Krishnan Iyer

Graduate Student

Delhi, India
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
Krishnan Iyer is an embedded systems engineer and graduate student with nine years of hands-on experience designing drivers and low-level firmware across ARM platforms. He has a strong track record in ARM NEON optimizations and driver development, contributing performance-focused changes to high-profile open-source projects like the AV1 encoder rav1e and dav1d. His roles span research and industry—from KAUST graduate work to embedded engineering at Peer Robotics and focused driver projects during Google Summer of Code—demonstrating the ability to move from algorithmic optimization to production-ready assembly. Based in Delhi, he combines formal electrical and electronics training with practical SIMD and DMA expertise, and is currently developing drivers for Cortex-M4 boards. An often-overlooked strength is his knack for rewriting load/store patterns and reducing register pressure to squeeze measurable speedups from constrained ARM cores.
code9 years of coding experience
job3 years of employment as a software developer
languagesEnglish, Hindi, Malayalam, Gujarati
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (11)

arm10
encode10
assembly10
intrinsics10
av1-codec10
performance-optimization10
assemble10
assembler10
neon10
video-encoder8
encoder8

Programming languages (8)

SystemVerilogJavaC++VerilogPHPHTMLAssemblyPython

Github contributions (5)

github-logo-circle
xiph/rav1e

Apr 2019 - Oct 2019

The fastest and safest AV1 encoder.
Role in this project:
userBack-end Developer & Performance Engineer
Contributions:11 commits in 6 months
Contributions summary:Krishnan focused on optimizing the performance of the AV1 encoder, primarily by implementing and improving the NEON implementations for various functions within the `arm/32` and `arm/64` architectures. They optimized the `blend`, `blend_h`, and `blend_v` functions, alongside the `w_mask` function, by leveraging NEON intrinsics. This included merging and rewriting load/store instructions, reducing register usage, and making code style consistent to yield performance gains, as shown by benchmark comparisons.
av1-encoderencoderfastestav1
krish-iyer/HackDrones

Feb 2020 - Sep 2024

Contributions:14 pushes, 1 branch in 4 years 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Krishnan Iyer - Graduate Student