1 |
* Volker Armin Hemmann <volkerarmin@××××××××××.com> wrote: |
2 |
|
3 |
> the CPU. All CPUs use microcode. For decades. Google, or go straight to |
4 |
> wikipedia. |
5 |
> http://en.wikipedia.org/wiki/Microcode |
6 |
|
7 |
Borroughs' large systems (b6500+) were designed as microcode |
8 |
machines from ground up, which essentially interpreted an algol |
9 |
bytecode (the whole OS was directly implemented in assembler, |
10 |
w/o any machine specific assembler code). Paired w/ their entirely |
11 |
stack-based architecture (there were no program-visible registers) |
12 |
they could easily do massive-multiprocessing (everything's reentrant |
13 |
by design), 24/7 uptime even w/ hw replacements/upgrades and |
14 |
cpu improvements w/o ever having to recompile. |
15 |
|
16 |
Their successors (now Unisys) are called emode machines - quite |
17 |
the same approach as nowadays w/ Java (interpreter/JIT). |
18 |
|
19 |
|
20 |
BTW: I'm currently designing an emode/microcode-base computer |
21 |
architecture built on an matrix of nanocores, they don't have a |
22 |
concept of main memory, instead a relatively large (linear |
23 |
addressable) register memory, part of the register space is |
24 |
shared with neighbours (multiport-RAMs). These are programmed |
25 |
by an horizontal microcode, which is decoded by an static demux, |
26 |
that directly connects registers to an micro-ALU (so there're |
27 |
no additional load+store cycles) ... |
28 |
|
29 |
|
30 |
cu |
31 |
-- |
32 |
---------------------------------------------------------------------- |
33 |
Enrico Weigelt, metux IT service -- http://www.metux.de/ |
34 |
|
35 |
phone: +49 36207 519931 email: weigelt@×××××.de |
36 |
mobile: +49 151 27565287 icq: 210169427 skype: nekrad666 |
37 |
---------------------------------------------------------------------- |
38 |
Embedded-Linux / Portierung / Opensource-QM / Verteilte Systeme |
39 |
---------------------------------------------------------------------- |