diff options
author | Jakub Jelinek <jakub@redhat.com> | 2023-06-20 20:17:41 +0200 |
---|---|---|
committer | Jakub Jelinek <jakub@redhat.com> | 2023-06-20 20:17:41 +0200 |
commit | f8f68c4ca622a24c2e8cf2b5f2f9fdcd47a7b369 (patch) | |
tree | 792b782251b929094be3e0b9be978a2e2c2c4f22 | |
parent | 4c7d264eee5084c15ace9c714987892e138ead14 (diff) | |
download | gcc-f8f68c4ca622a24c2e8cf2b5f2f9fdcd47a7b369.zip gcc-f8f68c4ca622a24c2e8cf2b5f2f9fdcd47a7b369.tar.gz gcc-f8f68c4ca622a24c2e8cf2b5f2f9fdcd47a7b369.tar.bz2 |
tree-ssa-math-opts: Small uaddc/usubc pattern matching improvement [PR79173]
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.
2023-06-20 Jakub Jelinek <jakub@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.
-rw-r--r-- | gcc/testsuite/g++.target/i386/pr79173-1.C | 33 | ||||
-rw-r--r-- | gcc/tree-ssa-math-opts.cc | 5 |
2 files changed, 38 insertions, 0 deletions
diff --git a/gcc/testsuite/g++.target/i386/pr79173-1.C b/gcc/testsuite/g++.target/i386/pr79173-1.C new file mode 100644 index 0000000..e6fc7cb --- /dev/null +++ b/gcc/testsuite/g++.target/i386/pr79173-1.C @@ -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); +} diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc index d2b7129..da01d4a 100644 --- a/gcc/tree-ssa-math-opts.cc +++ b/gcc/tree-ssa-math-opts.cc @@ -4728,6 +4728,7 @@ match_uaddc_usubc (gimple_stmt_iterator *gsi, gimple *stmt, tree_code code) 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 *gsi, gimple *stmt, tree_code code) 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 *gsi, gimple *stmt, tree_code code) { 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 *gsi, gimple *stmt, tree_code code) /* 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) |