see below, plz.
Dick
----- Original Message -----
From: "ajp166" <ajp166_at_bellatlantic.net>
To: <classiccmp_at_classiccmp.org>
Sent: Sunday, December 23, 2001 6:02 AM
Subject: Re: 6502/Z80 speed comparison (was MITS 2SIO serial chip?)
> The most common reason for not using an hll is that unless the compiler
> is well written and optimizing you see the compiler not the cpu.
>
That's exactly the thing that bothers me about HLL's for comparison purposes.
>
> Small C was a good language but the result was often so poor that
> even a small amount of hand optimization was easy to accomplish.
> For a cpu like 6502, this tended to be more true as many of the
> things the C language likes just dont map to cpu instruction set
> that directly. Same was true for most of the Z80 versions of
> small C as most treated it as an 8080 and didnt use the more
> useful instrucitons.
>
The 6502 had registers that would function as pointers, but only as short ones,
which bothers guys who write compilers, but indexed indirection, along the lines
that PDP-11's used, was possible with it via zero-page. I don't know that
anyone ever capitalized on that in a 'C' compiler. One problem, of course, was
that there really never was a serious operating system that could be used by a
compiler, so no compiler-generation effort could rely on an OS for support in
the "usual" ways.
>
> As to the PDP-11, that was the consumate C machine at the
> instruction set level.
>
No argument about that!
> -----Original Message-----
> From: Ben Franchuk <bfranchuk_at_jetnet.ab.ca>
> To: classiccmp_at_classiccmp.org <classiccmp_at_classiccmp.org>
> Date: Saturday, December 22, 2001 9:40 PM
> Subject: Re: 6502/Z80 speed comparison (was MITS 2SIO serial chip?)
>
>
> >Richard Erlacher wrote:
> >>
> >> Let's leave compilers out of the equation. Even the same small-C
> compiler,
> >> targeted at the two quite different CPU's potentially represent a
> significant
> >> skew in favor of one or another of the two.
> >>
> >> Dick
> >How can you have skew? That is the whole idea of benchmark is to
> >compare
> >two machines. I would expect that the simple C that was given would be a
> >good test
> >when judged with other benchmarks. The 8080/Z80/8086 all generate the
> >same poor
> >code. This surprised me as shows how poor the 16 bit intel product was.
> >The PDP-11
> >version was rather nice but it even has a few quirks.
> >--
> >Ben Franchuk --- Pre-historic Cpu's --
> >www.jetnet.ab.ca/users/bfranchuk/index.html
> >PS. Note all my FPGA machines generate nice 'Small C' code and have a
> >resonably orthogonal instruction set. The well hacked Small C compiler
> >self compiles under
> >24 KB. A similar compiler for the 8080 is about 48KB.
>
>
Received on Sun Dec 23 2001 - 12:14:41 GMT