[PATCH,rs6000] Add option to avoid generation of indexed load/store instructions

Paolo Bonzini bonzini@gnu.org
Mon Jan 26 16:57:00 GMT 2009


> Kind of, in that both deal with performance problems due to indexed load
> and store instructions.  PR28690 was about getting the operand order correct
> (address value in first reg and offset value in the second reg).
> This patch is dealing with performance problems even when we have the
> operand order correct, but due to specific values in the registers
> (the offset value causes the effective address to cross a 16M boundary)
> we still end up with a performance penalty.  Therefore, we'd like an
> option where we can completely disable generation of the indexed ops.

I see -- I was worried that we still got the incorrect order in some
cases.  The docs should mention the 16M boundary.

Paolo



More information about the Gcc-patches mailing list