-
Archives
- May 2022
- December 2021
- November 2021
- October 2021
- September 2021
- July 2021
- May 2021
- April 2021
- March 2021
- December 2020
- October 2020
- September 2020
- July 2020
- June 2020
- March 2020
- January 2020
- December 2019
- October 2019
- April 2019
- March 2019
- January 2019
- December 2018
- November 2018
- September 2018
- August 2018
- July 2018
- June 2018
- May 2018
- April 2018
- February 2018
- December 2017
- November 2017
- October 2017
- August 2017
- July 2017
- June 2017
- April 2017
- February 2017
- January 2017
- November 2016
- September 2016
- August 2016
- July 2016
- June 2016
- May 2016
- April 2016
- March 2016
- February 2016
- October 2015
- September 2015
- June 2015
- May 2015
- April 2015
- March 2015
- February 2015
- January 2015
- November 2014
- October 2014
- August 2014
- June 2014
- March 2014
- January 2014
- October 2013
- August 2013
- July 2013
- June 2013
- April 2013
- February 2013
- January 2013
- November 2012
- October 2012
- September 2012
- August 2012
- July 2012
- June 2012
- May 2012
- March 2012
- February 2012
- January 2012
- December 2011
- November 2011
- October 2011
- September 2011
- August 2011
- July 2011
- June 2011
- May 2011
- April 2011
- March 2011
- February 2011
- January 2011
- December 2010
- November 2010
- October 2010
- September 2010
- August 2010
- July 2010
- June 2010
- May 2010
- April 2010
- March 2010
- February 2010
- January 2010
- December 2009
- November 2009
- October 2009
- September 2009
- August 2009
- July 2009
- June 2009
- May 2009
- April 2009
- March 2009
- February 2009
-
Meta
Tag Archives: transactional memory everywhere
Transaction Memory Everywhere: Forward-Progress Guarantees
Last year, I noted that hardware transactional memory (HTM) announcements lacked forward-progress guarantees. As noted in that posting: Until HTM implementations provide some sort of forward-progress guarantee, HTM will be limited by its fallback code sequences. For example, if the … Continue reading
Posted in Uncategorized
Tagged transactional memory everywhere
Comments Off on Transaction Memory Everywhere: Forward-Progress Guarantees
Transactional Memory Everywhere: HTM and Cache Geometry
The previous post described some potential pitfalls in blindly applying hardware lock elision to legacy software. This post looks instead at how changes in CPU cache geometry have increased hardware transactional memory’s (HTM’s) cache footprint, at least from a theoretical … Continue reading
Transactional Memory Everywhere: Hardware Transactional Lock Elision
My earlier posting on hardware transactional memory (http://paulmck.livejournal.com/31853.html) brought an unusual amount of private email, especially on my discussion of the hazards of eliding empty critical sections (http://kernel.org/pub/linux/kernel/people/paulmck/Answers/TransactionalMemoryEverywhere/WhyEmptyLock.html). Several people made the interesting claim that any correct code involving empty … Continue reading
Posted in Uncategorized
Tagged parallel, transactional memory everywhere
Comments Off on Transactional Memory Everywhere: Hardware Transactional Lock Elision
Transactional Memory Everywhere: 2012 Update for HTM
In a recent post, I called out some of the past year’s activity in the area of transactional memory (TM). This post takes a closer look at hardware transactional memory (HTM), with an eye to where it might fit into … Continue reading
Transactional Memory Everywhere: 2012 Update
The past year has been a busy one for transactional memory (TM). IBM’s Blue Gene/Q and Intel’s Haswell TSX have joined Sun Rock and Azul’s Vega 2 in offering hardware transactional memory (HTM). All of these implementations seem to be … Continue reading
Stupid RCU Tricks: Can Transactional Memory Subsume RCU?
In theory, transactional memory (TM) can emulate RCU read-side critical sections quite straightforwardly: Change all occurrences of rcu_read_lock() into your favorite start-of-transaction primitive. Change all occurrences of rcu_read_unlock() into your favorite end-of-transaction primitive. Replace all rcu_dereference() primitives with their arguments. … Continue reading
Posted in Uncategorized
Tagged stupid rcu tricks, transactional memory everywhere
Comments Off on Stupid RCU Tricks: Can Transactional Memory Subsume RCU?
Transactional Memory Everywhere: Comparison to Locking
A comparison of transactional memory (TM) and locking by Maged Michael, Josh Triplett, Jonathan Walpole, and myself recently appeared in ACM Operating System Review. This is a journal version of an earlier workshop paper in PLOS 2007. This paper attempts … Continue reading
Transactional Memory Everywhere: Follow-Up I
One of the big challenges for any synchronization mechanism is synchronization overhead. The larger the synchronization overhead, the greater the granularity of parallelism required to attain high efficiency. Given that software transactional memory has significant synchronization overhead, one natural reaction … Continue reading
Posted in Uncategorized
Tagged parallel, transactional memory everywhere
Comments Off on Transactional Memory Everywhere: Follow-Up I
Transactional Memory Everywhere: Summary
If you actually read my full set of Transactional Memory Everywhere blog postings, I offer my enthusiastic congratulations and heartfelt condolences. In short, although TM offers much promise for small changes to memory-only data structures, there are a number of … Continue reading
Posted in Uncategorized
Tagged parallel, transactional memory everywhere
Comments Off on Transactional Memory Everywhere: Summary
Transactional Memory Everywhere: RCU
Because read-copy update (RCU) finds its main use in the Linux kernel, one might be forgiven for assuming that there had been no academic work on combining RCU and TM. However, the TxLinux group from the University of Texas at … Continue reading
Posted in Uncategorized
Tagged parallel, transactional memory everywhere
Comments Off on Transactional Memory Everywhere: RCU
You must be logged in to post a comment.