On Feb 8, 11:06, Jim Keohane wrote:
> The reference to "one cycle" instruction may have been referring
> to there being 2 cpu cycles per clock cycle. Also, there's the
"pipelining"
> some say the 6502 does when the last (or only) byte of an instruction
is
> acted upon simultaneous to next instruction's 1st byte (opcode) being
> fetched
>
> So perhaps "one instruction per clock cycle" may be awfully close
with
> pipelining and with use of zero page.
You must be thinking of some different 6502 to the rest of us :-) As
Sellam said, no 6502 opcode takes less than two clock cycles to
execute, and most take more (up to 7): the only 2-cycle instructions
are the ones with implied addressing, like RTS, CLI, TAX, ... This is
why a 6502 running typical well-written code, running on a 2MHz clock,
manages at best around 0.7 MIPS.
There's no pipelining at all in a 6502. No overlap of instructions
whatsoever.
Zero-page instructions like LDA $12 take three clock cycles.
There aren't two CPU cycles per clock cycle. Perhaps you're thinking
of the fact that the 6502 uses a two-phase clock, and does part of the
CPU cycle during phi-1, and part during phi-2?
> Of course, we're talking Apple ]['s which, if I can trust my
memory,
> steal every other clock cycle to refresh memory.
I believe you're thinking of how it uses part of the clock cycle when
the CPU isn't accessing memory, not alternate clock cycles.
> > > p.s. I also did quite well with 6502 asm code in cpu speed tests
vs
> > > 80x86 and Z80 programmers. The zero page, for all intents and
purposes,
> > > is 256 registers.
That was the designers' intention, but you have to remember that it
takes an extra clock cycle to access a zero-page location rather than a
register.
--
Pete Peter Turnbull
Network Manager
University of York
Received on Sat Feb 08 2003 - 13:08:00 GMT