i386: Support vectorized BF16 FMA with AVX10.2 instructions

gcc/ChangeLog:

	* config/i386/sse.md: Add V8BF/V16BF/V32BF to mode iterator FMAMODEM.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx10_2-512-bf-vector-fma-1.c: New test.
	* gcc.target/i386/avx10_2-bf-vector-fma-1.c: New test.

gcc/config/i386/sse.md

@@ -5677,7 +5677,10 @@
    (HF "TARGET_AVX512FP16")
    (V8HF "TARGET_AVX512FP16 && TARGET_AVX512VL")
    (V16HF "TARGET_AVX512FP16 && TARGET_AVX512VL")
-   (V32HF "TARGET_AVX512FP16 && TARGET_EVEX512")])
+   (V32HF "TARGET_AVX512FP16 && TARGET_EVEX512")
+   (V8BF "TARGET_AVX10_2_256")
+   (V16BF "TARGET_AVX10_2_256")
+   (V32BF "TARGET_AVX10_2_512")])
 
 (define_expand "fma<mode>4"
   [(set (match_operand:FMAMODEM 0 "register_operand")

gcc/testsuite/gcc.target/i386/avx10_2-512-bf-vector-fma-1.c

@@ -0,0 +1,34 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx10.2-512 -O2" } */
+/* { dg-final { scan-assembler-times "vfmadd132nepbf16\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfmsub132nepbf16\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132nepbf16\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132nepbf16\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+
+#include <immintrin.h>
+
+typedef __bf16 v32bf __attribute__ ((__vector_size__ (64)));
+
+v32bf
+foo_madd (v32bf a, v32bf b, v32bf c)
+{
+  return a * b + c;
+}
+
+v32bf
+foo_msub (v32bf a, v32bf b, v32bf c)
+{
+  return a * b - c;
+}
+
+v32bf
+foo_nmadd (v32bf a, v32bf b, v32bf c)
+{
+  return -a * b + c;
+}
+
+v32bf
+foo_nmsub (v32bf a, v32bf b, v32bf c)
+{
+  return -a * b - c;
+}

gcc/testsuite/gcc.target/i386/avx10_2-bf-vector-fma-1.c

@@ -0,0 +1,63 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx10.2 -O2" } */
+/* { dg-final { scan-assembler-times "vfmadd132nepbf16\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfmsub132nepbf16\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132nepbf16\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132nepbf16\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfmadd132nepbf16\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfmsub132nepbf16\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfnmadd132nepbf16\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+/* { dg-final { scan-assembler-times "vfnmsub132nepbf16\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
+
+#include <immintrin.h>
+
+typedef __bf16 v16bf __attribute__ ((__vector_size__ (32)));
+typedef __bf16 v8bf __attribute__ ((__vector_size__ (16)));
+
+v16bf
+foo_madd_256 (v16bf a, v16bf b, v16bf c)
+{
+  return a * b + c;
+}
+
+v16bf
+foo_msub_256 (v16bf a, v16bf b, v16bf c)
+{
+  return a * b - c;
+}
+
+v16bf
+foo_nmadd_256 (v16bf a, v16bf b, v16bf c)
+{
+  return -a * b + c;
+}
+
+v16bf
+foo_nmsub_256 (v16bf a, v16bf b, v16bf c)
+{
+  return -a * b - c;
+}
+
+v8bf
+foo_madd_128 (v8bf a, v8bf b, v8bf c)
+{
+  return a * b + c;
+}
+
+v8bf
+foo_msub_128 (v8bf a, v8bf b, v8bf c)
+{
+  return a * b - c;
+}
+
+v8bf
+foo_nmadd_128 (v8bf a, v8bf b, v8bf c)
+{
+  return -a * b + c;
+}
+
+v8bf
+foo_nmsub_128 (v8bf a, v8bf b, v8bf c)
+{
+  return -a * b - c;
+}