libgcc: Add DPD support + fix big-endian support of _BitInt <-> dfp conversions

The following patch fixes
FAIL: gcc.dg/dfp/bitint-1.c (test for excess errors)
FAIL: gcc.dg/dfp/bitint-2.c (test for excess errors)
FAIL: gcc.dg/dfp/bitint-3.c (test for excess errors)
FAIL: gcc.dg/dfp/bitint-4.c (test for excess errors)
FAIL: gcc.dg/dfp/bitint-5.c (test for excess errors)
FAIL: gcc.dg/dfp/bitint-6.c (test for excess errors)
FAIL: gcc.dg/dfp/bitint-8.c (test for excess errors)
FAIL: gcc.dg/dfp/int128-1.c (test for excess errors)
FAIL: gcc.dg/dfp/int128-2.c (test for excess errors)
FAIL: gcc.dg/dfp/int128-4.c (test for excess errors)
on s390x-linux (with the 3 not yet posted patches).

The patch does multiple things:
1) the routines were written for the DFP BID (binary integer decimal)
   format which is used on all arches but powerpc*/s390* (those use
   DPD - densely packed decimal format); as most of the code is actually
   the same for both BID and DPD formats, I haven't copied the sources
   + slightly modified them, but added the DPD support directly, + renaming
   of the exported symbols from __bid_* prefixed to __dpd_* prefixed that
   GCC expects on the DPD targets
2) while testing that I've found some big-endian issues in the existing
   support
3) testing also revealed that in some cases __builtin_clzll (~msb) was
   called with msb set to all ones, so invoking UB; apparently on aarch64
   and x86 we were lucky and got some value that happened to work well,
   but that wasn't the case on s390x

For 1), the patch uses two ~ 2KB tables to speed up the decoding/encoding.
I haven't found such tables in what is added into libgcc.a, though they
are in libdecnumber/bid/bid2dpd_dpd2bid.h, but there they are just huge
and next to other huge tables - there is d2b which is like __dpd_d2bbitint
in the patch but it uses 64-bit entries rather than 16-bit, then there is
d2b2 with 64-bit entries like in d2b all multiplied by 1000, then d2b3
similarly multiplied by 1000000, then d2b4 similarly multiplied by
1000000000, then d2b5 similarly multiplied by 1000000000000ULL and
d2b6 similarly multipled by 1000000000000000ULL.  Arguably it can
save some of the multiplications, but on the other side accesses memory
which is unlikely in the caches, and the 2048 bytes in the patch vs.
24 times more for d2b is IMHO significant.
For b2d, libdecnumber/bid/bid2dpd_dpd2bid.h has again b2d table like
__dpd_b2dbitint in the patch, except that it has 64-bit entries rather
than 16-bit (this time 1000 entries), but then has b2d2 which has the
same entries shifted left by 10, then b2d3 shifted left by 20, b2d4 shifted
left by 30 and b2d5 shifted left by 40.  I can understand for d2b paying
memory cost to speed up multiplications, but don't understand paying
extra 4 * 8 * 1000 bytes (+ 6 * 1000 bytes for b2d not using ushort)
just to avoid shifts.

2025-05-27  Jakub Jelinek  <jakub@redhat.com>

	* config/t-softfp (softfp_bid_list): Don't guard with
	$(enable_decimal_float) == bid.
	* soft-fp/bitint.h (__bid_pow10bitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_pow10bitint.
	(__dpd_d2bbitint, __dpd_b2dbitint): Declare.
	* soft-fp/bitintpow10.c (__dpd_d2bbitint, __dpd_b2dbitint): New
	variables.
	* soft-fp/fixsdbitint.c (__bid_fixsdbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixsdbitint.
	Add DPD support.  Fix big-endian support.
	* soft-fp/fixddbitint.c (__bid_fixddbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixddbitint.
	Add DPD support.  Fix big-endian support.
	* soft-fp/fixtdbitint.c (__bid_fixtdbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixtdbitint.
	Add DPD support.  Fix big-endian support.
	* soft-fp/fixsdti.c (__bid_fixsdbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixsdbitint.
	(__bid_fixsdti): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine to
	__dpd_fixsdti.
	* soft-fp/fixddti.c (__bid_fixddbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixddbitint.
	(__bid_fixddti): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine to
	__dpd_fixddti.
	* soft-fp/fixtdti.c (__bid_fixtdbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixtdbitint.
	(__bid_fixtdti): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine to
	__dpd_fixtdti.
	* soft-fp/fixunssdti.c (__bid_fixsdbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixsdbitint.
	(__bid_fixunssdti): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine
	to __dpd_fixunssdti.
	* soft-fp/fixunsddti.c (__bid_fixddbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixddbitint.
	(__bid_fixunsddti): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine
	to __dpd_fixunsddti.
	* soft-fp/fixunstdti.c (__bid_fixtdbitint): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_fixtdbitint.
	(__bid_fixunstdti): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine
	to __dpd_fixunstdti.
	* soft-fp/floatbitintsd.c (__bid_floatbitintsd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitintsd.
	Add DPD support.  Avoid calling __builtin_clzll with 0 argument.  Fix
	big-endian support.
	* soft-fp/floatbitintdd.c (__bid_floatbitintdd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitintdd.
	Add DPD support.  Avoid calling __builtin_clzll with 0 argument.  Fix
	big-endian support.
	* soft-fp/floatbitinttd.c (__bid_floatbitinttd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitinttd.
	Add DPD support.  Avoid calling __builtin_clzll with 0 argument.  Fix
	big-endian support.
	* soft-fp/floattisd.c (__bid_floatbitintsd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitintsd.
	(__bid_floattisd): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine to
	__dpd_floattisd.
	* soft-fp/floattidd.c (__bid_floatbitintdd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitintdd.
	(__bid_floattidd): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine to
	__dpd_floattidd.
	* soft-fp/floattitd.c (__bid_floatbitinttd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitinttd.
	(__bid_floattitd): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine to
	__dpd_floattitd.
	* soft-fp/floatuntisd.c (__bid_floatbitintsd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitintsd.
	(__bid_floatuntisd): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine
	to __dpd_floatuntisd.
	* soft-fp/floatuntidd.c (__bid_floatbitintdd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitintdd.
	(__bid_floatuntidd): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine
	to __dpd_floatuntidd.
	* soft-fp/floatuntitd.c (__bid_floatbitinttd): For
	!defined(ENABLE_DECIMAL_BID_FORMAT) redefine to __dpd_floatbitinttd.
	(__bid_floatuntitd): For !defined(ENABLE_DECIMAL_BID_FORMAT) redefine
	to __dpd_floatuntitd.

1 files changed, 65 insertions, 3 deletions

diff --git a/libgcc/soft-fp/floatbitinttd.c b/libgcc/soft-fp/floatbitinttd.c
index 5fff339..50b9e77 100644
--- a/libgcc/soft-fp/floatbitinttd.c
+++ b/libgcc/soft-fp/floatbitinttd.c
@@ -1,7 +1,7 @@
 /* Software floating-point emulation.
    Convert a _BitInt to _Decimal128.
 
-   Copyright (C) 2023 Free Software Foundation, Inc.
+   Copyright (C) 2023-2025 Free Software Foundation, Inc.
 
 This file is part of GCC.
 
@@ -28,6 +28,9 @@ see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
 #include "bitint.h"
 
 #ifdef __BITINT_MAXWIDTH__
+#ifndef ENABLE_DECIMAL_BID_FORMAT
+#define __bid_floatbitinttd __dpd_floatbitinttd
+#endif
 extern _Decimal128 __bid_floatbitinttd (const UBILtype *, SItype);
 
 _Decimal128
@@ -51,7 +54,11 @@ __bid_floatbitinttd (const UBILtype *i, SItype iprec)
     }
   if (iprec < 0)
     {
-      SItype n = sizeof (0ULL) * __CHAR_BIT__ + 1 - __builtin_clzll (~msb);
+      SItype n;
+      if (msb == ~(UBILtype) 0)
+	n = 1;
+      else
+	n = sizeof (0ULL) * __CHAR_BIT__ + 1 - __builtin_clzll (~msb);
       aiprec = (in - 1) * BIL_TYPE_SIZE + n;
     }
   else if (msb == 0)
@@ -117,7 +124,8 @@ __bid_floatbitinttd (const UBILtype *i, SItype iprec)
 	}
       else
 	{
-	  __builtin_memcpy (buf + BITINT_END (q_limbs - in + 1, 0), i,
+	  __builtin_memcpy (buf + BITINT_END (q_limbs - in + 1, 0),
+			    i + BITINT_END (1, 0),
 			    (in - 1) * sizeof (UBILtype));
 	  buf[BITINT_END (q_limbs - in, in - 1)] = msb;
 	  if (iprec < 0)
@@ -253,15 +261,69 @@ __bid_floatbitinttd (const UBILtype *i, SItype iprec)
     }
 
   exponent += 6176;
+#ifdef ENABLE_DECIMAL_BID_FORMAT
   u.u[__FLOAT_WORD_ORDER__ != __ORDER_BIG_ENDIAN__]
     = ((((UDItype) (iprec < 0)) << 63)
        | (((UDItype) exponent) << 49)
        | mantissahi);
+#else
+#ifdef __SIZEOF_INT128__
+  unsigned __int128 m = mantissahi;
+#else
+  unsigned _BitInt(128) m = mantissahi;
+#endif
+  m = (m << 64) | mantissalo;
+  u.u[0] = m / 1000000000000000ULL;
+  u.u[1] = m % 1000000000000000ULL;
+  mantissalo = __dpd_b2dbitint[u.u[1] % 1000];
+  u.u[1] /= 1000;
+  mantissalo |= ((UDItype) __dpd_b2dbitint[u.u[1] % 1000]) << 10;
+  u.u[1] /= 1000;
+  mantissalo |= ((UDItype) __dpd_b2dbitint[u.u[1] % 1000]) << 20;
+  u.u[1] /= 1000;
+  mantissalo |= ((UDItype) __dpd_b2dbitint[u.u[1] % 1000]) << 30;
+  u.u[1] /= 1000;
+  mantissalo |= ((UDItype) __dpd_b2dbitint[u.u[1] % 1000]) << 40;
+  mantissalo |= ((UDItype) __dpd_b2dbitint[u.u[0] % 1000]) << 50;
+  u.u[0] /= 1000;
+  mantissahi = __dpd_b2dbitint[u.u[0] % 1000];
+  u.u[0] /= 1000;
+  mantissalo |= mantissahi << 60;
+  mantissahi >>= 4;
+  mantissahi |= ((UDItype) __dpd_b2dbitint[u.u[0] % 1000]) << 6;
+  u.u[0] /= 1000;
+  mantissahi |= ((UDItype) __dpd_b2dbitint[u.u[0] % 1000]) << 16;
+  u.u[0] /= 1000;
+  mantissahi |= ((UDItype) __dpd_b2dbitint[u.u[0] % 1000]) << 26;
+  u.u[0] /= 1000;
+  mantissahi |= ((UDItype) __dpd_b2dbitint[u.u[0] % 1000]) << 36;
+  u.u[0] /= 1000;
+  if (u.u[0] >= 8)
+    u.u[__FLOAT_WORD_ORDER__ != __ORDER_BIG_ENDIAN__]
+      = (((((iprec < 0) << 2) | (UDItype) 3) << 61)
+	 | (((UDItype) exponent & (3 << 12)) << 47)
+	 | ((u.u[0] & 1) << 58)
+	 | (((UDItype) exponent & 4095) << 46)
+	 | mantissahi);
+  else
+    u.u[__FLOAT_WORD_ORDER__ != __ORDER_BIG_ENDIAN__]
+      = ((((UDItype) (iprec < 0)) << 63)
+	 | (((UDItype) exponent & (3 << 12)) << 49)
+	 | (u.u[0] << 58)
+	 | (((UDItype) exponent & 4095) << 46)
+	 | mantissahi);
+#endif
   u.u[__FLOAT_WORD_ORDER__ == __ORDER_BIG_ENDIAN__] = mantissalo;
   if (inexact)
     {
       ui.u[__FLOAT_WORD_ORDER__ != __ORDER_BIG_ENDIAN__]
+#ifdef ENABLE_DECIMAL_BID_FORMAT
 	= (((UDItype) (iprec < 0)) << 63) | (((UDItype) exponent - 1) << 49);
+#else
+	= ((((UDItype) (iprec < 0)) << 63)
+	   | ((((UDItype) exponent - 1) & (3 << 12)) << 49)
+	   | ((((UDItype) exponent - 1) & 4095) << 46));
+#endif
       ui.u[__FLOAT_WORD_ORDER__ == __ORDER_BIG_ENDIAN__] = inexact + 3;
       __asm ("" : "+g" (u.d));
       __asm ("" : "+g" (ui.d));