Hello Gabriel,
>> Thanks for the tip. With -march=pentiumpro, the speed gap is
>> closed to about 1%. BTW, I don't notice any difference in speed
>> with the /G6 (PPro optimization) flag to MSVC compared to the
>> default "blended" optimization.
GB> According to VC++ documentation, PPro is the default mode in
GB> VC++6, while it was Pentium in VC++5.
MSDN -> Visual Studio 6.0 Docs -> Visual C++ Docs:
/GB Blend Optimizes the code created to favor the Pentium. It
blends the optimizations for the 80386 (/G3), 80486
(/G4), Pentium (/G5), and Pentium Pro (/G6)
options. This option forces a value of 500 for the
_M_IX86 preprocessor macro. This value is the
default. Future versions of the compiler will issue
a different value to reflect the dominant
processor.
Best regards,
Serge mailto:[EMAIL PROTECTED]
--
MP3 ENCODER mailing list ( http://geek.rcc.se/mp3encoder/ )
- [MP3 ENCODER] LAME 3.29 under MSVC Mathew Hendry
- Re: [MP3 ENCODER] LAME 3.29 under MSVC Jake Hamby
- Re: [MP3 ENCODER] LAME 3.29 under MSVC Mark Taylor
- Re: [MP3 ENCODER] LAME 3.29 under MSVC Jake Hamby
- Re: [MP3 ENCODER] LAME 3.29 under MSVC dan the person
- Re: [MP3 ENCODER] LAME 3.29 under MSV... Jake Hamby
- Re: [MP3 ENCODER] LAME 3.29 unde... Gabriel Bouvigne
- [MP3 ENCODER] lame 3.30 Serge Pimenov
- [MP3 ENCODER] lame 3.30 Mark Taylor
- RE: [MP3 ENCODER] lame 3.30 mikecheng
- [MP3 ENCODER] Future Directions mikecheng
- Re: [MP3 ENCODER] Future Directions Scott Manley
- Re: [MP3 ENCODER] Future Directions Bill Eldridge
- Re: [MP3 ENCODER] Future Directi... Scott Manley
- Re: [MP3 ENCODER] Future Dir... Bill Eldridge
- Re: [MP3 ENCODER] Future... Warren Toomey
- Re: [MP3 ENCODER] Future Directions Sergey A. Maslyakov
- Re: [MP3 ENCODER] Future Directions Erik de Castro Lopo
