[comp.sys.apple2] Benchmarks are not what they seem to be

bazyar@ernie (Jawaid Bazyar) (03/19/91)

In article <8053@crash.cts.com> pat@pro-shop.cts.com (Pat Regan) writes:
>i saw that a 33mhz 386 is about 40 times faster than an apple iigs.  how
>much faster is a mac comparred to a iigs, or even a mac compared to a 33mhz
>386.  or maybe even compared to a slow 486?

   There are a couple things you need to consider when you're talking about
benchmarks like the Dhrystone- what exactly does it measure?
   In particular, the Dhrystone benchmark (stock GS gets 250-270, 33MHz '386
get 10000) was written to test C compilers.  And in fact that is what has
been compared- the Dhrystone program compiled and run on a '386 is 40 times
faster than that program compiled on the GS.  
   To answer your second question, the Macs are dogs compared to the '386,
but since the '386 sports one of the most grotesque architectures ever
(second only to the Vax), either way you lose out trying to do anything
other than run Unix, since almost NO IBM compat anything takes advantage
of a '386 (like the compiler the Dhrystone was compiled on did).
   What counts is that a GS w/Transwarp appears as fast as a '386 w/Windows
for everyday applications.

--
Jawaid Bazyar               |"I'm sure K&R have never heard of Mike." 
Senior/Computer Engineering |
bazyar@cs.uiuc.edu          |"That's okay. I'm sure Mike's never heard of K&R".
   Apple II Forever!        |  (discussion about Orca/C)