[X86] Move 128/256-bit FP16/BF16 typedef to emmintrin.h or avxintrin.h, NFCI

Author: phoebewang

clang/lib/Headers/avx512bf16intrin.h

@@ -17,8 +17,6 @@
 
 typedef __bf16 __v32bf __attribute__((__vector_size__(64), __aligned__(64)));
 typedef __bf16 __m512bh __attribute__((__vector_size__(64), __aligned__(64)));
-typedef __bf16 __v16bf __attribute__((__vector_size__(32), __aligned__(32)));
-typedef __bf16 __m256bh __attribute__((__vector_size__(32), __aligned__(32)));
 typedef __bf16 __bfloat16 __attribute__((deprecated("use __bf16 instead")));
 
 #define __DEFAULT_FN_ATTRS512 \

clang/lib/Headers/avx512fp16intrin.h

@@ -19,12 +19,6 @@
 typedef _Float16 __v32hf __attribute__((__vector_size__(64), __aligned__(64)));
 typedef _Float16 __m512h __attribute__((__vector_size__(64), __aligned__(64)));
 typedef _Float16 __m512h_u __attribute__((__vector_size__(64), __aligned__(1)));
-typedef _Float16 __v8hf __attribute__((__vector_size__(16), __aligned__(16)));
-typedef _Float16 __m128h __attribute__((__vector_size__(16), __aligned__(16)));
-typedef _Float16 __m128h_u __attribute__((__vector_size__(16), __aligned__(1)));
-typedef _Float16 __v16hf __attribute__((__vector_size__(32), __aligned__(32)));
-typedef _Float16 __m256h __attribute__((__vector_size__(32), __aligned__(32)));
-typedef _Float16 __m256h_u __attribute__((__vector_size__(32), __aligned__(1)));
 
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS512                                                  \

clang/lib/Headers/avx512vlbf16intrin.h

@@ -15,9 +15,6 @@
 #ifndef __AVX512VLBF16INTRIN_H
 #define __AVX512VLBF16INTRIN_H
 
-typedef __bf16 __v8bf __attribute__((__vector_size__(16), __aligned__(16)));
-typedef __bf16 __m128bh __attribute__((__vector_size__(16), __aligned__(16)));
-
 #define __DEFAULT_FN_ATTRS128 \
   __attribute__((__always_inline__, __nodebug__, \
                  __target__("avx512vl, avx512bf16"), __min_vector_width__(128)))

clang/lib/Headers/avxintrin.h

@@ -39,6 +39,16 @@ typedef float __m256_u __attribute__ ((__vector_size__ (32), __aligned__(1)));
 typedef double __m256d_u __attribute__((__vector_size__(32), __aligned__(1)));
 typedef long long __m256i_u __attribute__((__vector_size__(32), __aligned__(1)));
 
+#ifdef __SSE2__
+/* Both _Float16 and __bf16 require SSE2 being enabled. */
+typedef _Float16 __v16hf __attribute__((__vector_size__(32), __aligned__(32)));
+typedef _Float16 __m256h __attribute__((__vector_size__(32), __aligned__(32)));
+typedef _Float16 __m256h_u __attribute__((__vector_size__(32), __aligned__(1)));
+
+typedef __bf16 __v16bf __attribute__((__vector_size__(32), __aligned__(32)));
+typedef __bf16 __m256bh __attribute__((__vector_size__(32), __aligned__(32)));
+#endif
+
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS __attribute__((__always_inline__, __nodebug__, __target__("avx"), __min_vector_width__(256)))
 #define __DEFAULT_FN_ATTRS128 __attribute__((__always_inline__, __nodebug__, __target__("avx"), __min_vector_width__(128)))

clang/lib/Headers/emmintrin.h

@@ -38,6 +38,16 @@ typedef unsigned char __v16qu __attribute__((__vector_size__(16)));
  * appear in the interface though. */
 typedef signed char __v16qs __attribute__((__vector_size__(16)));
 
+#ifdef __SSE2__
+/* Both _Float16 and __bf16 require SSE2 being enabled. */
+typedef _Float16 __v8hf __attribute__((__vector_size__(16), __aligned__(16)));
+typedef _Float16 __m128h __attribute__((__vector_size__(16), __aligned__(16)));
+typedef _Float16 __m128h_u __attribute__((__vector_size__(16), __aligned__(1)));
+
+typedef __bf16 __v8bf __attribute__((__vector_size__(16), __aligned__(16)));
+typedef __bf16 __m128bh __attribute__((__vector_size__(16), __aligned__(16)));
+#endif
+
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS                                                     \
   __attribute__((__always_inline__, __nodebug__, __target__("sse2"),           \