================ @@ -124,10 +143,11 @@ _mm_cvtm64_si64(__m64 __m) /// written to the upper 32 bits of the result. /// \returns A 64-bit integer vector of [8 x i8] containing the converted /// values. -static __inline__ __m64 __DEFAULT_FN_ATTRS +static __inline__ __m64 __DEFAULT_FN_ATTRS_SSE2 _mm_packs_pi16(__m64 __m1, __m64 __m2) { - return (__m64)__builtin_ia32_packsswb((__v4hi)__m1, (__v4hi)__m2); + return __extract2_32(__builtin_ia32_packsswb128((__v8hi)__anyext128(__m1), ---------------- phoebewang wrote:
Should it be better to shuffle `__m1` and `__m2` first and then `__trunc64`? The same for below. https://github.com/llvm/llvm-project/pull/96540 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits