From 0b5f469171c340ef61a48a31877d495bb77bd35f Mon Sep 17 00:00:00 2001 From: oluade01 Date: Fri, 14 Apr 2023 10:24:43 +0100 Subject: [PATCH 1/4] Missed opportunity to use [SU]ABD This adds a recognition pattern for the non-widening absolute difference (ABD). gcc/ChangeLog: * doc/md.texi (sabd, uabd): Document them. * internal-fn.def (ABD): Use new optab. * optabs.def (sabd_optab, uabd_optab): New optabs, * tree-vect-patterns.cc (vect_recog_absolute_difference): Recognize the following idiom abs (a - b). (vect_recog_sad_pattern): Refactor to use vect_recog_absolute_difference. (vect_recog_abd_pattern): Use patterns found by vect_recog_absolute_difference to build a new ABD internal call. --- gcc/doc/md.texi | 10 ++ gcc/internal-fn.def | 3 + gcc/optabs.def | 2 + gcc/tree-vect-patterns.cc | 250 +++++++++++++++++++++++++++++++++----- 4 files changed, 234 insertions(+), 31 deletions(-) diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi index 07bf8bdebffb2e523f25a41f2b57e43c0276b745..0ad546c63a8deebb4b6db894f437d1e21f0245a8 100644 --- a/gcc/doc/md.texi +++ b/gcc/doc/md.texi @@ -5778,6 +5778,16 @@ Other shift and rotate instructions, analogous to the Vector shift and rotate instructions that take vectors as operand 2 instead of a scalar type. +@cindex @code{uabd@var{m}} instruction pattern +@cindex @code{sabd@var{m}} instruction pattern +@item @samp{uabd@var{m}}, @samp{sabd@var{m}} +Signed and unsigned absolute difference instructions. These +instructions find the difference between operands 1 and 2 +then return the absolute value. A C code equivalent would be: +@smallexample +op0 = abs (op0 - op1) +@end smallexample + @cindex @code{avg@var{m}3_floor} instruction pattern @cindex @code{uavg@var{m}3_floor} instruction pattern @item @samp{avg@var{m}3_floor} diff --git a/gcc/internal-fn.def b/gcc/internal-fn.def index 7fe742c2ae713e7152ab05cfdfba86e4e0aa3456..0f1724ecf37a31c231572edf90b5577e2d82f468 100644 --- a/gcc/internal-fn.def +++ b/gcc/internal-fn.def @@ -167,6 +167,9 @@ DEF_INTERNAL_OPTAB_FN (FMS, ECF_CONST, fms, ternary) DEF_INTERNAL_OPTAB_FN (FNMA, ECF_CONST, fnma, ternary) DEF_INTERNAL_OPTAB_FN (FNMS, ECF_CONST, fnms, ternary) +DEF_INTERNAL_SIGNED_OPTAB_FN (ABD, ECF_CONST | ECF_NOTHROW, first, + sabd, uabd, binary) + DEF_INTERNAL_SIGNED_OPTAB_FN (AVG_FLOOR, ECF_CONST | ECF_NOTHROW, first, savg_floor, uavg_floor, binary) DEF_INTERNAL_SIGNED_OPTAB_FN (AVG_CEIL, ECF_CONST | ECF_NOTHROW, first, diff --git a/gcc/optabs.def b/gcc/optabs.def index 695f5911b300c9ca5737de9be809fa01aabe5e01..29bc92281a2175f898634cbe6af63c18021e5268 100644 --- a/gcc/optabs.def +++ b/gcc/optabs.def @@ -359,6 +359,8 @@ OPTAB_D (mask_fold_left_plus_optab, "mask_fold_left_plus_$a") OPTAB_D (extract_last_optab, "extract_last_$a") OPTAB_D (fold_extract_last_optab, "fold_extract_last_$a") +OPTAB_D (uabd_optab, "uabd$a3") +OPTAB_D (sabd_optab, "sabd$a3") OPTAB_D (savg_floor_optab, "avg$a3_floor") OPTAB_D (uavg_floor_optab, "uavg$a3_floor") OPTAB_D (savg_ceil_optab, "avg$a3_ceil") diff --git a/gcc/tree-vect-patterns.cc b/gcc/tree-vect-patterns.cc index a49b09539776c0056e77f99b10365d0a8747fbc5..91e1f9d4b610275dd833ec56dc77f76367ee7886 100644 --- a/gcc/tree-vect-patterns.cc +++ b/gcc/tree-vect-patterns.cc @@ -770,6 +770,89 @@ vect_split_statement (vec_info *vinfo, stmt_vec_info stmt2_info, tree new_rhs, } } +/* Look for the following pattern + X = x[i] + Y = y[i] + DIFF = X - Y + DAD = ABS_EXPR + */ +static bool +vect_recog_absolute_difference (vec_info *vinfo, gassign *abs_stmt, + tree *half_type, bool reject_unsigned, + vect_unpromoted_value unprom[2], + tree diff_oprnds[2]) +{ + if (!abs_stmt) + return false; + + /* FORNOW. Can continue analyzing the def-use chain when this stmt in a phi + inside the loop (in case we are analyzing an outer-loop). */ + enum tree_code code = gimple_assign_rhs_code (abs_stmt); + if (code != ABS_EXPR && code != ABSU_EXPR) + return false; + + tree abs_oprnd = gimple_assign_rhs1 (abs_stmt); + tree abs_type = TREE_TYPE (abs_oprnd); + if (!abs_oprnd) + return false; + if (reject_unsigned && TYPE_UNSIGNED (abs_type)) + return false; + if (!ANY_INTEGRAL_TYPE_P (abs_type) || TYPE_OVERFLOW_WRAPS (abs_type)) + return false; + + /* Peel off conversions from the ABS input. This can involve sign + changes (e.g. from an unsigned subtraction to a signed ABS input) + or signed promotion, but it can't include unsigned promotion. + (Note that ABS of an unsigned promotion should have been folded + away before now anyway.) */ + vect_unpromoted_value unprom_diff; + abs_oprnd = vect_look_through_possible_promotion (vinfo, abs_oprnd, + &unprom_diff); + if (!abs_oprnd) + return false; + if (TYPE_PRECISION (unprom_diff.type) != TYPE_PRECISION (abs_type) + && TYPE_UNSIGNED (unprom_diff.type)) + if (!reject_unsigned) + return false; + + /* We then detect if the operand of abs_expr is defined by a minus_expr. */ + stmt_vec_info diff_stmt_vinfo = vect_get_internal_def (vinfo, abs_oprnd); + if (!diff_stmt_vinfo) + return false; + + bool assigned_oprnds = false; + gassign *diff = dyn_cast (STMT_VINFO_STMT (diff_stmt_vinfo)); + if (diff_oprnds && diff && gimple_assign_rhs_code (diff) == MINUS_EXPR) + { + assigned_oprnds = true; + diff_oprnds[0] = gimple_assign_rhs1 (diff); + diff_oprnds[1] = gimple_assign_rhs2 (diff); + } + + /* FORNOW. Can continue analyzing the def-use chain when this stmt in a phi + inside the loop (in case we are analyzing an outer-loop). */ + if (vect_widened_op_tree (vinfo, diff_stmt_vinfo, MINUS_EXPR, + WIDEN_MINUS_EXPR, + false, 2, unprom, half_type)) + { + if (diff_oprnds && !assigned_oprnds) + { + diff_oprnds[0] = unprom[0].op; + diff_oprnds[1] = unprom[1].op; + } + } + else if (!assigned_oprnds) + { + return false; + } + else + { + *half_type = NULL_TREE; + } + + return true; +} + /* Convert UNPROM to TYPE and return the result, adding new statements to STMT_INFO's pattern definition statements if no better way is available. VECTYPE is the vector form of TYPE. @@ -1308,40 +1391,13 @@ vect_recog_sad_pattern (vec_info *vinfo, /* FORNOW. Can continue analyzing the def-use chain when this stmt in a phi inside the loop (in case we are analyzing an outer-loop). */ gassign *abs_stmt = dyn_cast (abs_stmt_vinfo->stmt); - if (!abs_stmt - || (gimple_assign_rhs_code (abs_stmt) != ABS_EXPR - && gimple_assign_rhs_code (abs_stmt) != ABSU_EXPR)) - return NULL; - - tree abs_oprnd = gimple_assign_rhs1 (abs_stmt); - tree abs_type = TREE_TYPE (abs_oprnd); - if (TYPE_UNSIGNED (abs_type)) - return NULL; - - /* Peel off conversions from the ABS input. This can involve sign - changes (e.g. from an unsigned subtraction to a signed ABS input) - or signed promotion, but it can't include unsigned promotion. - (Note that ABS of an unsigned promotion should have been folded - away before now anyway.) */ - vect_unpromoted_value unprom_diff; - abs_oprnd = vect_look_through_possible_promotion (vinfo, abs_oprnd, - &unprom_diff); - if (!abs_oprnd) - return NULL; - if (TYPE_PRECISION (unprom_diff.type) != TYPE_PRECISION (abs_type) - && TYPE_UNSIGNED (unprom_diff.type)) - return NULL; - /* We then detect if the operand of abs_expr is defined by a minus_expr. */ - stmt_vec_info diff_stmt_vinfo = vect_get_internal_def (vinfo, abs_oprnd); - if (!diff_stmt_vinfo) + vect_unpromoted_value unprom[2]; + if (!vect_recog_absolute_difference (vinfo, abs_stmt, &half_type, + true, unprom, NULL)) return NULL; - /* FORNOW. Can continue analyzing the def-use chain when this stmt in a phi - inside the loop (in case we are analyzing an outer-loop). */ - vect_unpromoted_value unprom[2]; - if (!vect_widened_op_tree (vinfo, diff_stmt_vinfo, MINUS_EXPR, WIDEN_MINUS_EXPR, - false, 2, unprom, &half_type)) + if (!half_type) return NULL; vect_pattern_detected ("vect_recog_sad_pattern", last_stmt); @@ -1363,6 +1419,137 @@ vect_recog_sad_pattern (vec_info *vinfo, return pattern_stmt; } +/* Function vect_recog_abd_pattern + + Try to find the following ABsolute Difference (ABD) pattern: + + VTYPE x, y, out; + type diff; + loop i in range: + S1 diff = x[i] - y[i] + S2 out[i] = ABS_EXPR ; + + where 'type' is a integer and 'VTYPE' is a vector of integers + the same size as 'type' + + Input: + + * STMT_VINFO: The stmt from which the pattern search begins + + Output: + + * TYPE_out: The type of the output of this pattern + + * Return value: A new stmt that will be used to replace the sequence of + stmts that constitute the pattern; either SABD or UABD: + SABD_EXPR + UABD_EXPR + + UABD expressions are used when the input types are + narrower than the output types or the output type is narrower + than 32 bits + */ + +static gimple * +vect_recog_abd_pattern (vec_info *vinfo, + stmt_vec_info stmt_vinfo, tree *type_out) +{ + /* Look for the following patterns + X = x[i] + Y = y[i] + DIFF = X - Y + DAD = ABS_EXPR + out[i] = DAD + + In which + - X, Y, DIFF, DAD all have the same type + - x, y, out are all vectors of the same type + */ + gassign *last_stmt = dyn_cast (STMT_VINFO_STMT (stmt_vinfo)); + if (!last_stmt) + return NULL; + + tree out_type = TREE_TYPE (gimple_assign_lhs (last_stmt)); + + gassign *abs_stmt = last_stmt; + if (gimple_assign_cast_p (last_stmt)) + { + tree last_rhs = gimple_assign_rhs1 (last_stmt); + if (!SSA_VAR_P (last_rhs)) + return NULL; + + abs_stmt = dyn_cast (SSA_NAME_DEF_STMT (last_rhs)); + if (!abs_stmt) + return NULL; + } + + vect_unpromoted_value unprom[2]; + tree diff_oprnds[2]; + tree half_type; + if (!vect_recog_absolute_difference (vinfo, abs_stmt, &half_type, + false, unprom, diff_oprnds)) + return NULL; + +#define SAME_TYPE(A, B) (TYPE_PRECISION (A) == TYPE_PRECISION (B)) + + tree abd_oprnds[2]; + if (half_type) + { + if (!SAME_TYPE (unprom[0].type, unprom[1].type)) + return NULL; + + tree diff_type = TREE_TYPE (diff_oprnds[0]); + if (TYPE_PRECISION (out_type) != TYPE_PRECISION (diff_type)) + { + vect_convert_inputs (vinfo, stmt_vinfo, 2, abd_oprnds, half_type, unprom, + get_vectype_for_scalar_type (vinfo, half_type)); + } + else + { + abd_oprnds[0] = diff_oprnds[0]; + abd_oprnds[1] = diff_oprnds[1]; + } + } + else + { + if (unprom[0].op && unprom[1].op + && (!SAME_TYPE (unprom[0].type, unprom[1].type) + || !SAME_TYPE (unprom[0].type, out_type))) + return NULL; + + unprom[0].op = diff_oprnds[0]; + unprom[1].op = diff_oprnds[1]; + tree signed_out = signed_type_for (out_type); + tree signed_out_vectype = get_vectype_for_scalar_type (vinfo, signed_out); + vect_convert_inputs (vinfo, stmt_vinfo, 2, abd_oprnds, + signed_out, unprom, signed_out_vectype); + + if (!SAME_TYPE (TREE_TYPE (diff_oprnds[0]), TREE_TYPE (abd_oprnds[0]))) + return NULL; + } + + if (!SAME_TYPE (TREE_TYPE (abd_oprnds[0]), TREE_TYPE (abd_oprnds[1])) + || !SAME_TYPE (TREE_TYPE (abd_oprnds[0]), out_type)) + return NULL; + + vect_pattern_detected ("vect_recog_abd_pattern", last_stmt); + + tree vectype = get_vectype_for_scalar_type (vinfo, out_type); + if (!vectype + || !direct_internal_fn_supported_p (IFN_ABD, vectype, + OPTIMIZE_FOR_SPEED)) + return NULL; + + *type_out = STMT_VINFO_VECTYPE (stmt_vinfo); + + tree var = vect_recog_temp_ssa_var (out_type, NULL); + gcall *abd_stmt = gimple_build_call_internal (IFN_ABD, 2, + abd_oprnds[0], abd_oprnds[1]); + gimple_call_set_lhs (abd_stmt, var); + gimple_set_location (abd_stmt, gimple_location (last_stmt)); + return abd_stmt; +} + /* Recognize an operation that performs ORIG_CODE on widened inputs, so that it can be treated as though it had the form: @@ -6439,6 +6626,7 @@ struct vect_recog_func static vect_recog_func vect_vect_recog_func_ptrs[] = { { vect_recog_bitfield_ref_pattern, "bitfield_ref" }, { vect_recog_bit_insert_pattern, "bit_insert" }, + { vect_recog_abd_pattern, "abd" }, { vect_recog_over_widening_pattern, "over_widening" }, /* Must come after over_widening, which narrows the shift as much as possible beforehand. */ -- 2.25.1