[PATCH v5 2/7] math: Remove the SVID error handling from remainder

[Wilco Dijkstra]

Hi Adhemerval,

> The optimized i386 version is faster than the generic one, and
> gcc implements it through the builtin. This optimization enables
> us to migrate the implementation to a C version.  The performance
> on a Zen3 chip is similar to the SVID one.

+      /* |x| not finite or |y| is NaN */
+      if (__glibc_unlikely ((hx >= EXPONENT_MASK
+                            || hy > EXPONENT_MASK)))
+       return __math_invalid (x * y);
 
 That should be

+      if (__glibc_unlikely (hx >= EXPONENT_MASK || hy > EXPONENT_MASK))

OK with that.

Reviewed-by: Wilco Dijkstra  <Wilco.Dijkstra@arm.com>

Cheers,
Wilco