[gcc r15-3596] i386: Enable V2BF/V4BF vec_cmp with AVX10.2 vcmppbf16

[Levy Hsu]

https://gcc.gnu.org/g:89d50c45048e5d7230ddde9afc8fbc83143e34cb

commit r15-3596-g89d50c45048e5d7230ddde9afc8fbc83143e34cb
Author: Levy Hsu <admin@levyhsu.com>
Date:   Wed Sep 4 16:34:04 2024 +0930

    i386: Enable V2BF/V4BF vec_cmp with AVX10.2 vcmppbf16
    
    gcc/ChangeLog:
    
            * config/i386/i386.cc (ix86_get_mask_mode):
            Enable BFmode for targetm.vectorize.get_mask_mode with AVX10.2.
            * config/i386/mmx.md (vec_cmp<mode>qi):
            Implement vec_cmpv2bfqi and vec_cmpv4bfqi.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/i386/part-vect-vec_cmpbf.c: New test.

Diff:
---
 gcc/config/i386/i386.cc                            |  3 ++-
 gcc/config/i386/mmx.md                             | 17 ++++++++++++++
 .../gcc.target/i386/part-vect-vec_cmpbf.c          | 26 ++++++++++++++++++++++
 3 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 45320124b91c..7dbae1d72e35 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -24682,7 +24682,8 @@ ix86_get_mask_mode (machine_mode data_mode)
       /* AVX512FP16 only supports vector comparison
 	 to kmask for _Float16.  */
       || (TARGET_AVX512VL && TARGET_AVX512FP16
-	  && GET_MODE_INNER (data_mode) == E_HFmode))
+	  && GET_MODE_INNER (data_mode) == E_HFmode)
+      || (TARGET_AVX10_2_256 && GET_MODE_INNER (data_mode) == E_BFmode))
     {
       if (elem_size == 4
 	  || elem_size == 8
diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 4bc191b874b3..2f8d958dd5f0 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -2290,6 +2290,23 @@
   DONE;
 })
 
+;;This instruction does not generate floating point exceptions
+(define_expand "vec_cmp<mode>qi"
+  [(set (match_operand:QI 0 "register_operand")
+	(match_operator:QI 1 ""
+	  [(match_operand:VBF_32_64 2 "register_operand")
+	   (match_operand:VBF_32_64 3 "nonimmediate_operand")]))]
+  "TARGET_AVX10_2_256"
+{
+  rtx op2 = lowpart_subreg (V8BFmode,
+			     force_reg (<MODE>mode, operands[2]), <MODE>mode);
+  rtx op3 = lowpart_subreg (V8BFmode,
+			     force_reg (<MODE>mode, operands[3]), <MODE>mode);
+
+  emit_insn (gen_vec_cmpv8bfqi (operands[0], operands[1], op2, op3));
+  DONE;
+})
+
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 ;;
 ;; Parallel half-precision floating point rounding operations.
diff --git a/gcc/testsuite/gcc.target/i386/part-vect-vec_cmpbf.c b/gcc/testsuite/gcc.target/i386/part-vect-vec_cmpbf.c
new file mode 100644
index 000000000000..0bb720b64324
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/part-vect-vec_cmpbf.c
@@ -0,0 +1,26 @@
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-O2 -mavx10.2" } */
+/* { dg-final { scan-assembler-times "vcmppbf16" 10 } } */
+
+typedef __bf16 __attribute__((__vector_size__ (4))) v2bf;
+typedef __bf16 __attribute__((__vector_size__ (8))) v4bf;
+
+
+#define VCMPMN(type, op, name)	\
+type  \
+__attribute__ ((noinline, noclone)) \
+vec_cmp_##type##type##name (type a, type b) \
+{ \
+  return a op b;  \
+}
+
+VCMPMN (v4bf, <, lt)
+VCMPMN (v2bf, <, lt)
+VCMPMN (v4bf, <=, le)
+VCMPMN (v2bf, <=, le)
+VCMPMN (v4bf, >, gt)
+VCMPMN (v2bf, >, gt)
+VCMPMN (v4bf, >=, ge)
+VCMPMN (v2bf, >=, ge)
+VCMPMN (v4bf, ==, eq)
+VCMPMN (v2bf, ==, eq)