Best optimizations with gcc-3.2 (from freehackers and GOT)

• Pentium IV (Intel)
  CFLAGS="-O3 -mcpu=pentium4 -march=pentium4 -mfpmath=sse,387 -msse2 -mmmx -fforce-addr -fomit-frame-pointer -funroll-loops -frerun-cse-after-loop -frerun-loop-opt -falign-functions=4 -pipe"
  CXXFLAGS="${CFLAGS}"
  
• Pentium III (Intel)
  CFLAGS="-march=pentium3 -O3 -pipe -fomit-frame-pointer -fforce-addr -falign-functions=4 -fprefetch-loop-arrays"
  CXXFLAGS="${CFLAGS}"
  
• Athlon (AMD)
  CFLAGS="-march=athlon -O3 -pipe -fomit-frame-pointer -ffast-math -funroll-loops -fforce-addr -falign-functions=4"
  CXXFLAGS="${CFLAGS}"
  
• Athlon-tbird, aka K7 (AMD)
  CFLAGS="-march=athlon-tbird -O3 -pipe -fforce-addr -fomit-frame-pointer -funroll-loops -falign-functions=4 -maccumulate-outgoing-args"
  CXXFLAGS="${CFLAGS}"
  
• Athlon XP 2000+
  CFLAGS="-march=athlon-xp -m3dnow -msse -mfpmath=sse -mmmx -O3 -pipe -fforce-addr -fomit-frame-pointer -funroll-loops -frerun-cse-after-loop -frerun-loop-opt -falign-functions=4 -maccumulate-outgoing-args -ffast-math -fprefetch-loop-arrays"
  CXXFLAGS="${CFLAGS}"