This is the mail archive of the
mailing list for the GCC project.
Re: fancy x87 ops, SSE and -mfpmath=sse,387 performance
- From: Paolo Bonzini <paolo dot bonzini at lu dot unisi dot ch>
- To: tbp <tbptbp at gmail dot com>, GCC Development <gcc at gcc dot gnu dot org>
- Date: Sun, 06 Aug 2006 13:58:44 +0200
- Subject: Re: fancy x87 ops, SSE and -mfpmath=sse,387 performance
- References: <email@example.com>
Is there a way to enable such exotic codegen for 32bit environments?
With libgcc-math you didn't have exotic instructions, but you had
trascendental operations compiled with -mfpmath=sse and with a special
ABI. -mfpmath=sse won about 8% over -mfpmath=387 for tramp3d, which
does have trascendental operations.
Let's see what happens for 4.3.