|
|
|
Description
|
|
HardBD & Active'24 will be a one-day
workshop co-located with ICDE'24. The aim of this one-day workshop is to bring
together researchers, practitioners, system administrators, and others
interested to share their perspectives on exploiting new hardware technologies
for data-intensive systems, and to discuss and identify future directions and
challenges in this area. The workshop aims at providing a forum for academia
and industry to exchange ideas through research and position papers.
[
Go to Top ]
|
|
Topics
|
|
Topics of interest include but
are not limited to:
- Data Management with Software-Hardware-System
Co-design
- Main Memory Data Management (e.g. Multi-core,
Cache, SIMD)
- Active Technologies (e.g., GPU, FPGA, and ASIC)
in Co-design Architectures
- Data Management on New Memory Technologies (e.g.,
SSD, NVM, HBM, PIM)
- Distributed Data Management Utilizing New
Network Technologies (e.g., RDMA, CXL)
- Data Management on the Cloud (e.g.,
Scalability and Security, Disaggregation)
- Secure Data Management Exploiting Trusted Execution Environment
- Novel Applications of New Hardware Technologies in Query
Processing, Transaction Processing, or Big Data Systems
(e.g., SQL/NoSQL/NewSQL Databases, Hadoop/Spark,
Blockchains, etc.)
- Benchmarking, Performance Models, and/or Tuning of
Data Management Workloads on Modern Hardware
[
Go to Top ]
|
|
Submission Guidelines
|
|
|
|
Important Dates
|
| Paper submission: |
January 26 February 16, 2024 (Friday) 11:59:00 PM PT
|
| Notification of acceptance: |
February 23 March 8, 2024 (Friday)
|
| Camera-ready copies: |
March 8 March 22, 2024 (Friday)
|
| Workshop: |
May 13, 2024 (Monday) |
[
Go to Top ]
|
|
Program
|
9:00-9:10 Welcome Message
9:10-10:10 Keynote Talk 1
10:10-10:30 Coffee Break
10:30-11:30 Keynote Talk 2
12:00-13:30 Lunch
13:30-15:00 Research Session
-
HunIPU: Efficient Hungarian Algorithm on IPUs (22min).
Cheng Huang (Aarhus University), Alexander Mathiasen (Graphcore), Josef Dean (Graphcore), Davide Mottin (Aarhus University), Ira Assent (Aarhus University)
-
Give a JIT on GPUs: NVRTC for Code-Generating Database Systems (22min).
Anton Sachnov (University of Bamberg), Leonard von Merzljak (TUM), Maximilian E Schüle (University of Bamberg)
-
A Three-Tier Buffer Manager Integrating CXL Device Memory for Database Systems (22min).
Niklas Riekenbrauck, Marcel Weisgut, Daniel Lindner, Tilmann Rabl (Hasso Plattner Institute)
-
CPU and GPU Hash Joins on Skewed Data
(22min).
Yuzhou Cai, Shimin Chen (Insitute of Computing Technology, Chinese Academy of Sciences)
[
Go to Top ]
|
|
Keynote Talks
|
|
|
What is More Difficult, to Build or to Program a Hard DB?
Gustavo Alonso
ETH Zurich
|
Abstract:
Computing platforms are evolving rapidly along many dimensions: processors, specialization, disaggregation, acceleration, smart memory and storage, etc. Many of these developments are being driven by data science but very few existing engines and data processing platforms make us of modern hardware. One reason is the deluge of possible configurations and deployment options, most of them too new to have a precise idea of their performance implications and lacking proper support in the form of tools and platforms that can manage the underlying diversity. This growing heterogeneity opens up many opportunities but also raises significant challenges. In the talk I will describe our efforts to explore the possibilities that modern hardware opens for data management and discuss a system we are building for data processing on heterogeneous computing platforms that has as its main goal to effectively cope with the great variety of emerging hardware.
Bio:
Gustavo Alonso is a professor in the Department of Computer Science of ETH Zurich where he is a member of the Systems Group. His research interests include data management, distributed systems, cloud computing architecture, and hardware acceleration through reconfigurable computing. Gustavo has received 4 Test-of-Time Awards for his research in databases, software runtimes, middleware, and mobile computing. He is an ACM Fellow, an IEEE Fellow, a Distinguished Alumnus of the Department of Computer Science of UC Santa Barbara, and has received the Lifetime Achievements Award from the European Chapter of ACM SIGOPS (EuroSys).
|
|
Hybrid Data Analytical Processing and Hardware Acceleration Research at ByteDance
Jianjun Chen
Director of Infrastructure System Lab, ByteDance US
|
Abstract:
Three distinctive types of data processing workloads, including OLTP, OLAP and Serving, are commonly seen in real production systems at ByteDance. In the past, dedicated systems have been built and used to process them separately, forcing the same data to be ETLed into multiple systems, causing data consistency problems, low data freshness, wasting resources, and increasing learning and maintenance costs. In this talk, we describe our recent journey of building: 1)
ByteHTAP [VLDB 2022], an HTAP (hybrid transactional and analytical processing) system with high data freshness and strong data consistency. 2) Krypton [VLDB 2023], a competitive cloud-native HSAP (hybrid serving and analytical processing) system that provides excellent elasticity, query performance and high data freshness.
In addition, we briefly talk about some sampled recent work in hardware acceleration research at ByteDance, including: 1) Accelerating Cloud-Native Databases with Distributed PMem Stores [ICDE 2023]; 2) Exploring Performance and Cost Optimization with ASIC-Based CXL Memory [EuroSys 2024].
Bio:
Dr. Jianjun Chen is Director of Infrastructure System Lab at ByteDance US, where he leads a team of top-notch researchers and software engineers to work on cutting edge technologies in the infrastructure system related areas, including but not limited to database, storage, computing, networking, ML, hardware/software codesign etc. Before that, he was a technical VP of Huawei US Silicon Valley R&D Center, leading advanced database research and development in the Huawei database group. Dr. Chen received his Ph.D in 2001 from the Computer Sciences department of University of Wisconsin, Madison and is a recipient of the SIGMOD 10 year Test-Time award in 2010 for his visionary work in scalable continuous query processing, as part of his Ph.D dissertation research.
[
Go to Top ]
|
|
Organizers
|
[
Go to Top ]
|
|
PC Members
|
- Bingsheng He, National University of Singapore
- Wolfgang Lehner, TU Dresden
- Yinan Li, Microsoft Research
- Ilia Petrov, Reutlingen University
- Thamir Qadah, Umm Al-Qura University
- Kai-Uwe Sattler, TU Ilmenau
- Evangelia Sitaridi, NVIDIA
- Rebecca Taft, Cockroach Labs
- Tianzheng Wang, Simon Fraser University
- Xuan Zhou, East China Normal University
[
Go to Top ]
|
|
