Hi!
In the following testcase we fail to pattern recognize the least significant
.UADDC call. The reason is that arg3 in that case is
_3 = .ADD_OVERFLOW (...);
_2 = __imag__ _3;
_1 = _2 != 0;
arg3 = (unsigned long) _1;
and while before the changes arg3 has a single use in some .ADD_OVERFLOW
later on, we add a .UADDC call next to it (and gsi_remove/gsi_replace only
what is strictly necessary and leave quite a few dead stmts around which
next DCE cleans up) and so it all of sudden isn't used just once, but twice
(.ADD_OVERFLOW and .UADDC) and so uaddc_cast fails. While we could tweak
uaddc_cast and not require has_single_use in these uses, there is also
no vrp that would figure out that because __imag__ _3 is in [0, 1] range,
it can just use arg3 = __imag__ _3; and drop the comparison and cast.
We already search if either arg2 or arg3 is ultimately set from __imag__
of .{{ADD,SUB}_OVERFLOW,U{ADD,SUB}C} call, so the following patch just
remembers the lhs of __imag__ from that case and uses it later.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2023-06-20 Jakub Jelinek <ja...@redhat.com>
PR middle-end/79173
* tree-ssa-math-opts.cc (match_uaddc_usubc): Remember lhs of
IMAGPART_EXPR of arg2/arg3 and use that as arg3 if it has the right
type.
* g++.target/i386/pr79173-1.C: New test.
--- gcc/tree-ssa-math-opts.cc.jj 2023-06-20 08:57:38.000000000 +0200
+++ gcc/tree-ssa-math-opts.cc 2023-06-20 10:33:52.969805538 +0200
@@ -4728,6 +4728,7 @@ match_uaddc_usubc (gimple_stmt_iterator
if (!types_compatible_p (type, TREE_TYPE (arg1)))
return false;
int kind[2] = { 0, 0 };
+ tree arg_im[2] = { NULL_TREE, NULL_TREE };
/* At least one of arg2 and arg3 should have type compatible
with arg1/rhs[0], and the other one should have value in [0, 1]
range. If both are in [0, 1] range and type compatible with
@@ -4758,6 +4759,7 @@ match_uaddc_usubc (gimple_stmt_iterator
g = uaddc_ne0 (g);
if (!uaddc_is_cplxpart (g, IMAGPART_EXPR))
continue;
+ arg_im[i] = gimple_assign_lhs (g);
g = SSA_NAME_DEF_STMT (TREE_OPERAND (gimple_assign_rhs1 (g), 0));
if (!is_gimple_call (g) || !gimple_call_internal_p (g))
continue;
@@ -4781,6 +4783,7 @@ match_uaddc_usubc (gimple_stmt_iterator
{
std::swap (arg2, arg3);
std::swap (kind[0], kind[1]);
+ std::swap (arg_im[0], arg_im[1]);
}
if ((kind[0] & 1) == 0 || (kind[1] & 6) == 0)
return false;
@@ -4810,6 +4813,8 @@ match_uaddc_usubc (gimple_stmt_iterator
/* Build .UADDC/.USUBC call which will be placed before the stmt. */
gimple_stmt_iterator gsi2 = gsi_for_stmt (ovf2);
gimple *g;
+ if ((kind[1] & 4) != 0 && types_compatible_p (type, TREE_TYPE (arg_im[1])))
+ arg3 = arg_im[1];
if ((kind[1] & 1) == 0)
{
if (TREE_CODE (arg3) == INTEGER_CST)
--- gcc/testsuite/g++.target/i386/pr79173-1.C.jj 2023-06-20
09:44:37.515578731 +0200
+++ gcc/testsuite/g++.target/i386/pr79173-1.C 2023-06-20 10:35:33.650418101
+0200
@@ -0,0 +1,33 @@
+// PR middle-end/79173
+// { dg-do compile { target c++11 } }
+// { dg-options "-O2 -fno-stack-protector -masm=att" }
+// { dg-final { scan-assembler-times "addq\t%r\[^\n\r]*, \\\(%rdi\\\)" 1 {
target lp64 } } }
+// { dg-final { scan-assembler-times "adcq\t%r\[^\n\r]*, 8\\\(%rdi\\\)" 1 {
target lp64 } } }
+// { dg-final { scan-assembler-times "adcq\t%r\[^\n\r]*, 16\\\(%rdi\\\)" 1 {
target lp64 } } }
+// { dg-final { scan-assembler-times "adcq\t%r\[^\n\r]*, 24\\\(%rdi\\\)" 1 {
target lp64 } } }
+// { dg-final { scan-assembler-times "addl\t%e\[^\n\r]*, \\\(%e\[^\n\r]*\\\)"
1 { target ia32 } } }
+// { dg-final { scan-assembler-times "adcl\t%e\[^\n\r]*, 4\\\(%e\[^\n\r]*\\\)"
1 { target ia32 } } }
+// { dg-final { scan-assembler-times "adcl\t%e\[^\n\r]*, 8\\\(%e\[^\n\r]*\\\)"
1 { target ia32 } } }
+// { dg-final { scan-assembler-times "adcl\t%e\[^\n\r]*,
12\\\(%e\[^\n\r]*\\\)" 1 { target ia32 } } }
+
+template <typename T>
+inline constexpr T
+uaddc (T x, T y, T carry_in, T &carry_out) noexcept
+{
+ [[gnu::assume (carry_in <= 1)]];
+ x += y;
+ carry_out = x < y;
+ x += carry_in;
+ carry_out += x < carry_in;
+ return x;
+}
+
+void
+foo (unsigned long *p, unsigned long *q)
+{
+ unsigned long c;
+ p[0] = uaddc (p[0], q[0], 0UL, c);
+ p[1] = uaddc (p[1], q[1], c, c);
+ p[2] = uaddc (p[2], q[2], c, c);
+ p[3] = uaddc (p[3], q[3], c, c);
+}
Jakub
