Eight More '8-Bit Era' Microprocessors(thechipletter.substack.com) |
Eight More '8-Bit Era' Microprocessors(thechipletter.substack.com) |
https://en.wikipedia.org/wiki/COSMAC_Elf https://en.wikipedia.org/wiki/CHIP-8
The OS was interesting too: https://en.wikipedia.org/wiki/OS-9
A number of the Fujitsu computers (with various CPUs) also had a 6809 for video, so some of the ones with a 6809 main CPU had two 6809s in total. The FM-7, FM-8, and FM-77 series all have two 6809s, the FM-11 EX has an 8088 CPU and a 6809 for video, the Micro 16S could have any of the Z80, 8086, 68000, 80286, or Z8000 CPUs and had a 6809 for video. I may have missed some models.
Imagine these 8 bitters were mostly hardwired, with less than a million transistors.
They're correct: ARM won the mobile space, won Apple, and is very gradually seeping into wider availability for other operating systems.
Never mind the majority of raw FLOPS these days are almost certainly going through GPU architectures.
The first generation of true 16-bit CPUs, i.e. Intel 8086, Motorola MC68000 and Zilog Z8000, had almost an order of magnitude more transistors, i.e. in the range of 15000 transistors to 50000 transistors.
The first true 32-bit CPUs, like the National 32000 series, Motorola MC68020 and Intel 80386, had a few hundred thousand transistors.
By the end of the eighties, the second generation of 32-bit CPUs reached 1 million transistors.
The model number was decided long before the transistor-level design was finalized.
For example, https://developer.arm.com/documentation/den0013/0400/ARM-Pro...:
“The ARM architecture provides sixteen 32-bit general purpose registers (R0-R15) for software use. Fifteen of them (R0-R14) can be used for general purpose data storage, while R15 is the program counter whose value is altered as the core executes instructions. An explicit write to R15 by software will alter program flow.”
Similarly, the PDP-11 used R7 for that. https://en.wikipedia.org/wiki/PDP-11_architecture: “The CPU contains eight general-purpose 16-bit registers (R0 to R7). Register R7 is the program counter (PC)”
I’m not aware of any CPU where “every register could be the program counter”. Such a feature also feels weird to me from a design view because I think it complicates the hardware with few (code might be smaller for a limited set of jumps) benefits. Maybe you’re confusing that with the ability to jump to whatever address is in any of the general purpose registers?
EDIT: I just saw a comment mentioning the 1892. It indeed had that ability. https://en.wikipedia.org/wiki/RCA_1802#Registers_and_I/O:
“The SEP instruction can select any of the 16 registers to be the program counter. The SEX instruction can select any of the 16-bit registers to be the index register.”
There'll come a day when the final physical 6502, 80486 (etc etc) powers off for the final time, and it seems like these technologies would be worth preserving. (I'm sure this is much easier said than done, not trying to minimise the effort involved.)
Is there a project that does something like this?
Full die capture, full transistor level simulation.
Most of the others are being emulated in proportion to their importance to games, in arcade machines and consoles. Those emulations are going to be as cycle-accurate as required.
There are some issues around things like the Yamaha synth chips, which are mixed-signal and depend on analogue properties that can be difficult to emulate.
Note that 6502s are still being produced, albeit in a modern CMOS version.
Just calculating or shuffling data around was invisible. With that visualization I first realized how much stuff could be done with a 1MHz CPU.
Same size as a 6809, low-end 486 performance. Who cares ;)
The 68000 transistors number claimed by the Motorola marketing was close to what you get by dividing the die area to the area of one transistor, so it did not correspond to actual transistor positions.
The MC68000 die had large areas occupied with microprogram ROMs, and there as you say only a part of the array of transistors are active, depending on the stored bits. Nonetheless, a significant part of the die was occupied with random logic, where all the physical transistors are used and a part of the area does not have any transistors.