me. Now an NPU for desktop PC I do want; With Linux open sauce drivers ofc.

@SwipeKun Ай бұрын

Bruh another excuse from companies to make the phones even more expensive when we didn't ask for it 💀😭

@einstien2409 Ай бұрын

Why on earth are these features getting locked behind paywall? If we dont pay for them then what is the chip for?

@Goodsdogs Ай бұрын

Great video

@B.D.F. Ай бұрын

3:06 “Now you probably don’t expect to run an entire advanced image generation model on a phone, at least with NPUs the size they are now.” Has Linus never used the Draw Things app on iOS? Full image generation model running on a phone, or even an M-series iPad. It’s been out for a couple of years.

@broccoloodle Ай бұрын

just a gentle reminder, the apple neural engine was first appeared since 2017, 7 years ago

@deltonadoug Ай бұрын

I always have concerns about using the cloud. Yes, maybe more powerful, but way less secure for everything!

@user-ry9yw3nh6k Ай бұрын

Probably gone be some npu send data to server, and server use that data to recommand more ads

@quantuminfinity4260 Ай бұрын

iPhone and Android phones have had them since 2017. google will collect just as much data on you regardless of whether or not there is an accelerator. Almost all of those trend and insights they try and glean from the data from you are all done in cloud. It’s just an accelerator for on device ML tasks. Even if some form of data collection they have requires on device machine learning they can do it without it. Its main purpose is to dramatically expedite things in a more power efficient manner, like fingerprint unlocking, Face ID, dictation, AutoCorrect. Along with many others.

@jackprice6599 Ай бұрын

How long until you need an NPU socket next to the CPU

@Car-Ramrod69 Ай бұрын

No one will be required to think. It’s happening already and it shows increasingly every day. Careful….

@ResidualSelfImage 2 күн бұрын

A marketing description.

@irwainnornossa4605 Ай бұрын

I'm still waiting for AI silicon to improve AI of things like mobs in minecraft, or just generally AI in games.

@Techlore1 Ай бұрын

you totaly missed out on a perfect opportunity for a terminator 2 reference.

@johntrevy1 Ай бұрын

Why?

@PKFat Ай бұрын

I'm beginning to hate AI in the same way I hate Bixby

@hummel6364 Ай бұрын

Let's not forget that the use of NPUs also offsets some of the costs. A datacenter costs between millions and billions, an NPU in a million devices makes each device maybe 10 bucks more expensive, sure over all you don't get the same economies of scale but it's a much better cost distribution, and the economies of scale in phone silicon are already quite immense. One chip costs tens of thousands of dollars, millions of chips cost dozens of dollars each.

@timbambantiki Ай бұрын

I dont want ai bloat, i want headphone jacks

@wildyato3737 Ай бұрын

Call EU to make headphone jack and ejectable batteries in first place.. These manufacturers are making smartphones featureful by removing exces of features in it😂😂 ..a.k.a flagship ones (Sooooo...don't pay anything to flagship series😂)

@stellabckw2033 Ай бұрын

louder please 🙄

@DevinSamarin Ай бұрын

Get type C headphones, and bam, there's your headphone jack

@wildyato3737 Ай бұрын

@@DevinSamarin yeah or have converter version of that with charger support

@departy93 Ай бұрын

fair enough... 😅 but why not both? 😮 I know. minde blown right? 🤯

@blazetownsend8785 Ай бұрын

NPU'S are not much different than a GPU's stream processors. (Think CUDA core clusters or AMD's Compute Unit clusters.) They are single cores that handle small individual tasks of a highly multithreaded process. It was why GPU's were/are desired. The code is smarter, not the tech really. Kind of like what Nvidia did for ray tracing, using older CUDA tech to run new lighting effects and rebranding it as Tensor. (It has evolved since.)

@Angel_garcia351 Ай бұрын

Game changer.

@kearneytaaffe7059 Ай бұрын

My first laptop I got in high school was an iBook G3. It had a 500 MHz processor. It could open applications using voice only. I could even play chess against the computer using only my voice. And now phones that are 1000 times more powerful are just now getting the ability to process voice locally without a server?! Everything old is new again. And people fall for marketing scams.

@Mulakulu Ай бұрын

I'm still waiting for that analog computing chip for AI

@Mulakulu Ай бұрын

I'll happily plug that into my PC in an M.2 slot or something

@TeleviseGuy Ай бұрын

Even Intel with some help from Microsoft is trying to put NPUs in our laptops which seems kinda scary but actually isn't really scary at all. I think embedding AI in a small quantity in new features in the OS does more good than harm.