On Wed, Sep 24, 2025 at 09:58:38AM +0530, Surya Kumari Jangala wrote:
>
>
> On 31/07/25 11:55 am, Michael Meissner wrote:
> > I have rewritten this page, removing the 'ordered' terminology in the
> > coomit messages and comments that was a problem.
> >
> > I have also rewritten the patch to hopefully make it easier to
> > understand.
> >
> > I have built it on both big endian and little endian servers with no
> > regressions.
> >
> >
> > Proposed commit message follows:
> >
> > In bug PR target/118541 on power9, power10, and power11 systems, for the
> > function:
> >
> > extern double __ieee754_acos (double);
> >
> > double
> > __acospi (double x)
> > {
> > double ret = __ieee754_acos (x) / 3.14;
> > return __builtin_isgreater (ret, 1.0) ? 1.0 : ret;
> > }
> >
> > GCC currently generates the following code:
> >
> > Power9 Power10 and Power11
> > ====== ===================
> > bl __ieee754_acos bl __ieee754_acos@notoc
> > nop plfd 0,.LC0@pcrel
> > addis 9,2,.LC2@toc@ha xxspltidp 12,1065353216
> > addi 1,1,32 addi 1,1,32
> > lfd 0,.LC2@toc@l(9) ld 0,16(1)
> > addis 9,2,.LC0@toc@ha fdiv 0,1,0
> > ld 0,16(1) mtlr 0
> > lfd 12,.LC0@toc@l(9) xscmpgtdp 1,0,12
> > fdiv 0,1,0 xxsel 1,0,12,1
> > mtlr 0 blr
> > xscmpgtdp 1,0,12
> > xxsel 1,0,12,1
> > blr
> >
> > This is because ifcvt.cc optimizes the conditional floating point move to
> > use the
> > XSCMPGTDP instruction.
> >
> > However, the XSCMPGTDP instruction will generate an interrupt if one of the
> > arguments is a signalling NaN and signalling NaNs can generate an interrupt.
> > The IEEE comparison functions (isgreater, etc.) require that the comparison
> > not
> > raise an interrupt.
> >
> > The following patch changes the PowerPC back end so that ifcvt.cc will not
> > change
> > the if/then test and move into a conditional move if the comparison is one
> > of
> > the comparisons that do not raise an error with signalling NaNs and -Ofast
> > is
> > not used. If a normal comparison is used or -Ofast is used, GCC will
> > continue
> > to generate XSCMPGTDP and XXSEL.
>
> The isgreater() builtin is not supposed to set floating point exceptions,
> irrespective of which compilation flags are used. So, even if -Ofast is used
> or
> -ffinite-math-only is used, isgreater() should not set floating point
> exceptions.
> Using XSCMPGTDP will end up throwing exceptions if at least one of the
> operand is
> a qNaN or an sNaN.
The code to convert isgreater to > occurs in the machine independent
portion of the compiler if -Ofast is used. I.e. there is nothing that
can be done within the PowerPC backend because it has been eliminated
by the other code.
--
Michael Meissner, IBM
PO Box 98, Ayer, Massachusetts, USA, 01432
email: [email protected]
