01 // Identity

Skandan C Yalagach

Computer Science undergraduate focusing on Performance-critical numerical kernels and Systems-ML engineering.

Github LinkedIn Email
02 // Technical Work

Glacier.ML

C++20 OpenMP OpenBLAS perf

A performance-focused C++20 numerical algorithms library designed to build and experiment with machine learning algorithms while emphasizing efficiency on modern multi-core CPU architectures.

View Source →

Glacier.HPC

C++20 C17 OpenMP CUDA perf NSight

Profiling, benchmarking, and analysis of numerical kernels derived from common supervised machine learning algorithms on consumer-grade hardware.

View Source →
03 // From Math to Machines
2026 . 01 . 10

Building SVMs from Scratch in C++: Glacier’s PEGASOS Implementation

4 minutes ·
SVM PEGASOS
2026 . 01 . 03

Optimized k Nearest Neighbours: From Naive to Hardware-Aware

3 minutes ·
kNN Hardware optimization Software optimizations
2025 . 12 . 15

Building my own C++20 Numerical Algorithms library

3 minutes ·
Glacier.ML Systems-ML Machine learning library Linear Regression Logistic Regression
Archive // All Posts