Correct, but in many real cases you can do much better than using Horner's especially when you want to exploit SIMD. Infact dumb sum of powers of monomials can run faster than Horner's. Typically your compiler will vectorize them to use SIMD pretty effortlessly. It took me by surprise when I saw it. If you have millions you could probably do as you said and still gain a lot of speedup but for few hundreds it might be a different story.
EDIT @jacobolus does it cover Estrin's ? Its certainly older than the 90s. The main problem is Horners does not have any parallelism. With Estrin's one can oarallelize along two axes: Use threads for one and simd for another. Although I believe one can play with the parse tree to get better speed than Estrins on your specific hardware.