From 52b0536710ff3f3ace72ab00ce9ef6c630cd1183 Mon Sep 17 00:00:00 2001 From: Pan Li Date: Wed, 15 May 2024 10:14:05 +0800 Subject: Internal-fn: Support new IFN SAT_ADD for unsigned scalar int This patch would like to add the middle-end presentation for the saturation add. Aka set the result of add to the max when overflow. It will take the pattern similar as below. SAT_ADD (x, y) => (x + y) | (-(TYPE)((TYPE)(x + y) < x)) Take uint8_t as example, we will have: * SAT_ADD (1, 254) => 255. * SAT_ADD (1, 255) => 255. * SAT_ADD (2, 255) => 255. * SAT_ADD (255, 255) => 255. Given below example for the unsigned scalar integer uint64_t: uint64_t sat_add_u64 (uint64_t x, uint64_t y) { return (x + y) | (- (uint64_t)((uint64_t)(x + y) < x)); } Before this patch: uint64_t sat_add_uint64_t (uint64_t x, uint64_t y) { long unsigned int _1; _Bool _2; long unsigned int _3; long unsigned int _4; uint64_t _7; long unsigned int _10; __complex__ long unsigned int _11; ;; basic block 2, loop depth 0 ;; pred: ENTRY _11 = .ADD_OVERFLOW (x_5(D), y_6(D)); _1 = REALPART_EXPR <_11>; _10 = IMAGPART_EXPR <_11>; _2 = _10 != 0; _3 = (long unsigned int) _2; _4 = -_3; _7 = _1 | _4; return _7; ;; succ: EXIT } After this patch: uint64_t sat_add_uint64_t (uint64_t x, uint64_t y) { uint64_t _7; ;; basic block 2, loop depth 0 ;; pred: ENTRY _7 = .SAT_ADD (x_5(D), y_6(D)); [tail call] return _7; ;; succ: EXIT } The below tests are passed for this patch: 1. The riscv fully regression tests. 3. The x86 bootstrap tests. 4. The x86 fully regression tests. PR target/51492 PR target/112600 gcc/ChangeLog: * internal-fn.cc (commutative_binary_fn_p): Add type IFN_SAT_ADD to the return true switch case(s). * internal-fn.def (SAT_ADD): Add new signed optab SAT_ADD. * match.pd: Add unsigned SAT_ADD match(es). * optabs.def (OPTAB_NL): Remove fixed-point limitation for us/ssadd. * tree-ssa-math-opts.cc (gimple_unsigned_integer_sat_add): New extern func decl generated in match.pd match. (match_saturation_arith): New func impl to match the saturation arith. (math_opts_dom_walker::after_dom_children): Try match saturation arith when IOR expr. Signed-off-by: Pan Li --- gcc/match.pd | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) (limited to 'gcc/match.pd') diff --git a/gcc/match.pd b/gcc/match.pd index 07e743a..0f9c34f 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -3043,6 +3043,57 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) || POINTER_TYPE_P (itype)) && wi::eq_p (wi::to_wide (int_cst), wi::max_value (itype)))))) +/* Unsigned Saturation Add */ +(match (usadd_left_part_1 @0 @1) + (plus:c @0 @1) + (if (INTEGRAL_TYPE_P (type) + && TYPE_UNSIGNED (TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@1))))) + +(match (usadd_left_part_2 @0 @1) + (realpart (IFN_ADD_OVERFLOW:c @0 @1)) + (if (INTEGRAL_TYPE_P (type) + && TYPE_UNSIGNED (TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@1))))) + +(match (usadd_right_part_1 @0 @1) + (negate (convert (lt (plus:c @0 @1) @0))) + (if (INTEGRAL_TYPE_P (type) + && TYPE_UNSIGNED (TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@1))))) + +(match (usadd_right_part_1 @0 @1) + (negate (convert (gt @0 (plus:c @0 @1)))) + (if (INTEGRAL_TYPE_P (type) + && TYPE_UNSIGNED (TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@1))))) + +(match (usadd_right_part_2 @0 @1) + (negate (convert (ne (imagpart (IFN_ADD_OVERFLOW:c @0 @1)) integer_zerop))) + (if (INTEGRAL_TYPE_P (type) + && TYPE_UNSIGNED (TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@0)) + && types_match (type, TREE_TYPE (@1))))) + +/* We cannot merge or overload usadd_left_part_1 and usadd_left_part_2 + because the sub part of left_part_2 cannot work with right_part_1. + For example, left_part_2 pattern focus one .ADD_OVERFLOW but the + right_part_1 has nothing to do with .ADD_OVERFLOW. */ + +/* Unsigned saturation add, case 1 (branchless): + SAT_U_ADD = (X + Y) | - ((X + Y) < X) or + SAT_U_ADD = (X + Y) | - (X > (X + Y)). */ +(match (unsigned_integer_sat_add @0 @1) + (bit_ior:c (usadd_left_part_1 @0 @1) (usadd_right_part_1 @0 @1))) + +/* Unsigned saturation add, case 2 (branchless with .ADD_OVERFLOW). */ +(match (unsigned_integer_sat_add @0 @1) + (bit_ior:c (usadd_left_part_2 @0 @1) (usadd_right_part_2 @0 @1))) + /* x > y && x != XXX_MIN --> x > y x > y && x == XXX_MIN --> false . */ (for eqne (eq ne) -- cgit v1.1