Hi!
Multiplication/division/modulo/float operands are handled by libgcc calls
and so need to be passed as array of limbs with precision argument,
using handle_operand_addr. That code can't deal with more than one cast,
so the following patch avoids merging those cases.
.MUL_OVERFLOW calls use the same code, but we don't actually try to merge
the operands in that case already.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2023-12-21 Jakub Jelinek <ja...@redhat.com>
PR tree-optimization/112941
* gimple-lower-bitint.cc (gimple_lower_bitint): Disallow merging
a cast with multiplication, division or conversion to floating point
if rhs1 of the cast is result of another single use cast in the same
bb.
* gcc.dg/bitint-56.c: New test.
* gcc.dg/bitint-57.c: New test.
--- gcc/gimple-lower-bitint.cc.jj 2023-12-20 11:32:45.898425928 +0100
+++ gcc/gimple-lower-bitint.cc 2023-12-20 12:47:00.168727583 +0100
@@ -6060,6 +6060,26 @@ gimple_lower_bitint (void)
|| (bitint_precision_kind (TREE_TYPE (rhs1))
< bitint_prec_large))
continue;
+ if (is_gimple_assign (use_stmt))
+ switch (gimple_assign_rhs_code (use_stmt))
+ {
+ case MULT_EXPR:
+ case TRUNC_DIV_EXPR:
+ case TRUNC_MOD_EXPR:
+ case FLOAT_EXPR:
+ /* Uses which use handle_operand_addr can't
+ deal with nested casts. */
+ if (TREE_CODE (rhs1) == SSA_NAME
+ && gimple_assign_cast_p
+ (SSA_NAME_DEF_STMT (rhs1))
+ && has_single_use (rhs1)
+ && (gimple_bb (SSA_NAME_DEF_STMT (rhs1))
+ == gimple_bb (SSA_NAME_DEF_STMT (s))))
+ goto force_name;
+ break;
+ default:
+ break;
+ }
if ((TYPE_PRECISION (TREE_TYPE (rhs1))
>= TYPE_PRECISION (TREE_TYPE (s)))
&& mergeable_op (use_stmt))
@@ -6154,6 +6174,7 @@ gimple_lower_bitint (void)
&& (!SSA_NAME_VAR (s) || VAR_P (SSA_NAME_VAR (s))))
continue;
+ force_name:
if (!large_huge.m_names)
large_huge.m_names = BITMAP_ALLOC (NULL);
bitmap_set_bit (large_huge.m_names, SSA_NAME_VERSION (s));
--- gcc/testsuite/gcc.dg/bitint-56.c.jj 2023-12-20 12:41:28.208398219 +0100
+++ gcc/testsuite/gcc.dg/bitint-56.c 2023-12-20 12:38:08.548204489 +0100
@@ -0,0 +1,129 @@
+/* PR tree-optimization/112941 */
+/* { dg-do compile { target bitint } } */
+/* { dg-options "-std=c23 -O2" } */
+
+#if __BITINT_MAXWIDTH__ >= 4096
+void
+f1 (_BitInt(4096) *p, int r, _BitInt(115) s, _BitInt(128) t, _BitInt(231) u)
+{
+ p[0] *= (unsigned _BitInt(2048)) r;
+ p[1] *= (unsigned _BitInt(2048)) s;
+ p[2] *= (unsigned _BitInt(2048)) t;
+ p[3] *= (unsigned _BitInt(2048)) u;
+}
+
+void
+f2 (_BitInt(4094) *p, int r, _BitInt(115) s, _BitInt(128) t, _BitInt(231) u)
+{
+ p[0] /= (unsigned _BitInt(2048)) r;
+ p[1] /= (unsigned _BitInt(2048)) s;
+ p[2] /= (unsigned _BitInt(2048)) t;
+ p[3] /= (unsigned _BitInt(2048)) u;
+}
+
+void
+f3 (_BitInt(4096) *p, int r, _BitInt(115) s, _BitInt(128) t, _BitInt(231) u)
+{
+ p[0] *= (unsigned _BitInt(2110)) r;
+ p[1] *= (unsigned _BitInt(2110)) s;
+ p[2] *= (unsigned _BitInt(2110)) t;
+ p[3] *= (unsigned _BitInt(2110)) u;
+}
+
+void
+f4 (_BitInt(4094) *p, int r, _BitInt(115) s, _BitInt(128) t, _BitInt(231) u)
+{
+ p[0] /= (unsigned _BitInt(2110)) r;
+ p[1] /= (unsigned _BitInt(2110)) s;
+ p[2] /= (unsigned _BitInt(2110)) t;
+ p[3] /= (unsigned _BitInt(2110)) u;
+}
+
+void
+f5 (unsigned _BitInt(4096) *p, int r, _BitInt(115) s, _BitInt(128) t,
_BitInt(231) u)
+{
+ p[0] *= (unsigned _BitInt(2048)) r;
+ p[1] *= (unsigned _BitInt(2048)) s;
+ p[2] *= (unsigned _BitInt(2048)) t;
+ p[3] *= (unsigned _BitInt(2048)) u;
+}
+
+void
+f6 (unsigned _BitInt(4094) *p, int r, _BitInt(115) s, _BitInt(128) t,
_BitInt(231) u)
+{
+ p[0] /= (unsigned _BitInt(2048)) r;
+ p[1] /= (unsigned _BitInt(2048)) s;
+ p[2] /= (unsigned _BitInt(2048)) t;
+ p[3] /= (unsigned _BitInt(2048)) u;
+}
+
+void
+f7 (unsigned _BitInt(4096) *p, int r, _BitInt(115) s, _BitInt(128) t,
_BitInt(231) u)
+{
+ p[0] *= (unsigned _BitInt(2110)) r;
+ p[1] *= (unsigned _BitInt(2110)) s;
+ p[2] *= (unsigned _BitInt(2110)) t;
+ p[3] *= (unsigned _BitInt(2110)) u;
+}
+
+void
+f8 (unsigned _BitInt(4094) *p, int r, _BitInt(115) s, _BitInt(128) t,
_BitInt(231) u)
+{
+ p[0] /= (unsigned _BitInt(2110)) r;
+ p[1] /= (unsigned _BitInt(2110)) s;
+ p[2] /= (unsigned _BitInt(2110)) t;
+ p[3] /= (unsigned _BitInt(2110)) u;
+}
+
+#if __SIZEOF_INT128__
+void
+f9 (_BitInt(4096) *p, __int128 r)
+{
+ p[0] *= (unsigned _BitInt(2048)) r;
+}
+
+void
+f10 (_BitInt(4094) *p, __int128 r)
+{
+ p[0] /= (unsigned _BitInt(2048)) r;
+}
+
+void
+f11 (_BitInt(4096) *p, __int128 r)
+{
+ p[0] *= (unsigned _BitInt(2110)) r;
+}
+
+void
+f12 (_BitInt(4094) *p, __int128 r)
+{
+ p[0] /= (unsigned _BitInt(2110)) r;
+}
+
+void
+f13 (unsigned _BitInt(4096) *p, __int128 r)
+{
+ p[0] *= (unsigned _BitInt(2048)) r;
+}
+
+void
+f14 (unsigned _BitInt(4094) *p, __int128 r)
+{
+ p[0] /= (unsigned _BitInt(2048)) r;
+}
+
+void
+f15 (unsigned _BitInt(4096) *p, __int128 r)
+{
+ p[0] *= (unsigned _BitInt(2110)) r;
+}
+
+void
+f16 (unsigned _BitInt(4094) *p, __int128 r)
+{
+ p[0] /= (unsigned _BitInt(2110)) r;
+}
+#endif
+#else
+int i;
+#endif
--- gcc/testsuite/gcc.dg/bitint-57.c.jj 2023-12-20 12:42:12.691772991 +0100
+++ gcc/testsuite/gcc.dg/bitint-57.c 2023-12-20 12:42:49.900250015 +0100
@@ -0,0 +1,21 @@
+/* PR tree-optimization/112941 */
+/* { dg-do compile { target bitint } } */
+/* { dg-options "-std=c23 -O1 -fno-tree-forwprop" } */
+
+#if __BITINT_MAXWIDTH__ >= 6384
+unsigned _BitInt(2049)
+foo (unsigned _BitInt(6384) x, _BitInt(8) y)
+{
+ unsigned _BitInt(6384) z = y;
+ return x * z;
+}
+
+_BitInt(2049)
+bar (unsigned _BitInt(6384) x, _BitInt(1023) y)
+{
+ unsigned _BitInt(6384) z = y;
+ return x * z;
+}
+#else
+int i;
+#endif
Jakub
