From: Pan Li <pan2...@intel.com> This patch depends on below scalar enabling patch:
https://gcc.gnu.org/pipermail/gcc-patches/2024-May/650822.html For vectorize, we leverage the existing vect pattern recog to find the pattern similar to scalar and let the vectorizer to perform the rest part for standard name usadd<mode>3 in vector mode. The riscv vector backend have insn "Vector Single-Width Saturating Add and Subtract" which can be leveraged when expand the usadd<mode>3 in vector mode. For example: void vec_sat_add_u64 (uint64_t *out, uint64_t *x, uint64_t *y, unsigned n) { unsigned i; for (i = 0; i < n; i++) out[i] = (x[i] + y[i]) | (- (uint64_t)((uint64_t)(x[i] + y[i]) < x[i])); } Before this patch: void vec_sat_add_u64 (uint64_t *out, uint64_t *x, uint64_t *y, unsigned n) { ... _80 = .SELECT_VL (ivtmp_78, POLY_INT_CST [2, 2]); ivtmp_58 = _80 * 8; vect__4.7_61 = .MASK_LEN_LOAD (vectp_x.5_59, 64B, { -1, ... }, _80, 0); vect__6.10_65 = .MASK_LEN_LOAD (vectp_y.8_63, 64B, { -1, ... }, _80, 0); vect__7.11_66 = vect__4.7_61 + vect__6.10_65; mask__8.12_67 = vect__4.7_61 > vect__7.11_66; vect__12.15_72 = .VCOND_MASK (mask__8.12_67, { 18446744073709551615, ... }, vect__7.11_66); .MASK_LEN_STORE (vectp_out.16_74, 64B, { -1, ... }, _80, 0, vect__12.15_72); vectp_x.5_60 = vectp_x.5_59 + ivtmp_58; vectp_y.8_64 = vectp_y.8_63 + ivtmp_58; vectp_out.16_75 = vectp_out.16_74 + ivtmp_58; ivtmp_79 = ivtmp_78 - _80; ... } After this patch: void vec_sat_add_u64 (uint64_t *out, uint64_t *x, uint64_t *y, unsigned n) { ... _62 = .SELECT_VL (ivtmp_60, POLY_INT_CST [2, 2]); ivtmp_46 = _62 * 8; vect__4.7_49 = .MASK_LEN_LOAD (vectp_x.5_47, 64B, { -1, ... }, _62, 0); vect__6.10_53 = .MASK_LEN_LOAD (vectp_y.8_51, 64B, { -1, ... }, _62, 0); vect__12.11_54 = .SAT_ADD (vect__4.7_49, vect__6.10_53); .MASK_LEN_STORE (vectp_out.12_56, 64B, { -1, ... }, _62, 0, vect__12.11_54); ... } The below test suites are passed for this patch. * The riscv fully regression tests. * The aarch64 fully regression tests. * The x86 bootstrap tests. * The x86 fully regression tests. PR target/51492 PR target/112600 gcc/ChangeLog: * tree-vect-patterns.cc (gimple_unsigned_integer_sat_add): New func decl generated by match.pd match. (vect_recog_sat_add_pattern): New func impl to recog the pattern for unsigned SAT_ADD. Signed-off-by: Pan Li <pan2...@intel.com> --- gcc/tree-vect-patterns.cc | 51 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc index 87c2acff386..8ffcaf71d5c 100644 --- a/gcc/tree-vect-patterns.cc +++ b/gcc/tree-vect-patterns.cc @@ -4487,6 +4487,56 @@ vect_recog_mult_pattern (vec_info *vinfo, return pattern_stmt; } +extern bool gimple_unsigned_integer_sat_add (tree, tree*, tree (*)(tree)); + +/* + * Try to detect saturation add pattern (SAT_ADD), aka below gimple: + * _7 = _4 + _6; + * _8 = _4 > _7; + * _9 = (long unsigned int) _8; + * _10 = -_9; + * _12 = _7 | _10; + * + * And then simplied to + * _12 = .SAT_ADD (_4, _6); + */ + +static gimple * +vect_recog_sat_add_pattern (vec_info *vinfo, stmt_vec_info stmt_vinfo, + tree *type_out) +{ + gimple *last_stmt = STMT_VINFO_STMT (stmt_vinfo); + + if (!is_gimple_assign (last_stmt)) + return NULL; + + tree res_ops[2]; + tree lhs = gimple_assign_lhs (last_stmt); + + if (gimple_unsigned_integer_sat_add (lhs, res_ops, NULL)) + { + tree itype = TREE_TYPE (res_ops[0]); + tree vtype = get_vectype_for_scalar_type (vinfo, itype); + + if (vtype != NULL_TREE && direct_internal_fn_supported_p ( + IFN_SAT_ADD, vtype, OPTIMIZE_FOR_SPEED)) + { + *type_out = vtype; + gcall *call = gimple_build_call_internal (IFN_SAT_ADD, 2, res_ops[0], + res_ops[1]); + + gimple_call_set_lhs (call, vect_recog_temp_ssa_var (itype, NULL)); + gimple_call_set_nothrow (call, /* nothrow_p */ false); + gimple_set_location (call, gimple_location (last_stmt)); + + vect_pattern_detected ("vect_recog_sat_add_pattern", last_stmt); + return call; + } + } + + return NULL; +} + /* Detect a signed division by a constant that wouldn't be otherwise vectorized: @@ -6987,6 +7037,7 @@ static vect_recog_func vect_vect_recog_func_ptrs[] = { { vect_recog_vector_vector_shift_pattern, "vector_vector_shift" }, { vect_recog_divmod_pattern, "divmod" }, { vect_recog_mult_pattern, "mult" }, + { vect_recog_sat_add_pattern, "sat_add" }, { vect_recog_mixed_size_cond_pattern, "mixed_size_cond" }, { vect_recog_gcond_pattern, "gcond" }, { vect_recog_bool_pattern, "bool" }, -- 2.34.1