Return of the database machines? Towards a hardware-software approach for high-performance databases.
Host
Sam Madden
CSAIL MIT
Title:
Return of the database machines? Towards a hardware-software approach for high-performance databases.
Abstract:
Analytic database applications have an insatiable appetite for higher performance. In the past, a large part of this appetite was met by leveraging the gift of Moore’s Law. However, the slowing down of Moore’s Law now requires a new approach. Fortunately, the hardware landscape is currently undergoing a Cambrian explosion of new architectures. In this talk, I will describe how one class of architecture may provide part of the answer to our search for future high-performance database systems. This architecture closely integrates compute and storage, making it a promising candidate for accelerating database analytic workloads. Nevertheless, achieving high performance requires a true hardware-software co-design strategy. I will explain how such a strategy requires critical changes on both the hardware and software sides. This talk will also highlight how there are rich opportunities in redesigning core database kernels to work with a broader class of hardware by considering circuit-level parallelism that is present in abundance in most computing substrates. Finally, I will look back five decades to the early days of the database field when a similar co-design approach (then known as database machines) prevailed and explore how that history can provide valuable insights for the future.
Bio:
Jignesh Patel is a professor in the Computer Science Department at the University of Wisconsin-Madison. His research interests are in data management systems. His papers have been selected as the best papers in several top database venues, including SIGMOD and VLDB. He is a fellow of the AAAS, the ACM, and the IEEE organizations. Additionally, he has won teaching awards at the University of Wisconsin and the University of Michigan. He has a keen interest in technology transfer from university research and has spun off four startups from his research group. At Wisconsin, he has also co-founded entrepreneurship organizations at both the department and university levels to help other entrepreneurs.
If you would like to join remotely please use the following link:
Tianyu Li is inviting you to a scheduled Zoom meeting.
Topic: Return of the database machines? Towards a hardware-software approach for high-performance databases.
Time: Mar 8, 2023 01:00 PM Eastern Time (US and Canada)
Join Zoom Meeting
https://mit.zoom.us/j/95151149005?pwd=aDVwRjAyUlhBWDh6dzZBSVlVU3o4dz09
Password: 080782
One tap mobile
+16465588656,,95151149005# US (New York)
+16699006833,,95151149005# US (San Jose)
Meeting ID: 951 5114 9005
US : +1 646 558 8656 or +1 669 900 6833
International Numbers: https://mit.zoom.us/u/ad3RCslmz1
Join by SIP
95151149005@zoomcrc.com
Join by Skype for Business
https://mit.zoom.us/skype/95151149005
Return of the database machines? Towards a hardware-software approach for high-performance databases.
Abstract:
Analytic database applications have an insatiable appetite for higher performance. In the past, a large part of this appetite was met by leveraging the gift of Moore’s Law. However, the slowing down of Moore’s Law now requires a new approach. Fortunately, the hardware landscape is currently undergoing a Cambrian explosion of new architectures. In this talk, I will describe how one class of architecture may provide part of the answer to our search for future high-performance database systems. This architecture closely integrates compute and storage, making it a promising candidate for accelerating database analytic workloads. Nevertheless, achieving high performance requires a true hardware-software co-design strategy. I will explain how such a strategy requires critical changes on both the hardware and software sides. This talk will also highlight how there are rich opportunities in redesigning core database kernels to work with a broader class of hardware by considering circuit-level parallelism that is present in abundance in most computing substrates. Finally, I will look back five decades to the early days of the database field when a similar co-design approach (then known as database machines) prevailed and explore how that history can provide valuable insights for the future.
Bio:
Jignesh Patel is a professor in the Computer Science Department at the University of Wisconsin-Madison. His research interests are in data management systems. His papers have been selected as the best papers in several top database venues, including SIGMOD and VLDB. He is a fellow of the AAAS, the ACM, and the IEEE organizations. Additionally, he has won teaching awards at the University of Wisconsin and the University of Michigan. He has a keen interest in technology transfer from university research and has spun off four startups from his research group. At Wisconsin, he has also co-founded entrepreneurship organizations at both the department and university levels to help other entrepreneurs.
If you would like to join remotely please use the following link:
Tianyu Li is inviting you to a scheduled Zoom meeting.
Topic: Return of the database machines? Towards a hardware-software approach for high-performance databases.
Time: Mar 8, 2023 01:00 PM Eastern Time (US and Canada)
Join Zoom Meeting
https://mit.zoom.us/j/95151149005?pwd=aDVwRjAyUlhBWDh6dzZBSVlVU3o4dz09
Password: 080782
One tap mobile
+16465588656,,95151149005# US (New York)
+16699006833,,95151149005# US (San Jose)
Meeting ID: 951 5114 9005
US : +1 646 558 8656 or +1 669 900 6833
International Numbers: https://mit.zoom.us/u/ad3RCslmz1
Join by SIP
95151149005@zoomcrc.com
Join by Skype for Business
https://mit.zoom.us/skype/95151149005