CUDA Explained - Why Deep Learning uses GPUs

  Рет қаралды 245,441

deeplizard

deeplizard

Күн бұрын

Пікірлер: 136
@deeplizard
@deeplizard 6 жыл бұрын
Check out the corresponding blog and other resources for this video at: deeplizard.com/learn/video/6stDhEA0wFQ
@kudoamv
@kudoamv 6 жыл бұрын
So I can't use Computer Vision Programs which require GPU because I am an AMD card user?
@mae1000
@mae1000 4 жыл бұрын
@@kudoamv Actually, you can, I think. AMD invested in that field too, google "gpuopen".
@majeedhussain3276
@majeedhussain3276 6 жыл бұрын
This channel seriously deserves million subs.Have been watching many series from this channel.Great work !!!!! keep going I'm sure this channel gonna flow with lots of subscribers someday .
@deeplizard
@deeplizard 6 жыл бұрын
Thank you, Majeed! We're glad to hear you've been enjoying multiple series here, and we're happy to have you as an engaged member of the community! Always appreciate seeing your comments :)
@Xiler6969
@Xiler6969 5 жыл бұрын
Congratulations, You've impressed me. Very professional series. Right to the good stuff, clear and sharp voice, broad yet specific explanations.
@debajyotisg
@debajyotisg 5 жыл бұрын
Great job speeding Jensen Huang up. xD
@sudeepkadyan5480
@sudeepkadyan5480 4 жыл бұрын
Can i use 1050ti 4gb for data science
@faroukmokhtar6900
@faroukmokhtar6900 4 жыл бұрын
Ofcourse
@atisbasak
@atisbasak 3 жыл бұрын
But it will be quite slow.
@larryteslaspacexboringlawr739
@larryteslaspacexboringlawr739 5 жыл бұрын
5:13 ballmer ambush, panic clicking to skip (thank you for awesome video)
@deeplizard
@deeplizard 5 жыл бұрын
lol. You are welcome!
@ajwadakil6020
@ajwadakil6020 4 жыл бұрын
This channel should have more subscribers, seriously
@gabriellugmayr2871
@gabriellugmayr2871 5 жыл бұрын
wow, I saw these first 4 videos of the Pytorch series and am impressed how much time & effort you put into these tutorials. Thanks a lot. Also, you have developed enormously (although the older tutorials were already very good)
@Sikuq
@Sikuq 4 жыл бұрын
Beautifully done, Chris. Wow. Thanks. I learned a lot.
@engkamyabi
@engkamyabi 2 жыл бұрын
Amazing video and loved the short clips! Thank you!
@shivangitomar5557
@shivangitomar5557 2 жыл бұрын
The BEST VIDEO on this topic!
@Aweheid
@Aweheid 4 жыл бұрын
Rich informative video !! No better explanation is more than yours!!
@IgorAherne
@IgorAherne 6 жыл бұрын
Good overview, also having 8 cores won't necessarily speed up computation by exactly x8, perhaps by x7 in practice I just wish you would mention that processors use SSE2, AVX2 and similar things that allow each core do 8 summations/multiplications/shifts/etc at a time, rather than one by one. This allows a CPU registers to process arrays in chunks of 8. Many C/C++ programmers don't know about those, and build programs that are by default doomed to underperform. So I feel everyone is always unfair towards the CPU. Everybody is pointing at the cores, but each core can (and should) use intrinsics, doing parallel things. Especially with various RNNs where we only win if we move the entire algorithm to the GPU to avoid data transfer bottlenecks, and when the RNN is decently wide in each layer for the GPU. Also, CPU is really flexible when it comes to 'if/else' or while loops, reacting faster and wiry when the branch occurs.
@deeplizard
@deeplizard 6 жыл бұрын
Hey Igor - Thanks for adding these details. Great stuff. Much appreciated! 🙏
@MarcelloNesca
@MarcelloNesca 3 жыл бұрын
Thank you very much, currently learning deep learning and this was perfect to explain why I need a good GPU
@chinonsoalumona6734
@chinonsoalumona6734 2 жыл бұрын
Hi Marcello how’s your deep learning experience going?
@bazzinga204
@bazzinga204 3 жыл бұрын
Beautifully explained.
@estebansevilla2229
@estebansevilla2229 Жыл бұрын
I ended up here because my daughter is learning "AI" at high school and now I need to understand how this all works to make her a PC.
@deeplizard
@deeplizard Жыл бұрын
😅😅
@SDRIFTERAbdlmounaim
@SDRIFTERAbdlmounaim 4 ай бұрын
did you build that pc just fine or you needed further help ?
@mayur9876
@mayur9876 6 жыл бұрын
Thanks for putting in all the efforts.
@deeplizard
@deeplizard 6 жыл бұрын
You are welcome!
@Ammothief41
@Ammothief41 5 жыл бұрын
Any idea on how the rtx graphics cards and their tensor core stuff compares to the standard gtx gpus? Is that something that tensorflow or pytorch take advantage of?
@deeplizard
@deeplizard 5 жыл бұрын
Haven't seen the comparisons. And. Yes. www.geforce.com/hardware/technology/cuda/supported-gpus
@jamesferry8484
@jamesferry8484 6 жыл бұрын
Thank you for sharing. Very helpful.
@deeplizard
@deeplizard 6 жыл бұрын
Hey James - You are welcome!
@taj-ulislam6902
@taj-ulislam6902 8 ай бұрын
Very professional video. Good information.
@Not0rious7
@Not0rious7 4 жыл бұрын
Nice video, I like all the graphics you used. Where do you find them?
@durafshanjawad5250
@durafshanjawad5250 4 жыл бұрын
Very Helpful Series
@ajaykrishnan4277
@ajaykrishnan4277 6 жыл бұрын
you just nailed it
@rifatmasud
@rifatmasud 5 жыл бұрын
Anyone have that video link regarding "python is slow"?
@deeplizard
@deeplizard 5 жыл бұрын
Added it to the description. Here you go: kzbin.info/www/bejne/enO5fZadppd4nZI
@arkamitra4345
@arkamitra4345 5 жыл бұрын
GIL is evil 😓
@kudoamv
@kudoamv 6 жыл бұрын
PLEASE HELP, Is it something like - "you have to download pytorch with cuda if you wanna use gpu or else you will only be able to use cpu" ? I am an AMD user.
@JasperHatilima
@JasperHatilima 5 жыл бұрын
CUDA is NVIDIA platform and so only supports NVIDIA cards like the GTX GPUs. For AMD, the framework for parallel programming is OpenCL...which unfortunately does not have a development community as big as the CUDA community.
@ankitaharwal5886
@ankitaharwal5886 5 жыл бұрын
I can feel your pain 😔 😔
@SW-ud1wt
@SW-ud1wt 8 ай бұрын
I have HP envy ci7 laptop having GeForce rtx 2050 card, will it be used for machine learning tasks?
@mexzarkashiev2435
@mexzarkashiev2435 5 жыл бұрын
So which graphics card should I buy for deep learning?
@AdrianDucao
@AdrianDucao 5 жыл бұрын
my girl friend and i been doing a lot of deep learning lately
@osumanaaa9982
@osumanaaa9982 4 жыл бұрын
you sure it's not just shallow computations ? :p
@q3d385
@q3d385 4 жыл бұрын
@@osumanaaa9982 🤣
@Aditya_Kumar_12_pass
@Aditya_Kumar_12_pass 4 жыл бұрын
I hope you are not hoping for any output.
@anamitrasingha6362
@anamitrasingha6362 4 жыл бұрын
@@Aditya_Kumar_12_pass KZbin should have a Haha react xD
@vibesnovibes6320
@vibesnovibes6320 4 жыл бұрын
How many layers for protection? Are you clear on how back propogation is supposed to work? 😂😂😂
@nozaxi0327
@nozaxi0327 6 жыл бұрын
Thank you. This series so helpful for me
@deeplizard
@deeplizard 6 жыл бұрын
Glad to hear that, jesse! You're welcome!
@e4r281
@e4r281 6 жыл бұрын
Maybe if we start telling people the brain is an app they will start using it.
@clbl8706
@clbl8706 4 жыл бұрын
That's some cringeworthy joke my grandma would share on FB.
@e4r281
@e4r281 4 жыл бұрын
@@clbl8706 actually, it's not a joke.
@nikhilmathur3351
@nikhilmathur3351 4 жыл бұрын
@@e4r281 Unlike you
@hailongvan8285
@hailongvan8285 4 жыл бұрын
ok commie
@henson2k
@henson2k 4 жыл бұрын
When multiple apps are using CUDA how it's managed by GPU? Can GPU execute different kernels at the same time?
@jackt9535
@jackt9535 2 жыл бұрын
I'd like to know whether you could use dedicated graphic card for deep learning while you don't have a CPU with no iGPU. This will help me much with my screen cable management issue (I'm new to this) ! Thanks!
@True38
@True38 5 жыл бұрын
Did they remove all those stats/functions on a newer version of Cudo? Because I just recently downloaded it, and the only thing I can see on the screen is CPU, XMRig, h/s to the left and Payout Coin to the right. That's it! I'm using CPU but want to use GPU, but can't see any option. Please help if you can.
@Henry..s
@Henry..s 4 жыл бұрын
What I learned from this video is that nvidia gpu got their speed from the CEO
@faizahmed8034
@faizahmed8034 4 жыл бұрын
Aren't GPU's used for image processing (i.e conversion of binary code to analog Graphic pixels)? If so how can we use them for mathematical computations ?
@adithi729
@adithi729 4 жыл бұрын
Sir is there any way to do cuda programing online? i mean any online compiler is present now? my system is not supporting cuda..pls help
@dalirkosimov4623
@dalirkosimov4623 3 жыл бұрын
You can do it on jupyter
@vibesnovibes6320
@vibesnovibes6320 4 жыл бұрын
Great video
@qusayhamad7243
@qusayhamad7243 4 жыл бұрын
thank you
@zeppybrawlstars3906
@zeppybrawlstars3906 5 жыл бұрын
So when I play games with advance Ai make sure my gpu is ready
@deeplizard
@deeplizard 5 жыл бұрын
Exactly. 🤖
@krishna_o15
@krishna_o15 4 жыл бұрын
I am agreeing since Soumith has said it.
@sqliu9489
@sqliu9489 3 жыл бұрын
brilliant explanation
@RohanSawant-s3q
@RohanSawant-s3q 8 ай бұрын
😄very nice video
@ezevictor4448
@ezevictor4448 4 жыл бұрын
Is a gtx 960m or 1050m worth using?
@TheTariqibnziyad
@TheTariqibnziyad 5 жыл бұрын
Finally these nerds got the guts to call something a funny name, Embarrassingly parallel xD
@deeplizard
@deeplizard 5 жыл бұрын
🤓
@zackrider3708
@zackrider3708 3 жыл бұрын
@@deeplizard can the new XE server gpu from intel handle ai or Deep Learning workloads like nvidia gpu ?
@anujsaboo7081
@anujsaboo7081 5 жыл бұрын
You have a mistake in the quiz section: Q. Different PyTorch components are written in different programming languages. PyTorch is written in all of the following programming languages except? Ans. Java (on blog correct answer is coming as Python)
@deeplizard
@deeplizard 5 жыл бұрын
Hey Anuj - Thank you so much for pointing this out! I've fixed it. You may need to clear your cache to see the change. Chris
@robertatvitalitystar2444
@robertatvitalitystar2444 6 жыл бұрын
ty! Peeling the plastic of a brand new GPU is a good day, lol.
@kanui3618
@kanui3618 5 жыл бұрын
Can I combine Nvidia GTX 1070 or higher with amd ryzen 5
@deeplizard
@deeplizard 5 жыл бұрын
no amd at the moment.
@MMphego
@MMphego 4 жыл бұрын
Subscribed.............
@lancelotxavier9084
@lancelotxavier9084 5 жыл бұрын
nVidia is holding back processing power in order to make selling their products sustainable.
@deeplizard
@deeplizard 5 жыл бұрын
This is important. A company's incentive to make a profit can be a double-edged-sword. Consider the same problem in healthcare or biotech.
@henson2k
@henson2k 4 жыл бұрын
@@deeplizard conflict of interests indeed, every software developer knows that LOL
@Priya_dancelover
@Priya_dancelover 2 жыл бұрын
excellent
@benjaminhansen4808
@benjaminhansen4808 3 ай бұрын
You can explain this whole AI trend 5 YEARS AGO
@jordan5253
@jordan5253 5 жыл бұрын
Jesus @2:41 I spit out my water lol
@henson2k
@henson2k 4 жыл бұрын
At research stage I can see how Python is acceptable choice. However for production systems Python too large in size and not fast enough!
@sajolsajol8393
@sajolsajol8393 Жыл бұрын
wow!
@magelauditore333
@magelauditore333 4 жыл бұрын
5:25 i was like wtf. Can anyone have the link of whole video. 😂😂. Man i got excited and started shouting at home
@deeplizard
@deeplizard 4 жыл бұрын
It's a popular one. Google and you will find 😂
@A-Predator
@A-Predator 4 жыл бұрын
i just learned the name of deep learning 😵
@vky771
@vky771 6 ай бұрын
Everyone wishes they saw your video 5 years back 😅
@isbestlizard
@isbestlizard 5 жыл бұрын
OH MY GOD WOW are you a lizard too? i love ai and stuff as well :D
@deeplizard
@deeplizard 5 жыл бұрын
🤣
@richarda1630
@richarda1630 3 жыл бұрын
exciting and if you read WBW blog thrilling times
@hedonismbot1508
@hedonismbot1508 Жыл бұрын
Never in my lifetime would I have ever imagined "Embarrassingly [something]" would be an actual technical term.
@deeplizard
@deeplizard Жыл бұрын
😅😅
@beomheelee1249
@beomheelee1249 3 жыл бұрын
you're so geinus!! Thanks
@louerleseigneur4532
@louerleseigneur4532 4 жыл бұрын
merci merci
@pscheuerling
@pscheuerling 4 жыл бұрын
I came Here to learn how to utilitise deep learning cores for Training my own ai... I still don't know why i should buy cores i cant use.
@A-Predator
@A-Predator 4 жыл бұрын
😵
@lakeguy65616
@lakeguy65616 2 жыл бұрын
the forward pass can rely on matrix math which can be run through CUDA(software layer) and done on an NVIDIA GPU. The more GPU cores, the faster the process. A gpu with 100 cores will perform this step 10x faster than a GPU with 10 cores (in general...).
@alkeryn1700
@alkeryn1700 5 жыл бұрын
Guys, don't use cuda, use HIP so it runs everywhere or use opencl or sycl but don't have your software stuck to proprietary and platform specific hardware and software
@SuperMIKevin
@SuperMIKevin Жыл бұрын
Lmao, I can't believe they actually named it embarrassingly parallel.
@avdhutjadhav5657
@avdhutjadhav5657 2 жыл бұрын
Does that mean GPU with more CUDA is better for Deep learning ?
@lakeguy65616
@lakeguy65616 2 жыл бұрын
yes (and more gpu ram...)
@Infinityxx3
@Infinityxx3 6 жыл бұрын
u need some music in vid... attracks views.... cool vid
@deeplizard
@deeplizard 6 жыл бұрын
What kind of music do you like?
@Infinityxx3
@Infinityxx3 6 жыл бұрын
​@@deeplizard PEWDIEPIE bitch lasanga ? jk... any relaxing music when u talk... when u changing camera shot etc... ;)
@deeplizard
@deeplizard 6 жыл бұрын
haha. That sent us on a tangent. Hadn't seen that before.🤣
@DinoFancellu
@DinoFancellu 4 жыл бұрын
Its a pity that AMD don't seem to support CUDA. Their new big navi cars look really nice apart from that
@Joco5012
@Joco5012 3 жыл бұрын
Wow was it this ok to do so much coke back in the day? 5:12 damn dude take it down a notch
@MeowsyDancer
@MeowsyDancer 3 жыл бұрын
I will now send this to anyone who asked why I bought a 3090! rip wallet tho
@deeplizard
@deeplizard 3 жыл бұрын
🤣💰
@alebecker12
@alebecker12 10 ай бұрын
I have a doubt, does Nvidia has a monopoly in such hardware? If not, does CUDA only work on Nvidia hardware?
@deeplizard
@deeplizard 10 ай бұрын
Yes. Nvidia built CUDA. It only works with their hardware.
@robertsmith512
@robertsmith512 5 жыл бұрын
SUBBED ! EVERYBODY SUB THIS CHAN ! THIS ONE KNOWS HE'S STUFF ! GO LOOK AT THE PLAYLIST LIB !
@deeplizard
@deeplizard 5 жыл бұрын
Thanks Robert! Note that there are two of us here. 🦎🦎
@cubul32
@cubul32 4 жыл бұрын
Former CEO - and we can see why.
@deeplizard
@deeplizard 4 жыл бұрын
Although, he became a billionaire from his tenure at Microsoft 😄
@りょりょりょ-b6s
@りょりょりょ-b6s 4 жыл бұрын
5:57 東工大でるのは草www
@MilesBellas
@MilesBellas Жыл бұрын
Jensen is better at 2x
@invest8198
@invest8198 3 ай бұрын
someone who bought $NVDA 2018 ?
@ErrorRaffyline0
@ErrorRaffyline0 4 жыл бұрын
I really dislike CUDA becouse it’s not open-source and AMD is not able to use it, it makes development for both AMD and NVIDIA much harder.
@iLevelTechnology
@iLevelTechnology 6 ай бұрын
He doesn’t explain tensor very well but overall good job
@Drtsaga
@Drtsaga 4 жыл бұрын
"Deep learning" should not be on the title in my opinion.
@jacobcorr337
@jacobcorr337 3 жыл бұрын
CUDA not explained at all
@lakeguy65616
@lakeguy65616 2 жыл бұрын
CUDA is a software layer that interfaces with Nvidia GPUS to allow porting some problems (think forward pass) to the GPU which can be done in parallel. (your pc has an Nvidia GPU, with software like Pytorch, you tell PC cuda is available and to send certain processes to GPU for processing in parallel.) vastly over simplified.
@escapefelicity2913
@escapefelicity2913 3 жыл бұрын
I'm glad I don't need to listen to Jensen Huang.
@mmm-ie5ws
@mmm-ie5ws 7 ай бұрын
u did a rly bad job at explaining why gpu's are better for parrallel computing than cpu's.
@_SupremeKing
@_SupremeKing Жыл бұрын
Although still being confused, I just picked up some new knowledge for a layman like me
Tensors Explained - Data Structures of Deep Learning
6:06
deeplizard
Рет қаралды 106 М.
You don't understand AI until you watch this
37:22
AI Search
Рет қаралды 942 М.
Сестра обхитрила!
00:17
Victoria Portfolio
Рет қаралды 958 М.
How Strong Is Tape?
00:24
Stokes Twins
Рет қаралды 96 МЛН
Une nouvelle voiture pour Noël 🥹
00:28
Nicocapone
Рет қаралды 9 МЛН
CPU vs GPU vs TPU vs DPU vs QPU
8:25
Fireship
Рет қаралды 1,9 МЛН
How Nvidia Won AI
18:08
Asianometry
Рет қаралды 433 М.
Mini Project: How to program a GPU? | CUDA C/C++
12:53
0Mean1Sigma
Рет қаралды 31 М.
The Most Important Algorithm in Machine Learning
40:08
Artem Kirsanov
Рет қаралды 546 М.
How do Graphics Cards Work?  Exploring GPU Architecture
28:30
Branch Education
Рет қаралды 2,4 МЛН
MAMBA from Scratch: Neural Nets Better and Faster than Transformers
31:51
Algorithmic Simplicity
Рет қаралды 211 М.
Writing Code That Runs FAST on a GPU
15:32
Low Level
Рет қаралды 572 М.
Transformers (how LLMs work) explained visually | DL5
27:14
3Blue1Brown
Рет қаралды 4,1 МЛН
Learn Machine Learning Like a GENIUS and Not Waste Time
15:03
Infinite Codes
Рет қаралды 259 М.