Nihal Pasham (@npashi) / X

Nihal Pasham

1,875 posts

Nihal Pasham

@npashi

🦀 Rust Tech | @Nvidia | Make general purpose GPU programming accessible 🖖 Disclaimer: The views, opinions expressed are my own (not my employer's)

Bangalore, IN

github.com/nihalpasham

Joined October 2011

Pinned
Nihal Pasham
@npashi
May 8
Finally able to talk about what I've been heads-down on for 6 months at @nvidia 🦀⚡ We just open-sourced cuda-oxide — an experimental rustc backend that lets you write CUDA kernels in pure Rust. No DSLs. No FFI. No source-to-source step. Single source. Short🧵👇
Made with AI
Nihal Pasham
@npashi
Aug 2
New video 🦀⚡ Safe Rust's bounds checks on the GPU. Can we elide it? Safe Rust bounds-checks every slice index. In a GEMM hot loop that's a 2.4x perf tax, and LLVM can't remove it for you: the proof the buffers are big enough lives in your host code, not the IR.
Nihal Pasham
@npashi
Jul 22
Pure Rust GEMM on Nvidia Blackwell, part 2 🦀 Part 1 broke down the kernel. Part 2: measurements. 48-SM Blackwell, vs live cuBLASLt FP16: 4096³ ▸ 445 TFLOPS (98.7%) 8192³ ▸ 518 TFLOPS (97.8%) 16384³ ▸ 507 TFLOPS (119% 🤯) We're not SoL, sometimes we're past it. 🧵👇
Nihal Pasham
@npashi
Jun 29
Pure Rust GEMM on Nvidia Blackwell 🦀 ...🖖 I break down (the basics of) a state-of-the-art matrix multiply kernel, written as a plain Rust function and compiled to PTX with cuda-oxide. One scary kernel. Eight ideas. Each removes a bottleneck. Are we speed-of-light yet? 🧵👇
Rust Programming Language
Nihal Pasham
@npashi
May 9
I know our community won’t be around come June (as ‘X’ has other plans). But before we go — I thought I’d drop something I’ve been working on for a while here.
Nihal Pasham
@npashi
May 8
Finally able to talk about what I've been heads-down on for 6 months at @nvidia 🦀⚡ We just open-sourced cuda-oxide — an experimental rustc backend that lets you write CUDA kernels in pure Rust. No DSLs. No FFI. No source-to-source step. Single source. Short🧵👇