New CPU Architecture
I was looking at old Microprocessors 6500, 68000, 6800 etc. and noticing that the instruction sets have only 3 types of operations: 1. data movement, 2. branch and 3. math - logical operations on registers so it would be only a JMP or BRANCH, a LOAD from Memory and an ADD (or AND etc.) Number to Memory or register, etc.
So given that these old CPUs had only 5,000 transistors, with the level of integration available today (billions of transistors) you could completely change the CPU architecture: do away with data movement operations, each memory location could have a CPU attached or something like that to do the logical operations, the branches could simply be signals to the memory locations, massively parallel CPU, completely new designs, very fast machines, etc.
If you consider that those old CPU systems had a 4k ROM for BASIC, then 4000 locations times 5000 transistors makes only 25 million transistors, it could be done or experimented, etc.
New CPU architectures, changing completely the way those CPUs were designed, make the memory the processor, make the logic diffused, try all possible combinations, etc.
CPUs in 50 years have only tried about 20 to 50 different combinations, we can now try thousands of new ideas (who cares if most don’t work, the possibilities are there, some can be breakthroughs!).
And imagine if we don’t even use logic or something, new ways of thinking and such. Just like pure blind forces created life and complexity exactly because those forces didn’t use any logic, anything could go, any combination, in as logic simply limits what can be while nature follows no rules it just keeps on making a mess until a brain pops out of the soup, so new CPU designs could be tried, billions of new combinations, with millions of transistors so many new connections and circuits and such…
APE