Mon 18 Feb 2019 15:15 - 15:40 at Salon 12/13 - Session 3: Transactional Memory Chair(s): Milind Chabbi
In this paper we provide a high performance solution to the problem of committing transactions while enforcing a predefined order. We provide the design and implementation of three algorithms, which deploy a specialized cooperative transaction execution model. This model permits the propagation of written values along the chain of ordered transactions. We show that, even in the presence of data conflicts, the proposed algorithms outperform single threaded execution, and other baseline and specialized state-of-the-art competitors (e.g., STMLite). The maximum speedup achieved in micro benchmarks, STAMP, PARSEC and SPEC200 applications is in the range of 4.3x - 16.5x.
Mon 18 FebDisplayed time zone: Guadalajara, Mexico City, Monterrey change
Mon 18 Feb
Displayed time zone: Guadalajara, Mexico City, Monterrey change
14:00 - 15:40 | Session 3: Transactional MemoryMain Conference at Salon 12/13 Chair(s): Milind Chabbi Uber Technologies | ||
14:00 25mTalk | Modular Transactions: Bounding Mixed Races in Space and Time Main Conference Brijesh Dongol University of Surrey, Radha Jagadeesan DePaul University, James Riely DePaul University DOI | ||
14:25 25mTalk | Leveraging Hardware TM in Haskell Main Conference DOI Authorizer link File Attached | ||
14:50 25mTalk | Stretching the capacity of Hardware Transactional Memory in IBM POWER architectures Main Conference Ricardo Jorge Duarte Filipe , Shady Issa INESC-ID, João Barreto INESC-ID, Paolo Romano University of Lisbon, Portugal DOI | ||
15:15 25mTalk | Processing Transactions in a Predefined Order Main Conference Mohamed M. Saad Virginia Tech, Masoomeh Javidi Kishi Lehigh University, Shihao Jing Lehigh University, Sandeep Hans IBM India Research Lab, Roberto Palmieri Lehigh University DOI |