i386: Add bf8 -> fp16 intrin

Since BF8 and FP16 have same bits for exponent, the type conversion
between them is just a cast for fraction part. We will use a sequence
of instrctions instead of new instructions to do that. For convenience,
intrins are also provided.

gcc/ChangeLog:

	* config/i386/avx10_2-512convertintrin.h
	(_mm512_cvtpbf8_ph): New.
	(_mm512_mask_cvtpbf8_ph): Ditto.
	(_mm512_maskz_cvtpbf8_ph): Ditto.
	* config/i386/avx10_2convertintrin.h
	(_mm_cvtpbf8_ph): Ditto.
	(_mm_mask_cvtpbf8_ph): Ditto.
	(_mm_maskz_cvtpbf8_ph): Ditto.
	(_mm256_cvtpbf8_ph): Ditto.
	(_mm256_mask_cvtpbf8_ph): Ditto.
	(_mm256_maskz_cvtpbf8_ph): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx10_2-512-convert-1.c: Add tests for new
	intrin.
	* gcc.target/i386/avx10_2-convert-1.c: Ditto.

4 files changed, 109 insertions, 5 deletions

diff --git a/gcc/config/i386/avx10_2-512convertintrin.h b/gcc/config/i386/avx10_2-512convertintrin.h
index 4ad339b..dfbdfc3 100644
--- a/gcc/config/i386/avx10_2-512convertintrin.h
+++ b/gcc/config/i386/avx10_2-512convertintrin.h
@@ -540,6 +540,30 @@ _mm512_maskz_cvtnesph_phf8 (__mmask32 __U, __m512h __A)
 							 (__mmask32) __U);
 }
 
+extern __inline __m512h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_cvtpbf8_ph (__m256i __A)
+{
+  return (__m512h) _mm512_castsi512_ph ((__m512i) _mm512_slli_epi16 (
+	 (__m512i) _mm512_cvtepi8_epi16 (__A), 8));
+}
+
+extern __inline __m512h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_mask_cvtpbf8_ph (__m512h __S, __mmask16 __U, __m256i __A)
+{
+  return (__m512h) _mm512_castsi512_ph ((__m512i) _mm512_mask_slli_epi16 (
+	 (__m512i) __S, __U, (__m512i) _mm512_cvtepi8_epi16 (__A), 8));
+}
+
+extern __inline __m512h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm512_maskz_cvtpbf8_ph (__mmask16 __U, __m256i __A)
+{
+  return (__m512h) _mm512_castsi512_ph ((__m512i) _mm512_slli_epi16 (
+	 (__m512i) _mm512_maskz_cvtepi8_epi16 (__U, __A), 8));
+}
+
 #ifdef __DISABLE_AVX10_2_512__
 #undef __DISABLE_AVX10_2_512__
 #pragma GCC pop_options
diff --git a/gcc/config/i386/avx10_2convertintrin.h b/gcc/config/i386/avx10_2convertintrin.h
index ac62d12..8d2c1a5 100644
--- a/gcc/config/i386/avx10_2convertintrin.h
+++ b/gcc/config/i386/avx10_2convertintrin.h
@@ -970,6 +970,54 @@ _mm256_maskz_cvtnesph_phf8 (__mmask16 __U, __m256h __A)
 							 (__mmask16) __U);
 }
 
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cvtpbf8_ph (__m128i __A)
+{
+  return (__m128h) _mm_castsi128_ph ((__m128i) _mm_slli_epi16 (
+	 (__m128i) _mm_cvtepi8_epi16 (__A), 8));
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_cvtpbf8_ph (__m128h __S, __mmask8 __U, __m128i __A)
+{
+  return (__m128h) _mm_castsi128_ph ((__m128i) _mm_mask_slli_epi16 (
+	 (__m128i) __S, __U, (__m128i) _mm_cvtepi8_epi16 (__A), 8));
+}
+
+extern __inline __m128h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_maskz_cvtpbf8_ph (__mmask8 __U, __m128i __A)
+{
+  return (__m128h) _mm_castsi128_ph ((__m128i) _mm_slli_epi16 (
+	 (__m128i) _mm_maskz_cvtepi8_epi16 (__U, __A), 8));
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_cvtpbf8_ph (__m128i __A)
+{
+  return (__m256h) _mm256_castsi256_ph ((__m256i) _mm256_slli_epi16 (
+	 (__m256i) _mm256_cvtepi8_epi16 (__A), 8));
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_mask_cvtpbf8_ph (__m256h __S, __mmask8 __U, __m128i __A)
+{
+  return (__m256h) _mm256_castsi256_ph ((__m256i) _mm256_mask_slli_epi16 (
+	 (__m256i) __S, __U, (__m256i) _mm256_cvtepi8_epi16 (__A), 8));
+}
+
+extern __inline __m256h
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm256_maskz_cvtpbf8_ph (__mmask8 __U, __m128i __A)
+{
+  return (__m256h) _mm256_castsi256_ph ((__m256i) _mm256_slli_epi16 (
+	 (__m256i) _mm256_maskz_cvtepi8_epi16 (__U, __A), 8));
+}
+
 #ifdef __DISABLE_AVX10_2_256__
 #undef __DISABLE_AVX10_2_256__
 #pragma GCC pop_options
diff --git a/gcc/testsuite/gcc.target/i386/avx10_2-512-convert-1.c b/gcc/testsuite/gcc.target/i386/avx10_2-512-convert-1.c
index bbbff18..f67138c 100644
--- a/gcc/testsuite/gcc.target/i386/avx10_2-512-convert-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx10_2-512-convert-1.c
@@ -45,13 +45,17 @@
 /* { dg-final { scan-assembler-times "vcvtneph2hf8s\[ \\t\]*%zmm\[0-9\]+,\[^\{\n\]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
 /* { dg-final { scan-assembler-times "vcvtneph2hf8s\[ \\t\]*%zmm\[0-9\]+,\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
 /* { dg-final { scan-assembler-times "vcvtneph2hf8s\[ \\t\]*%zmm\[0-9\]+,\[^\{\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpsllw\[ \t]\+\\\$8, %zmm\[0-9]\+, %zmm\[0-9]\+(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpsllw\[ \t]\+\\\$8, %zmm\[0-9]\+, %zmm\[0-9]\+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpmovsxbw\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\]*%zmm\[0-9\](?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpmovsxbw\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\]*%zmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
 
 #include <immintrin.h>
 
-volatile __m256i x256i;
+volatile __m256i x256i, z1;
 volatile __m512i x512i;
 volatile __m512 x, a1, b1;
-volatile __m512h y, x512h;
+volatile __m512h y, x512h, z;
 volatile __mmask16 m16;
 volatile __mmask32 m32;
 volatile __mmask64 m64;
@@ -174,3 +178,11 @@ avx10_2_512_vcvtneph2hf8s_test (void)
   x256i = _mm512_mask_cvtnesph_phf8 (x256i, m32, x512h);
   x256i = _mm512_maskz_cvtnesph_phf8 (m32, x512h);
 }
+
+void extern
+avx10_2_512_cvtbf8_fp16_test (void)
+{
+  y = _mm512_cvtpbf8_ph (z1);
+  y = _mm512_mask_cvtpbf8_ph (z, m16, z1);
+  y = _mm512_maskz_cvtpbf8_ph (m16, z1);
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx10_2-convert-1.c b/gcc/testsuite/gcc.target/i386/avx10_2-convert-1.c
index 015474f..9c3e857 100644
--- a/gcc/testsuite/gcc.target/i386/avx10_2-convert-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx10_2-convert-1.c
@@ -87,14 +87,22 @@
 /* { dg-final { scan-assembler-times "vcvtneph2hf8sy\[ \\t\]*%ymm\[0-9\]+,\[^\{\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
 /* { dg-final { scan-assembler-times "vcvtneph2hf8sy\[ \\t\]*%ymm\[0-9\]+,\[^\{\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
 /* { dg-final { scan-assembler-times "vcvtneph2hf8sy\[ \\t\]*%ymm\[0-9\]+,\[^\{\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpmovsxbw\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%ymm\[0-9\](?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpsllw\[ \t]\+\\\$8, %ymm\[0-9]\+, %ymm\[0-9]\+(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpsllw\[ \t]\+\\\$8, %ymm\[0-9]\+, %ymm\[0-9]\+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpmovsxbw\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%ymm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpmovsxbw\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpsllw\[ \t]\+\\\$8, %xmm\[0-9]\+, %xmm\[0-9]\+(?:\n|\[ \\t\]+#)" 2 } } */
+/* { dg-final { scan-assembler-times "vpsllw\[ \t]\+\\\$8, %xmm\[0-9]\+, %xmm\[0-9]\+\{%k\[1-7\]\}(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vpmovsxbw\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\]*%xmm\[0-9\]+\{%k\[1-7\]\}\{z\}(?:\n|\[ \\t\]+#)" 1 } } */
 
 #include <immintrin.h>
 
 volatile __m128 x1,a1,b1;
 volatile __m256 x2,a2,b2;
-volatile __m128h y,x128h;
-volatile __m256h y2,x256h;
-volatile __m128i x128i;
+volatile __m128h y,x128h,z;
+volatile __m256h y2,x256h,z2;
+volatile __m128i x128i,z3;
 volatile __m256i x256i;
 volatile __mmask8 m8;
 volatile __mmask16 m16;
@@ -272,3 +280,15 @@ avx10_2_vcvtneph2hf8s_test (void)
   x128i = _mm256_mask_cvtnesph_phf8 (x128i, m16, x256h);
   x128i = _mm256_maskz_cvtnesph_phf8 (m16, x256h);
 }
+
+void extern
+avx10_2_cvtbf8_fp16_test (void)
+{
+  y = _mm_cvtpbf8_ph (z3);
+  y = _mm_mask_cvtpbf8_ph (z, m8, z3);
+  y = _mm_maskz_cvtpbf8_ph (m8, z3);
+
+  y2 = _mm256_cvtpbf8_ph (z3);
+  y2 = _mm256_mask_cvtpbf8_ph (z2, m8, z3);
+  y2 = _mm256_maskz_cvtpbf8_ph (m8, z3);
+}