Petr Andreev

How does CPython really handle memory? This talk follows an object’s full journey: allocation, refcounting, deallocation, freelists, and allocator swaps. You’ll see why memory seems to `stick`, how pymalloc and mimalloc differ, and what actually happens in hot loops. Leave with a sharp mental...

Learn how Python leverages AVX-512, hyper-threading, and GPU for extreme performance. We'll dive into hardware internals, code patterns, and scaling strategies for HighLoad systems. We'll look at how we get compute modules from sand and how they execute your Python code.

The problem of matching GPS locations to roads and local government areas (LGAs) involves handling large datasets and a number of geospatial operations. In this deep dive, we will outline the challenges of developing scalable solutions for these tasks. We will discuss our multi-step approach, first focusing on the use of H3 indexing to isolate matches with single candidates, then explaining use of different geospatial computational techniques to accurately match points with multiple candidates. From technical perspective, the talk will showcase the use of broadcasting and partitioning techniques, their effect on autoscaling, memory usage and effective data parallelization. This session is for anyone interested in geospatial data, spark performance optimization and the real-world challenges of large-scale data engineering.