SVE intrinsics: Fold constant operands for svdiv.

This patch implements constant folding for svdiv:
The new function aarch64_const_binop was created, which - in contrast to
int_const_binop - does not treat operations as overflowing. This function is
passed as callback to vector_const_binop from the new gimple_folder
method fold_const_binary, if the predicate is ptrue or predication is _x.
From svdiv_impl::fold, fold_const_binary is called with TRUNC_DIV_EXPR as
tree_code.
In aarch64_const_binop, a case was added for TRUNC_DIV_EXPR to return 0
for division by 0, as defined in the semantics for svdiv.
Tests were added to check the produced assembly for different
predicates, signed and unsigned integers, and the svdiv_n_* case.

The patch was bootstrapped and regtested on aarch64-linux-gnu, no regression.
OK for mainline?

Signed-off-by: Jennifer Schmitz <jschmitz@nvidia.com>

gcc/
	* config/aarch64/aarch64-sve-builtins-base.cc (svdiv_impl::fold):
	Try constant folding.
	* config/aarch64/aarch64-sve-builtins.h: Declare
	gimple_folder::fold_const_binary.
	* config/aarch64/aarch64-sve-builtins.cc (aarch64_const_binop):
	New function to fold binary SVE intrinsics without overflow.
	(gimple_folder::fold_const_binary): New helper function for
	constant folding of SVE intrinsics.

gcc/testsuite/
	* gcc.target/aarch64/sve/const_fold_div_1.c: New test.

4 files changed, 410 insertions, 3 deletions

diff --git a/gcc/config/aarch64/aarch64-sve-builtins-base.cc b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
index d55bee0..6c94d14 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins-base.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins-base.cc
@@ -755,8 +755,13 @@ public:
   gimple *
   fold (gimple_folder &f) const override
   {
-    tree divisor = gimple_call_arg (f.call, 2);
-    tree divisor_cst = uniform_integer_cst_p (divisor);
+    if (auto *res = f.fold_const_binary (TRUNC_DIV_EXPR))
+      return res;
+
+    /* If the divisor is a uniform power of 2, fold to a shift
+       instruction.  */
+    tree op2 = gimple_call_arg (f.call, 2);
+    tree divisor_cst = uniform_integer_cst_p (op2);
 
     if (!divisor_cst || !integer_pow2p (divisor_cst))
       return NULL;
@@ -770,7 +775,7 @@ public:
 				    shapes::binary_uint_opt_n, MODE_n,
 				    f.type_suffix_ids, GROUP_none, f.pred);
 	call = f.redirect_call (instance);
-	tree d = INTEGRAL_TYPE_P (TREE_TYPE (divisor)) ? divisor : divisor_cst;
+	tree d = INTEGRAL_TYPE_P (TREE_TYPE (op2)) ? op2 : divisor_cst;
 	new_divisor = wide_int_to_tree (TREE_TYPE (d), tree_log2 (d));
       }
     else
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.cc b/gcc/config/aarch64/aarch64-sve-builtins.cc
index 5ca9ec3..8f9aa3c 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins.cc
@@ -1132,6 +1132,30 @@ report_not_enum (location_t location, tree fndecl, unsigned int argno,
 	    " a valid %qT value", actual, argno + 1, fndecl, enumtype);
 }
 
+/* Try to fold constant arguments ARG1 and ARG2 using the given tree_code.
+   Operations are not treated as overflowing.  */
+static tree
+aarch64_const_binop (enum tree_code code, tree arg1, tree arg2)
+{
+  if (poly_int_tree_p (arg1) && poly_int_tree_p (arg2))
+    {
+      poly_wide_int poly_res;
+      tree type = TREE_TYPE (arg1);
+      signop sign = TYPE_SIGN (type);
+      wi::overflow_type overflow = wi::OVF_NONE;
+
+      /* Return 0 for division by 0, like SDIV and UDIV do.  */
+      if (code == TRUNC_DIV_EXPR && integer_zerop (arg2))
+	return arg2;
+
+      if (!poly_int_binop (poly_res, code, arg1, arg2, sign, &overflow))
+	return NULL_TREE;
+      return force_fit_type (type, poly_res, false,
+			     TREE_OVERFLOW (arg1) | TREE_OVERFLOW (arg2));
+    }
+  return NULL_TREE;
+}
+
 /* Return a hash code for a function_instance.  */
 hashval_t
 function_instance::hash () const
@@ -3593,6 +3617,25 @@ gimple_folder::fold_to_vl_pred (unsigned int vl)
   return gimple_build_assign (lhs, builder.build ());
 }
 
+/* Try to fold the call to a constant, given that, for integers, the call
+   is roughly equivalent to binary operation CODE.  aarch64_const_binop
+   handles any differences between CODE and the intrinsic.  */
+gimple *
+gimple_folder::fold_const_binary (enum tree_code code)
+{
+  gcc_assert (gimple_call_num_args (call) == 3);
+  tree pg = gimple_call_arg (call, 0);
+  tree op1 = gimple_call_arg (call, 1);
+  tree op2 = gimple_call_arg (call, 2);
+
+  if (type_suffix (0).integer_p
+      && (pred == PRED_x || is_ptrue (pg, type_suffix (0).element_bytes)))
+    if (tree res = vector_const_binop (code, op1, op2, aarch64_const_binop))
+      return gimple_build_assign (lhs, res);
+
+  return NULL;
+}
+
 /* Try to fold the call.  Return the new statement on success and null
    on failure.  */
 gimple *
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.h b/gcc/config/aarch64/aarch64-sve-builtins.h
index 9ab6f20..e388050 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.h
+++ b/gcc/config/aarch64/aarch64-sve-builtins.h
@@ -636,6 +636,7 @@ public:
   gimple *fold_to_pfalse ();
   gimple *fold_to_ptrue ();
   gimple *fold_to_vl_pred (unsigned int);
+  gimple *fold_const_binary (enum tree_code);
 
   gimple *fold ();
 
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/const_fold_div_1.c b/gcc/testsuite/gcc.target/aarch64/sve/const_fold_div_1.c
new file mode 100644
index 0000000..c15b3fc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/const_fold_div_1.c
@@ -0,0 +1,358 @@
+/* { dg-final { check-function-bodies "**" "" } } */
+/* { dg-options "-O2" } */
+
+#include "arm_sve.h"
+
+/*
+** s64_x_pg:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_x_pg (svbool_t pg)
+{
+  return svdiv_x (pg, svdup_s64 (5), svdup_s64 (3));
+}
+
+/*
+** s64_x_pg_0:
+**	mov	z[0-9]+\.b, #0
+**	ret
+*/
+svint64_t s64_x_pg_0 (svbool_t pg)
+{
+  return svdiv_x (pg, svdup_s64 (0), svdup_s64 (3));
+}
+
+/*
+** s64_x_pg_by0:
+**	mov	z[0-9]+\.b, #0
+**	ret
+*/
+svint64_t s64_x_pg_by0 (svbool_t pg)
+{
+  return svdiv_x (pg, svdup_s64 (5), svdup_s64 (0));
+}
+
+/*
+** s64_z_pg:
+**	mov	z[0-9]+\.d, p[0-7]/z, #1
+**	ret
+*/
+svint64_t s64_z_pg (svbool_t pg)
+{
+  return svdiv_z (pg, svdup_s64 (5), svdup_s64 (3));
+}
+
+/*
+** s64_z_pg_0:
+**	mov	z[0-9]+\.d, p[0-7]/z, #0
+**	ret
+*/
+svint64_t s64_z_pg_0 (svbool_t pg)
+{
+  return svdiv_z (pg, svdup_s64 (0), svdup_s64 (3));
+}
+
+/*
+** s64_z_pg_by0:
+**	mov	(z[0-9]+\.d), #5
+**	mov	(z[0-9]+)\.b, #0
+**	sdivr	\2\.d, p[0-7]/m, \2\.d, \1
+**	ret
+*/
+svint64_t s64_z_pg_by0 (svbool_t pg)
+{
+  return svdiv_z (pg, svdup_s64 (5), svdup_s64 (0));
+}
+
+/*
+** s64_m_pg:
+**	mov	(z[0-9]+\.d), #3
+**	mov	(z[0-9]+\.d), #5
+**	sdiv	\2, p[0-7]/m, \2, \1
+**	ret
+*/
+svint64_t s64_m_pg (svbool_t pg)
+{
+  return svdiv_m (pg, svdup_s64 (5), svdup_s64 (3));
+}
+
+/*
+** s64_x_ptrue:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_x_ptrue ()
+{
+  return svdiv_x (svptrue_b64 (), svdup_s64 (5), svdup_s64 (3));
+}
+
+/*
+** s64_z_ptrue:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_z_ptrue ()
+{
+  return svdiv_z (svptrue_b64 (), svdup_s64 (5), svdup_s64 (3));
+}
+
+/*
+** s64_m_ptrue:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_m_ptrue ()
+{
+  return svdiv_m (svptrue_b64 (), svdup_s64 (5), svdup_s64 (3));
+}
+
+/*
+** s64_x_pg_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_x_pg_n (svbool_t pg)
+{
+  return svdiv_n_s64_x (pg, svdup_s64 (5), 3);
+}
+
+/*
+** s64_x_pg_n_s64_0:
+**	mov	z[0-9]+\.b, #0
+**	ret
+*/
+svint64_t s64_x_pg_n_s64_0 (svbool_t pg)
+{
+  return svdiv_n_s64_x (pg, svdup_s64 (0), 3);
+}
+
+/*
+** s64_x_pg_n_s64_by0:
+**	mov	z[0-9]+\.b, #0
+**	ret
+*/
+svint64_t s64_x_pg_n_s64_by0 (svbool_t pg)
+{
+  return svdiv_n_s64_x (pg, svdup_s64 (5), 0);
+}
+
+/*
+** s64_z_pg_n:
+**	mov	z[0-9]+\.d, p[0-7]/z, #1
+**	ret
+*/
+svint64_t s64_z_pg_n (svbool_t pg)
+{
+  return svdiv_n_s64_z (pg, svdup_s64 (5), 3);
+}
+
+/*
+** s64_z_pg_n_s64_0:
+**	mov	z[0-9]+\.d, p[0-7]/z, #0
+**	ret
+*/
+svint64_t s64_z_pg_n_s64_0 (svbool_t pg)
+{
+  return svdiv_n_s64_z (pg, svdup_s64 (0), 3);
+}
+
+/*
+** s64_z_pg_n_s64_by0:
+**	mov	(z[0-9]+\.d), #5
+**	mov	(z[0-9]+)\.b, #0
+**	sdivr	\2\.d, p[0-7]/m, \2\.d, \1
+**	ret
+*/
+svint64_t s64_z_pg_n_s64_by0 (svbool_t pg)
+{
+  return svdiv_n_s64_z (pg, svdup_s64 (5), 0);
+}
+
+/*
+** s64_m_pg_n:
+**	mov	(z[0-9]+\.d), #3
+**	mov	(z[0-9]+\.d), #5
+**	sdiv	\2, p[0-7]/m, \2, \1
+**	ret
+*/
+svint64_t s64_m_pg_n (svbool_t pg)
+{
+  return svdiv_n_s64_m (pg, svdup_s64 (5), 3);
+}
+
+/*
+** s64_x_ptrue_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_x_ptrue_n ()
+{
+  return svdiv_n_s64_x (svptrue_b64 (), svdup_s64 (5), 3);
+}
+
+/*
+** s64_z_ptrue_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_z_ptrue_n ()
+{
+  return svdiv_n_s64_z (svptrue_b64 (), svdup_s64 (5), 3);
+}
+
+/*
+** s64_m_ptrue_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svint64_t s64_m_ptrue_n ()
+{
+  return svdiv_n_s64_m (svptrue_b64 (), svdup_s64 (5), 3);
+}
+
+/*
+** s32_m_ptrue_dupq:
+**	mov	z[0-9]+\.b, #0
+**	ret
+*/
+svint32_t s32_m_ptrue_dupq ()
+{
+  return svdiv_s32_m (svptrue_b32 (), svdupq_s32 (3, 0, -5, 11),
+		      svdupq_s32 (4, 1, -6, 0));
+}
+
+/*
+** s32_z_ptrue_dupq:
+**	mov	z[0-9]+\.s, #-2
+**	ret
+*/
+svint32_t s32_z_ptrue_dupq ()
+{
+  return svdiv_s32_z (svptrue_b32 (), svdupq_s32 (6, -30, 100, -4),
+		      svdupq_s32 (-3, 15, -50, 2));
+}
+
+/*
+** u64_x_pg:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_x_pg (svbool_t pg)
+{
+  return svdiv_x (pg, svdup_u64 (5), svdup_u64 (3));
+}
+
+/*
+** u64_z_pg:
+**	mov	z[0-9]+\.d, p[0-7]/z, #1
+**	ret
+*/
+svuint64_t u64_z_pg (svbool_t pg)
+{
+  return svdiv_z (pg, svdup_u64 (5), svdup_u64 (3));
+}
+
+/*
+** u64_m_pg:
+**	mov	(z[0-9]+\.d), #3
+**	mov	(z[0-9]+\.d), #5
+**	udiv	\2, p[0-7]/m, \2, \1
+**	ret
+*/
+svuint64_t u64_m_pg (svbool_t pg)
+{
+  return svdiv_m (pg, svdup_u64 (5), svdup_u64 (3));
+}
+
+/*
+** u64_x_ptrue:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_x_ptrue ()
+{
+  return svdiv_x (svptrue_b64 (), svdup_u64 (5), svdup_u64 (3));
+}
+
+/*
+** u64_z_ptrue:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_z_ptrue ()
+{
+  return svdiv_z (svptrue_b64 (), svdup_u64 (5), svdup_u64 (3));
+}
+
+/*
+** u64_m_ptrue:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_m_ptrue ()
+{
+  return svdiv_m (svptrue_b64 (), svdup_u64 (5), svdup_u64 (3));
+}
+
+/*
+** u64_x_pg_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_x_pg_n (svbool_t pg)
+{
+  return svdiv_n_u64_x (pg, svdup_u64 (5), 3);
+}
+
+/*
+** u64_z_pg_n:
+**	mov	z[0-9]+\.d, p[0-7]/z, #1
+**	ret
+*/
+svuint64_t u64_z_pg_n (svbool_t pg)
+{
+  return svdiv_n_u64_z (pg, svdup_u64 (5), 3);
+}
+
+/*
+** u64_m_pg_n:
+**	mov	(z[0-9]+\.d), #3
+**	mov	(z[0-9]+\.d), #5
+**	udiv	\2, p[0-7]/m, \2, \1
+**	ret
+*/
+svuint64_t u64_m_pg_n (svbool_t pg)
+{
+  return svdiv_n_u64_m (pg, svdup_u64 (5), 3);
+}
+
+/*
+** u64_x_ptrue_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_x_ptrue_n ()
+{
+  return svdiv_n_u64_x (svptrue_b64 (), svdup_u64 (5), 3);
+}
+
+/*
+** u64_z_ptrue_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_z_ptrue_n ()
+{
+  return svdiv_n_u64_z (svptrue_b64 (), svdup_u64 (5), 3);
+}
+
+/*
+** u64_m_ptrue_n:
+**	mov	z[0-9]+\.d, #1
+**	ret
+*/
+svuint64_t u64_m_ptrue_n ()
+{
+  return svdiv_n_u64_m (svptrue_b64 (), svdup_u64 (5), 3);
+}