From: dxforth@gmail.com   
      
   On 13/07/2025 7:01 pm, Anton Ertl wrote:   
   > ...   
   > For Forth, Inc. and MPE AFAIK their respective IA-32 Forth system was   
   > the only one with hardware FP for many years, so there probably was   
   > little pressure from users for bit-identical results with, say, SPARC,   
   > because they did not have a Forth system that ran on SPARC.   
      
   What do you mean by "bit-identical results"?  Since SSE2 comes without   
   transcendentals (or basics such as FABS and FNEGATE) and implementers   
   are expected to supply their own, if anything, I expect results across   
   platforms and compilers to vary.   
      
   > ...   
   > And as long as customers did not ask for bit-identical results to   
   > those on, say, a Raspi, there was little reason to reimplement FP with   
   > SSE2.  I wonder if the development of the SSE2 package for VFX was   
   > influenced by the availability of VFX for the Raspi.   
      
   According to the change log it originally began as software floating   
   point for embedded systems and circa 2020 was converted to SSE and x64.   
   Perhaps Stephen can advise as to the reasons.   
      
   >   
   > These Forth systems also don't do global register allocation or   
   > auto-vectorization, so two other reasons why, e.g., C compilers chose   
   > to use SSE2 on AMD64 (where SSE2 was guaranteed to be available) don't   
   > exist for them.   
   >   
   > - anton   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)