Tesla Reveals The New DOJO Supercomputer!

  Рет қаралды 649,787

The Tesla Space

The Tesla Space

Күн бұрын

Пікірлер: 769
@terryterry1655
@terryterry1655 Жыл бұрын
The fundamental unit of the Dojo supercomputer is the D1 chip,[21] designed by a team at Tesla led by ex-AMD CPU designer Ganesh Venkataramanan, including Emil Talpes, Debjit Das Sarma, Douglas Williams, Bill Chang, and Rajiv Kurian.[5] The D1 chip is manufactured by the Taiwan Semiconductor Manufacturing Company (TSMC) using 7 nanometer (nm) semiconductor nodes, has 50 billion transistors and a large die size of 645 mm2 (1.0 square inch).[22] As an update at Artificial Intelligence (AI) Day in 2022, Tesla announced that Dojo would scale by deploying multiple ExaPODs, in which there would be:[20] 354 computing cores per D1 chip 25 D1 chips per Training Tile (8,850 cores) 6 Training Tiles per System Tray (53,100 cores, along with host interface hardware) 2 System Trays per Cabinet (106,200 cores, 300 D1 chips) 10 Cabinets per ExaPOD (1,062,000 cores, 3,000 D1 chips) Tesla Dojo architecture overview According to Venkataramanan, Tesla's senior director of Autopilot hardware, Dojo will have more than an exaflop (a million teraflops) of computing power.[23] For comparison, according to Nvidia, in August 2021, the (pre-Dojo) Tesla AI-training center used 720 nodes, each with eight Nvidia A100 Tensor Core GPUs for 5,760 GPUs in total, providing up to 1.8 exaflops of performance.[24] credit: wiki
@balaji-kartha
@balaji-kartha Жыл бұрын
Elon , with his outrageously audacious visions attracts the most talented and brilliant people to his companies ❤
@jaimeduncan6167
@jaimeduncan6167 Жыл бұрын
Thanks for sharing the actual numbers. Do you know if Tesla's numbers are fo reduced precision like the ones used for AI inference (16 bit) or Training (32 bits)? Thanks!
@tatradak9781
@tatradak9781 Жыл бұрын
The speed of change and "successful change" is going to be staggering....
@chrisrogers1092
@chrisrogers1092 Жыл бұрын
It should be noted that Telsa is still buying as many Nvidia GPUs as they can get their hands on.
@Toxa1300
@Toxa1300 Жыл бұрын
So they had 1.8 exaflops in 2021 and now are building a computer that only has one exaflop?
@maxwellhouse750
@maxwellhouse750 Жыл бұрын
In an unprecedented move, Dojo changed its name to Skynet.
@NickWindham
@NickWindham Жыл бұрын
Underrated comment
@Tailspin80
@Tailspin80 Жыл бұрын
SkynetX to be exact.
@valdisgerasymiak1403
@valdisgerasymiak1403 Жыл бұрын
@@Tailspin80 Just X :)
@nanakutube
@nanakutube Жыл бұрын
Xnet💫
@cliftondavis6520
@cliftondavis6520 Жыл бұрын
Why Yes lol 😅😆😅😆😅😆😆😅😆😅😆😅
@Rafsways
@Rafsways Жыл бұрын
🎯 Key Takeaways for quick navigation: 00:00 🖥️ Tesla's AI Division has created a supercomputer called Dojo, already operational and growing in power rapidly, set to become a top 5 supercomputer by early 2024. 01:25 💹 Dojo's computing power forecasted to reach over 30 exaflops by Feb 2024, with plans to ramp up to 100 exaflops by Oct 2024. 03:02 💰 Tesla's Dojo, a specialized AI training cluster, equates to a $3 billion supercomputer, offering remarkable AI model training capabilities. 04:00 🚗Dojo focuses on training Tesla's full self-driving neural network, surpassing standard supercomputer definitions for specialized AI training. 05:38 📸 Dojo processes immense amounts of visual data for AI model training through labeling, aiming to automate a task previously done by humans. 07:01 🧠 Dojo adopts a unique "system on a chip" architecture, like Apple's M1, optimizing efficiency and minimizing power and cooling requirements. 08:10 💼 Dojo operates on tile levels, fusing multiple chips to create unified systems, enhancing efficiency and power in AI training. 10:00 ⚙️ Tesla can add computing power through Dojo at a lower cost, avoiding competition for industry-standard GPUs, potentially leading to a new business model. 11:23 🌐 Future versions of Dojo could be used for general-purpose AI training, enabling Tesla to rent out computing power as a lucrative business model. 12:45 🔄 Renting out excess computing power from Dojo can potentially revolutionize Tesla's profitability, similar to Amazon Web Services. Made with HARPA AI
@F3PIZZA
@F3PIZZA Жыл бұрын
You feed a link somewhere and it spits these out?! Please share the secrets of your ways?
@prashanthb6521
@prashanthb6521 Жыл бұрын
Thanks.
@Mr7O5
@Mr7O5 Жыл бұрын
It’s crazy to see how far ahead Tesla is in the auto industry
@JrbWheaton
@JrbWheaton Жыл бұрын
Not just auto industry
@fredfrond6148
@fredfrond6148 Жыл бұрын
@@JrbWheaton well said AI too.
@JrbWheaton
@JrbWheaton Жыл бұрын
@@fredfrond6148 Energy, computing, solar, robotics, mining, the list goes on
@davidbeppler3032
@davidbeppler3032 Жыл бұрын
​@@fredfrond6148and lithium refining.
@bits2646
@bits2646 Жыл бұрын
Yeah, autonomous self driving is working for them... Except there are at least 5 manufacturers that already have Level 3 ... And they scrapped all that work and went from visual to AI powered self driving.... Well said, really... amateurs
@intheshell35ify
@intheshell35ify Жыл бұрын
Nice pace, good graphics, not too "fanboy", plenty of terminology, and raised a few questions I need to go look up and think about. All around effective KZbin. Well done.
@cookasaurus_rex
@cookasaurus_rex Жыл бұрын
Except for "Artificial Intelligence *traning* cluster" @ 04:12 :/
@intheshell35ify
@intheshell35ify Жыл бұрын
@@cookasaurus_rex oh man we got an English major in our midst!! I could have watched that a thousand times and not caught it cause that is one superfluous "e" in my estimation and yet we still need to know how to differentiate long and short vowels.
@EdwinAbalain
@EdwinAbalain Жыл бұрын
Well brought presentation with understable analogies!
@Star_Dust___
@Star_Dust___ Жыл бұрын
Can you Imagine, hundreds of thousands of teslas are feeding data to this machine every day
@schrodingerscat1863
@schrodingerscat1863 Жыл бұрын
That is their main advantage, the limiting factor for AI systems is becoming the amount of training data available.
@codingispower1816
@codingispower1816 5 ай бұрын
And still Tesla hasn't done much other than slightly improve FSD that is still widely ridiculed. Don't even get started in BOT until it can actually do something useful at a fast pace.
@AngelSharksXPRIZECarbon
@AngelSharksXPRIZECarbon Ай бұрын
millions
@Star_Dust___
@Star_Dust___ Ай бұрын
@@codingispower1816they’re still years ahead of everyone also they just switched to AI learning so the improvements will be big in short time
@Sammasambuddha
@Sammasambuddha Жыл бұрын
If every vehicle on public streets had a "gps" transmitter giving out data like direction, speed, etc. FSD could take advantage incorporating this localized data (car to car) to help determine its next action. A Futurama episode when the gang went to Robot Planet the robots move like vehicle traffic but fit between each other at high speeds. Perfect trafgic management.
@tomservo5007
@tomservo5007 Жыл бұрын
no one wants to put in a tracking device in their car ffs, this isn't China
@Fastotec9
@Fastotec9 Жыл бұрын
Privacy has left the chat
@getsideways7257
@getsideways7257 Жыл бұрын
@@Fastotec9 What privacy are you talking of this day and age?
@davidbowl9650
@davidbowl9650 Жыл бұрын
@@getsideways7257trust me, we still have a lot of privacy in this day and age. And although I want technology to improve and would love the sharing of location data and things between cars without intrusive being able to monitor people. I would avoid any reduction in privacy
@bitcoinburzanet80
@bitcoinburzanet80 11 ай бұрын
They will kill us all
@paulm7267
@paulm7267 Жыл бұрын
Actually, the semiconductor trend for the past few years is moving away from single chip SoC designs to multi-chip packages, which means the SoC is not on a single piece of silicon, but multiple pieces of silicon inside a single “cpu” package. This is what is used in the M1, the chips in the iPhone, and inside AMD and Intel’s latest cutting edge CPUa etc. Multiple chiplets are placed very close to each other, even stacked one on top of the other inside a “cpu package,” but the SoC is no longer a single piece of silicon in cutting edge products. The reason this is happening is, of course, economics. The different chips are produced in the process nodes that are most economical. So the I/O hub in an AMD cpu is in one process while the cpu clusters are on cutting edge processes in units of 8 or 16 cores per cluster. Then the cpu package has one or more of these separate cluster chiplets placed around an I/O hub chiplet in the AMD example. In an Apple products, the A-series and M1 cpus, separate pieces of silicon for CPU and for memory are stacked inside the CPU package. This is why your M-series computers system memory can’t be upgraded.
@Trust_but_Verify
@Trust_but_Verify Жыл бұрын
Technically they could add additional bus logic to allow external memory for expansion, but that defeats the purpose of being compact.
@TheWallReports
@TheWallReports Жыл бұрын
🎯💯
@schrodingerscat1863
@schrodingerscat1863 Жыл бұрын
The reason chiplets work well is also yields, smaller chips mean higher yields per wafer. Large chips can be made useless by one tiny imperfection where as with say 8 smaller chips covering the same area that same imperfection only loses one smaller chip with all the others being fully functional. Interposers are then constructed using very old and reliable techniques to stitch all the chiplets together. Not quite as fast as a single large chip but considerably cheaper.
@patrikhadorn200
@patrikhadorn200 Жыл бұрын
You need to use the tensor core throughput of the A100. Probably even at lower precision (BF16) to have something realistic to compare against
@MagusArtStudios
@MagusArtStudios Жыл бұрын
it looks like they have the memory right on the chip to maximize the memory speed
@TheBann90
@TheBann90 Жыл бұрын
The Dojo compute figure is 8 bit. The A100 compute figure he uses are 16 bit.
@MarksShrimpTanks
@MarksShrimpTanks Жыл бұрын
Dojo is making the matrix!
@robertb1508
@robertb1508 Жыл бұрын
I more than liked this video. It was a wealth of information in less than 15 minutes. 🙂
@stevemccrea2688
@stevemccrea2688 Жыл бұрын
A 'flop' is a floating point operation which is more complicated than a mere computer instruction.
@GEOsustainable
@GEOsustainable Жыл бұрын
I take it he is Mac man. In the old days we called this 'cascading', and we had 27 iMacs connected. No one ever talks about the software needed to use this configuration. This sounds impressive, but the Hardware is far beyond available Software to run them. They still don't have much to do. Back then we thought 10 gigaflops was incredible. Working on these things is what I used to do and explains why I garden now.
@MeatMechArchitect
@MeatMechArchitect Жыл бұрын
What’s amazing is that the auto industry is just the beginning. This will be the foundation of advances in gaming, MMO-VR, physics research, simulations, and more.
@Ivdde
@Ivdde Жыл бұрын
This is the beginning of true FSD, and will be an epic win if tesla plays their cards correctly.
@L3nny666
@L3nny666 Жыл бұрын
which new marketing scam term will it be next? FULL self driving? TRUE FULL self driving? I SWEAR BY GOD THIS IS THE TRUEST AND FULLEST self driving? THIS TIME FOR REAL FULL self driving? I PROMISE NEXT YEAR IT'S READY FULL self driving?
@Astra2
@Astra2 Жыл бұрын
​@@L3nny666The term is just full self driving. Always has been and always will be.
@L3nny666
@L3nny666 Жыл бұрын
@@Astra2 as we all know, FULL SELF DRIVING is a marketing term as it's not fully autonomous. Now the comment above me said "true" full self driving...which is rather funny considering for how long musk has promised true autonomy...if you don't get a joke and rather be a butthurt tesla fanboy and billionaire boot licker, go ahead.
@Astra2
@Astra2 Жыл бұрын
@@L3nny666 Full self driving means fully autonomous. It's currently in beta, that's why it's not fully autonomous. I understand what you mean but I think it would be unwise to doubt the same person who figured out how to land rockets.
@L3nny666
@L3nny666 Жыл бұрын
@@Astra2 yeah sure..."beta". tesla is still at SAE level 2, while mercedes and toyota are already at sae level 3. and you don't really believe musk figuered out any of this technology, right? this man is an investor and not an engineer.
@lab.growth
@lab.growth Жыл бұрын
Amazing video for better understanding the implications and funcionality of dojo! Thanks :)
@rippingbag
@rippingbag Жыл бұрын
Fear does not exist in this Dojo!
@UmangPatel
@UmangPatel Жыл бұрын
strike first strike hard
@colinmorand129
@colinmorand129 Жыл бұрын
No sensai
@TimeTravel1314
@TimeTravel1314 Жыл бұрын
tesla ,forever
@mikewallace8087
@mikewallace8087 Жыл бұрын
Leonardo da Vinci forever !!!
@rosslawrence4628
@rosslawrence4628 Жыл бұрын
@1:55 Too funny. An Exoflop is a 1 with 18 zeros behind it.... and the video shows 15 zeros. A lot of good info here on Dojo... thanks for the update.
@vinnylamoureux1187
@vinnylamoureux1187 Жыл бұрын
18 zeros would be too small on the display. We don't all have your perfect eyesight. Hehe
@TheOlvan
@TheOlvan Жыл бұрын
At 2:11 your big number is missing three more zeros! That number is only 1 quadrillion.
@JulissaLucas-f5w
@JulissaLucas-f5w Жыл бұрын
Well brought presentation with understable analogies!. Thank you for your hard work .
@nexpro6985
@nexpro6985 Жыл бұрын
Apart from the inaccuracies and generalizations in this video there were some nice images.
@SomeThingElseYT
@SomeThingElseYT Жыл бұрын
We squandered the train
@ClaudeEnckels
@ClaudeEnckels 11 ай бұрын
infinite possibilities of developments
@IngeniousDimensions369
@IngeniousDimensions369 Жыл бұрын
Keep up the great work, Elon & Tesla Team.💯💯 Ready to see the luxury Tesla RVs also, Boss.😉😉
@corbinf7313
@corbinf7313 Жыл бұрын
What is a wait if we’ve ever been sursnagged to unforgivable faulty price presumptions👽
@daviddickey9832
@daviddickey9832 Жыл бұрын
Imagine car insurance companies deciding to only insure driverless cars.
@bitcoinburzanet80
@bitcoinburzanet80 11 ай бұрын
Thats so stupid to say. Think about what you just said
@phvaessen
@phvaessen 6 ай бұрын
that's going to happen sooner than you think ! Governments will refuse people to drive cars not being autonomous ! 95% of accidents are due to human error, that's an enormous cost to the social security.
@daviddickey9832
@daviddickey9832 6 ай бұрын
@phvaessen it's going to happen but it shouldn't, even if it means a higher mortality rate
@11insertusernamehere
@11insertusernamehere 6 ай бұрын
@@daviddickey9832 what do you mean higher mortality rate? will driverless cars cause more accidents than human drivers in your opinion?
@daviddickey9832
@daviddickey9832 6 ай бұрын
@@11insertusernamehere what I'm saying is that automated cars have a lower mortality rate, but we shouldn't allow institutions to effectively prevent any person from driving even though people driving has a higher mortality rate
@MengHiongTan-c5t
@MengHiongTan-c5t 9 ай бұрын
This Is out of my mind, amazing ❤❤❤❤❤
@michaelrichey8516
@michaelrichey8516 Жыл бұрын
2:11 - that's only 15 zeros, you're 3 zeros short.
@clothcapkev2088
@clothcapkev2088 Жыл бұрын
Time will tell like the hyperloop and Tesla truck could go either way.
@v.gedace1519
@v.gedace1519 Жыл бұрын
Realy a great video! Thanks!
@nedyalkokarabadzhakov5405
@nedyalkokarabadzhakov5405 Жыл бұрын
absolutly professional and detail expalnation stright to the point. Thank and wait for the next.
@mpd8633
@mpd8633 Жыл бұрын
Excellent video.
@Zoom_1012
@Zoom_1012 Жыл бұрын
That was quite interesting. Thanks. 🌴☀️🌴
@KenCharleton
@KenCharleton Жыл бұрын
Great description of Dojo.
@stevenrushing334
@stevenrushing334 Жыл бұрын
Great explanation, thanks!
@EricRatzlaff_
@EricRatzlaff_ Жыл бұрын
Love your content, thanks for all you do
@marlbankian
@marlbankian Жыл бұрын
Excellent food for thought
@BikeNutt1970
@BikeNutt1970 Жыл бұрын
Another great vid. Thanks 👍
@mikemccormick6128
@mikemccormick6128 Жыл бұрын
I had a thought. Smartphones fall into basically two camps. iOS and Android. Is it possible that autonomous vehicles would also fall into two camps? Tesla and Apple instead of Apple and Google. The traditional car companies are too far behind and will likely never catch up to Tesla because they wanted to wait and see, because no one actually believed that Tesla's vision only would work. Everyone was betting that Tesla would fail. Well it's pretty clear now that Tesla was right. So I believe that Tesla will license their technology to other car companies. I also believe that Apple will license their technology to car companies. I believe that Apple will come out with their autonomous car technology in 2026. That should be about when Tesla perfects their autonomous car technology. In Teslas case, no later than the end of 2026 and in Apple's case, no earlier than 2026.
@timmuyrers2057
@timmuyrers2057 Жыл бұрын
Even with massive computing data, you still need as much training data as you can get. I love Apple, and am invested in their stock, but I don’t believe it will come close to teslas date of achieving FSD..
@mikemccormick6128
@mikemccormick6128 Жыл бұрын
@@timmuyrers2057 I can't say you are wrong. Apple, like everyone else, is too scared of the cars making mistakes. Allowing the beta process is a huge advantage. I did say in my post that Apple would come out with something maybe AFTER 2026 (later then). But that Tesla would be maybe EARLIER than 2026( no later than). Or I could be wrong altogether. But I wouldn't count Apple out just yet.
@aero1000
@aero1000 Жыл бұрын
In Apple's case most likely not earlier than 2028 or even 2030. While I do applaud apple for what they have done with computer chips and he new AR headset is impressive. They have reportedly reduced their ambitions in the car space. Even if they went all in, I don't think that FSD is something you can take shortcuts on.
@daniel_960_
@daniel_960_ Жыл бұрын
There’s no Apple autonomous car technology lol. They can’t even get Siri right. That’s not their stronghold. Apple won’t be present in auto market. With the Apple and Android analogy in the auto market it’s indeed interesting. But in that case it looks more like Tesla being Apple, making the few premium products in a huge scale, but also Android, licensing their software and ecosystem to others. Really looks more like a world where Android doesn’t exist and everyone licenses iOS.
@berated4541
@berated4541 Жыл бұрын
AMD deserves the credit for the MCM design. As they were the first to show its benefits large scale with their Ryzen processors.
@darrelldarrell1447
@darrelldarrell1447 10 ай бұрын
Actually it was the thread ripper.
@redredred1
@redredred1 Жыл бұрын
@2:10 - You're either missing 3 zeroes, or an exaflop is 15 zeroes.
@modern-hestia
@modern-hestia Жыл бұрын
super liked the video thank you so much
@jaysmithdesign
@jaysmithdesign Жыл бұрын
Elon: "Hey world don't do AI" Elon: "Welcome Dojo"
@mike-ology22
@mike-ology22 Жыл бұрын
When you said, you showed a paper dollar. That is currency. Gold and silver is money. Money is something of value
@JarrodR84
@JarrodR84 Жыл бұрын
I love your news letter!!
@robwashere69
@robwashere69 Жыл бұрын
Hey, i was the first viewer and first lile. Lol. Grewt video. This is a game changer. One more money maker for Tesla. Here comes FSD and Optimus.
@sa34w
@sa34w Жыл бұрын
That will come because of Dojo, Dojo is the secret sauce of Tesla for FSD and Optimus.
@jeffharmed1616
@jeffharmed1616 Жыл бұрын
Nice work thanks
@neversaynever5157
@neversaynever5157 5 ай бұрын
GREAT VIDEO THANKS FOR EXPLAINING ALL THAT, IT MAKES IT CLEAR ITS A NO BRAINER FANTASTIC 🙂👍
@1Eagler
@1Eagler Жыл бұрын
Its crazy to find a company like Tesla in auto industry
@tatradak9781
@tatradak9781 Жыл бұрын
why?
@RocketPal
@RocketPal Жыл бұрын
Meaning of your comment?
@dylanthomas12321
@dylanthomas12321 Жыл бұрын
I think he means crazy great!
@frozenfishjohan
@frozenfishjohan Жыл бұрын
Thank you very much
@tibiloft7471
@tibiloft7471 Жыл бұрын
Yeye when I see it in action I will believe it
@christopheraldrich665
@christopheraldrich665 Жыл бұрын
Thanks!
@JohnWarner-lu8rq
@JohnWarner-lu8rq Жыл бұрын
Thankfully, self-driving cars, like EV's, will never be mainstream.
@WhosAmI
@WhosAmI Жыл бұрын
Thank you for your hard work ❤
@petersimon985
@petersimon985 Жыл бұрын
Huge Thank you 🎉❤
@jacoblf
@jacoblf Жыл бұрын
I imagine a scenario where Tesla sells Trainjng Tiles and makes more profit from TTs than cars. Your “game changer” is spot on.
@laStar972chuck
@laStar972chuck Жыл бұрын
That video was PACKED with analogy, relevant comparison and an amazing level of pedagogy. Wow ! Thanks, man. Im already familiar with all this so I thought I was just getting an over-stretched spec video just to get a specs update on the next model coming (like most tech youtuber like to do)... I got so much more out of it. Congrats.
@mitch_the_-itch
@mitch_the_-itch Жыл бұрын
I wonder if that would run DCS in VR with full graphics options?
@NA-rh7iy
@NA-rh7iy 9 ай бұрын
Nvidia can do it
@KingDavid9999
@KingDavid9999 Жыл бұрын
wow i want one!
@NicholasNerios
@NicholasNerios Жыл бұрын
Dojo tesla optimus, can't wait.
@MRF77
@MRF77 Жыл бұрын
Excellent video my man!
@andrewsolomon9877
@andrewsolomon9877 Жыл бұрын
The Mojo Dojo Casa Supercomputer!
@flavioprojects8974
@flavioprojects8974 Жыл бұрын
Great stuff! Please turn up the background music a little more in the next videos.
@azamat_bezhanov
@azamat_bezhanov 7 ай бұрын
Is it real to make laptop on DOJO Chip
@bobmutchseo
@bobmutchseo Жыл бұрын
There is a difference between these two, Try to get it right. OPS -- Operations per second. FLOPS -- Floating point operations per second.
@HumanAction76
@HumanAction76 Жыл бұрын
In the future, Tesla will make trillions selling Dojo systems to other AI companies.
@landofstan246
@landofstan246 Жыл бұрын
Well done.
@HobokenHam
@HobokenHam Жыл бұрын
I loved your video but.......to define an exaflop you show 1 followed by 15 zeros and say the 1 should be followed by 18 zeros. I am just curious which you intended.
@skaltura
@skaltura Жыл бұрын
M2 Ultra !== the most powerful computer you can buy. Sure for ARM it is probably the most powerful, but it is far from actual client (end user) max performance chip.
@schrodingerscat1863
@schrodingerscat1863 Жыл бұрын
Not even the most powerful ARM system not by a long way. There are ARM processors available that have hundreds of cores not the dozen or so Apple put into their designs.
@cubertmiso
@cubertmiso Жыл бұрын
Well, the channel is catered to Tesla fanboys. No need to check any facts, just join the movement and fly to the stars.
@anthonyshiels9273
@anthonyshiels9273 Жыл бұрын
​@@cubertmisoThe Boring Company, Neuralink, Starlink, SpaceX, "Twitter", ... It's not just about cars, it's about EVERYTHING Elon Musk.
@Panzilla1
@Panzilla1 10 ай бұрын
if i had none the year before and the next year I have some, I have created a 100% increase in my production...
@cosmoshfa88savant66
@cosmoshfa88savant66 Жыл бұрын
Good content well presented,,,
@mworld
@mworld Жыл бұрын
With great power, comes great ... oh wait, the batteries caught fire again.
@guruware8612
@guruware8612 Жыл бұрын
love it when talking about supercomputers and showing html and javascript, exactly the thing which needs exa-flops a one with EIGHTEEN zeros- and showing 15 in the video, btw here we call that trillions.
@KDzilna
@KDzilna Жыл бұрын
You said 1 with 18 zeros, but put 15, make sure minor details add up!
@shiwansvaishya4803
@shiwansvaishya4803 Жыл бұрын
Mind blown up
@MikkoRantalainen
@MikkoRantalainen Жыл бұрын
Compared to Apple CPUs that still use DRAM for memory, Dojo is using lots of SRAM which is highly expensive but much faster than DRAM. Most computers use SRAM only of L1 cache in the CPU and the main memory is using cheaper DRAM tech.
@schrodingerscat1863
@schrodingerscat1863 Жыл бұрын
Totally different applications, the Dojo processors only need small amounts of memory because their task is very specific and highly optimised for that single task. Apple CPUs are just general purpose CPUs with a lot of sub systems integrated into a single package to reduce communication power consumption and latency. Dojo is more like a GPU than a CPU.
@MikkoRantalainen
@MikkoRantalainen Жыл бұрын
@@schrodingerscat1863 Dojo also has system-wide DDR4 SDRAM but it's used as fast storage device instead of treating it like a traditional RAM. Load and store speeds to storage (I would assume SDRAM) are 400 GB/s and 270 GB/s according to Wikipedia article. If you compare this to modern computers, Intel i9-13900K has max memory bandwidth about 90 GB/s while using all cores in optimal memory channel configuration. But yes, SRAM has single clock latency: Dojo runs at 2 GHz so that would be 0.5 ns vs best available DDR4 SDRAM has latency around CL12 or about 6.7 ns. So obviously you would try to write apps so that you can use only the memory that as 13x smaller latency. However, that doesn't mean that Dojo cannot run other apps, too, only that you cannot get optimal performance with apps that cannot fit at least the full inner loop into the available SRAM.
@hammerfist8763
@hammerfist8763 Жыл бұрын
The comparison of M2 to traditional PC is flat out wrong. The M2 at 3.6 TFLOPS is about twice as powerful as an Intel processor (I9-13900K) @ 1.7 TFLOPS. But an M2 is a joke compared to any PC workstation. A pc with even a moderately priced $600 GPU (RTX 4070) has anywhere from 8-times (FP32) to 125 (tensor) times the processing power of an M2.
@IndenturedYoutubeSlave
@IndenturedYoutubeSlave Жыл бұрын
Desktop cpu is a utility vehicle that supercharged by a powerful GPU, ( go any where vehicle that can be fitted with upgrades to fit multiple purposes) Apple M2 is a street drivable dragster.(light multi purpose vehicle but really only fast in a straight line)
@hammerfist8763
@hammerfist8763 Жыл бұрын
@@IndenturedKZbinSlave Fastest M2 chip is 24 cores at 3.5 ghz. As an RISC chip without the CISC overhead it is theoretically more efficient. But a comparable PC chip, Intel or AMD runs 4-4.5 ghz, with 16-32 cores. The base M2 is a faster, more efficient low-end setup, but more expensive. The high end M2 and M2 ultra are twice as expensive as comparable PC's so I don't see the value. Where is the efficiency/value?
@Asterra2
@Asterra2 Жыл бұрын
2:10 Says 18 zeros. Shows 15 zeros.
@Shazbat5
@Shazbat5 Жыл бұрын
Still turns left in front of oncoming traffic...
@sgrdpdrsn
@sgrdpdrsn Жыл бұрын
Your BEST video up to now!! Thank you!!😛
@Vega2099x
@Vega2099x Жыл бұрын
... Ok, that's a cool name, well done 👏🏻👏🏻👏🏻
@Doidera-h5f
@Doidera-h5f 2 ай бұрын
I am a big fan of this super computers race.. this subject...
@biggstile
@biggstile Жыл бұрын
Keep up the good work
@brucesearl4407
@brucesearl4407 Жыл бұрын
This is very well done. Thank you!
@sociopathicnarcissist8810
@sociopathicnarcissist8810 Жыл бұрын
Be interested in seeing how it compares with the new Grace Hopper processor and scalability capability from nvidia.
@caralosmendezgomez9048
@caralosmendezgomez9048 Жыл бұрын
probably Nvidia will be faster and for all purposes, in the same way AMD will epic thread reaper 128 cores smokes into oblivion anything from Apple, apart from being able to compute open source
@jonasnitz7678
@jonasnitz7678 Жыл бұрын
"That is a one with 18 zeroes behind it" and they show 15 zeroes... brilliant.
@ThrashLawPatentsAndTMs
@ThrashLawPatentsAndTMs Жыл бұрын
Does Tesla also manufacture the DoJo chips?
@beretteres4031
@beretteres4031 Жыл бұрын
finally, the Mojo Dojo Supercomputer
@pvic6959
@pvic6959 Жыл бұрын
not sure why google/google cloud was not mentioned. This seems to be similar to googles "TPU" or Tensor Processing Unit right? Just asking to make sure i ve understood correctly. Google uses TPUs for AI training as well. I imagine its been used for their self driving car too
@cosmoshfa88savant66
@cosmoshfa88savant66 Жыл бұрын
Liked & subbed!!! Ireland,,,
@Jam-In-With-Ben
@Jam-In-With-Ben Жыл бұрын
hi
@somaday2595
@somaday2595 Жыл бұрын
Is Tesla constantly uploading vehicle driving data to revise its autonomous driving program and then downloading those revisions?
@bigpicture3
@bigpicture3 Жыл бұрын
To put it simply, FSD must produce a set of correct and safe driving responses, to a set of situational images created by the cars cameras. That requires some amount of "prediction", or what each object in the image is, and what it is likely to do next. Ignoring inattentiveness, even human drivers can get that wrong a lot of times. If FSD is to be successful it needs to get that right more often than human drivers do. Also driving responses need to be different under different road surface and weather conditions, and I don't even know if FSD accommodates this. But in any case the "computational power" required for this, probably cannot be "on board" the vehicle. It might resolve to image analysis, object identification within the image, and probabilities of what each object will do next, and the driving response to that. That is a lot of possible "image" - "driving response" combinations to be processed in real time. Even if the super computer could do it, then there is also the "real time" communication between the computer and the vehicle. (the bandwidth)
@georgeginsburg545
@georgeginsburg545 Жыл бұрын
I think that first picture of the number of instructions in an exa-flop, is wrong. It should show 18 zeros for 10 to the eighteenth power, no? It’s showing 15 zeros.
@QTPewPew
@QTPewPew Жыл бұрын
Saying the M2 ultra is the most powerful computer you can buy is HILARIOUS.
@JavGaracia
@JavGaracia Жыл бұрын
The chip will eventually resemble a rubics cube . And spin automatically for multiple use combinations.
@stanislav4607
@stanislav4607 Жыл бұрын
2:20 why not just say 1 ExaFlop of compute is equivalent to 3 000 Nvidia A100 GPUs?
@grey7513
@grey7513 Жыл бұрын
Judge a person by their actions, not their words. Judging by history this is vaporware.
@pibblesnbits
@pibblesnbits Жыл бұрын
Dojocat supports this computer design.
How Supercomputers ACTUALLY Run The World
21:17
The Tesla Space
Рет қаралды 113 М.
Tesla is Quietly Building Up a 10 Trillion Dollar Weapon
13:32
TMIO Tesla
Рет қаралды 133 М.
Я сделала самое маленькое в мире мороженое!
00:43
2 MAGIC SECRETS @denismagicshow @roman_magic
00:32
MasomkaMagic
Рет қаралды 24 МЛН
The Real Reason Tesla Built The DOJO Supercomputer!
17:05
The Tesla Space
Рет қаралды 250 М.
WATCH: Niall Ferguson Stuns World Leaders at ARC Australia - "Are we the Soviets now?"
19:44
Alliance for Responsible Citizenship
Рет қаралды 190 М.
Tesla Solar Roof Review: Was it Worth It?
30:27
Marques Brownlee
Рет қаралды 13 МЛН
Ingenious Construction Workers That Are at Another Level
33:17
#Mind Warehouse
Рет қаралды 73 М.
The Problem With Elon Musk
42:46
Johnny Harris
Рет қаралды 4,9 МЛН
Why It Was Almost Impossible to Make the Blue LED
33:45
Veritasium
Рет қаралды 26 МЛН
The Death of Europe's Last Electronics Giant
18:39
TechAltar
Рет қаралды 4,1 МЛН
Deep Learning: A Crash Course (2018) | SIGGRAPH Courses
3:33:03
ACMSIGGRAPH
Рет қаралды 3,2 МЛН