Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.programming > #4983 > unrolled thread
| Started by | Ramine <ramine@1.1> |
|---|---|
| First post | 2014-12-06 17:04 -0800 |
| Last post | 2014-12-06 17:04 -0800 |
| Articles | 1 — 1 participant |
Back to article view | Back to comp.programming
I have just read the following about Intel TSX Ramine <ramine@1.1> - 2014-12-06 17:04 -0800
| From | Ramine <ramine@1.1> |
|---|---|
| Date | 2014-12-06 17:04 -0800 |
| Subject | I have just read the following about Intel TSX |
| Message-ID | <m5vuff$uk6$1@dont-email.me> |
Hello, I have just read the following about Intel TSX: "At the moment, TSX is quite slow, even if there's no contention and you don't do anything in the block. There's a lot of overhead. Using TSX naively may slow down even threaded code. Getting significant performance gains from it is non-trivial." read more here a little bit down the webpage: http://cbloomrants.blogspot.ca/search?updated-min=2014-01-01T00:00:00-08:00&updated-max=2015-01-01T00:00:00-08:00&max-results=43 So i think my newer scalable distributed sequential lock is faster than Intel TSX on read-mostly scenarios, also my newer algorithm is kind of general synchronization mechanism because it works with both memory and hardisk. Thank you, Amine Moulay Ramdane.
Back to top | Article view | comp.programming
csiph-web