Does Linux SMP perform at its optimum in Intel Core i7?

[gerry.butler]

This is a general technical question about Symmetric Multiprocessing in relation to the Intel Core i7. (Actually, it's more about Hyperthreading than i7.)

My understanding is that Symmetric Multiprocessing means that the operating system treats all processors as identical, and therefore it can assign a new thread to any free processor.

And that i7 appears to the OS as 8 processors, 0 thru 7.

But from a performance perspective, the 8 processors are not identical, because each core has 1 execution engine plus the ability to store the state of 2 threads. This is, as far as I understand it, the essence of Intel's Hyperthreading. So each execution engine can quickly switch between 2 threads without bothering the OS, but only one thread at a time actually executes.

Suppose, for example, all processors are idle and the OS assigns one thread to processor 0, then has a second thread to assign. Since all free processors are considered identical, the OS could assign the second thread to any free processor, say 1. The result would be that both threads are competing for the same execution engine, while the other 3 cores remain idle.

Is my understanding of SMP correct?

If so, does linux SMP take full advantage of Intel Hyperthreading (which existed also in earlier Intel processors)? That is, does linux SMP assign threads in such a way that it attempts to choose an idle execution engine?

I don't know what algorithm SMP actually uses to choose the processor. For example, it could be the first free processor, or any free processor chosen at random.

How about Windows? How does it handle the situation?

Thanks. Gerry

Edit: I have also posted this question in linuxforums and phoronix forums. I hope this doesn't count as cross-posting, since those forums are not on this site and they have different readership. If it is indeed cross-posting, please let me know and I will avoid doing it in future.

[markkuk]

Originally Posted by gerry.butler

So each execution engine can quickly switch between 2 threads without bothering the OS, but only one thread at a time actually executes.

That would be plain old multithreading with hardware assist, not hyperthreading. All modern CPU cores have multiple parallel execution pipelines and a HT core tries to keep the pipelines working at maximum capacity by choosing instructions from two different threads instead of just one.

Originally Posted by gerry.butler

If so, does linux SMP take full advantage of Intel Hyperthreading

Yes, Linux understands processor hierarchies of threads, cores and physical packages: http://www.kernel.org/doc/ols/2006/o...es-337-348.pdf

[gerry.butler]

Hello markkuk

Thank you for the references. It looks like I've got a bit of reading to do. I may get back with some more questions after I've digested this information and whatever else I get hold of.

Someone has also pointed out that in the kernel config there is an option called SMT scheduler support, which "improves the CPU scheduler's decision making when dealing with Intel Pentium 4 chips with HyperThreading at a cost of slightly increased overhead in some places."

One of the wikipedia articles you reference says that multithreading CPUs have been around since the 1950s, and I recall now that the Honeywell 800 series (1958 until about 1970) executed 8 concurrent threads. The processor didn't have a pipeline. It just took 1 instruction in turn from each active thread and executed it.

Thanks. Gerry