Thanks for helping bridge enthusiasts to start creating amazing experiences with WebGPU, all thanks to your passion for creating invaluable videos like this. Much love!
Congratulations for the very nice and informative tutorial. Love the way you used markdown to write into the video. Hope you get a lot of subs and likes you deserve it. Cheers 🙃
As a small Web Graphics/WebGPU RUclipsr, it’s great see more folks talking about this! Especially showing how it can be used for AI workflows. Great work 🤓
Idk man, I wasn't sure if it's faster to bounce off a pointer to the value, or to perform one entire multiplication every time I want a specific index. I went with an array of arrays approcach to access indeces simply by pointers instead of having extra calculations (multiplication is expensive).
@@danser_theplayer01 Fair. It could be faster as I haven’t done any performance testing. You brought up a good point 👍 However for building a tensor math system you need a buffer and a shape for flexibility. Also WebGPU only supports CS shaders up to 3 dimensions. For higher dimensional tensors we’re forced to flatten the array anyways.
Darn shame it's not supported in Node. I'm making some math package and I could really benefit from like a hundred distinct cores on the GPU instead of an average of 12 logical processors in a mid range computer CPU.
![Healthbars, SDFs & Lighting • Shaders for Game Devs [Part 2]](http://i.ytimg.com/vi/mL8U8tIiRRg/mqdefault.jpg)
![Blox Fruits Dragon Rework Update [Full Stream]](http://i.ytimg.com/vi/EqDAp8udhm0/mqdefault.jpg)
plz continue, youtube lacks structured and comprehensive content on webGPU
Sure! Thanks for watching
very true
Please more WebGPU compute shaders! not enough of this content. Cheers.
Thanks for helping bridge enthusiasts to start creating amazing experiences with WebGPU, all thanks to your passion for creating invaluable videos like this. Much love!
@@vokusz I’m hoping to see some amazing stuff 😃.
Thanks for the kind words, I appreciate it ❤️
Been trying to get into WebGPU for compute with no prior GPU prog. experience (e.g. CUDA). As such, this video was very helpful. Thank you!
Congratulations for the very nice and informative tutorial.
Love the way you used markdown to write into the video.
Hope you get a lot of subs and likes you deserve it.
Cheers 🙃
Thank You!
Yeah that markdown trick was very exciting when I discovered it 😄
Thanks for giving me lots of positive energy!
I appreciate it ♥
@@visionary_3_d No problem my friend, I know you are awesome!!! Keep up the good work!!!!
As a small Web Graphics/WebGPU RUclipsr, it’s great see more folks talking about this! Especially showing how it can be used for AI workflows. Great work 🤓
please, more vedios on compute shaders, this was amazing
@@ozzy-fr7vj alright 🤝
This is exactly what i was thinking. Thanks
Fk yeah!! Been waiting for this sooo long
@@peoplebehindindustry Let’s Go 🔥
Wow i just started it then there's a video.
Thanks for sharing. Part 6 is...not explained?
That's right!
I will explain that part in a dev log (soon).
i can do 92% in 6.5 seconds (1epoch) on the cpu without CNN so definitely some optimization needed there :D
Yes. Exactly!
There's a lot of room for optimization.
Can you also share if your algorithm uses SIMD, or other optimization techniques ?
love your conetnt ncie job
@@ErwinMotor0 Thanks 🙏 appreciate the kind words 🤝
Thank you
yw.
thanks bro
yw.
Can GPU be utilized to run a Genetic Algorithm run!
What font you're using for coding?
Glad you liked it!
I'm using Consolas ligaturized v3.
Hello, what's the color schema do you use for coding and code examples in this video?
@@romanl.4293 it’s a custom one. but I use Monokai Pro ( Octagon ) as the base.
Idk man, I wasn't sure if it's faster to bounce off a pointer to the value, or to perform one entire multiplication every time I want a specific index. I went with an array of arrays approcach to access indeces simply by pointers instead of having extra calculations (multiplication is expensive).
@@danser_theplayer01 Fair. It could be faster as I haven’t done any performance testing.
You brought up a good point 👍 However for building a tensor math system you need a buffer and a shape for flexibility.
Also WebGPU only supports CS shaders up to 3 dimensions. For higher dimensional tensors we’re forced to flatten the array anyways.
so, from now on, don't we have to use torch?
for serious machine learning stuff ? sure!
@ wow, please make a video for the huggingface transformer alternative.
Lesgo, we gonna lure all the math and ML people over from Python to JavaScript🔥🔥 (which is faster than python from the get go).
eh, mojo has a higher chance for that to happen, since it's more familiar and it's a sane environment unlike js, TS idk enough to say.
I mean, I’m planning on taking everything in this video to C and compiling to WASM / WebGPU, so I’m not sure how many people you’re converting, lol.
Darn shame it's not supported in Node. I'm making some math package and I could really benefit from like a hundred distinct cores on the GPU instead of an average of 12 logical processors in a mid range computer CPU.
@@danser_theplayer01 it should be available in node :
developer.chrome.com/blog/webgpu-ecosystem
Although I haven’t tried it myself.