Why we don't have 128-bit CPUs

jwr1@kbin.earth to Technology@lemmy.world – 274 points –
xda-developers.com
123

You are viewing a single comment

So "instruction encoding length".

I don't think that works though. For something like RISC-V, RV64 has a maximum 32-bit instruction encoding. For x86-64 those original 8-bit intructions still exist, and take up a huge part of the encoding space, cutting the number of n-bit instructions to more like 2^(n-7)

RV64 has a maximum 32-bit instruction encoding

I kinda expected that to happen, since there's already enough to fit all required functions. So yeah, even this is not a good enough criteria for bit rating.

those original 8-bit intructions still exist, and take up a huge part of the encoding space, cutting the number of n-bit instructions to more like 2^(n-7)

err... they are still instructions, right? And they are implemented. I don't see why you would negate that from the number of instructions.

If the 8088 had used all but one 256 8-bit values as legal instructions, all your new instructions after that point would need to start with that unused value and then you can add a maximum of 256 instructions by using the next byte. End result is 511 instructions can be encoded in 16-bits.

Ah right! I forgot about that.

So you either have to pad all instructions in all previous binaries, or reduce the amount of available instructions in the arch update.