Linked by David Adams on Wed 4th Aug 2010 18:28 UTC, submitted by estherschindler
Hardware, Embedded Systems Anyone contemplating a new computer purchase (for personal use or business) is confronted with new (and confusing) hardware choices. Intel and AMD have done their best to differentiate the x86 architecture as much as possible while retaining compatibility between the two CPUs, but the differences between the two are growing. One key differentiator is hyperthreading; Intel does it, AMD does not. This article explains what that really means, with particular attention to the way different server OSes take advantage (or don't). Plenty of meaty tech stuff.
Permalink for comment 435485
To read all comments associated with this story, please click here.
Panajev
Member since:
2008-01-09

Citations (from author of parent)

IBM HT Google: A multithreaded PowerPC processor for commercial servers

I can't find the simplified version of IBM's documentation.

Intel HT: ftp://download.intel.com/technology/itj/2002/volume06issue01/vol6i...


One more thing about your comment on bubbles and using SMT to solve them...

What Intel mentions in that PDF at page 22 is basically a software version of the Scout Threads feature mentioned for Niagara and Rock processors (which they meant to implement in HW and trigger dynamically).

The idea is to help single threaded programs, or programs with low thread level parallelism, by spawning additional threads whose only purpose is to trigger cache misses and pre-fetch data as well as run down both paths of a branch to pre-calculate the target address of both and do work in advance for the main thread.

This does not change the fact that the SMT hardware in Intel's CPU's is able to issue instructions to its execution units from more than one thread at once.

Edited 2010-08-05 08:53 UTC

Reply Parent Score: 2