Matri𝕏tang⚡️

Semi-programmer.

[Matri𝕏tang⚡️ @matrixkook67]

With 4 years industry experience. Specializing in traditional compiler mid-end optimizations using MLIR, with hands-on LLVM framework experience. Seeking opportunities to pursue a suitable PhD position in program analysis or "classical" compiler .🙏

[Matri𝕏tang⚡️ @matrixkook67]

@roifex 本地大模型就是土法炼钢

[Vivek Galatage @vivekgalatage]

Understand the impact of branching

https://t.co/04FZLB6Hl4

[José Cano @jcanore]

Take a look at our paper "𝘿𝙚𝙛𝙚𝙖𝙩 𝙩𝙝𝙚 𝙃𝙚𝙖𝙥: 𝙕𝙚𝙧𝙤-𝘾𝙤𝙥𝙮 𝘿𝙖𝙩𝙖 𝙈𝙤𝙫𝙚𝙢𝙚𝙣𝙩 𝙞𝙣 𝘼𝙓𝙄4𝙈𝙇𝙄𝙍" which was presented at the C4ML workshop at #CGO2026! 🙂
https://t.co/VZgdUsiLTA

[Meeting C++ @meetingcpp]

The fastest JVM is the C++26 compiler
https://t.co/4yVFL6P0rN
#cpp
#cplusplus

[Matri𝕏tang⚡️ @matrixkook67]

@RealAkemiHomura 出差回来？

[Matri𝕏tang⚡️ @matrixkook67]

@Alenjonesyi 看了下加上基础代谢4k了

[Matri𝕏tang⚡️ @matrixkook67]

@Alenjonesyi 自行车4个小时

[Matri𝕏tang⚡️ @matrixkook67]

@lfk_dsk @RealAkemiHomura ≡ω≡

[Matri𝕏tang⚡️ @matrixkook67]

@RealAkemiHomura 运动！

[Matri𝕏tang⚡️ @matrixkook67]

@lfk_dsk @RealAkemiHomura 我没有 我在做神秘端侧推理引擎 猛学vulkan中，gpu苦手

[Matri𝕏tang⚡️ @matrixkook67]

@RealAkemiHomura @lfk_dsk 带带我

[Matri𝕏tang⚡️ @matrixkook67]

@RealAkemiHomura 职业倦怠了

[Matt @matt_dz]

A Case for Tracing Based DSL Kernel Languages
https://t.co/1i909GWE3t
On the architectural divide between parsing and tracing kernel DSLs, and what tends to go wrong in each.
by George Karpenkov

[Matri𝕏tang⚡️ @matrixkook67]

@LynzRand @AcboxLiu 重大历史猫遇

[Matri𝕏tang⚡️ @matrixkook67]

@LynzRand 哇 还有药物控制

[Charles 🎉 Frye @charles_irl]

New articles in the GPU Glossary for CuTe DSL, CUTLASS, and CuTe -- the tools used to write some of the highest-performance kernels on contemporary data center GPUs.

https://t.co/hhdyvAO092

[Math Cafe @Riazi_Cafe_en]

Stanford's "Mathematical Foundations of Computing"

PDF: https://t.co/lFH06RwTKL

[Onur Mutlu @_onurmutlu_]

Digital Design & Comp. Arch: L24: Prefetching (Spring 2026) https://t.co/jz1zNYx9si via @YouTube

Join us in ~15 mins to discuss Advanced Caching and Prefetching.

We will discuss both fundamentals and recent research in this critical area.

@SAFARI_ETH_CMU

[Vivek Galatage @vivekgalatage]

Yesterday's lecture on GPU Architectures by @_onurmutlu_

https://t.co/XnHP64b19U

[Vivek Galatage @vivekgalatage]

Best structured reference I've found for GPU optimization - 450 papers, 14 years of research. Some techniques will have evolved, but the mental models hold up.

https://t.co/2kFfsEq31h