Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.programming.threads > #2492 > unrolled thread
| Started by | aminer <aminer@toto.net> |
|---|---|
| First post | 2014-06-11 07:44 -0700 |
| Last post | 2014-06-11 07:44 -0700 |
| Articles | 1 — 1 participant |
Back to article view | Back to comp.programming.threads
Sequential consistency aminer <aminer@toto.net> - 2014-06-11 07:44 -0700
| From | aminer <aminer@toto.net> |
|---|---|
| Date | 2014-06-11 07:44 -0700 |
| Subject | Sequential consistency |
| Message-ID | <lnapk3$4eu$1@news.albasani.net> |
Hello, Why have i not spook about sequential consistency and memory models ? Cause that is not a difficult subject for me... On strong memory models like the x86 architecture , you have to take care of the following: There is one important non-guarantee listed in the x86 spec: "Loads may be reordered with older stores to different locations" So i have taking care of that and i have imnplemented my parallel projects taking care of sequential consistency on strong memory model like x86. But on weaker memory models that's not so difficult for me, but i have not decided to port my parallel projects and scalable synchronization algorithms on other memory models than x86 architecture. Thank you for your attention. Amine Moulay Ramdane.
Back to top | Article view | comp.programming.threads
csiph-web