Chedy of the Najjars
@CppChedy
Followers
103
Following
6K
Media
62
Statuses
2K
a Muslim, anime, manga, C++, Compiler Explorer.
Joined July 2017
Finally, graduated with 18/20. thanks for the amazing experience @VectorizedIO. specially thank you to: @emaxerrno, @MaslankaMichal, @dotnwat, @KKyrimis, @_0x5d. also thanks for @mattgodbolt for everything in all the past years.
5
0
8
๐ ๐น๐ถ๐๐ ๐ผ๐ณ ๐ต๐ฒ๐น๐ฝ๐ณ๐๐น ๐๐ผ๐ผ๐น๐ ๐ถ๐ป ๐ฎ ๐๐ถ๐ป๐๐
๐๐๐๐๐ฒ๐บ ๐น๐ฝ๐ถ๐ฑ๐๐๐ฎ๐ - monitors how much of the system's resources, such as CPU, memory, device IO, task switching, and threads, are being used by all or a specific set of programs. ๐น๐ป๐ฒ๐๐๐๐ฎ๐ -
8
160
1K
I wrote a new post showing how to write LLVM transformation passes. Check it out!! #llvm #blogpost #cpp #tutorial
https://t.co/uQp1FIuT2g
#LLVM #cpp #compiler #blogpost
dev.to
Introduction In the previous article, we learned about LLVM passes and wrote our first...
0
0
0
Copy-pasting PyTorch code is fast โ using an AI coding model is even faster โ but both skip the learning. That's why I asked my students to write by hand โ๏ธ. ๐ฝ Download: https://t.co/tMWgeYKzz9 After the exercise, my students can understand what every line really does and
8
53
293
Published new post on writing LLVM pass - check it out. #llvm #cpptutorials #blogpost
https://t.co/AvJrmOia0i
dev.to
Introduction In my previous post, we went through the not-so-glamorous part: building LLVM...
0
1
0
"I just sent 100 cover letters for jobs!" one of my students proudly told me back in late 2022, just weeks after ChatGPT first arrived. Good for that student. Fast forward to the present. "I just sent 100 cover letters for jobs..." another student told me the same thing, a bit
3
12
63
IO devices and latency by @BenjDicken A cool animated explainer about i/o devices and associated latency https://t.co/zDIPPOh2bK
8
228
1K
KV caching, clearly explained:
You're in an ML Engineer interview at OpenAI. The interviewer asks: "Our GPT model generates 100 tokens in 42 seconds. How do you make it 5x faster?" You: "I'll optimize the model architecture and use a better GPU." Interview over. Here's what you missed:
4
175
1K
How to multiply two matrices on a GPU or TPU by hand โ๏ธ? Learn more at my keynote lecture next week ๐ https://t.co/ydmA0ypkvg (hosted by Together AI) I drew 91 frames in total to create this animation. ๐ช
10
126
838
Latency vs. Throughput Ever wondered why your app feels slow even when the bandwidth looks fine? Latency and throughput explain two very different stories of performance. Latency measures the delay per packet. It is what users feel when they click a button. Itโs responsiveness.
7
249
1K
Published new post on writing LLVM pass - check it out. #llvm #cpptutorials #blogpost
https://t.co/AvJrmOia0i
dev.to
Introduction In my previous post, we went through the not-so-glamorous part: building LLVM...
0
1
0
MIT's 6.851: Advanced Data Structures (Spring'21) https://t.co/QmUpWFOEUY This has been on my recommendation list for a while, and the Memory hierarchy discussions are great in the context of cache-oblivious algorithms.
"CacheโOblivious Algorithms and Data Structures" by Erik D. Demaine https://t.co/whP88XqPAV This is a foundational survey on designing cacheโoblivious algorithms and data structures that perform as well as cacheโaware approaches that require hardcoding cache size (M) and block
9
276
2K
If I had to scale a database, here are 6 techniques I'd consider (not joking):
18
89
580
Event-Driven Architecture (EDA) Overview Think of EDA like a concert with a crowd. When something happens on stage (an event), the audience reacts in different ways. The band doesnโt need to know who claps, dances, or records โ they just play, and everyone responds in their own
13
107
730
Neural Network Activation Function! Credit-> Damien Benveniste
7
79
545
