Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 23 May 2006 10:14:06 +0200
From:      Lars Heidieker <lars@heidieker.de>
To:        m m <needacoder@gmail.com>
Cc:        current@freebsd.org, "Chad Leigh -- Shire.Net LLC" <chad@shire.net>
Subject:   Re: FreeBSD is now self-hosting on the UltraSPARC T1
Message-ID:  <0B0D940E-213A-456F-964A-2D7A922D0315@heidieker.de>
In-Reply-To: <1e4841eb0605221133s428d9136p3d5f7eff964167f4@mail.gmail.com>
References:  <1e4841eb0605211854i44c4aa4cm9dfc72506c2232ea@mail.gmail.com> <FB03D201-4154-411E-AFE4-572CEBF76A92@shire.net> <1e4841eb0605221133s428d9136p3d5f7eff964167f4@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1


On 22 May 2006, at 20:33, m m wrote:

> On 5/22/06, Chad Leigh -- Shire.Net LLC <chad@shire.net> wrote:
>>
>> On May 21, 2006, at 7:54 PM, m m wrote:
>>
>> > While
>> > on topic, the Opterons aren't SMP either, and neither are the
>> > ht-Xeons...
>>
>> I would like t\o hear the rational for the Opterons (presumably the
>> dual core ones) not being SMP.  They have two independent operating
>> cores in one physical package.  Who cares how it is packaged?  I
>> would tend to agree with you on the ht-Xeon in terms of general
>> descriptions.  I do not know as well how the ht-xeon work as I don't
>> use any but it seems to me that the "SMP" moniker, at least in
>> FreeBSD, relate to how things are scheduled.
>
> SMP stands for "Symmetric MultiProcessing", which means that multiple
> processors have equal access latency to memory - typically
> accomplished by sitting the processors on a shared bus with memory.
> The MultiProcessor Opterons are _NOT_ SMP, they are _NUMA_ machines,
> "NonUniform Memory Access"; in the MP Opterons each processor has (or
> can have) its own "local" memory, which makes up only part of the
> shared address space.  When an Opteron accesses an address that is not
> in its "local" memory, it has to talk to a remote processor's memory,
> thereby incurring a different access latency.
> _______________________________________________
> freebsd-current@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-current
> To unsubscribe, send any mail to "freebsd-current- 
> unsubscribe@freebsd.org"
>

I don't think this is right, SMP stands for "Symmetric  
MultiProcessing" in opposite to MultiProcessing where the OS image runs
only on one CPU UMA and NUMA are a different thing, but yes a NUMA  
machine with big latency differences would have
problems to run efficiently as a SMP machine.
Therefor a dual core Opteron has SMP (two cores two caches etc) and  
totally UMA and a dual single core Opteron is not
because it is NUMA. I don't take if this is the result.
For me I would seperate NUMA/UMA from SMP and call it SMP if there  
are more than one processor core.
Yes this leaves Intels HT in the dark I don't know if I would call  
that SMP, but probably I would as it appears (to the os) to be two cpus.

Lars

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.3 (Darwin)

iD8DBQFEcsRTcxuYqjT7GRYRAmBwAJ9CTYwCsQlClJX+jXwl+U/rtUv0MQCgrAqo
2+MZhRW8kDdSGAvQp0mFE+c=
=fDqM
-----END PGP SIGNATURE-----



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?0B0D940E-213A-456F-964A-2D7A922D0315>