Making Sense of Multi-Threaded Application Performance at Scale with NonSequitur
This program is tentative and subject to change.
Modern multi-threaded systems are highly complex. This makes their behavior difficult to understand. Developers frequently capture behavior in the form of program traces and then manually inspect these traces. Existing tools, however, fail to scale to traces larger than a million events.
In this paper we present an approach to compress multi-threaded traces in order to allow developers to visually explore these traces at scale. Our approach is able to compression traces that contain millions of events down to a few hundred events. We use this approach to design and implement a tool called NonSequitur.
We evaluate NonSequitur with 42 participants on traces from RocksDB and WiredTiger, two complex database back-ends. We demonstrate that with NonSequitur, participants performed some performance analysis tasks on large execution traces up to 11 times more accurately as compared with other tools. Additionally, for some performance analysis tasks, the participants spent on average three times longer with other tools than with NonSequitur.
This program is tentative and subject to change.
Wed 23 OctDisplayed time zone: Pacific Time (US & Canada) change
16:00 - 17:40 | |||
16:00 20mTalk | Jmvx: Fast Multi-threaded Multi-Version eXecution and Record-Replay for Managed Languages OOPSLA 2024 David Schwartz University of Illinois at Chicago, Ankith Kowshik University of Illinois Chicago, Luís Pina University of Illinois at Chicago | ||
16:20 20mTalk | libLISA: Instruction Discovery and Analysis on x86-64 OOPSLA 2024 Jos Craaijo Open Universiteit, Freek Verbeek Open Universiteit & Virginia Tech, Binoy Ravindran Virginia Tech | ||
16:40 20mTalk | Making Sense of Multi-Threaded Application Performance at Scale with NonSequitur OOPSLA 2024 Augustine Wong University of British Columbia, Paul Bucci University of British Columbia, Ivan Beschastnikh University of British Columbia, Alexandra (Sasha) Fedorova University of British Columbia | ||
17:00 20mTalk | TorchQL: A Programming Framework for Integrity Constraints in Machine Learning OOPSLA 2024 Aaditya Naik University of Pennsylvania, Adam Stein University of Pennsylvania, Yinjun Wu University of Pennsylvania, Mayur Naik University of Pennsylvania, Eric Wong | ||
17:20 20mTalk | Verification of Neural Networks' Global Robustness OOPSLA 2024 |