Re: Why VAX Was the Ultimate CISC and Not RISC

John Levine <johnl@taugh.com> writes:

I'm not so sure. The IBM Fortran H compiler used a lot of the 360's instruction
set and it is my recollection that even the dmr C compiler would generate memory
to memory instructions when appropriate. The PL.8 compiler generated code for 5
architectures including S/360 and 68K, and I think I read somewhere that its
S/360 code was considrably better than the native PL/I compilers.
>
I get the impression that they found that once you have a reasonable number of
registers, like 16 or more, the benefit of complex instructions drops because
you can make good use of the values in the registers.

long ago and far away ... comparing pascal to pascal front-end with
pl.8 back-end (3033 is 370 about 4.5MIPS)

Date: 8 August 1981, 16:47:28 EDT
To: wheeler

the 801 group here has run a program under several different PASCAL
"systems".  The program was about 350 statements and basically
"solved" SOMA (block puzzle..).  Although this is only one test, and
all of the usual caveats apply, I thought the numbers were
interesting...  The numbers given in each case are EXECUTION TIME ONLY
(Virtual on 3033).

6m 30 secs               PERQ (with PERQ's Pascal compiler, of course)
4m 55 secs               68000 with PASCAL/PL.8 compiler at OPT 2
0m 21.5 secs             3033 PASCAL/VS with Optimization
0m 10.5 secs             3033 with PASCAL/PL.8 at OPT 0
0m 5.9 secs              3033 with PASCAL/PL.8 at OPT 3

--
virtualization experience starting Jan1968, online at home since Mar1970