Rajesh Pandian M

I ❤️= 🚀+❤️ codes.
#GPU #Performance, Graph Analytics and #HPC #CUDA & #CPP #LINUX. #Research Masters + #PhD @iitmadras

[Rajesh Pandian M @mrprajesh]

And that's my favourite algorithm and one of my favourite inventor/scientist.

[MIT CSAIL @MIT_CSAIL]

Happy birthday to the late Edsger Dijkstra, whose algorithm solved the “single-source shortest path” problem: https://t.co/BtHipJSX7H (Nathaniel Fan)

[Rajesh Pandian M @mrprajesh]

#irctc weird senior citizens rules. 😭

[Anatoli Kopadze @AnatoliKopadze]

Former Meta top-tier engineer:

"I don't review the code anymore. I got to a point where I never catch anything the agents don't catch."

He runs 20-30 agents at once and ships 20-40 PRs a day, work that used to take a full team a month.

In 55 minutes he explains everything he knows and builds a fully working workflow from scratch.

Watch it, then read the full guide on building loops below.

[HPCwire @HPCwire]

ETH Zurich Team Wins 15th Annual ISC Student Cluster Competition
@cscsch @ETH_en #HPC #ISC26
https://t.co/cJz9BDFTQZ

[Google Cloud Tech @GoogleCloudTech]

Introducing the Open Knowledge Format (OKF), an open specification that formalizes the LLM-wiki pattern into a portable, interoperable format.

AI is only as smart as the context we give it. As we build more advanced, agentic AI systems, they need accurate metadata and context to be useful. But in most organizations, that context is locked inside fragmented data catalogs, isolated wikis, scattered code comments, or the minds of senior engineers. Every time a new AI agent is built, teams are forced to solve the exact same context-assembly problem from scratch.

To solve this, we've announced OKF, a vendor-neutral, open specification that formalizes the "LLM-wiki pattern" into a portable, interoperable format. It provides a standardized way to represent the enterprise knowledge that modern AI systems rely on.

— Just markdown: readable in any editor, renderable on GitHub, indexable by any search tool
— Just files: shippable as a tarball, hostable in any git repo, mountable on any filesystem
— Just YAML frontmatter: for the small set of structured fields that need to be queryable: type, title, description, resource, tags, and timestamp

We’ve also shipped reference implementations to help you hit the ground running, including an enrichment agent for BigQuery, a static HTML visualizer, and live sample bundles on @github → https://t.co/ilhAMCrcTc

➕ Knowledge Catalog can now natively ingest OKF!

Stop reinventing data models and building bespoke integrations for every new AI tool. Here's more about how OKF works → https://t.co/FR4kJRsgEH

[Rajesh Pandian M @mrprajesh]

Prof CPR and the Resuscitation of Algorithmic Thinking ❤️ https://t.co/GZFfi2qG8f

[ani @anirudhbv_ce]

I implemented @GoogleResearch's TurboQuant as a CUDA-native compression engine on Blackwell B200.

5x KV cache compression on Qwen 2.5-1.5B, near-loseless attention scores, generating live from compressed memory.

5 custom cuTile CUDA kernels ft:
- fused attention (with QJL corrections)
- online softmax
-on-chip cache decompression
- pipelined TMA loads

Try it out: https://t.co/m5vkJxWIY6

s/o @blelbach and the cuTile team at @nvidia for lending me Blackwell GPU access :)

cc @sundeep @GavinSherry

[NVIDIA HPC Developer @NVIDIAHPCDev]

🎉 "This is the 20th anniversary of CUDA. We have been working on this architecture for 20 years ... to now have built up hundreds of millions of GPUs and computing systems around the world that run CUDA."

[Andrej Karpathy @karpathy]

New art project.
Train and inference GPT in 243 lines of pure, dependency-free Python. This is the *full* algorithmic content of what is needed. Everything else is just for efficiency. I cannot simplify this any further.
https://t.co/HmiRrQugnP

[Mark Saroufim @marksaroufim]

Cool data from ~100K deduplicated submissions to the nvfp4 competition
1. CUDA C++ still on top
2. Cute DSL is the only pythonic DSL that matters in the top 10%
3. Triton decently popular but not among the top 10%

[Association for Computing Machinery @TheOfficialACM]

Happy New Year! As of January 1, 2026, all ACM publications and related artifacts in the ACM Digital Library are now open access, making computing research more accessible, discoverable, and reusable worldwide.

“This is a truly monumental milestone,” said ACM President Yannis Ioannidis, marking a new era for the global computing community.

Explore ACM’s open access journey:
👉 https://t.co/3bvtqxEqiU

#OpenAccess #ACM #OpenScience #ComputingResearch

[Jared Roesch @roeschinc]

Thrilled to announce we're open-sourcing the CUDA Tile dialect and bytecode! https://t.co/wpy2BoybAk

What's included:
    • CUDA Tile MLIR dialect
    • Bytecode serialization/deserialization support
    • MLIR Python bindings for programmatic IR construction
    • Conformance test suite

For developers: You can now integrate CUDA Tile directly into your projects using MLIR and generate CUDA Tile dialect or bytecode natively!

Learn more about CUDA Tile:
    • NVIDIA Developer: https://t.co/vjf6KnrMMU
    • CUDA Tile Specification: https://t.co/QJiF8QVd2i

This project represents the collaborative effort of multiple teams across NVIDIA. A huge thanks to everyone who made this possible!

It has been a privilege to be involved.

[Rajesh Pandian M @mrprajesh]

Yay. Waiting for it try them hands on. ❤️❤️❤️

[Bryce, the CUDA Colonel @blelbach]

CUDA Tile has shipped! You can now `pip install cuda-tile`. I'm excited to see what y'all will build with it!

Docs & resources:
https://t.co/COaPkL7ZIV

GitHub:
https://t.co/XWmNmrUi8F

[Rajesh Pandian M @mrprajesh]

Focus on Your Algorithm—NVIDIA CUDA Tile Handles the Hardware | NVIDIA Technical Blog https://t.co/EC11Ej5aDJ
❤️❤️

[Rajesh Pandian M @mrprajesh]

GATE prep https://t.co/H8XoXacJdi

[Rajesh Pandian M @mrprajesh]

Inside NVIDIA GPUs: Anatomy of high performance matmul kernels https://t.co/leL4vDJgt3

[Rajesh Pandian M @mrprajesh]

Qualcomm buys open-source electronics firm Arduino https://t.co/hxiQajl7ts

[Rajesh Pandian M @mrprajesh]

Introducing NVFP4 for Efficient and Accurate Low-Precision Inference
https://t.co/XJUIL7sAq2

[Rajesh Pandian M @mrprajesh]

NVFP4 Trains with Precision of 16-Bit and Speed and Efficiency of 4-Bit | NVIDIA Technical Blog
https://t.co/KQCJyp9w5q

[Rajesh Pandian M @mrprajesh]

Happy Retirement, Amma. 🤩😍

[Rajesh Pandian M @mrprajesh]

How to Improve CUDA Kernel Performance with Shared Memory Register Spilling
https://t.co/VHDLIV3yz6 ❤️❤️