M
Michael Spear
Researcher at Lehigh University
Publications - 94
Citations - 3073
Michael Spear is an academic researcher from Lehigh University. The author has contributed to research in topics: Transactional memory & Software transactional memory. The author has an hindex of 29, co-authored 93 publications receiving 2986 citations. Previous affiliations of Michael Spear include Microsoft & University of Rochester.
Papers
More filters
Proceedings ArticleDOI
Nonblocking transactions without indirection using alert-on-update
TL;DR: A second nonblocking STM system is presented that uses multiple AOU lines (one per accessed object) to eliminate validation overhead entirely, resulting in a nonblocking, zero-indirection STM systems that outperforms competing systems by as much as a factor of 2.
STAMP Need Not Be Considered Harmful
TL;DR: It is taken that STAMP should not be considered harmful, and the TM research community should embark upon a disciplined effort to produce up-to-date benchmarks, using STAMP as a starting point, and several flaws in STAMP are repaired.
Journal IssueDOI
Compiler and runtime techniques for software transactional memory optimization
Peng Wu,Maged M. Michael,Christoph von Praun,Takuya Nakaike,Rajesh Bordawekar,Harold W. Cain,Calin Cascaval,Siddhartha Chatterjee,Stefanie R. Chiras,Rui Hou,Mark F. Mergen,Xiaowei Shen,Michael Spear,Huayong Wang,Kun Wang +14 more
TL;DR: An initial work on supporting automatic instrumentation of the STM primitives for C-C++ and Java programs in the IBM XL compiler and J9 Java virtual machine is presented.
Proceedings ArticleDOI
Reducing Memory Ordering Overheads in Software Transactional Memory
TL;DR: This work proposes compiler optimizations that can safely eliminate many fence instructions and obtains a reduction of up to 89% in the number of fences, and 20% in per-transaction latency, for common transactional benchmarks.
Book ChapterDOI
Transactions as the foundation of a memory consistency model
TL;DR: This work argues that traditional synchronization objects, such as locks, conditions, and atomic/volatile variables, should be defined in terms of transactions, rather than the other way around, and shows that selective relaxation of the relationship between program order and transaction order can allow the implementation of transaction-based locks to be as efficient as conventional locks.