AVX512FP16: Add *_set1_pch intrinsics.

Add *_set1_pch (_Float16 _Complex A) intrinsics.

gcc/ChangeLog:

	* config/i386/avx512fp16intrin.h:
	(_mm512_set1_pch): New intrinsic.
	* config/i386/avx512fp16vlintrin.h:
	(_mm256_set1_pch): New intrinsic.
	(_mm_set1_pch): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx512fp16-set1-pch-1a.c: New test.
	* gcc.target/i386/avx512fp16-set1-pch-1b.c: New test.
	* gcc.target/i386/avx512fp16vl-set1-pch-1a.c: New test.
	* gcc.target/i386/avx512fp16vl-set1-pch-1b.c: New test.

gcc/config/i386/avx512fp16intrin.h

@@ -7149,6 +7149,19 @@ _mm512_permutexvar_ph (__m512i __A, __m512h __B)
 						     (__mmask32)-1);
 }
 
+extern __inline __m512h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_set1_pch (_Float16 _Complex __A)
+{
+  union
+  {
+    _Float16 _Complex a;
+    float b;
+  } u = { .a = __A};
+
+  return (__m512h) _mm512_set1_ps (u.b);
+}
+
 #ifdef __DISABLE_AVX512FP16__
 #undef __DISABLE_AVX512FP16__
 #pragma GCC pop_options

gcc/config/i386/avx512fp16vlintrin.h

@@ -3311,6 +3311,32 @@ _mm_permutexvar_ph (__m128i __A, __m128h __B)
 						     (__mmask8)-1);
 }
 
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_set1_pch (_Float16 _Complex __A)
+{
+  union
+  {
+    _Float16 _Complex a;
+    float b;
+  } u = { .a = __A };
+
+  return (__m256h) _mm256_set1_ps (u.b);
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_set1_pch (_Float16 _Complex __A)
+{
+  union
+  {
+    _Float16 _Complex a;
+    float b;
+  } u = { .a = __A };
+
+  return (__m128h) _mm_set1_ps (u.b);
+}
+
 #ifdef __DISABLE_AVX512FP16VL__
 #undef __DISABLE_AVX512FP16VL__
 #pragma GCC pop_options

gcc/testsuite/gcc.target/i386/avx512fp16-set1-pch-1a.c

@@ -0,0 +1,13 @@
+/* { dg-do compile} */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include <immintrin.h>
+
+__m512h
+__attribute__ ((noinline, noclone))
+test_mm512_set1_pch (_Float16 _Complex A)
+{
+  return _mm512_set1_pch(A);
+}
+
+/* { dg-final { scan-assembler "vbroadcastss\[ \\t\]+\[^\n\r\]*%zmm\[01\]" } } */

gcc/testsuite/gcc.target/i386/avx512fp16-set1-pch-1b.c

@@ -0,0 +1,42 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#include<stdio.h>
+#include <math.h>
+#include <complex.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+
+#include <immintrin.h>
+#include "avx512-check.h"
+
+static void
+do_test (void)
+{
+ _Float16 _Complex fc = 1.0 + 1.0*I;
+  union
+  {
+    _Float16 _Complex a;
+    float b;
+  } u = { .a = fc };
+  float ff= u.b;
+
+  typedef union
+  {
+    float fp[16];
+    __m512h m512h;
+  } u1;
+
+  __m512h test512 = _mm512_set1_pch(fc);
+
+  u1 test;
+  test.m512h = test512;
+  for (int i = 0; i<16; i++)
+  {
+    if (test.fp[i] != ff) abort();
+  }
+
+}

gcc/testsuite/gcc.target/i386/avx512fp16vl-set1-pch-1a.c

@@ -0,0 +1,20 @@
+/* { dg-do compile} */
+/* { dg-options "-O2 -mavx512fp16 -mavx512vl" } */
+
+#include <immintrin.h>
+
+__m256h
+__attribute__ ((noinline, noclone))
+test_mm256_set1_pch (_Float16 _Complex A)
+{
+  return _mm256_set1_pch(A);
+}
+
+__m128h
+__attribute__ ((noinline, noclone))
+test_mm_set1_pch (_Float16 _Complex A)
+{
+  return _mm_set1_pch(A);
+}
+
+/* { dg-final { scan-assembler-times "vbroadcastss" 2 } } */

gcc/testsuite/gcc.target/i386/avx512fp16vl-set1-pch-1b.c

@@ -0,0 +1,57 @@
+/* { dg-do run { target avx512fp16 } } */
+/* { dg-options "-O2 -mavx512fp16 -mavx512vl" } */
+
+#include<stdio.h>
+#include <math.h>
+#include <complex.h>
+
+static void do_test (void);
+
+#define DO_TEST do_test
+#define AVX512FP16
+
+#include <immintrin.h>
+#include "avx512-check.h"
+
+static void
+do_test (void)
+{
+  _Float16 _Complex fc = 1.0 + 1.0*I;
+  union
+  { 
+    _Float16 _Complex a;
+    float b;
+  } u = { .a = fc };
+  float ff= u.b;
+
+  typedef union
+  {
+    float fp[8];
+    __m256h m256h;
+  } u1;
+
+  __m256h test256 = _mm256_set1_pch(fc);
+
+  u1 test1;
+  test1.m256h = test256;
+  for (int i = 0; i<8; i++)
+  {
+    if (test1.fp[i] != ff) abort();
+  }
+
+  typedef union
+  {
+    float fp[4];
+    __m128h m128h;
+  } u2;
+
+  __m128h test128 = _mm_set1_pch(fc);
+
+  u2 test2;
+  test2.m128h = test128;
+  for (int i = 0; i<4; i++)
+  {
+    if (test2.fp[i] != ff) abort();
+  }
+
+}