xanthous :
Yes and no to whether or not x86-64 is built for Multi-Core systems.
When AMD was creating the Hammer architecture one of their design priorities was to enable seamless / glueless connection of the processors. So, yes, the x86-64 specification does account for running in a Multi-Core / Multi-Processor configuration.
I don't want to say that it was designed to run in SMP from the start since x86-64 does inherit x86 / IA32.
To answer the how does it tie in gets a little more complex.
Most of Intel's 64bit problems were caused by a broken implementation of x86-64 on the Prescott based Intel Pentium4 processor series. Essentially, Intel ran x64-64 calls in an emulation mode rather than at the hardware level.
In the case of Conroe based processors, it is not fully known if Intel is still following the emulation path or if Conroe is performing the instructions in hardware.
The issue is clouded by a couple of factors.
Intel is beginning to open up to the concept of Open Source and has been working closer with Open Source Communities and kernel developers. Many of the deviances from the x86-64 specification may be accounted for by Kernel Developers, which might account for the increased stability.
However, given the amount of documentation produced by Intel about the Pentium III and how it would poorly scale to 64bits and how Pentium4 was the future (back when Hammer was shaping up in 2000, 2001, and 2002), and how 64bits was not important, there are some who hold the opinion that Intel did not take the time to extend the Pentium III derived Banias to 64bits, and that Conroe, as derived from Banias, is still a 32bit architecture running x86-64 in emulation rather than hardware.
Realistically speaking, on current Conroe based processors, running in x86-64 should not technically cause any spectacularly bad problems.
I haven't seen any major issues cropping up on the kernel mailing lists about it.
|