[tenebrisalietum]

I think your second point hits it and is the primary benefit to hiding the microarchitecture layer - it can be improved and existing code will benefit from it.

Basically Intel is saying if you had 200 GPRs, you couldn't do better at using the free ones than the CPU scheduler/decoder.

> Adding *architecturally visible* registers increases complexity for people writing assembly and/or compilers.

More registers just makes your code less likely to have to shuffle stuff to and back from RAM - which is where stuff will go if you don't have registers.

It's always faster for a CPU to access registers within itself than have to talk over a bus to a memory. Even when RAM was the same speed as CPUs (8-bit era) you would still save a cycle or two.

[brucedawson]

Having more logical/architectural registers is great except for a few costs:

1) More bits to encode register numbers in instructions. Doubling the number of logical registers costs another two or three bits depending on how many registers are referenced in an instruction

2) Logical registers have to be saved on context switches

3) Logical registers have to be saved around function calls. Either the caller or the callee has to save (or not use) registers, and most functions are both callers and callees. That is, if you are not a leaf-node function then every register you use you have to first save to the stack, or else assume that the functions you call will trash it. Thus, more registers have diminishing returns.

4) No matter how many logical registers you have you _always_ want to have an order of magnitude more physical registers, because otherwise you can't implement OOO or speculative execution.

Point #4 is probably the most critical because I think what people are really asking is why are there more physical than logical registers, and OOO/speculative execution is the answer.