hunter@oakhill.UUCP (Hunter Scales) (05/02/85)
In article <563@intelca.UUCP> clif@intelca.UUCP (Clif Purkiser) writes: > > Since, I'm a product marketing engineer for the 386, I won't bother to >inject my obviously baised :) views on the iAPX vs 68K architecture. However, I > would like to state for the record that the 386 is not an announced part. >Therefore, Mr Spencer's statements about it are generally SPECULATION and not >facts. I find it unfortunate that he blasts a new CPU before he even knows >the facts about, just because it is from Intel. >(I couldn't find any record of Mr Spencer signing a non-disclosure agreement >on the 386.) > > Obviously, Henry is within in his rights to flame about the 8086 and >80286, but I think he is premature to nail Intel on the 386. > While Mr. Purisker is correct when he says that Intel has not formally announced the 80386, I would like to point out that the information that is available is not rumor. In the April 15, 1985 issue of Electronics Week, the was a copyrighted article entitled "Intel take the Wraps of 386". Apparently, Intel, in conjunction with one of its distributors, Hamilton Avnet, held a series of 33 public technical briefings to describe the 386. The "pre-announcement" is a common marketing ploy (Motorola did it for the MC68020, as well) that is meant to stave off commitment by designers to the competition. Since the information given by Intel at these seminars does not differ in any way from the (again, publically available) "Advanced information" from Intel, I would go into it in detail. Suffice it to say that the 386 has 32-bit registers (i.e. 16-bit extensions to the 8086 set) a segment descriptor "cache" and a page descriptor cache, 32-bit data and address buses. This is all available in the March, 1985 "Advanced Information" sheet from Intel. By the way, the only way this differs from the April, 1984 "Advanced Information" is that a code cache described there has apparently been deleted. As for performance, Intel would not claim a MIPs number (a wise move since MIPs are meaningless) but did say that the 386 would be 2 to 3 times faster than the 286, depending on application. Just wanted to get the record straight. Motorola Semiconductor Inc. Hunter Scales Austin, Texas {ihnp4,seismo,ctvax,gatech}!ut-sally!oakhill!hunter (I am responsible for me and my dog and no-one else)