Author: Craig Topper Date: 2020-01-22T16:00:23-06:00 New Revision: 16b9410caa35da976fa5f3cf6dd3d6f3776d51ca
URL: https://github.com/llvm/llvm-project/commit/16b9410caa35da976fa5f3cf6dd3d6f3776d51ca DIFF: https://github.com/llvm/llvm-project/commit/16b9410caa35da976fa5f3cf6dd3d6f3776d51ca.diff LOG: [X86] Cast to __v4hi instead of __m64 in the implementation of _mm_extract_pi16 and _mm_insert_pi16. __m64 is a vector of 1 long long. But the builtins these intrinsics are calling expect a vector of 4 shorts. Fixes PR44589 Added: Modified: clang/lib/Headers/xmmintrin.h Removed: ################################################################################ diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h index 0e61eab44aeb..9b8de63f04d5 100644 --- a/clang/lib/Headers/xmmintrin.h +++ b/clang/lib/Headers/xmmintrin.h @@ -2181,7 +2181,7 @@ void _mm_sfence(void); /// 3: Bits [63:48] are copied to the destination. /// \returns A 16-bit integer containing the extracted 16 bits of packed data. #define _mm_extract_pi16(a, n) \ - (int)__builtin_ia32_vec_ext_v4hi((__m64)a, (int)n) + (int)__builtin_ia32_vec_ext_v4hi((__v4hi)a, (int)n) /// Copies data from the 64-bit vector of [4 x i16] to the destination, /// and inserts the lower 16-bits of an integer operand at the 16-bit offset @@ -2212,7 +2212,7 @@ void _mm_sfence(void); /// \returns A 64-bit integer vector containing the copied packed data from the /// operands. #define _mm_insert_pi16(a, d, n) \ - (__m64)__builtin_ia32_vec_set_v4hi((__m64)a, (int)d, (int)n) + (__m64)__builtin_ia32_vec_set_v4hi((__v4hi)a, (int)d, (int)n) /// Compares each of the corresponding packed 16-bit integer values of /// the 64-bit integer vectors, and writes the greater value to the _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
