libgcc, i386: Add __fix{,uns}bfti and __float{,un}tibf [PR107703]

While DI <-> BF conversions can be handled (and are) through
DI <-> XF <-> BF and for narrower integral modes even sometimes
through DF or SF, because XFmode has 64-bit mantissa and so all
the DImode values are exactly representable in XFmode.
That is not the case for TImode, and while e.g. the HF -> TI
conversions are IMHO useless in libgcc, because HFmode has
-65504.0f16, 65504.0f16 range, all the integers will be already
representable in SImode (or even HImode for unsigned) and so
I think HF -> DI -> TI conversions are faster and valid,
BFmode has roughly the same range as SFmode and so we absolutely need
the TI -> BF conversions to avoid double rounding.

As for BF -> TI conversions, they can be either also implemented
in libgcc, or they can be implemented (as done in this commit)
as BF -> SF -> TI conversions with the same code generation used
elsewhere, just doing the 16-bit left shift of the bits - I think
we don't need to handle sNaNs during the BF -> SF part because
SF -> TI (which is already a libcall too) will handle that too.

The BF -> SF -> TI path avoids wasting
    32: 0000000000015e10   321 FUNC    GLOBAL DEFAULT   13 __fixbfti@@GCC_13.0.0
    89: 0000000000015f60   299 FUNC    GLOBAL DEFAULT   13 __fixunsbfti@@GCC_13.0.0

2023-03-10  Jakub Jelinek  <jakub@redhat.com>

	PR target/107703
	* optabs.cc (expand_fix): For conversions from BFmode to integral,
	use shifts to convert it to SFmode first and then convert SFmode
	to integral.

	* soft-fp/floattibf.c: New file.
	* soft-fp/floatuntibf.c: New file.
	* config/i386/libgcc-glibc.ver: Export __float{,un}tibf @ GCC_13.0.0.
	* config/i386/64/t-softfp (softfp_extras): Add floattibf and
	floatuntibf.
	(CFLAGS-floattibf.c, CFLAGS-floatunstibf.c): Add -msse2.

1 files changed, 46 insertions, 2 deletions

diff --git a/gcc/optabs.cc b/gcc/optabs.cc
index 4c641ca..c725f35 100644
--- a/gcc/optabs.cc
+++ b/gcc/optabs.cc
@@ -5674,7 +5674,21 @@ expand_fix (rtx to, rtx from, int unsignedp)
 	    rtx_insn *last = get_last_insn ();
 	    rtx from1 = from;
 	    if (fmode != GET_MODE (from))
-	      from1 = convert_to_mode (fmode, from, 0);
+	      {
+		if (REAL_MODE_FORMAT (GET_MODE (from))
+		    == &arm_bfloat_half_format
+		    && REAL_MODE_FORMAT (fmode) == &ieee_single_format)
+		  /* The BF -> SF conversions can be just a shift, doesn't
+		     need to handle sNANs.  */
+		  {
+		    int save_flag_finite_math_only = flag_finite_math_only;
+		    flag_finite_math_only = true;
+		    from1 = convert_to_mode (fmode, from, 0);
+		    flag_finite_math_only = save_flag_finite_math_only;
+		  }
+		else
+		  from1 = convert_to_mode (fmode, from, 0);
+	      }
 
 	    if (must_trunc)
 	      {
@@ -5746,7 +5760,21 @@ expand_fix (rtx to, rtx from, int unsignedp)
 	    lab2 = gen_label_rtx ();
 
 	    if (fmode != GET_MODE (from))
-	      from = convert_to_mode (fmode, from, 0);
+	      {
+		if (REAL_MODE_FORMAT (GET_MODE (from))
+		    == &arm_bfloat_half_format
+		    && REAL_MODE_FORMAT (fmode) == &ieee_single_format)
+		  /* The BF -> SF conversions can be just a shift, doesn't
+		     need to handle sNANs.  */
+		  {
+		    int save_flag_finite_math_only = flag_finite_math_only;
+		    flag_finite_math_only = true;
+		    from = convert_to_mode (fmode, from, 0);
+		    flag_finite_math_only = save_flag_finite_math_only;
+		  }
+		else
+		  from = convert_to_mode (fmode, from, 0);
+	      }
 
 	    /* See if we need to do the subtraction.  */
 	    do_pending_stack_adjust ();
@@ -5790,6 +5818,22 @@ expand_fix (rtx to, rtx from, int unsignedp)
 	  }
       }
 
+#ifdef HAVE_SFmode
+  if (REAL_MODE_FORMAT (GET_MODE (from)) == &arm_bfloat_half_format
+      && REAL_MODE_FORMAT (SFmode) == &ieee_single_format)
+    /* We don't have BF -> TI library functions, use BF -> SF -> TI
+       instead but the BF -> SF conversion can be just a shift, doesn't
+       need to handle sNANs.  */
+    {
+      int save_flag_finite_math_only = flag_finite_math_only;
+      flag_finite_math_only = true;
+      from = convert_to_mode (SFmode, from, 0);
+      flag_finite_math_only = save_flag_finite_math_only;
+      expand_fix (to, from, unsignedp);
+      return;
+    }
+#endif
+
   /* We can't do it with an insn, so use a library call.  But first ensure
      that the mode of TO is at least as wide as SImode, since those are the
      only library calls we know about.  */