https://gcc.gnu.org/g:21e3565927eda5ce9907d91100623052fa8182cd
commit r15-1721-g21e3565927eda5ce9907d91100623052fa8182cd
Author: Pan Li <pan2...@intel.com>
Date: Fri Jun 28 11:33:41 2024 +0800
Match: Support imm form for unsigned scalar .SAT_ADD
This patch would like to support the form of unsigned scalar .SAT_ADD
when one of the op is IMM. For example as below:
Form IMM:
#define DEF_SAT_U_ADD_IMM_FMT_1(T) \
T __attribute__((noinline)) \
sat_u_add_imm_##T##_fmt_1 (T x) \
{ \
return (T)(x + 9) >= x ? (x + 9) : -1; \
}
DEF_SAT_U_ADD_IMM_FMT_1(uint64_t)
Before this patch:
__attribute__((noinline))
uint64_t sat_u_add_imm_uint64_t_fmt_1 (uint64_t x)
{
long unsigned int _1;
uint64_t _3;
;; basic block 2, loop depth 0
;; pred: ENTRY
_1 = MIN_EXPR <x_2(D), 18446744073709551606>;
_3 = _1 + 9;
return _3;
;; succ: EXIT
}
After this patch:
__attribute__((noinline))
uint64_t sat_u_add_imm_uint64_t_fmt_1 (uint64_t x)
{
uint64_t _3;
;; basic block 2, loop depth 0
;; pred: ENTRY
_3 = .SAT_ADD (x_2(D), 9); [tail call]
return _3;
;; succ: EXIT
}
The below test suites are passed for this patch:
1. The rv64gcv fully regression test with newlib.
2. The x86 bootstrap test.
3. The x86 fully regression test.
gcc/ChangeLog:
* match.pd: Add imm form for .SAT_ADD matching.
* tree-ssa-math-opts.cc (math_opts_dom_walker::after_dom_children):
Add .SAT_ADD matching under PLUS_EXPR.
Signed-off-by: Pan Li <pan2...@intel.com>
Diff:
---
gcc/match.pd | 24 ++++++++++++++++++++++++
gcc/tree-ssa-math-opts.cc | 2 ++
2 files changed, 26 insertions(+)
diff --git a/gcc/match.pd b/gcc/match.pd
index 3fa3f2e8296..7fff7b5f9fe 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -3154,6 +3154,30 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(match (unsigned_integer_sat_add @0 @1)
(cond^ (gt @0 (usadd_left_part_1@2 @0 @1)) integer_minus_onep @2))
+/* Unsigned saturation add, case 9 (one op is imm):
+ SAT_U_ADD = (X + 3) >= x ? (X + 3) : -1. */
+(match (unsigned_integer_sat_add @0 @1)
+ (plus (min @0 INTEGER_CST@2) INTEGER_CST@1)
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0, @1))
+ (with
+ {
+ unsigned precision = TYPE_PRECISION (type);
+ wide_int cst_1 = wi::to_wide (@1);
+ wide_int cst_2 = wi::to_wide (@2);
+ wide_int max = wi::mask (precision, false, precision);
+ wide_int sum = wi::add (cst_1, cst_2);
+ }
+ (if (wi::eq_p (max, sum))))))
+
+/* Unsigned saturation add, case 10 (one op is imm):
+ SAT_U_ADD = __builtin_add_overflow (X, 3, &ret) == 0 ? ret : -1. */
+(match (unsigned_integer_sat_add @0 @1)
+ (cond^ (ne (imagpart (IFN_ADD_OVERFLOW@2 @0 INTEGER_CST@1)) integer_zerop)
+ integer_minus_onep (realpart @2))
+ (if (INTEGRAL_TYPE_P (type) && TYPE_UNSIGNED (type)
+ && types_match (type, @0))))
+
/* Unsigned saturation sub, case 1 (branch with gt):
SAT_U_SUB = X > Y ? X - Y : 0 */
(match (unsigned_integer_sat_sub @0 @1)
diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
index 3783a874699..3b5433ec000 100644
--- a/gcc/tree-ssa-math-opts.cc
+++ b/gcc/tree-ssa-math-opts.cc
@@ -6195,6 +6195,8 @@ math_opts_dom_walker::after_dom_children (basic_block bb)
break;
case PLUS_EXPR:
+ match_unsigned_saturation_add (&gsi, as_a<gassign *> (stmt));
+ /* fall-through */
case MINUS_EXPR:
if (!convert_plusminus_to_widen (&gsi, stmt, code))
{
