HPI Data Engineering Systems

alsatian

Code for "Alsatian: Optimizing Model Search for Deep Transfer Learning" @ SIGMOD 2025

cxlbench

Code for papers @ VLDB 2025, ADMS 2025, and HCDS 2025.

inferdb

Code for "InferDB: In-Database Machine Learning Inference Using Indexes"

multi-gpu-sort-merge-join

Source code for "Efficiently Joining Large Relations on Multi-GPU Systems" @ VLDB 2025

multi-gpu-sorting

This repository contains the source code for our ACM SIGMOD '22 paper (Evaluating Multi-GPU Sorting with Modern Interconnects)

perma-bench

A benchmarking suite to evaluate the performance of persistent memory access (PerMA-Bench @ VLDB '22)

pmem-olap

This repository contains the source code for our ACM SIGMOD '21 paper (Maximizing Persistent Memory Bandwidth Utilization for OLAP Workloads)

skyrise

Skyrise is a research project exploring data processing on elastic cloud resources.

vectorized-hash-tables

Code and results for our paper "Analyzing Vectorized Hash Tables Across CPU Architectures" @ VLDB '23.

viper

Viper: A hybrid PMem-DRAM Key-Value Store for Persistent Memory (VLDB '21)

hpides/viper

Viper: A hybrid PMem-DRAM Key-Value Store for Persistent Memory (VLDB '21)

hpides/vectorized-hash-tables

Code and results for our paper "Analyzing Vectorized Hash Tables Across CPU Architectures" @ VLDB '23.

hpides/pmem-olap

This repository contains the source code for our ACM SIGMOD '21 paper (Maximizing Persistent Memory Bandwidth Utilization for OLAP Workloads)

hpides/perma-bench

A benchmarking suite to evaluate the performance of persistent memory access (PerMA-Bench @ VLDB '22)

hpides/skyrise

Skyrise is a research project exploring data processing on elastic cloud resources.

hpides/autovec-db

Code for our paper "Evaluating SIMD Compiler-Intrinsics for Database Systems"

hpides/pmem-nvme-dropin

This repository contains the code for our DaMoN '21 paper.

hpides/thesis-proposal-template

This is a Latex template for thesis proposals at the Data Engineering Systems Group.

hpides/disco

Stream processing engine for distributed window aggregation (EDBT '20)

hpides/End-to-end-ML-System-Benchmark

A modular suite for benchmarking all stages of Machine Learning pipelines. To find bottlenecks in such pipelines and compare different ML tools, this framework can calculate and visualize several metrics in the data preparation, model training, model validation and inference stages.

hpides/inferdb

Code for "InferDB: In-Database Machine Learning Inference Using Indexes"

hpides/mexico-flink-tutorial

hpides/multi-gpu-sorting

This repository contains the source code for our ACM SIGMOD '22 paper (Evaluating Multi-GPU Sorting with Modern Interconnects)

hpides/rmg-sort

RMG Sort: Radix-Partitioning-Based Multi-GPU Sorting (BTW '23)

hpides/alsatian

Code for "Alsatian: Optimizing Model Search for Deep Transfer Learning" @ SIGMOD 2025

hpides/babelmr-applications

Code for our paper "BabelMR: A Polyglot Framework for Serverless MapReduce"

hpides/DESengine

hpides/mmlib

Efficiently Managing Deep Learning Models in a Distributed Environment (Awarded as best paper @ EDBT 2022)

hpides/mp-ddsp-ws20

hpides/prefetching

hpides/BDL

Code and Tutorials for Big Data Lab

hpides/HDP-Code-Examples

Repository for code examples of the Hardware-Conscious Data Processing lecture

hpides/mmlib-multi

hpides/cxlbench

Code for papers @ VLDB 2025, ADMS 2025, and HCDS 2025.

hpides/multi-gpu-sort-merge-join

Source code for "Efficiently Joining Large Relations on Multi-GPU Systems" @ VLDB 2025

hpides/fonda-flink-tutorial

hpides/Ghostwriter

Ghostwriter - a distributed message broker on RDMA and NVM

hpides/pq-bench

hpides/stork

hpides/TCO2

A tool for quantifying the total CO2 cost of ownership of database servers.