Mini Project: How to program a GPU? | CUDA C/C++

preview_player
Показать описание
Matrix multiplication on a GPU using CUDA C/C++.

Useful References:

Chapters:
00:00 - Introduction
00:36 - Step 1 (Basic CUDA C/C++)
03:02 - Step 2 (Memory Coalescing)
05:57 - Step 3 (GPU Shared Memory)
06:57 - Step 4 (Thread Registers)
09:18 - Step 5 (More Thread Registers)
10:43 - Step 6 (Vectorized Memory Accesses)
12:02 - Final Thoughts
Рекомендации по теме
Комментарии
Автор

Some days the internet makes me sad. Other days it reminds me of all the people with the same niche interests as me and how incredibly talented some of them are. Thanks for putting so much effort into this :)

jarrodangove
Автор

"MINI" Project? What the heck?! You just munched a lot of hard to grasp technical implementations, coded a working example, shared it on your blog, AND made a fully animated video about it!! You make me mad.

Otakutaru
Автор

This is not a "mini" project, you made some real content here! Fantastic video, congrats!

antoninmeunier
Автор

I am reading the CUDA C programming book and your videos are super helpful in visualizing the memory access process! Thank you very much!

eyannoronha
Автор

Yay, CUDA video. Feel like my timeline has been needing CUDA content

nathanpotter
Автор

Hey, I’ve been going through the Programming Massively Parallel Processors book lately and doing some CUDA and this was a GREAT video!!!

jorgegimenezperez
Автор

dude this is actually amazing. you’re the cs version of 3b1b… keep up the great work!

markzakharyan
Автор

I am from embedded systems background but I love your work. Keep Going brother, Just don't quit ! There's always an audience for great content.

epic_mole
Автор

Great stuff Tushar. I have been keen on learning GPU programming so great to see your videos in my feed. Keep it up and all the best.

sanesanyo
Автор

This is by far the most awesome video I’ve seen about gpu compute

danar
Автор

Outstanding video and great explanation. Thanks!

rodrigobernalc
Автор

Good job. The reason workgroups are laid out in 1d/2d/3d grids is that all GPU compute APIs were first designed and implemented on top of existing graphics concepts where calculating outputs as e.g. 2D grids is a natural thing.

jojodi
Автор

Super satisfying to see Manim to show the algorithm like that.

Friedbutter
Автор

Great video. I love the simplicity, and the great explanation.

anwar
Автор

Very cool project, I will definitely go through the project code in the evening!

ihmejakki
Автор

I found your video very helpful and the writeup as well, Thanks

ShadowDC
Автор

Thanks for the research! Keep going! I would like to see other algorithms being run an optimized on GPUs...

zeugzeugzeug
Автор

Beautiful video as usual. I'll am motivated to pick up PMPP after sem end just from watching your videos!

siddharth-gandhi
Автор

Beautiful visualization!! i am enjoying watching your videos. Keep up the good work

qwickstart
Автор

Your videos have similar vibes to 3Blue1Brown Channel!
Great content

AbhishekS-cvcr