9 Nov
2001
9 Nov
'01
6:43 a.m.
On November 9, Iggy Drougge wrote:
Isn't this rather odd? The MicroVAX II is supposed
to be 0,5 VUP, right? So
what have the DEC engineers done to make it just as fast in the Dhrystone and
even faster than the 11/780 in the Whetstone benchmarks?
0.9 VUP, not 0.5.
-Dave
--
Dave McGuire
St. Petersburg, FL
10 Nov
10 Nov
12:49 a.m.
At 03:43 PM 11/9/01 -0500, Dave wrote:
Didn't the uVax II implement some of the original VAX instructions
with emulation? I always wondered what the VUP rating would have
been were they not emulated.
--------------------------------------------------------------
Carlos E. Murillo-Sanchez carlos_murillo(a)nospammers.ieee.org
On November 9, Iggy Drougge wrote:
> Isn't this rather odd? The MicroVAX II is supposed to be 0,5 VUP, right? So
> what have the DEC engineers done to make it just as fast in the
Dhrystone and
even faster
than the 11/780 in the Whetstone benchmarks?
0.9 VUP, not 0.5.
-Dave 
11 Nov
11 Nov
12:02 p.m.
New subject: VAX (Was: Cromemco landmarks)
Carlos Murillo skrev:
At 03:43 PM 11/9/01 -0500, Dave wrote:
>On November 9, Iggy Drougge wrote:
>> Isn't this rather odd? The MicroVAX II is supposed to be 0,5 VUP, right?
>> So what have the DEC engineers done to make it just as fast in the
>>Dhrystone and
>> even faster than the 11/780 in the Whetstone benchmarks?
>
> 0.9 VUP, not 0.5.
Didn't the uVax II implement some of the original
VAX instructions
with emulation? I always wondered what the VUP rating would have
been were they not emulated.
According to "Great Microprocessors of the Past and Present (V 12.1.2)":
Further inspiration came from the MicroVAX (VAX 78032) implementation, since
in order to reduce the architecture to a single (integer) chip, only 175 of
the 304 instructions (and 6 of 14 native data types) were implemented (through
microcode), while the rest were emulated - this subset included 98% of
instructions in a typical program. The optional FPU implemented 70
instructions and 3 VAX data types, which was another 1.7% of VAX instructions.
All remaining VAX instructions were only used 0.2% of the time, and this
allowed MicroVAX designs to eventually exceed the speed of full VAX
implementations, before being replaced by the Alpha architecture.
Mind you, the original MicroVAX was only 0,3 VUP (I really hope I'm right this
time =).
I wonder if that qualifies as the slowest machine to run NetBSD. On further
inspection, NetBSD doesn't mention any MicroVAX I support. Still, 0,9 VUP is
quite little. One competitor might be the 010-based Sun 2s (a new port).
Some time ago, someone on thist list used the phrase "though not as slow as a
PC523". Is the PC532 really that slow?
--
En ligne avec Thor 2.6a.
Amiga 4000/040 25MHz/64MB/20GB RetinaBLTZ3/VLab/FastlaneZ3/Ariadne/Toccata
1:30 p.m.
New subject: VAX (Was: Cromemco landmarks)
At 03:02 AM 11/12/01 +0100, Iggy wrote:
Carlos Murillo skrev:
(through
Didn't the uVax II implement some of the
original VAX instructions
with emulation? I always wondered what the VUP rating would have
been were they not emulated.
in order to reduce the architecture to a single (integer) chip, only 175 of
the 304 instructions (and 6 of 14 native data types) were implemented microcode), while the rest were emulated - this subset
included 98% of
instructions in a typical program. The optional FPU implemented 70
instructions and 3 VAX data types, which was another 1.7% of VAX
instructions.
All remaining VAX instructions were only used 0.2% of
the time, and this
allowed MicroVAX designs to eventually exceed the speed of full VAX
implementations
Aha! So, if I were doing numerical linear algebra in a uVaxII w/o the optional
FPU, I could expect performance to be badly hit with respect to the 0.9 VUP
rating.
(FYI, I always tend to benchmark machines using float performance,
because that's the kind of thing that I do for a living. I look at integer
performance only as something that has an impact on sparse linear algebra
blocks, as opposed to dense system methods).
How do I know if my Vaxstation 2000 has the optional FPU? What is
its model number?
What about the Vaxstation 4000/60? Does it have a built-in FPU?
carlos.
--------------------------------------------------------------
Carlos E. Murillo-Sanchez carlos_murillo(a)nospammers.ieee.org
7:17 p.m.
New subject: VAX (Was: Cromemco landmarks)
Carlos Murillo skrev:
>microcode), while the rest were emulated - this
subset included 98% of
>instructions in a typical program. The optional FPU implemented 70
>instructions and 3 VAX data types, which was another 1.7% of VAX
Aha! So, if I were doing numerical linear algebra in a
uVaxII w/o the
optional FPU, I could expect performance to be badly hit with respect to the
0.9 VUP rating.
You mean you actually use your FPU? I thought that was just a dongle for
running NetBSD on 68k Macs. ;-)
How do I know if my Vaxstation 2000 has the optional
FPU? What is
its model number?
Conversely, NetBSD's notes on system models says this:
"In fact, at the time the 78032 was the first 32-bit microprocessor with both
memory management and floating point on a single chip. It showed up in many
system including the MicroVAX II and the VAX 8200."
--
En ligne avec Thor 2.6a.
Among the best Swedish achievements are those that closely combine social and
architectural developments, such as the carefully planned new towns built in
recent years outside Stockholm: V?llingby and Farsta.
J.M. Richards, Modern Architecture
15 Nov
15 Nov
4:36 a.m.
New subject: VAX (Was: Cromemco landmarks)
--- Iggy Drougge <optimus(a)canit.se> wrote:
Mind you, the original MicroVAX was only 0,3 VUP (I
really hope I'm right
this time =).
AFAIK, you are. My memory of the (s)low end of VAXen is...
VUPs Model
0.3 uVAX-I
0.4 11/725 & 11/730
0.6 11/750
0.9 uVAX-II, VAX8200
1.0 11/780 (the first one of these I _don't_ own ;-)
Speaking of the 8200, does anyone have any 8250 CPUs lying around? I
would love to take my 8300 up to an 8350. I'd rather trade than buy
at this point - it's a very low-priority upgrade.
-ethan
__________________________________________________
Do You Yahoo!?
Find the one for you at Yahoo! Personals
http://personals.yahoo.com
8438
days inactive
8444
days old
5 comments
4 participants
participants (4)
-
cmurillo＠emtelsa.multi.net.co -
erd_6502＠yahoo.com -
mcguire＠neurotica.com -
optimus＠canit.se