[X86] Support *_set1_pch(Float16 _Complex h)

[LuoYuanke]

LGTM, thanks.

clang/lib/Headers/avx512fp16intrin.h

 /*===----------- avx512fp16intrin.h - AVX512-FP16 intrinsics ---------------===
  *
  * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
  * See https://llvm.org/LICENSE.txt for license information.
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  *
  *===-----------------------------------------------------------------------===
  */
 #ifndef __IMMINTRIN_H
 #error "Never use <avx512fp16intrin.h> directly; include <immintrin.h> instead."
 #endif
 
 #ifndef __AVX512FP16INTRIN_H
 #define __AVX512FP16INTRIN_H
 
 /* Define the default attributes for the functions in this file. */
 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                                                  \
   __attribute__((__always_inline__, __nodebug__, __target__("avx512fp16"),     \
                  __min_vector_width__(512)))
 #define __DEFAULT_FN_ATTRS256                                                  \
   __attribute__((__always_inline__, __nodebug__, __target__("avx512fp16"),     \
                  __min_vector_width__(256)))
 #define __DEFAULT_FN_ATTRS128                                                  \
   __attribute__((__always_inline__, __nodebug__, __target__("avx512fp16"),     \
                  __min_vector_width__(128)))
 
 static __inline__ _Float16 __DEFAULT_FN_ATTRS512 _mm512_cvtsh_h(__m512h __a) {
   return __a[0];
 }
 
 static __inline __m128h __DEFAULT_FN_ATTRS128 _mm_setzero_ph(void) {
   return (__m128h){0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0};
 }
 
 static __inline __m256h __DEFAULT_FN_ATTRS256 _mm256_setzero_ph(void) {

 static __inline__ __m128h __DEFAULT_FN_ATTRS128 _mm_undefined_ph(void) {
   return (__m128h)__builtin_ia32_undef128();
 }
 
 static __inline__ __m512h __DEFAULT_FN_ATTRS512 _mm512_undefined_ph(void) {
   return (__m512h)__builtin_ia32_undef512();
 }
 
 static __inline __m512h __DEFAULT_FN_ATTRS512 _mm512_set1_ph(_Float16 __h) {
   return (__m512h)(__v32hf){__h, __h, __h, __h, __h, __h, __h, __h,
                             __h, __h, __h, __h, __h, __h, __h, __h,
                             __h, __h, __h, __h, __h, __h, __h, __h,
                             __h, __h, __h, __h, __h, __h, __h, __h};
 }
 
 static __inline __m512h __DEFAULT_FN_ATTRS512
 _mm512_set_ph(_Float16 __h1, _Float16 __h2, _Float16 __h3, _Float16 __h4,
               _Float16 __h5, _Float16 __h6, _Float16 __h7, _Float16 __h8,
               _Float16 __h9, _Float16 __h10, _Float16 __h11, _Float16 __h12,
               _Float16 __h13, _Float16 __h14, _Float16 __h15, _Float16 __h16,
               _Float16 __h17, _Float16 __h18, _Float16 __h19, _Float16 __h20,
               _Float16 __h21, _Float16 __h22, _Float16 __h23, _Float16 __h24,
               _Float16 __h25, _Float16 __h26, _Float16 __h27, _Float16 __h28,
               _Float16 __h29, _Float16 __h30, _Float16 __h31, _Float16 __h32) {
   return (__m512h)(__v32hf){__h32, __h31, __h30, __h29, __h28, __h27, __h26,
                             __h25, __h24, __h23, __h22, __h21, __h20, __h19,
                             __h18, __h17, __h16, __h15, __h14, __h13, __h12,
                             __h11, __h10, __h9,  __h8,  __h7,  __h6,  __h5,
                             __h4,  __h3,  __h2,  __h1};
 }
 
 #define _mm512_setr_ph(h1, h2, h3, h4, h5, h6, h7, h8, h9, h10, h11, h12, h13, \
                        h14, h15, h16, h17, h18, h19, h20, h21, h22, h23, h24,  \
                        h25, h26, h27, h28, h29, h30, h31, h32)                 \
   _mm512_set_ph((h32), (h31), (h30), (h29), (h28), (h27), (h26), (h25), (h24), \
                 (h23), (h22), (h21), (h20), (h19), (h18), (h17), (h16), (h15), \
                 (h14), (h13), (h12), (h11), (h10), (h9), (h8), (h7), (h6),     \
                 (h5), (h4), (h3), (h2), (h1))
 
+static __inline __m512h __DEFAULT_FN_ATTRS512
+_mm512_set1_pch(_Float16 _Complex h) {
+  return (__m512h)_mm512_set1_ps(__builtin_bit_cast(float, h));
+}
+
 static __inline__ __m128 __DEFAULT_FN_ATTRS128 _mm_castph_ps(__m128h __a) {
   return (__m128)__a;
 }
 
 static __inline__ __m256 __DEFAULT_FN_ATTRS256 _mm256_castph_ps(__m256h __a) {
   return (__m256)__a;
 }
 

clang/lib/Headers/avx512vlfp16intrin.h

 /*===---------- avx512vlfp16intrin.h - AVX512-FP16 intrinsics --------------===
  *
  * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
  * See https://llvm.org/LICENSE.txt for license information.
  * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
  *
  *===-----------------------------------------------------------------------===
  */
 #ifndef __IMMINTRIN_H
 #error                                                                         \
     "Never use <avx512vlfp16intrin.h> directly; include <immintrin.h> instead."
 #endif
 
 #ifndef __AVX512VLFP16INTRIN_H
 #define __AVX512VLFP16INTRIN_H
 
 /* Define the default attributes for the functions in this file. */
 #define __DEFAULT_FN_ATTRS256                                                  \
   __attribute__((__always_inline__, __nodebug__,                               \
                  __target__("avx512fp16, avx512vl"),                           \
                  __min_vector_width__(256)))
 #define __DEFAULT_FN_ATTRS128                                                  \
   __attribute__((__always_inline__, __nodebug__,                               \
                  __target__("avx512fp16, avx512vl"),                           \
                  __min_vector_width__(128)))
 
 static __inline__ _Float16 __DEFAULT_FN_ATTRS128 _mm_cvtsh_h(__m128h __a) {
   return __a[0];
 }
 
 static __inline__ _Float16 __DEFAULT_FN_ATTRS256 _mm256_cvtsh_h(__m256h __a) {
   return __a[0];
 }
 
 static __inline__ __m128h __DEFAULT_FN_ATTRS128 _mm_set_sh(_Float16 __h) {
   return __extension__(__m128h){__h, 0, 0, 0, 0, 0, 0, 0};
 }
 
 static __inline __m128h __DEFAULT_FN_ATTRS128 _mm_set1_ph(_Float16 __h) {
   return (__m128h)(__v8hf){__h, __h, __h, __h, __h, __h, __h, __h};
 }
 
 static __inline __m256h __DEFAULT_FN_ATTRS256 _mm256_set1_ph(_Float16 __h) {
   return (__m256h)(__v16hf){__h, __h, __h, __h, __h, __h, __h, __h,
                             __h, __h, __h, __h, __h, __h, __h, __h};
 }
 
 static __inline __m128h __DEFAULT_FN_ATTRS128
 _mm_set_ph(_Float16 __h1, _Float16 __h2, _Float16 __h3, _Float16 __h4,
            _Float16 __h5, _Float16 __h6, _Float16 __h7, _Float16 __h8) {
   return (__m128h)(__v8hf){__h8, __h7, __h6, __h5, __h4, __h3, __h2, __h1};
 }
 
+static __inline__ __m256h __DEFAULT_FN_ATTRS256
+_mm256_set1_pch(_Float16 _Complex h) {
+  return (__m256h)_mm256_set1_ps(__builtin_bit_cast(float, h));
+}
+
+static __inline__ __m128h __DEFAULT_FN_ATTRS128
+_mm_set1_pch(_Float16 _Complex h) {
+  return (__m128h)_mm_set1_ps(__builtin_bit_cast(float, h));
+}
+
 static __inline __m256h __DEFAULT_FN_ATTRS256
 _mm256_set_ph(_Float16 __h1, _Float16 __h2, _Float16 __h3, _Float16 __h4,
               _Float16 __h5, _Float16 __h6, _Float16 __h7, _Float16 __h8,
               _Float16 __h9, _Float16 __h10, _Float16 __h11, _Float16 __h12,
               _Float16 __h13, _Float16 __h14, _Float16 __h15, _Float16 __h16) {
   return (__m256h)(__v16hf){__h16, __h15, __h14, __h13, __h12, __h11,
                             __h10, __h9,  __h8,  __h7,  __h6,  __h5,
                             __h4,  __h3,  __h2,  __h1};

clang/test/CodeGen/X86/avx512fp16-builtins.c

__m512h test_mm512_set1_ph(_Float16 h) {
   // CHECK: insertelement <32 x half> {{.*}}, i32 27
   // CHECK: insertelement <32 x half> {{.*}}, i32 28
   // CHECK: insertelement <32 x half> {{.*}}, i32 29
   // CHECK: insertelement <32 x half> {{.*}}, i32 30
   // CHECK: insertelement <32 x half> {{.*}}, i32 31
   return _mm512_set1_ph(h);
 }
 
+__m512h test_mm512_set1_pch(_Float16 _Complex h) {
+  // CHECK-LABEL: @test_mm512_set1_pch
+  // CHECK: bitcast { half, half }{{.*}} to float
+  // CHECK: insertelement <16 x float> {{.*}}, i32 0
+  // CHECK: insertelement <16 x float> {{.*}}, i32 1
+  // CHECK: insertelement <16 x float> {{.*}}, i32 2
+  // CHECK: insertelement <16 x float> {{.*}}, i32 3
+  // CHECK: insertelement <16 x float> {{.*}}, i32 4
+  // CHECK: insertelement <16 x float> {{.*}}, i32 5
+  // CHECK: insertelement <16 x float> {{.*}}, i32 6
+  // CHECK: insertelement <16 x float> {{.*}}, i32 7
+  // CHECK: insertelement <16 x float> {{.*}}, i32 8
+  // CHECK: insertelement <16 x float> {{.*}}, i32 9
+  // CHECK: insertelement <16 x float> {{.*}}, i32 10
+  // CHECK: insertelement <16 x float> {{.*}}, i32 11
+  // CHECK: insertelement <16 x float> {{.*}}, i32 12
+  // CHECK: insertelement <16 x float> {{.*}}, i32 13
+  // CHECK: insertelement <16 x float> {{.*}}, i32 14
+  // CHECK: insertelement <16 x float> {{.*}}, i32 15
+  // CHECK: bitcast <16 x float>{{.*}} to <32 x half>
+  return _mm512_set1_pch(h);
+}
+
 __m512h test_mm512_set_ph(_Float16 __h1, _Float16 __h2, _Float16 __h3, _Float16 __h4,
                           _Float16 __h5, _Float16 __h6, _Float16 __h7, _Float16 __h8,
                           _Float16 __h9, _Float16 __h10, _Float16 __h11, _Float16 __h12,
                           _Float16 __h13, _Float16 __h14, _Float16 __h15, _Float16 __h16,
                           _Float16 __h17, _Float16 __h18, _Float16 __h19, _Float16 __h20,
                           _Float16 __h21, _Float16 __h22, _Float16 __h23, _Float16 __h24,
                           _Float16 __h25, _Float16 __h26, _Float16 __h27, _Float16 __h28,
                           _Float16 __h29, _Float16 __h30, _Float16 __h31, _Float16 __h32) {

clang/test/CodeGen/X86/avx512vlfp16-builtins.c

__m256h test_mm256_set1_ph(_Float16 h) {
   // CHECK: insertelement <16 x half> {{.*}}, i32 11
   // CHECK: insertelement <16 x half> {{.*}}, i32 12
   // CHECK: insertelement <16 x half> {{.*}}, i32 13
   // CHECK: insertelement <16 x half> {{.*}}, i32 14
   // CHECK: insertelement <16 x half> {{.*}}, i32 15
   return _mm256_set1_ph(h);
 }
 
+__m128h test_mm_set1_pch(_Float16 _Complex h) {
+  // CHECK-LABEL: @test_mm_set1_pch
+  // CHECK: bitcast { half, half }{{.*}} to float
+  // CHECK: insertelement <4 x float> {{.*}}, i32 0
+  // CHECK: insertelement <4 x float> {{.*}}, i32 1
+  // CHECK: insertelement <4 x float> {{.*}}, i32 2
+  // CHECK: insertelement <4 x float> {{.*}}, i32 3
+  // CHECK: bitcast <4 x float>{{.*}} to <8 x half>
+  return _mm_set1_pch(h);
+}
+
+__m256h test_mm256_set1_pch(_Float16 _Complex h) {
+  // CHECK-LABEL: @test_mm256_set1_pch
+  // CHECK: bitcast { half, half }{{.*}} to float
+  // CHECK: insertelement <8 x float> {{.*}}, i32 0
+  // CHECK: insertelement <8 x float> {{.*}}, i32 1
+  // CHECK: insertelement <8 x float> {{.*}}, i32 2
+  // CHECK: insertelement <8 x float> {{.*}}, i32 3
+  // CHECK: insertelement <8 x float> {{.*}}, i32 4
+  // CHECK: insertelement <8 x float> {{.*}}, i32 5
+  // CHECK: insertelement <8 x float> {{.*}}, i32 6
+  // CHECK: insertelement <8 x float> {{.*}}, i32 7
+  // CHECK: bitcast <8 x float>{{.*}} to <16 x half>
+  return _mm256_set1_pch(h);
+}
+
 __m128h test_mm_set_ph(_Float16 __h1, _Float16 __h2, _Float16 __h3, _Float16 __h4,
                        _Float16 __h5, _Float16 __h6, _Float16 __h7, _Float16 __h8) {
   // CHECK-LABEL: @test_mm_set_ph
   // CHECK: insertelement <8 x half> {{.*}}, i32 0
   // CHECK: insertelement <8 x half> {{.*}}, i32 1
   // CHECK: insertelement <8 x half> {{.*}}, i32 2
   // CHECK: insertelement <8 x half> {{.*}}, i32 3
   // CHECK: insertelement <8 x half> {{.*}}, i32 4