When did the Z80 compatibles reach very high clock speed?

Question

In the early eighties, the Z80B and Z80H at 6 and 8 MHz respectively, were released.

In 1985, the Hitachi HD64180 reached 10 MHz (with some enhancements such that it seems to be reckoned the equivalent of a Z80 at around 13 MHz).

Later, according to https://en.wikipedia.org/wiki/Zilog_Z180 the Z180 reached speeds of 16, 20, ultimately 33 MHz. When were these milestones reached?

Best I've been able to find so far is http://www.z80.info/z80lives.htm dated 1992, which says the ceiling as of the time of writing is 15 MHz. That means the faster variants came later in the nineties?

Answer 1

An article from 2000 on embedded.com dates the Hitachi 64180 (which Zilog second sourced as the Z180) to 1985, the Z280 to 1976, but that's almost certainly a typo for 1986, the Z380 to "the mid '90s", the Rabbit 2000 to "last fall" (i.e. 1999), and the eZ80 explicitly to 1999. (Aside: it's an interesting read beyond those data points, giving a lot of technical detail rather than merely a dry recitation of dates).

As per my comment, I'd add to that the R800, which was developed by the ASCII Corporation as an enhancement to the Z80 that had powered MSX machines until then; the bottom dropped out of the MSX market in the interim but it made it to market in the Panasonic Turbo R in 1990.

The 64180's product sheet states that it has an operating frequency up to 10Mhz. The same is true of the Z180. In both cases instructions have already become more efficient than the Z80.

The Z280 includes a clock divider and a clock output, the intention being that you feed it a fast clock and then it produces a divided one for everybody else and inserts wait states if and when necessary so that it isn't talking too quickly. It includes a cache, so a lot of the same considerations apply as with a more conventional clock multiplier, in addition to the instructions generally being more efficiently implemented. It topped out at 12.5Mhz.

The R800 in the Turbo R is clocked at 14.32Mhz — four times the NTSC colour burst, and like the others mentioned here, is more efficient per cycle than a Z80.

The Z380 scales up to 18Mhz, with similar considerations about Mhz not meaning the same thing as on a vanilla Z80.

The Rabbit 2000 "uses an external crystal with a frequency typically in the range from 1.8 MHz to 29.5 MHz". Which I take to mean that it tops out at 29.5 Mhz.

The eZ80 was initially announced as being intended to become available at up to 80Mhz, but it's unclear to me what actually launched. I defer to Raffzahn's existing answer which states that they only actually managed to push it to 50.

Answer 2

While it's easy to setup a timeline for early models, it gets harder when the CPU was no longer a dedicated chip, but part of a SoC, or just an ebedded component, as this data is not free available. Even more as later developments, like the eZ80 may be code compatible, but of different internal design. It would be much like comparing an 8086 with a Pentium.

Having said that, spring 2002 was the time the eZ80 became available at 50 MHz. Considering that it got about 4 times the thruput per clock as a genuine Z80, this would set it at a 200 MHz equivalent. As a (more or less) seperate CPU, that'S the top notch Z80 code can run on dedicated/real hardare. Real in a sense that it's hardware made to execute Z80 code direct, not via an (internal) emulation layer or similar.

Answer 3

I have used Z180 10Mhz version in early 2000 start using Z180 33Mhz in 2006 to 2009 because it was any an easy replacement of the slower Z180's. I think I started to see the fast Z180's in the market around 2005. I don't if you can call that a milestone.

Answer 4

I worked on Hypercom ICE credit card terminals in the noughties but the terminals date from the late nineties. They had dual Z80s running at approx 50mhz (one was used as the crypto engine). The terminals I worked on had 2MB of ram but were still constrained by the 64KB limit of the Z80. A paging scheme was used and the compiler supported the concept of long calls/jumps (24 bit, the upper 8 bits was a page number). The upper 32K was paged.