diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c index 5a4f07d5810..f2724e792c9 100644 --- a/gcc/config/rs6000/rs6000.c +++ b/gcc/config/rs6000/rs6000.c @@ -5177,6 +5177,34 @@ rs6000_add_stmt_cost (class vec_info *vinfo, void *data, int count, return retval; } +/* For some target specific vectorization cost which can't be handled per stmt, + we check the requisite conditions and adjust the vectorization cost + accordingly if satisfied. One typical example is to model shift cost for + vector with length by counting number of required lengths under condition + LOOP_VINFO_FULLY_WITH_LENGTH_P. */ + +static void +adjust_vect_cost (rs6000_cost_data *data) +{ + struct loop *loop = data->loop_info; + gcc_assert (loop); + loop_vec_info loop_vinfo = loop_vec_info_for_loop (loop); + + if (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo)) + { + rgroup_controls *rgc; + unsigned int num_vectors_m1; + unsigned int shift_cnt = 0; + FOR_EACH_VEC_ELT (LOOP_VINFO_LENS (loop_vinfo), num_vectors_m1, rgc) + if (rgc->type) + /* Each length needs one shift to fill into bits 0-7. */ + shift_cnt += (num_vectors_m1 + 1); + + rs6000_add_stmt_cost (loop_vinfo, (void *) data, shift_cnt, scalar_stmt, + NULL, NULL_TREE, 0, vect_body); + } +} + /* Implement targetm.vectorize.finish_cost. */ static void @@ -5186,7 +5214,10 @@ rs6000_finish_cost (void *data, unsigned *prologue_cost, rs6000_cost_data *cost_data = (rs6000_cost_data*) data; if (cost_data->loop_info) - rs6000_density_test (cost_data); + { + adjust_vect_cost (cost_data); + rs6000_density_test (cost_data); + } /* Don't vectorize minimum-vectorization-factor, simple copy loops that require versioning for any reason. The vectorization is at diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index e933441b922..99e1fd7bdd0 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -3652,7 +3652,7 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, TODO: Build an expression that represents peel_iters for prologue and epilogue to be used in a run-time test. */ - if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) + if (LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo)) { peel_iters_prologue = 0; peel_iters_epilogue = 0; @@ -3663,45 +3663,145 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, peel_iters_epilogue += 1; stmt_info_for_cost *si; int j; - FOR_EACH_VEC_ELT (LOOP_VINFO_SCALAR_ITERATION_COST (loop_vinfo), - j, si) + FOR_EACH_VEC_ELT (LOOP_VINFO_SCALAR_ITERATION_COST (loop_vinfo), j, + si) (void) add_stmt_cost (loop_vinfo, target_cost_data, si->count, si->kind, si->stmt_info, si->vectype, si->misalign, vect_epilogue); } - /* Calculate how many masks we need to generate. */ - unsigned int num_masks = 0; - rgroup_controls *rgm; - unsigned int num_vectors_m1; - FOR_EACH_VEC_ELT (LOOP_VINFO_MASKS (loop_vinfo), num_vectors_m1, rgm) - if (rgm->type) - num_masks += num_vectors_m1 + 1; - gcc_assert (num_masks > 0); - - /* In the worst case, we need to generate each mask in the prologue - and in the loop body. One of the loop body mask instructions - replaces the comparison in the scalar loop, and since we don't - count the scalar comparison against the scalar body, we shouldn't - count that vector instruction against the vector body either. - - Sometimes we can use unpacks instead of generating prologue - masks and sometimes the prologue mask will fold to a constant, - so the actual prologue cost might be smaller. However, it's - simpler and safer to use the worst-case cost; if this ends up - being the tie-breaker between vectorizing or not, then it's - probably better not to vectorize. */ - (void) add_stmt_cost (loop_vinfo, - target_cost_data, num_masks, vector_stmt, - NULL, NULL_TREE, 0, vect_prologue); - (void) add_stmt_cost (loop_vinfo, - target_cost_data, num_masks - 1, vector_stmt, - NULL, NULL_TREE, 0, vect_body); - } - else if (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo)) - { - peel_iters_prologue = 0; - peel_iters_epilogue = 0; + if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) + { + /* Calculate how many masks we need to generate. */ + unsigned int num_masks = 0; + rgroup_controls *rgm; + unsigned int num_vectors_m1; + FOR_EACH_VEC_ELT (LOOP_VINFO_MASKS (loop_vinfo), num_vectors_m1, rgm) + if (rgm->type) + num_masks += num_vectors_m1 + 1; + gcc_assert (num_masks > 0); + + /* In the worst case, we need to generate each mask in the prologue + and in the loop body. One of the loop body mask instructions + replaces the comparison in the scalar loop, and since we don't + count the scalar comparison against the scalar body, we shouldn't + count that vector instruction against the vector body either. + + Sometimes we can use unpacks instead of generating prologue + masks and sometimes the prologue mask will fold to a constant, + so the actual prologue cost might be smaller. However, it's + simpler and safer to use the worst-case cost; if this ends up + being the tie-breaker between vectorizing or not, then it's + probably better not to vectorize. */ + (void) add_stmt_cost (loop_vinfo, target_cost_data, num_masks, + vector_stmt, NULL, NULL_TREE, 0, vect_prologue); + (void) add_stmt_cost (loop_vinfo, target_cost_data, num_masks - 1, + vector_stmt, NULL, NULL_TREE, 0, vect_body); + } + else + { + gcc_assert (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo)); + + /* Consider cost for LOOP_VINFO_PEELING_FOR_ALIGNMENT. */ + if (npeel < 0) + { + peel_iters_prologue = assumed_vf / 2; + /* See below, if peeled iterations are unknown, count a taken + branch and a not taken branch per peeled loop. */ + (void) add_stmt_cost (loop_vinfo, target_cost_data, 1, + cond_branch_taken, NULL, NULL_TREE, 0, + vect_prologue); + (void) add_stmt_cost (loop_vinfo, target_cost_data, 1, + cond_branch_not_taken, NULL, NULL_TREE, 0, + vect_prologue); + } + else + { + peel_iters_prologue = npeel; + if (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)) + /* See vect_get_known_peeling_cost, if peeled iterations are + known but number of scalar loop iterations are unknown, count + a taken branch per peeled loop. */ + (void) add_stmt_cost (loop_vinfo, target_cost_data, 1, + cond_branch_taken, NULL, NULL_TREE, 0, + vect_prologue); + } + + stmt_info_for_cost *si; + int j; + FOR_EACH_VEC_ELT (LOOP_VINFO_SCALAR_ITERATION_COST (loop_vinfo), j, + si) + (void) add_stmt_cost (loop_vinfo, target_cost_data, + si->count * peel_iters_prologue, si->kind, + si->stmt_info, si->vectype, si->misalign, + vect_prologue); + + /* Refer to the functions vect_set_loop_condition_partial_vectors + and vect_set_loop_controls_directly, we need to generate each + length in the prologue and in the loop body if required. Although + there are some possible optimization, we consider the worst case + here. */ + + /* For now we only operate length-based partial vectors on Power, + which has constant VF all the time, we need some tweakings below + if it doesn't hold in future. */ + gcc_assert (LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant ()); + + /* For wrap around checking. */ + tree compare_type = LOOP_VINFO_RGROUP_COMPARE_TYPE (loop_vinfo); + unsigned int compare_precision = TYPE_PRECISION (compare_type); + widest_int iv_limit = vect_iv_limit_for_partial_vectors (loop_vinfo); + + bool niters_known_p = LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo); + bool need_iterate_p + = (!LOOP_VINFO_EPILOGUE_P (loop_vinfo) + && !vect_known_niters_smaller_than_vf (loop_vinfo)); + + /* Init min/max, shift and minus cost relative to single scalar_stmt. + For now we only use length-based partial vectors on Power, target + specific cost tweaking may be needed for other ports in future. */ + unsigned int min_max_cost = 2; + unsigned int shift_cost = 1, minus_cost = 1; + + /* Init cost relative to single scalar_stmt. */ + unsigned int prol_cnt = 0; + unsigned int body_cnt = 0; + + rgroup_controls *rgc; + unsigned int num_vectors_m1; + FOR_EACH_VEC_ELT (LOOP_VINFO_LENS (loop_vinfo), num_vectors_m1, rgc) + if (rgc->type) + { + unsigned nitems = rgc->max_nscalars_per_iter * rgc->factor; + + /* Need one shift for niters_total computation. */ + if (!niters_known_p && nitems != 1) + prol_cnt += shift_cost; + + /* Need to handle wrap around. */ + if (iv_limit == -1 + || (wi::min_precision (iv_limit * nitems, UNSIGNED) + > compare_precision)) + prol_cnt += (min_max_cost + minus_cost); + + /* Need to handle batch limit excepting for the 1st one. */ + prol_cnt += (min_max_cost + minus_cost) * num_vectors_m1; + + unsigned int num_vectors = num_vectors_m1 + 1; + /* Need to set up lengths in prologue, only one MIN required + since start index is zero. */ + prol_cnt += min_max_cost * num_vectors; + + /* Need to update lengths in body for next iteration. */ + if (need_iterate_p) + body_cnt += (2 * min_max_cost + minus_cost) * num_vectors; + } + + (void) add_stmt_cost (loop_vinfo, target_cost_data, prol_cnt, + scalar_stmt, NULL, NULL_TREE, 0, vect_prologue); + (void) add_stmt_cost (loop_vinfo, target_cost_data, body_cnt, + scalar_stmt, NULL, NULL_TREE, 0, vect_body); + } } else if (npeel < 0) { @@ -3913,8 +4013,8 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, } /* ??? The "if" arm is written to handle all cases; see below for what - we would do for !LOOP_VINFO_FULLY_MASKED_P. */ - if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) + we would do for !LOOP_VINFO_USING_PARTIAL_VECTORS_P. */ + if (LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo)) { /* Rewriting the condition above in terms of the number of vector iterations (vniters) rather than the number of @@ -3941,7 +4041,7 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, dump_printf (MSG_NOTE, " Minimum number of vector iterations: %d\n", min_vec_niters); - if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) + if (LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo)) { /* Now that we know the minimum number of vector iterations, find the minimum niters for which the scalar cost is larger: @@ -3996,6 +4096,10 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, && min_profitable_iters < (assumed_vf + peel_iters_prologue)) /* We want the vectorized loop to execute at least once. */ min_profitable_iters = assumed_vf + peel_iters_prologue; + else if (min_profitable_iters < peel_iters_prologue) + /* For LOOP_VINFO_USING_PARTIAL_VECTORS_P, we need to ensure the + vectorized loop to execute at least once. */ + min_profitable_iters = peel_iters_prologue; if (dump_enabled_p ()) dump_printf_loc (MSG_NOTE, vect_location, @@ -4013,7 +4117,7 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, if (vec_outside_cost <= 0) min_profitable_estimate = 0; - else if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) + else if (LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo)) { /* This is a repeat of the code above, but with + SOC rather than - SOC. */ @@ -4025,7 +4129,7 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, if (outside_overhead > 0) min_vec_niters = outside_overhead / saving_per_viter + 1; - if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo)) + if (LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo)) { int threshold = (vec_inside_cost * min_vec_niters + vec_outside_cost