- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
is there any official documentation describing the internals of Hyper-threading as implemented in the Nehalem microarchitecture? I am looking for something similar to the article on the first (P4) implementation published in ITJ 2002. As far as I can tell by comparing experimental results with dual-threaded workloads on the two HT implementations (P4 and Nehalem), the latest implementation must have been subjected under radical changes regarding the way threads share resources, which yields dramatically better performance (reaches up to 2x in some cases). So, I was wondering if these modifications are documented somewhere..
Regards,
Nick
Link Copied
3 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Don't know if this is what you are looking for:
http://software.intel.com/en-us/articles/performance-insights-to-intel-hyper-threading-technology/
but it's worth a look.
http://software.intel.com/en-us/articles/performance-insights-to-intel-hyper-threading-technology/
but it's worth a look.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Not exactly what I was looking for, but a good overview anyway. Thanks Tudor!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The Intel 64 and IA 32 Architecture Optimization Reference Manual contains a comparison of the implementations of Intel Hyper-Threading technology in NetBurst and Nehalem architecture. Furthermore, section 2.2.9 contains a list of the ressources in the core that are shared or partitioned by the 2 threads.
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page