Chief Coffee Consumer

Biography

Hi there! My name is Hristo and I’m what you get when you combine a theoretical physicist and a software developer, and then let it run on a supercomputer. I’m the chief data scientist of Notolytix and most of my time goes in coming up with novel ways to fight fraud more efficiently. You can also find me building compute clusters here and there and answering questions on Stack Overflow. I seem to have become something of an authority on parallel programming, and in particular am the only one as of today (July 2020) to simultaneously hold golden badges for all three major HPC programming tags: mpi, openmp, and parallel-processing.

In my free time, I like to reverse engineer stuff – it fascinates me to understand how stuff works and I learn so many new things. I also optimise serial and parallel engineering and scientific codes for performance and in my past life used to do research in physics.

Interests

High-Performance Computing
Performance Optimisation
Artificial Intelligence
Statistical Learning
Information Retrieval
Software Development

Education

PhD in Atomic and Molecular Physics

University of Sofia
BSc in Physics

University of Sofia

Recent Posts

Recovering Datasets from Broken ZFS raidz Pools

There are generally two kinds of people–those who’ve suffered a severe data loss and those who are about to suffer a severe data loss. I repeatedly jump back and forth between the two kinds. Recently, a combination of hardware defects and a series of power outages rendered the raidz pool of the NAS of my previous research group unreadable. The OS, an old Solaris 10 x86, would not import the pool with a dreaded I/O error message.

2017-07-09 9 min read

Recipe: Obtaining Peak VM Size in Pure Fortran

Often in High Performance Computing one needs to know about the various memory metrics of a given program with the peak memory usage probably being the most important one. While the getrusage(2) syscall provides some of that information, it’s use in Fortran programs is far from optimal and there are lots of metrics that are not exposed by it. On Linux one could simply parse the /proc/PID/status file. Being a simple text file it could easily be processed entirely with the built-in Fortran machinery as shown in the following recipe:

2014-05-22 2 min read

MPI Programming Basics

Embracing the current development in educational technologies, the IT Center of the RWTH Aachen University (former Center for Computing and Communication) makes available online the audio recordings of most tutorials delivered during this year’s PPCES seminar. Participation in PPCES is for free and course materials are available online, but this is the first time when proper audio recordings were taken. All videos (presentation slides + audio) are available on the PPCES YouTube channel under Creative Commons Attribution license.

2014-03-18 1 min read

Linear Congruency Considered Harmful

Recently I stumbled upon this Stack Overflow question. The question author was puzzled with why he doesn’t see any improvement in the resultant value of $\pi$ approximated using a parallel implementation of the well-known Monte Carlo method when he increase the number of OpenMP threads. His expectation was that, since the number of Monte Carlo trials that each thread performs was kept constant, adding more threads would increase linearly the sample size and therefore improve the precision of the approximation.

2013-12-15 6 min read