Hi!
The following testcases show 2 bugs in the .{ADD,SUB}_OVERFLOW lowering,
both related to storing of the REALPART_EXPR part of the result.
On the first testcase prec is 255, prec_limbs is 4 and for the second limb
in the loop the store of the REALPART_EXPR of .USUBC (_30) is stored through:
if (_27 <= 3)
goto <bb 12>; [80.00%]
else
goto <bb 15>; [20.00%]
<bb 12> [local count: 1073741824]:
if (_27 < 3)
goto <bb 14>; [80.00%]
else
goto <bb 13>; [20.00%]
<bb 13> [local count: 1073741824]:
bitint.3[_27] = _30;
goto <bb 15>; [100.00%]
<bb 14> [local count: 858993464]:
MEM[(unsigned long *)&bitint.3 + 24B] = _30;
<bb 15> [local count: 1073741824]:
The first check is right, as prec_limbs is 4, we don't want to store
bitint.3[4] or above at all, those limbs are just computed for the overflow
checking and nothing else, so _27 > 4 leads to no store.
But the other condition is exact opposite of what should be done, if
the current index of the second limb (_27) is < 3, then it should
bitint.3[_27] = _30;
and if it is == 3, it should
MEM[(unsigned long *)&bitint.3 + 24B] = _30;
and (especially important for the targets which would bitinfo.extended = 1)
should actually in this case zero extend it from the 63 bits to 64, that is
the handling of the partial limb. The if_then_if_then_else helper if
there are 2 conditions sets m_gsi to be at the start of the
edge_true_false->dest bb, i.e. when the first condition is true and second
false, and that is where we store the SSA_NAME indexed limb store, so the
condition needs to be reversed.
The following patch does that and adds the cast as well, the usual
assumption that already handle_operand has the partial limb type doesn't
have to be true here, because the source operand could have much larger
precision than the REALPART_EXPR of the lhs.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2024-02-23 Jakub Jelinek <ja...@redhat.com>
PR tree-optimization/114040
* gimple-lower-bitint.cc (bitint_large_huge::lower_addsub_overflow):
Use EQ_EXPR rather than LT_EXPR for g2 condition and change its
probability from likely to unlikely. When handling the true true
store, first cast to limb_access_type and then to l's type.
* gcc.dg/torture/bitint-60.c: New test.
* gcc.dg/torture/bitint-61.c: New test.
--- gcc/gimple-lower-bitint.cc.jj 2024-02-22 10:13:54.123058152 +0100
+++ gcc/gimple-lower-bitint.cc 2024-02-22 14:51:01.655335350 +0100
@@ -4255,12 +4255,12 @@ bitint_large_huge::lower_addsub_overflow
NULL_TREE, NULL_TREE);
gimple *g2 = NULL;
if (!single_comparison)
- g2 = gimple_build_cond (LT_EXPR, idx,
+ g2 = gimple_build_cond (EQ_EXPR, idx,
size_int (prec_limbs - 1),
NULL_TREE, NULL_TREE);
edge edge_true_true, edge_true_false, edge_false;
if_then_if_then_else (g, g2, profile_probability::likely (),
- profile_probability::likely (),
+ profile_probability::unlikely (),
edge_true_true, edge_true_false,
edge_false);
tree l = limb_access (type, var ? var : obj, idx, true);
@@ -4269,8 +4269,11 @@ bitint_large_huge::lower_addsub_overflow
if (!single_comparison)
{
m_gsi = gsi_after_labels (edge_true_true->src);
- l = limb_access (type, var ? var : obj,
- size_int (prec_limbs - 1), true);
+ tree plm1idx = size_int (prec_limbs - 1);
+ tree plm1type = limb_access_type (type, plm1idx);
+ l = limb_access (type, var ? var : obj, plm1idx, true);
+ if (!useless_type_conversion_p (plm1type, TREE_TYPE (rhs)))
+ rhs = add_cast (plm1type, rhs);
if (!useless_type_conversion_p (TREE_TYPE (l),
TREE_TYPE (rhs)))
rhs = add_cast (TREE_TYPE (l), rhs);
--- gcc/testsuite/gcc.dg/torture/bitint-60.c.jj 2024-02-22 14:54:52.996121115
+0100
+++ gcc/testsuite/gcc.dg/torture/bitint-60.c 2024-02-22 14:54:42.656264784
+0100
@@ -0,0 +1,24 @@
+/* PR tree-optimization/114040 */
+/* { dg-do run { target bitint } } */
+/* { dg-options "-std=c23 -pedantic-errors" } */
+/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */
+/* { dg-skip-if "" { ! run_expensive_tests } { "-flto" } { "" } } */
+
+#if __BITINT_MAXWIDTH__ >= 8671
+__attribute__((noipa)) unsigned
+foo (unsigned _BitInt(8671) x, unsigned y, unsigned _BitInt(512) z)
+{
+ unsigned _BitInt (8671) r
+ = x * __builtin_sub_overflow_p (y * z, 0, (unsigned _BitInt(255)) 0);
+ return r;
+}
+#endif
+
+int
+main ()
+{
+#if __BITINT_MAXWIDTH__ >= 8671
+ if (foo (1, 1, 0xfffa46471e7c2dd60000000000000000wb))
+ __builtin_abort ();
+#endif
+}
--- gcc/testsuite/gcc.dg/torture/bitint-61.c.jj 2024-02-22 15:19:24.562704298
+0100
+++ gcc/testsuite/gcc.dg/torture/bitint-61.c 2024-02-22 15:19:57.964241439
+0100
@@ -0,0 +1,36 @@
+/* PR tree-optimization/114040 */
+/* { dg-do run { target { bitint && int128 } } } */
+/* { dg-options "-std=c23" } */
+/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */
+/* { dg-skip-if "" { ! run_expensive_tests } { "-flto" } { "" } } */
+
+unsigned a;
+signed char b;
+short c;
+long d;
+__int128 e;
+int f;
+
+#if __BITINT_MAXWIDTH__ >= 511
+__attribute__((noinline)) void
+foo (_BitInt(3) x, unsigned _BitInt(511) y, unsigned *z)
+{
+ int g = __builtin_sub_overflow_p (y ^ x, 0, (unsigned _BitInt(255)) 0);
+ unsigned h = y + e, i = h + d;
+ unsigned _BitInt(2) j = i + g;
+ unsigned k = j + c;
+ unsigned l = k + a + f + b;
+ *z = l;
+}
+#endif
+
+int
+main ()
+{
+#if __BITINT_MAXWIDTH__ >= 511
+ unsigned x;
+ foo (0, 0x81e4a5fa7c408f370000000000000000uwb, &x);
+ if (x)
+ __builtin_abort ();
+#endif
+}
Jakub
