bitint: Introduce abi_limb_mode

Given what I saw in the aarch64/arm psABIs for BITINT_TYPE, as I said
earlier I'm afraid we need to differentiate between the limb mode/precision
specified in the psABIs (what is used to decide how it is actually passed,
aligned or what size it has) vs. what limb mode/precision should be used
during bitint lowering and in the libgcc bitint APIs.
While in the x86_64 psABI a limb is 64-bit, which is perfect for both,
that is a wordsize which we can perform operations natively in,
e.g. aarch64 wants 128-bit limbs for alignment/sizing purposes, but
on the bitint lowering side I believe it would result in terribly bad code
and on the libgcc side wouldn't work at all (because it relies there on
longlong.h support).

So, the following patch makes it possible for aarch64 to use TImode
as abi_limb_mode for _BitInt(129) and larger, while using DImode as
limb_mode.

2023-12-15  Jakub Jelinek  <jakub@redhat.com>

	* target.h (struct bitint_info): Add abi_limb_mode member, adjust
	comment.
	* target.def (bitint_type_info): Mention abi_limb_mode instead of
	limb_mode.
	* varasm.cc (output_constant): Use abi_limb_mode rather than
	limb_mode.
	* stor-layout.cc (finish_bitfield_representative): Likewise.  Assert
	that if precision is smaller or equal to abi_limb_mode precision or
	if info.big_endian is different from WORDS_BIG_ENDIAN, info.limb_mode
	must be the same as info.abi_limb_mode.
	(layout_type): Use abi_limb_mode rather than limb_mode.
	* gimple-fold.cc (clear_padding_bitint_needs_padding_p): Likewise.
	(clear_padding_type): Likewise.
	* config/i386/i386.cc (ix86_bitint_type_info): Also set
	info->abi_limb_mode.
	* doc/tm.texi: Regenerated.

7 files changed, 29 insertions, 13 deletions

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 3e78949..0bba93f 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -25679,6 +25679,7 @@ ix86_bitint_type_info (int n, struct bitint_info *info)
     info->limb_mode = SImode;
   else
     info->limb_mode = DImode;
+  info->abi_limb_mode = info->limb_mode;
   info->big_endian = false;
   info->extended = false;
   return true;
diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi
index 768ada0a..0bb6da0 100644
--- a/gcc/doc/tm.texi
+++ b/gcc/doc/tm.texi
@@ -1032,8 +1032,8 @@ applied.
 @deftypefn {Target Hook} bool TARGET_C_BITINT_TYPE_INFO (int @var{n}, struct bitint_info *@var{info})
 This target hook returns true if @code{_BitInt(@var{N})} is supported and
 provides details on it.  @code{_BitInt(@var{N})} is to be represented as
-series of @code{info->limb_mode}
-@code{CEIL (@var{N}, GET_MODE_PRECISION (info->limb_mode))} limbs,
+series of @code{info->abi_limb_mode}
+@code{CEIL (@var{N}, GET_MODE_PRECISION (info->abi_limb_mode))} limbs,
 ordered from least significant to most significant if
 @code{!info->big_endian}, otherwise from most significant to least
 significant.  If @code{info->extended} is false, the bits above or equal to
diff --git a/gcc/gimple-fold.cc b/gcc/gimple-fold.cc
index a5be2ee..cb4b572 100644
--- a/gcc/gimple-fold.cc
+++ b/gcc/gimple-fold.cc
@@ -4604,7 +4604,7 @@ clear_padding_bitint_needs_padding_p (tree type)
   gcc_assert (ok);
   if (info.extended)
     return false;
-  scalar_int_mode limb_mode = as_a <scalar_int_mode> (info.limb_mode);
+  scalar_int_mode limb_mode = as_a <scalar_int_mode> (info.abi_limb_mode);
   if (TYPE_PRECISION (type) < GET_MODE_PRECISION (limb_mode))
     return true;
   else if (TYPE_PRECISION (type) == GET_MODE_PRECISION (limb_mode))
@@ -4881,7 +4881,8 @@ clear_padding_type (clear_padding_struct *buf, tree type,
 	struct bitint_info info;
 	bool ok = targetm.c.bitint_type_info (TYPE_PRECISION (type), &info);
 	gcc_assert (ok);
-	scalar_int_mode limb_mode = as_a <scalar_int_mode> (info.limb_mode);
+	scalar_int_mode limb_mode
+	  = as_a <scalar_int_mode> (info.abi_limb_mode);
 	if (TYPE_PRECISION (type) <= GET_MODE_PRECISION (limb_mode))
 	  {
 	    gcc_assert ((size_t) sz <= clear_padding_unit);
diff --git a/gcc/stor-layout.cc b/gcc/stor-layout.cc
index ba375fa..0c095aa 100644
--- a/gcc/stor-layout.cc
+++ b/gcc/stor-layout.cc
@@ -2154,7 +2154,8 @@ finish_bitfield_representative (tree repr, tree field)
 	  unsigned prec = TYPE_PRECISION (TREE_TYPE (field));
 	  bool ok = targetm.c.bitint_type_info (prec, &info);
 	  gcc_assert (ok);
-	  scalar_int_mode limb_mode = as_a <scalar_int_mode> (info.limb_mode);
+	  scalar_int_mode limb_mode
+	    = as_a <scalar_int_mode> (info.abi_limb_mode);
 	  unsigned lprec = GET_MODE_PRECISION (limb_mode);
 	  if (prec > lprec)
 	    {
@@ -2416,16 +2417,20 @@ layout_type (tree type)
 	int cnt;
 	bool ok = targetm.c.bitint_type_info (TYPE_PRECISION (type), &info);
 	gcc_assert (ok);
-	scalar_int_mode limb_mode = as_a <scalar_int_mode> (info.limb_mode);
+	scalar_int_mode limb_mode
+	  = as_a <scalar_int_mode> (info.abi_limb_mode);
 	if (TYPE_PRECISION (type) <= GET_MODE_PRECISION (limb_mode))
 	  {
 	    SET_TYPE_MODE (type, limb_mode);
+	    gcc_assert (info.abi_limb_mode == info.limb_mode);
 	    cnt = 1;
 	  }
 	else
 	  {
 	    SET_TYPE_MODE (type, BLKmode);
 	    cnt = CEIL (TYPE_PRECISION (type), GET_MODE_PRECISION (limb_mode));
+	    gcc_assert (info.abi_limb_mode == info.limb_mode
+			|| !info.big_endian == !WORDS_BIG_ENDIAN);
 	  }
 	TYPE_SIZE (type) = bitsize_int (cnt * GET_MODE_BITSIZE (limb_mode));
 	TYPE_SIZE_UNIT (type) = size_int (cnt * GET_MODE_SIZE (limb_mode));
diff --git a/gcc/target.def b/gcc/target.def
index 08218f3..ca030ab 100644
--- a/gcc/target.def
+++ b/gcc/target.def
@@ -6357,8 +6357,8 @@ DEFHOOK
 (bitint_type_info,
  "This target hook returns true if @code{_BitInt(@var{N})} is supported and\n\
 provides details on it.  @code{_BitInt(@var{N})} is to be represented as\n\
-series of @code{info->limb_mode}\n\
-@code{CEIL (@var{N}, GET_MODE_PRECISION (info->limb_mode))} limbs,\n\
+series of @code{info->abi_limb_mode}\n\
+@code{CEIL (@var{N}, GET_MODE_PRECISION (info->abi_limb_mode))} limbs,\n\
 ordered from least significant to most significant if\n\
 @code{!info->big_endian}, otherwise from most significant to least\n\
 significant.  If @code{info->extended} is false, the bits above or equal to\n\
diff --git a/gcc/target.h b/gcc/target.h
index a055b25..53f03b3 100644
--- a/gcc/target.h
+++ b/gcc/target.h
@@ -69,15 +69,23 @@ union cumulative_args_t { void *p; };
 #endif /* !CHECKING_P */
 
 /* Target properties of _BitInt(N) type.  _BitInt(N) is to be represented
-   as series of limb_mode CEIL (N, GET_MODE_PRECISION (limb_mode)) limbs,
-   ordered from least significant to most significant if !big_endian,
+   as series of abi_limb_mode CEIL (N, GET_MODE_PRECISION (abi_limb_mode))
+   limbs, ordered from least significant to most significant if !big_endian,
    otherwise from most significant to least significant.  If extended is
    false, the bits above or equal to N are undefined when stored in a register
    or memory, otherwise they are zero or sign extended depending on if
-   it is unsigned _BitInt(N) or _BitInt(N) / signed _BitInt(N).  */
+   it is unsigned _BitInt(N) or _BitInt(N) / signed _BitInt(N).
+   limb_mode is either the same as abi_limb_mode, or some narrower mode
+   in which _BitInt lowering should actually perform operations in and
+   what libgcc _BitInt helpers should use.
+   E.g. abi_limb_mode could be TImode which is something some processor
+   specific ABI would specify to use, but it would be desirable to handle
+   it as an array of DImode instead for efficiency.
+   Note, abi_limb_mode can be different from limb_mode only if big_endian
+   matches WORDS_BIG_ENDIAN.  */
 
 struct bitint_info {
-  machine_mode limb_mode;
+  machine_mode abi_limb_mode, limb_mode;
   bool big_endian;
   bool extended;
 };
diff --git a/gcc/varasm.cc b/gcc/varasm.cc
index 167aea8..69f8f8e 100644
--- a/gcc/varasm.cc
+++ b/gcc/varasm.cc
@@ -5315,7 +5315,8 @@ output_constant (tree exp, unsigned HOST_WIDE_INT size, unsigned int align,
 	  tree type = TREE_TYPE (exp);
 	  bool ok = targetm.c.bitint_type_info (TYPE_PRECISION (type), &info);
 	  gcc_assert (ok);
-	  scalar_int_mode limb_mode = as_a <scalar_int_mode> (info.limb_mode);
+	  scalar_int_mode limb_mode
+	    = as_a <scalar_int_mode> (info.abi_limb_mode);
 	  if (TYPE_PRECISION (type) <= GET_MODE_PRECISION (limb_mode))
 	    {
 	      cst = expand_expr (exp, NULL_RTX, VOIDmode, EXPAND_INITIALIZER);