2021 Whova User Guide Videos: Youtube | Bilibili
We prepare two similar runs on each day for the convenience of people in different time zones. Note that all the time has been adjusted to your local time zone.


Beijing Time



MONDAY (June 21, 2021, Beijing Time)


21 JUN

09:30 - 11:30


PODS Opening and Keynote: Synchronization Schemas


Session Chair: Reinhard Pichler

Multimedia II Hall 1 (多二1厅)

Zoom Link
Youtube Live
Bilibili Live
Youtube Video
Bilibili Video

Speaker: Rajeev Alur (University of Pennsylvania)
Abstract: We present a type-theoretic framework for data stream processing for real-time decision making, where the desired computation involves a mix of sequential computation, such as smoothing and detection of peaks and surges, and naturally parallel computation, such as relational operations, key-based partitioning, and map-reduce. To unify sequential (ordered) and relational (unordered) data models, we define synchronization schemas as types and series-parallel streams (SPS) as objects of these types. A synchronization schema imposes a hierarchical structure over relational types that succinctly captures ordering and synchronization requirements among different kinds of data items. Series-parallel streams naturally model objects such as relations, sequences, sequences of relations, sets of streams indexed by key values, time-based and event-based windows, and more complex structures obtained by nesting of these. We introduce series-parallel stream transformers (SPST) as a domain-specific language for modular specification of deterministic transformations over such streams. SPSTs provably specify only monotonic transformations allowing streamability, have a modular structure that can be exploited for correct parallel implementation, and are composable allowing specification of complex queries as a pipeline of transformations. We conclude by discussing research directions for both theory and practice of distributed stream processing.


21 JUN

11:30 - 14:30


Break


21 JUN

14:30 - 16:30


PODS Invited Tutorial 1:
Modern Lower Bound Techniques in Database Theory and Constraint Satisfaction


Session Chair: Marco Calautti

Multimedia II Hall 1 (多二1厅)

Zoom Link
Youtube Live
Bilibili Live
Youtube Video
Bilibili Video

Speaker: Dániel Marx (Max-Planck-Institut für Informatik)
Abstract: Conditional lower bounds based on P!=NP, the Exponential-Time Hypothesis (ETH), or similar complexity assumptions can provide very useful information about what type of algorithms are likely to be possible. Ideally, such lower bounds would be able to demonstrate that the best known algorithms are essentially optimal and cannot be improved further. In this tutorial, we overview different types of lower bounds, and see how they can be applied to problems in database theory and constraint satisfaction.


21 JUN

16:30 - 17:30


PODS Session: Compressed Data


Session Chair: Pierre Bourhis

Multimedia II Hall 1 (多二1厅)

Zoom Link
Youtube Live
Bilibili Live

Minimum Coresets for Maxima Representation of Multidimensional Data

Yanhao Wang, Michael Mathioudakis, Yuchen Li and Kian-Lee Tan

Spanner Evaluation over SLP-Compressed Documents

Markus L. Schmid and Nicole Schweikardt


Second Run


21 JUN

20:00 - 21:30


International Workshop on
Data Management on New Hardware


Zoom Link
Youtube Live

Session 1: 20:00 - 21:00 (Beijing Time)

Resource-Efficient Database Query Processing on FPGAs
Mehdi Moghaddamfar (TU Dresden & SAP SE)*; Christian Faerber (Intel Corporation); Wolfgang Lehner (TU Dresden); Norman May (SAP SE); Akash Kumar (TU Dresden)

An Energy-Efficient Stream Join for the Internet of Things
Adrian Michalke (DFKI GmbH)*; Philipp Marian Grulich (Technische Universität Berlin); Clemens Lutz (DFKI GmbH); Steffen Zeuch (DFKI Berlin); Volker Markl (Technische Universität Berlin)

XJoin: Portable, parallel hash join across diverse XPU architectures with oneAPI
Raja Appuswamy (Eurecom)*; Eugenio Marinelli (Eurecom)

Fresh Thinking Talk 1: Extend, Not Just Accelerate!
Zsolt István (IT University of Copenhagen)

Session 2: Keynote 23:30 - 00:30 (+1 day) (Beijing Time)

Introduction to the Arm Neoverse N and V series: Cloud-to-Edge Infrastructure SoCs
Andrea Pellegrini (Arm)

Session 3: 00:45 - 01:45 (Beijing Time)

Reducing Bloom Filter CPU Overhead in LSM-Trees on Modern Storage Devices
Zichen Zhu (Boston University)*; Ju Hyoung Mun (Boston University); Aneesh Raman (Boston University); Manos Athanassoulis (Boston University)

Drop It In Like It's Hot: An Analysis of Persistent Memory as a Drop-in Replacement for NVMe SSDs
Maximilian Böther (Hasso Plattner Institute, University of Potsdam)*; Otto Kißig (Hasso Plattner Institute, University of Potsdam); Lawrence Benson (Hasso Plattner Institute, University of Potsdam); Tilmann Rabl (HPI, University of Potsdam)

Workload-Driven Placement of Column-Store Data Structures on DRAM and NVM
Robert Lasch (TU Ilmenau, SAP SE)*; Robert Schulze (SAP SE); Thomas Legler (SAP SE); Kai-Uwe Sattler (TU Ilmenau)

Session 4: 02:00 - 03:00 (Beijing Time)

Filter Representation in Vectorized Query Execution
Amadou L Ngom (MIT)*; Prashanth Menon (Carnegie Mellon Universiy); Matthew Butrovich (Carnegie Mellon University); Lin Ma (Carnegie Mellon University); Wan Shen Lim (Carnegie Mellon University); Todd Mowry (Carnegie Mellon University); Andrew Pavlo (Carnegie Mellon University)

The Case for SIMDified Analytical Query Processing on GPUs
Johannes Fett (TU Dresden); Annett Ungethüm (TU Dresden); Dirk Habich (TU Dresden)*; Wolfgang Lehner (TU Dresden)

GalOP - Towards a GPU-accelerated OLTP DBMS
Nils Boeschen (TU Darmstadt)*; Carsten Binnig (TU Darmstadt)

Fresh Thinking Talk 2: Cloud-native databases: opportunities and challenges
Xiangyao Yu (University of Wisconsin-Madison)

Session 5: 03:30 - 04:30 (Beijing Time)

Hardware-Conscious Sliding Window Aggregation on GPUs
Georgios Michas (National and Kapodistrian University of Athens); Periklis Chrysogelos (EPFL); Ioannis Mytilinis (EPFL)*; Anastasia Ailamaki (EPFL)

Playing Fetch with CAT - Composing Cache Partitioning and Prefetching for Task-based Query Processing
Qitian Zeng (Illinois Institute of Technology)*; Kyle C Hale (Illinois Institute of Technology); Boris Glavic (Illinois Institute of Technology)

A cost model for NDP-aware query optimization for KV-stores
Christian Knoedler (Reutlingen University); Tobias Vincon (Reutlingen University); Arthur Bernhardt (Reutlingen University); Leonardo Solis-Vasquez (Technical University of Darmstadt); Lukas Weber (TU Darmstadt); Andreas Koch (TU Darmstadt); Ilia Petrov (Reutlingen University)*

Instant Graph Query Recovery on Persistent Memory
Alexander Baumstark (TU Ilmenau)*; Muhammad Attahir Jibril (TU Ilmenau); Philipp Götze (TU Ilmenau); Kai-Uwe Sattler (TU Ilmenau)

A Parametric I/O Model for Modern Storage Devices
Tarikul Islam Papon (Boston University)*; Manos Athanassoulis (Boston University)

KallaxDB: A Table-less Hash-based Key-Value Store on Storage Hardware with Built-in Transparent Compression
Xubin Chen (Rensselaer Polytechnic Institute)*; Ning Zheng (ScaleFlux); Shukun Xu (ScaleFlux); Yifan Qiao (Rensselaer Polytechnic Institute); Yang Liu (ScaleFlux); Jiangpeng Li (ScaleFlux); Tong Zhang (Rensselaer Polytechnic Institute)


21 JUN

21:30 - 23:30


PODS Opening and Keynote: Synchronization Schemas


Session Chair: Leonid Libkin

Zoom Link
Youtube Live
Youtube Video
Bilibili Video

Speaker: Rajeev Alur (University of Pennsylvania)
Abstract: We present a type-theoretic framework for data stream processing for real-time decision making, where the desired computation involves a mix of sequential computation, such as smoothing and detection of peaks and surges, and naturally parallel computation, such as relational operations, key-based partitioning, and map-reduce. To unify sequential (ordered) and relational (unordered) data models, we define synchronization schemas as types and series-parallel streams (SPS) as objects of these types. A synchronization schema imposes a hierarchical structure over relational types that succinctly captures ordering and synchronization requirements among different kinds of data items. Series-parallel streams naturally model objects such as relations, sequences, sequences of relations, sets of streams indexed by key values, time-based and event-based windows, and more complex structures obtained by nesting of these. We introduce series-parallel stream transformers (SPST) as a domain-specific language for modular specification of deterministic transformations over such streams. SPSTs provably specify only monotonic transformations allowing streamability, have a modular structure that can be exploited for correct parallel implementation, and are composable allowing specification of complex queries as a pipeline of transformations. We conclude by discussing research directions for both theory and practice of distributed stream processing.


21 JUN

23:30 - 00:00 (+1 day)


Break


22 JUN

00:00 - 02:00


PODS Business Meeting


Zoom Link
Youtube Live


22 JUN

02:00 - 02:30


Break


22 JUN

02:30 - 04:30


PODS Invited Tutorial 1:
Modern Lower Bound Techniques in Database Theory and Constraint Satisfaction


Session Chair: Marcelo Arenas

Zoom Link
Youtube Live
Youtube Video
Bilibili Video

Speaker: Dániel Marx (Max-Planck-Institut für Informatik)
Abstract: Conditional lower bounds based on P!=NP, the Exponential-Time Hypothesis (ETH), or similar complexity assumptions can provide very useful information about what type of algorithms are likely to be possible. Ideally, such lower bounds would be able to demonstrate that the best known algorithms are essentially optimal and cannot be improved further. In this tutorial, we overview different types of lower bounds, and see how they can be applied to problems in database theory and constraint satisfaction.


22 JUN

04:30 - 05:30


PODS Session: Compressed Data


Session Chair: Matthias Niewerth

Zoom Link
Youtube Live

Minimum Coresets for Maxima Representation of Multidimensional Data

Yanhao Wang, Michael Mathioudakis, Yuchen Li and Kian-Lee Tan

Spanner Evaluation over SLP-Compressed Documents

Markus L. Schmid and Nicole Schweikardt