XPost: comp.os.ms-windows.misc, alt.windows7.general, microsoft.   
   ublic.windowsxp.general   
   From: nospam@needed.invalid   
      
   On 12/31/2023 3:39 PM, Mark Lloyd wrote:   
   >   
   > [snip]   
   >   
   >>> Did anyone ever manage to "crack" the 486SX or the 487 to enable the   
   >>>  disabled part, or make it work without the other?   
   >>   
   >> "487"?? All DuckDuckGo shows seems to concern a Californian Penal Code   
   >> clause 487!! ;-P   
   >   
   > 80487. The add-on FPU for the 80486sx, that was actually a 486dx.   
   >   
      
   These may have worked via F line.   
      
      "$Fxxx, F-Line instructions, emulating co-pro on the systems w/o FPU,   
       or propagating directly to the real co-pro on systems with FPU in the   
   socket."   
      
   The accelerator, may have been watching the bus as the main processor   
   accessed stuff. And if an instruction with an F in the appropriate place   
   showed up, the FPU knew it had a job to do. That was part of the coordination.   
   But I never worked on anything like that, and that info likely came   
   from one of my magazines at the time.   
      
   For a thing like that to work, the CPU could only have the one core.   
   Back in those days, instruction traces were a wee bit easier to arrange,   
   than they are on modern CPU sockets.   
      
      Paul   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)