cvs commit: src/lib/msun Makefile src/lib/msun/i387 e_atan2f.S e_log10f.S e_logf.S e_remainderf.S e_scalbf.S e_sqrtf.S s_ceilf.S s_copysignf.S s_cosf.S s_floorf.S s_logbf.S s_rintf.S s_scalbnf.S s_significandf.S s_sinf.S s_tanf.S

[David Schultz]

das         2005-01-13 18:58:26 UTC

  FreeBSD src repository

  Modified files:
    lib/msun             Makefile 
  Added files:
    lib/msun/i387        e_atan2f.S e_log10f.S e_logf.S 
                         e_remainderf.S e_scalbf.S e_sqrtf.S 
                         s_ceilf.S s_copysignf.S s_cosf.S 
                         s_floorf.S s_logbf.S s_rintf.S 
                         s_scalbnf.S s_significandf.S s_sinf.S 
                         s_tanf.S 
  Log:
  Import the subset of J.T. Conklin's single-precision x86-optimized
  math routines that appear to be (a) correct and (b) faster than their
  MI counterparts on my Pentium 4.
  
  Obtained from:  NetBSD
  
  Revision  Changes    Path
  1.57      +4 -2      src/lib/msun/Makefile
  1.1       +15 -0     src/lib/msun/i387/e_atan2f.S (new)
  1.1       +15 -0     src/lib/msun/i387/e_log10f.S (new)
  1.1       +15 -0     src/lib/msun/i387/e_logf.S (new)
  1.1       +19 -0     src/lib/msun/i387/e_remainderf.S (new)
  1.1       +15 -0     src/lib/msun/i387/e_scalbf.S (new)
  1.1       +14 -0     src/lib/msun/i387/e_sqrtf.S (new)
  1.1       +29 -0     src/lib/msun/i387/s_ceilf.S (new)
  1.1       +19 -0     src/lib/msun/i387/s_copysignf.S (new)
  1.1       +15 -0     src/lib/msun/i387/s_cosf.S (new)
  1.1       +29 -0     src/lib/msun/i387/s_floorf.S (new)
  1.1       +15 -0     src/lib/msun/i387/s_logbf.S (new)
  1.1       +14 -0     src/lib/msun/i387/s_rintf.S (new)
  1.1       +16 -0     src/lib/msun/i387/s_scalbnf.S (new)
  1.1       +15 -0     src/lib/msun/i387/s_significandf.S (new)
  1.1       +15 -0     src/lib/msun/i387/s_sinf.S (new)
  1.1       +16 -0     src/lib/msun/i387/s_tanf.S (new)