On Tue, Jan 23, 2018 at 04:46:02PM +0100, Matthias Kretz wrote:
> I just hit a compile error on AVX512 code. The fix is trivial enough that I
> didn't bother writing a PR and just fixed it. Acceptable?
>
> I hope this doesn't require the paperwork, though my employer is willing to
> do
> it anyway. :-)
CCing maintainers.
> 2018-01-23 Matthias Kretz <kr...@kde.org>
>
> * config/i386/avx512fintrin.h: Fix signatures of _mm512_abs_ps and
> _mm512_mask_abs_pd to use __m512d instead of __m512.
This should have been:
* config/i386/avx512fintrin.h (_mm512_abs_ps, _mm512_mask_abs_pd):
Change type of arguments with __m512 type to __m512d.
or so.
> diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h
> index 71e36a5..de68675 100644
> --- a/gcc/config/i386/avx512fintrin.h
> +++ b/gcc/config/i386/avx512fintrin.h
> @@ -7612,7 +7612,7 @@ _mm512_mask_abs_ps (__m512 __W, __mmask16 __U, __m512
> __A)
>
> extern __inline __m512d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_abs_pd (__m512 __A)
> +_mm512_abs_pd (__m512d __A)
> {
> return (__m512d) _mm512_and_epi64 ((__m512i) __A,
> _mm512_set1_epi64 (0x7fffffffffffffffLL));
> @@ -7620,7 +7620,7 @@ _mm512_abs_pd (__m512 __A)
>
> extern __inline __m512d
> __attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
> -_mm512_mask_abs_pd (__m512d __W, __mmask8 __U, __m512 __A)
> +_mm512_mask_abs_pd (__m512d __W, __mmask8 __U, __m512d __A)
> {
> return (__m512d)
> _mm512_mask_and_epi64 ((__m512i) __W, __U, (__m512i) __A,
>
> --
> ──────────────────────────────────────────────────────────────────────────
> Dr. Matthias Kretz https://kretzfamily.de
> GSI Helmholtzzentrum für Schwerionenforschung https://gsi.de
> SIMD easy and portable https://github.com/VcDevel/Vc
> ──────────────────────────────────────────────────────────────────────────
Jakub
