M.Sc. Alexis Engelke


kein Bild

Technische Universität München

Informatik 10 - Lehrstuhl für Rechnerarchitektur & Parallele Systeme (Prof. Schulz)

Postadresse

Postal:
Boltzmannstr. 3
85748 Garching b. München

Vita

Alexis Engelke is a PhD candidate at the Chair of Computer Architecture and Parallel Systems at Technical University of Munich (TUM), where he also earned his Master of Science in Computer Science in 2017. He conducts research in the area of runtime code generation, focusing on dynamic binary rewriting and optimization. His other research interests include parallel performance optimization, reverse engineering, software security, and low-level aspects of modern processor architectures in general.

Research Interests

  • Binary rewriting and instrumentation
  • Dynamic code generation and optimization
  • New/modern processor architectures
  • Programmability of non-linear architectures
  • Reverse engineering, software security, hacking
  • Low-level aspects of modern processor architectures
  • ... and more.

Ongoing Projects

  • Instrew: A framework for high performance dynamic binary translation and instrumentation based on LLVM
  • Rellume: Lifting machine code to performant LLVM-IR; currently supports x86-64 and RISC-V
  • BinOpt: A library for self-guided binary specialization at runtime with support for multiple rewriters
    • DBLL: A binary optimizer and specializer using LLVM-IR for transformations (lives in BinOpt repository)
    • Drob: A binary optimizer using a low-level IR to support whole function optimizations
    • DBrew: A tracing binary rewriter and optimizer
  • Fadec: A very fast and small decoder for x86 and x86-64
  • HimMUC (Live Status): An ARM cluster for teaching and research
     
  • ... and more interesting things — get in contact to find it out.
Projects no longer under active development:
  • Mandel-QPU: Mandelbrot computation for the Raspberry Pi GPU

Teaching

  • SS 21: Praktikum Rechnerarchitektur
  • SS 21: Seminar Geschichte der Rechnerarchitektur
  • WS 20/21: Praktikum Aspekte der systemnahen Programmierung bei der Spieleentwicklung
  • WS 20/21: Praktikum Rechnerarchitektur
  • SS 20: Praktikum Rechnerarchitektur
  • SS 20: Seminar Geschichte der Rechnerarchitektur
  • SS 20: Seminar Ethik für Nerds
  • WS 19/20: Praktikum Aspekte der systemnahen Programmierung bei der Spieleentwicklung
  • WS 19/20: Seminar Code Generation and Innovative Programming Models
  • WS 19/20: Seminar Ethik für Nerds
  • SS 19: Praktikum Rechnerarchitektur
  • WS 18/19: Praktikum Aspekte der systemnahen Programmierung bei der Spieleentwicklung
  • WS 18/19: Praktikum Rechnerarchitektur
  • WS 18/19: Praktikum Advanced Topics in Computer Architecture and Parallel Systems
  • WS 18/19: Seminar Code Generation and Innovative Programming Models
  • SS 18: Seminar Geschichte der Rechnerarchitektur
  • SS 18: Seminar Rechnertechnik in der Raumfahrt
  • WS 17/18: Praktikum Aspekte der systemnahen Programmierung bei der Spieleentwicklung
  • WS 16/17: Praktikum Aspekte der systemnahen Programmierung bei der Spieleentwicklung (Tutor)

Publications & Talks

  • Michael Jungmair, Tobias Schmidt, Alexis Engelke, Armin Ettenhofer, Felix Krayer, Jonas Lauer, Malte von Ehren, and Martin Schulz. A Flexible Uncore Infrastructure for RISC-V Core Development. CARRV'21 (workshop at ISCA'21). Paper Slides
  • Alexis Engelke, Dominik Okwieka, and Martin Schulz. Efficient LLVM-Based Dynamic Binary Translation. VEE'21, April 2021. Paper Slides
  • Talk: Alexis Engelke. Instrew: Fast LLVM-based Dynamic Binary Instrumentation and Translation. LLVM-CGO (workshop at CGO'21). Februrary 2021. Slides
  • Alexis Engelke and Martin Schulz. Robust Practical Binary Optimization at Run-time using LLVM. LLVM-HPC'20 (workshop at SC'20). November 2020. Paper Slides
  • Alexis Engelke and Martin Schulz. Instrew: Leveraging LLVM for High Performance Dynamic Binary Instrumentation. VEE'20, March 2020. Paper Slides
  • Poster: Alexis Engelke, David Hildenbrand, Martin Schulz. Optimizing Performance at Runtime Using Binary Rewriting. SC'19, November 2019. Poster Abstract
  • Alexis Engelke. Reconstructing Program Semantics from Go Binaries. Master's Thesis. Department of Informatics, Technical University of Munich. September 2017. Thesis
  • Alexis Engelke and Josef Weidendorfer. Using LLVM for Optimized Lightweight Binary Re-Writing at Runtime. In Proceedings of the 22nd int. Workshop on High-Level Parallel Programming Models and Supportive Environments (HIPS 2017). Orlando, US, 2017. Paper