[Simh] Virtual VAXen
Bob Supnik
bob at supnik.org
Sun Jul 8 17:09:52 EDT 2012
Ah yes, the VVAX option... another attempted graft on the VAX
architecture tree. Unlike vectors, it never got as far as a real
implementation.
The origin of VVAX was not virtualization per se, but rather, the desire
to have a A1-rated secure VMS OS (under the old Federal Trusted Computer
System Evaluation Criteria -
http://en.wikipedia.org/wiki/Trusted_Computer_System_Evaluation_Criteria),
for deployment in national security environments. The security gurus at
DEC determined that a virtualized environment was the most ironclad way
to provide the required security with adequate performance, so VVAX was
proposed.
I believe both Rigel and Aquarius did paper studies of microcode
feasibility. The Rigel microcode includes a VVAX.MIC that reserves the
required code points for later implementation, but there's no other
evidence of any work. As I recall, the VVAX changes slowed down normal
operation a tad. More importantly, there was no room left in the Rigel
microstore for the extra capability.
By the time VVAX was fully defined, Alpha was underway, and the idea was
not pursued.
/Bob
On 7/8/2012 12:00 PM, simh-request at trailing-edge.com wrote:
> Message: 1
> Date: Sun, 8 Jul 2012 08:22:56 -0400
> From: Stephen Hoffman<Info at HoffmanLabs.Com>
> To: simh at trailing-edge.com
> Subject: Re: [Simh] Throttling and this release
> Message-ID:<493F40D4-85F3-48E5-BBE0-C5491B808336 at HoffmanLabs.Com>
> Content-Type: text/plain; charset=us-ascii
> Solely as VAX trivia and not as a solution for NetBSD or OpenVMS VAX, VAX had an architected idle notification mechanism for operating in a virtual machine, and related instructions and registers.
>
> 02FD WAIT Wait for Interrupt
>
> This instruction signals idle time from the guest operating system to the real machine operating system (RMOS); from the guest to the virtual machine.
>
> OpenVMS VAX does not implement WAIT nor other related instructions, which means that this is architectural trivia and not generally useful for idle detection nor related virtual machine processing.
>
> For details, see chapter 12 of DEC Standard 32<http://bitsavers.org/pdf/dec/vax/archSpec/> document. Don't bother looking in your handbook.
>
> Yes; using IPL detection is the easiest approach, and generally applicable.
>
>
More information about the Simh
mailing list