Hi Paul, LGTM. Recommend maintainers approve.
Thanks for the cleanups, Bill On 7/15/21 6:29 PM, Paul A. Clarke wrote:
Add a naive implementation of the subject x86 intrinsic to ease porting. 2021-07-15 Paul A. Clarke <p...@us.ibm.com> gcc * config/rs6000/smmintrin.h (_mm_minpos_epu16): New. --- v3: Minor formatting changes per review from Bill. v2: Minor formatting changes per review from Segher. gcc/config/rs6000/smmintrin.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h index 16fd34d836ff..6a010fdbb96f 100644 --- a/gcc/config/rs6000/smmintrin.h +++ b/gcc/config/rs6000/smmintrin.h @@ -172,4 +172,31 @@ _mm_test_mix_ones_zeros (__m128i __A, __m128i __mask) return any_ones * any_zeros; }+/* Return horizontal packed word minimum and its index in bits [15:0]+ and bits [18:16] respectively. */ +__inline __m128i +__attribute__ ((__gnu_inline__, __always_inline__, __artificial__)) +_mm_minpos_epu16 (__m128i __A) +{ + union __u + { + __m128i __m; + __v8hu __uh; + }; + union __u __u = { .__m = __A }, __r = { .__m = {0} }; + unsigned short __ridx = 0; + unsigned short __rmin = __u.__uh[__ridx]; + for (unsigned long __i = 1; __i < 8; __i++) + { + if (__u.__uh[__i] < __rmin) + { + __rmin = __u.__uh[__i]; + __ridx = __i; + } + } + __r.__uh[0] = __rmin; + __r.__uh[1] = __ridx; + return __r.__m; +} + #endif
