[Bug middle-end/92436] SIMD integer subtract with constant always becomes add

[pinskia at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92436

Andrew Pinski  changed:

   What|Removed |Added

 Target|x86, aarch  |x86, aarch64

--- Comment #2 from Andrew Pinski  ---
Testcases:
x86:
#include 
__m128i fn(__m128i a) {
return _mm_or_si128(
_mm_sub_epi8(a, _mm_set1_epi8(99)),
_mm_set1_epi8(99)
);
}


aarch64:
#include 
uint8x16_t fn(uint8x16_t a) {
return vorrq_u8(
vsubq_u8(a, vdupq_n_u8(99)),
vdupq_n_u8(99)
);
}

Note aarch64 is a regression from GCC 5.

[Bug middle-end/92436] SIMD integer subtract with constant always becomes add

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92436

Richard Biener  changed:

   What|Removed |Added

 Status|UNCONFIRMED |NEW
   Last reconfirmed||2019-11-11
 Ever confirmed|0   |1

--- Comment #1 from Richard Biener  ---
Confirmed, I think we have dups for this (also applies to FP non-vector
constants).

[Bug middle-end/92436] SIMD integer subtract with constant always becomes add

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92436

Andrew Pinski  changed:

   What|Removed |Added

   Severity|normal  |enhancement