publications
Markus Püschel
Professor
Computer Science
ETH Zürich
Switzerland

home

publications

teaching

short CV

personal

the pub

home

If you are interested in pursuing a PhD with me, please submit your application to our online application system and drop me an email.

Right now I am looking especially for these projects and profiles

  • Program generation for linear algebra/machine learning/optimization/other domains: strong programming skills (meta programming a plus), compilers, mathematics
  • Meta programming, generative programming
  • A new theory of algorithms for structured matrices: strong background in math and theory
  • Textures and invariants in image processing and computer vision: strong math, image processing background

Master theses (for ETH students) on various topics are always available - just email me.

Current Research Areas and Interests

I like to combine techniques from mathematics, computer science, and engineering to attack difficult problems.

One longstanding interest of mine is what I call "program synthesis for performance." For functionality of mathematical nature we aim to automatically generate highest performance code from a high level mathematical description. In Spiral, we have built such a generator for the domain of linear transforms. The project combines techniques from mathematics, programming languages, symbolic computation, compilers, and machine learning (short overview). We are currently expanding this project in several directions:

Other current and recent research directions

Some recent past research projects

Assistant

Franziska Mäder
+41 44 632 7311
Universitätsstrasse 6
8092 Zurich, Switzerland

Research Group

PhD. students

  • Eliza Wszola
  • Gagandeep Singh (with Martin Vechev)
  • Francois Serre
  • Alen Stojanov
  • Daniele Spampinato
  • Georg Ofenbeck
  • Victoria Caparros Cabezas

Current master theses:

  • Ivaylo Toskov: Explicit SIMD instructions into JVM using LMS
  • Stefan Dietiker: Program generation for finite state machines

Latest Teaching

Spring 2017:
How to Write Fast Numerical Code (CS: 263-2300)

Current Collaborators

Paolo Bientinesi (RWTH Aaachen), Andreas Krause (ETH), Tiark Rompf (Purdue), Martin Vechev (ETH)

The Pub

Check out the pub, a tool for maintaining publications and presenting them on the web.

Contact Info

Markus Püschel
Dept. of Computer Science
ETH Zurich, CAB H69.3
Universitätsstrasse 6
8092 Zurich, Switzerland
phone: +41 44 632 7303
email: pueschel at inf.ethz.ch
web: http://www.inf.ethz.ch/~markusp