Huh. I thought TX memory had been written off circa five years ago? "Doesn't scale out of research toy scenarios" and the like. Always seemed like a "Great if it works" idea to me.https://twitter.com/TimSweeneyEpic/status/943633234746888192 …
-
-
Quite right. For example ten years ago we at MS seriously explored transactional memory for easier composition of multithreaded managed code and ultimately did not go to market with it. See https://blogs.msdn.microsoft.com/stmteam/ and
@funcOfJoe's retrospective at http://joeduffyblog.com/2010/01/03/a-brief-retrospective-on-transactional-memory/ … -
The C++ standards effort on STM also seems to have ground to a halt. Probably best to re-explore it in the context of a limited-scope library that can grow over time. As the number of cores grows, the value of STM (and thus willingness to pay performance cost for it) will grow.
- 1 more reply
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.