Hullo Brian McCloud, hope you are having a nice day!!
25-Jan-98 11:10:00, Brian McCloud wrote to Fernando Ariel Gont
          Subject: micro-ops             1/2
 BM> FAG>I was reading an Intel tutorial about optimization, and they
 BM> really used a FAG>lot the number of micro-ops ecah instruction
 BM> produces...
 BM> I can do this, simplifying from my tasm qref: I will not include
 BM> the 186 and up instructions, or protected-mode timings.
============================================
 BM> Instruction     Clocks Mnemonic        486     386     286
 BM> 8086 --------------------------------------------AAA
[....]
I really thank you for your help... but the fact is that I'm looking for
the _*micro-ops*_ table...
That means, at least in Pentium II and Pentium Pro, Each instruction is
decoded to "simpler" instructions called micro-ops....
The speed with which a program executes depends on the orden in which you
put the instructions of the program (besides a lot of things), because
there are threee decode units, but one of them can handle some instructions
that the others can, so that you must put the instructions in a certain
order so that you keep all decode-units busy all the time...
It's a very simple and not-so-good explanation about Pentium II and Pentium
Pro microarchitecture, but it does to explain you what I am needing, I
think...
That means that I need to know how many micro-ops each instruction
produces, so that I know the order in which I should put the instructions,
so the condition I explained above would be valid....
Anyway, thank you very much! (Do you know where I can get the table I
need?)
Bye! :)
 -=> Yours sincerely, Fernando Ariel Gont <=-
e-mail: FGont@siscor.bibnal.edu.ar
e-mail "Good Stuff!" _*Magazine*_ : gstuff@siscor.bibnal.edu.ar
FidoNet: 4:900/470.10
Sk-Network (Argentina): Murdock's Point (200:201/200.1)
--- Terminate 5.00 UnReg(112)
---------------