i386: Fix cstorebf4 fp comparison operand [PR117495]

For cstorebf4 it uses comparison_operator for BFmode compare, which is
incorrect when directly uses ix86_expand_setcc as it does not canonicalize
the input comparison to correct the compare code by swapping operands.
The original code without AVX10.2 calls emit_store_flag_force, who
actually calls to emit_store_flags_1 and recurisive calls to this expander
again with swapped operand and flag.
Therefore, we can avoid do the redundant recurisive call by adjusting
the comparison_operator to ix86_fp_comparison_operator, and calls
ix86_expand_setcc directly.

gcc/ChangeLog:

	PR target/117495
	* config/i386/i386.md (cstorebf4): Use ix86_fp_comparison_operator
	and calls ix86_expand_setcc directly.

gcc/testsuite/ChangeLog:

	PR target/117495
	* gcc.target/i386/pr117495.c: New test.

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index f4aae80b7a9575abf2ffa6a9497b35bee77c420a..03b0f548467eac2729d9feb0f95897c177412b90 100644 (file)
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -1853,23 +1853,19 @@
        (compare:CC (match_operand:BF 2 "cmp_fp_expander_operand")
                    (match_operand:BF 3 "cmp_fp_expander_operand")))
    (set (match_operand:QI 0 "register_operand")
-       (match_operator 1 "comparison_operator"
+       (match_operator 1 "ix86_fp_comparison_operator"
          [(reg:CC FLAGS_REG)
           (const_int 0)]))]
   "TARGET_80387 || (SSE_FLOAT_MODE_P (SFmode) && TARGET_SSE_MATH)"
 {
-  if (TARGET_AVX10_2_256 && !flag_trapping_math)
-    ix86_expand_setcc (operands[0], GET_CODE (operands[1]),
-                      operands[2], operands[3]);
-  else
+  rtx op2 = operands[2], op3 = operands[3];
+  if (!TARGET_AVX10_2_256 || flag_trapping_math)
     {
-      rtx op1 = ix86_expand_fast_convert_bf_to_sf (operands[2]);
-      rtx op2 = ix86_expand_fast_convert_bf_to_sf (operands[3]);
-      rtx res = emit_store_flag_force (operands[0], GET_CODE (operands[1]),
-                                      op1, op2, SFmode, 0, 1);
-      if (!rtx_equal_p (res, operands[0]))
-      emit_move_insn (operands[0], res);
+      op2 = ix86_expand_fast_convert_bf_to_sf (operands[2]);
+      op3 = ix86_expand_fast_convert_bf_to_sf (operands[3]);
     }
+  ix86_expand_setcc (operands[0], GET_CODE (operands[1]),
+                    op2, op3);
   DONE;
 })
 

diff --git a/gcc/testsuite/gcc.target/i386/pr117495.c b/gcc/testsuite/gcc.target/i386/pr117495.c
new file mode 100644 (file)
index 0000000..274b6ce
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr117495.c
@@ -0,0 +1,26 @@
+/* PR target/117495 */
+/* { dg-do compile } */
+/* { dg-options "-march=x86-64-v3 -fno-trapping-math" } */
+/* { dg-final { scan-assembler-times "vcomsbf16" 2 } } */
+
+__attribute__((target("avx10.2")))
+int foo (int b, int x)
+{
+  return (__bf16) b < x;
+}
+
+int foo2 (int b, int x)
+{
+  return (__bf16) b < x;
+}
+
+__attribute__((target("avx10.2")))
+int foo3 (__bf16 b, __bf16 x)
+{
+  return (__bf16) b < x;
+}
+
+int foo4 (__bf16 b, __bf16 x)
+{
+  return (__bf16) b < x;
+}