One thing about the RISC vs. CISC debate is the revisionist history on what was CISC. The paper says the trend towards complexity was given by comparing VAX vs. PDP-11, iAPX-432 vs. 8086, System 38 vs. System 3. The VAX and the 432 were the ones that we questioned, and we think those concerns hold up pretty well today. The 8086 may have been inelegant, but it was not particularly complex, and this paper used it as the example of a simple machine. I think the trade press concluded that any commercial computer that wasn't a RISC must be a CISC, and hence the confusion.
この話ですが、文献はコレ http://dx.doi.org/10.1145/285930.285941 で、当該の段落を引用すると、