On Fri, 24 Nov 2023, Tamar Christina wrote:
> Good morning,
>
> This is a respun patch with a fix for VLA.
>
> This adds support to vectorizable_live_reduction to handle multiple exits by
> doing a search for which exit the live value should be materialized in.
>
> Additionally which value in the index we're after depends on whether the exit
> it's materialized in is an early exit or whether the loop's main exit is
> different from the loop's natural one (i.e. the one with the same src block as
> the latch).
>
> In those two cases we want the first rather than the last value as we're going
> to restart the iteration in the scalar loop. For VLA this means we need to
> reverse both the mask and vector since there's only a way to get the last
> active element and not the first.
>
> For inductions and multiple exits:
> - we test if the target will support vectorizing the induction
> - mark all inductions in the loop as relevant
> - for codegen of non-live inductions during codegen
> - induction during an early exit gets the first element rather than last.
>
> For reductions and multiple exits:
> - Reductions for early exits reduces the reduction definition statement
> rather than the reduction step. This allows us to get the value at the
> start of the iteration.
> - The peeling layout means that we just have to update one block, the merge
> block. We expect all the reductions to be the same but we leave it up to
> the value numbering to clean up any duplicate code as we iterate over all
> edges.
>
> These two changes fix the reduction codegen given before which has been added
> to the testsuite for early vect.
>
> Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
>
> Ok for master?
>
> Thanks,
> Tamar
>
> gcc/ChangeLog:
>
> * tree-vect-loop.cc (vectorizable_live_operation): Support early exits.
> (vect_analyze_loop_operations): Check if target supports vectorizing IV.
> (vect_transform_loop): Call vectorizable_live_operation for non-live
> inductions or reductions.
> (find_connected_edge, vectorizable_live_operation_1): New.
> (vect_create_epilog_for_reduction): Support reductions in early break.
> * tree-vect-stmts.cc (perm_mask_for_reverse): Expose.
> (vect_stmt_relevant_p): Mark all inductions when early break as being
> relevant.
> * tree-vectorizer.h (perm_mask_for_reverse): Expose.
> (vect_iv_increment_position): New.
> * tree-vect-loop-manip.cc (vect_iv_increment_position): Expose.
>
> --- inline copy of patch ---
>
> diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
> index
> 476be8a0bb6da2d06c4ca7052cb07bacecca60b1..1a4ba349fb6ae39c79401aecd4e7eaaaa9e2b8a0
> 100644
> --- a/gcc/tree-vect-loop-manip.cc
> +++ b/gcc/tree-vect-loop-manip.cc
> @@ -453,7 +453,7 @@ vect_adjust_loop_lens_control (tree iv_type, gimple_seq
> *seq,
> INSERT_AFTER is set to true if the increment should be inserted after
> *BSI. */
>
> -static void
> +void
> vect_iv_increment_position (edge loop_exit, gimple_stmt_iterator *bsi,
> bool *insert_after)
> {
> diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc
> index
> 8a50380de49bc12105be47ea1d8ee3cf1f2bdab4..b42318b2999e6a27e6983382190792602cb25af1
> 100644
> --- a/gcc/tree-vect-loop.cc
> +++ b/gcc/tree-vect-loop.cc
> @@ -2163,6 +2163,15 @@ vect_analyze_loop_operations (loop_vec_info loop_vinfo)
> ok = vectorizable_live_operation (loop_vinfo, stmt_info, NULL, NULL,
> -1, false, &cost_vec);
>
> + /* Check if we can perform the operation for early break if we force
> + the live operation. */
> + if (ok
> + && LOOP_VINFO_EARLY_BREAKS (loop_vinfo)
> + && !STMT_VINFO_LIVE_P (stmt_info)
> + && STMT_VINFO_DEF_TYPE (stmt_info) == vect_induction_def)
> + ok = vectorizable_live_operation (loop_vinfo, stmt_info, NULL, NULL,
> + -1, false, &cost_vec);
can you add && !PURE_SLP_STMT?
> +
> if (!ok)
> return opt_result::failure_at (phi,
> "not vectorized: relevant phi not "
> @@ -5842,6 +5851,10 @@ vect_create_partial_epilog (tree vec_def, tree
> vectype, code_helper code,
> SLP_NODE_INSTANCE is the SLP node instance containing SLP_NODE
> REDUC_INDEX says which rhs operand of the STMT_INFO is the reduction phi
> (counting from 0)
> + LOOP_EXIT is the edge to update in the merge block. In the case of a
> single
> + exit this edge is always the main loop exit.
> + MAIN_EXIT_P indicates whether we are updating the main exit or an
> alternate
> + exit. This determines whether we use the final or original value.
>
> This function:
> 1. Completes the reduction def-use cycles.
> @@ -5882,7 +5895,9 @@ static void
> vect_create_epilog_for_reduction (loop_vec_info loop_vinfo,
> stmt_vec_info stmt_info,
> slp_tree slp_node,
> - slp_instance slp_node_instance)
> + slp_instance slp_node_instance,
> + edge loop_exit,
> + bool main_exit_p = true)
isn't main_exit_p computable from 'loop_exit' by comparing that to
the one recorded in loop_vinfo? If so please do that instead of passing
in another argument.
> {
> stmt_vec_info reduc_info = info_for_reduction (loop_vinfo, stmt_info);
> gcc_assert (reduc_info->is_reduc_info);
> @@ -6053,7 +6068,7 @@ vect_create_epilog_for_reduction (loop_vec_info
> loop_vinfo,
> /* Create an induction variable. */
> gimple_stmt_iterator incr_gsi;
> bool insert_after;
> - standard_iv_increment_position (loop, &incr_gsi, &insert_after);
> + vect_iv_increment_position (loop_exit, &incr_gsi, &insert_after);
> create_iv (series_vect, PLUS_EXPR, vec_step, NULL_TREE, loop,
> &incr_gsi,
> insert_after, &indx_before_incr, &indx_after_incr);
>
> @@ -6132,23 +6147,30 @@ vect_create_epilog_for_reduction (loop_vec_info
> loop_vinfo,
> Store them in NEW_PHIS. */
> if (double_reduc)
> loop = outer_loop;
> - exit_bb = LOOP_VINFO_IV_EXIT (loop_vinfo)->dest;
> + /* We need to reduce values in all exits. */
> + exit_bb = loop_exit->dest;
> exit_gsi = gsi_after_labels (exit_bb);
> reduc_inputs.create (slp_node ? vec_num : ncopies);
> + vec <gimple *> vec_stmts;
> + if (main_exit_p)
> + vec_stmts = STMT_VINFO_VEC_STMTS (rdef_info);
> + else
> + vec_stmts = STMT_VINFO_VEC_STMTS (STMT_VINFO_REDUC_DEF (rdef_info));
both would be wrong for SLP, also I think you need to look at
STMT_VINFO_REDUC_DEF (vect_orig_stmt (stmt_info))? For SLP the
PHI SLP node is reached via slp_node_instance->reduc_phis.
I think an overall better structure would be to add a
vect_get_vect_def (stmt_vec_info, slp_tree, unsigned);
abstracting SLP and non-SLP and doing
for (unsigned i = 0; i < vec_num * ncopies; ++i)
{
def = vect_get_vect_def (stmt_info, slp_node, i);
...
}
and then adjusting stmt_info/slp_node according to main_exit_p?
(would be nice to transition stmt_info->vec_stmts to stmt_info->vec_defs)
That said, wherever possible please think of SLP ;)
> +
> for (unsigned i = 0; i < vec_num; i++)
> {
> gimple_seq stmts = NULL;
> if (slp_node)
> def = vect_get_slp_vect_def (slp_node, i);
> else
> - def = gimple_get_lhs (STMT_VINFO_VEC_STMTS (rdef_info)[0]);
> + def = gimple_get_lhs (vec_stmts[0]);
> for (j = 0; j < ncopies; j++)
> {
> tree new_def = copy_ssa_name (def);
> phi = create_phi_node (new_def, exit_bb);
> if (j)
> - def = gimple_get_lhs (STMT_VINFO_VEC_STMTS (rdef_info)[j]);
> - SET_PHI_ARG_DEF (phi, LOOP_VINFO_IV_EXIT (loop_vinfo)->dest_idx, def);
> + def = gimple_get_lhs (vec_stmts[j]);
> + SET_PHI_ARG_DEF (phi, loop_exit->dest_idx, def);
> new_def = gimple_convert (&stmts, vectype, new_def);
> reduc_inputs.quick_push (new_def);
> }
> @@ -6885,7 +6907,20 @@ vect_create_epilog_for_reduction (loop_vec_info
> loop_vinfo,
> FOR_EACH_IMM_USE_STMT (use_stmt, imm_iter, orig_name)
> {
> FOR_EACH_IMM_USE_ON_STMT (use_p, imm_iter)
> - SET_USE (use_p, scalar_result);
> + {
> + gimple *stmt = USE_STMT (use_p);
> + if (main_exit_p)
> + SET_USE (use_p, scalar_result);
> + else if (is_a <gphi *> (stmt))
> + {
> + /* If an early exit only update usages in the merge
> + block. */
shouldn't that be the only use at this point anyway? You only
update uses in PHI nodes btw. and you can use SET_USE, maybe
you wanted to check that
gimple_phi_arg_edge (stmt, phi_arg_index_from_use (use_p)) == merge_e
instead?
That said, the comment could be more precise
Are we calling vect_create_epilog_for_reduction for each early exit?
I suppose not?
> + edge merge_e = single_succ_edge (loop_exit->dest);
> + if (gimple_bb (stmt) != merge_e->dest)
> + continue;
> + SET_PHI_ARG_DEF (stmt, merge_e->dest_idx, scalar_result);
> + }
> + }
> update_stmt (use_stmt);
> }
> }
> @@ -10481,6 +10516,156 @@ vectorizable_induction (loop_vec_info loop_vinfo,
> return true;
> }
>
> +/* Function vectorizable_live_operation_1.
> +
> + helper function for vectorizable_live_operation. */
> +
> +tree
> +vectorizable_live_operation_1 (loop_vec_info loop_vinfo,
> + stmt_vec_info stmt_info, edge exit_e,
> + tree vectype, int ncopies, slp_tree slp_node,
> + tree bitsize, tree bitstart, tree vec_lhs,
> + tree lhs_type, bool restart_loop,
> + gimple_stmt_iterator *exit_gsi)
> +{
> + basic_block exit_bb = exit_e->dest;
> + gcc_assert (single_pred_p (exit_bb) || LOOP_VINFO_EARLY_BREAKS
> (loop_vinfo));
> +
> + tree vec_lhs_phi = copy_ssa_name (vec_lhs);
> + gimple *phi = create_phi_node (vec_lhs_phi, exit_bb);
> + for (unsigned i = 0; i < gimple_phi_num_args (phi); i++)
> + SET_PHI_ARG_DEF (phi, i, vec_lhs);
> +
> + gimple_seq stmts = NULL;
> + tree new_tree;
> + if (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo))
> + {
> + /* Emit:
> +
> + SCALAR_RES = VEC_EXTRACT <VEC_LHS, LEN + BIAS - 1>
> +
> + where VEC_LHS is the vectorized live-out result and MASK is
> + the loop mask for the final iteration. */
> + gcc_assert (ncopies == 1 && !slp_node);
> + gimple_seq tem = NULL;
> + gimple_stmt_iterator gsi = gsi_last (tem);
> + tree len = vect_get_loop_len (loop_vinfo, &gsi,
> + &LOOP_VINFO_LENS (loop_vinfo),
> + 1, vectype, 0, 0);
> +
> + /* BIAS - 1. */
> + signed char biasval = LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS (loop_vinfo);
> + tree bias_minus_one
> + = int_const_binop (MINUS_EXPR,
> + build_int_cst (TREE_TYPE (len), biasval),
> + build_one_cst (TREE_TYPE (len)));
> +
> + /* LAST_INDEX = LEN + (BIAS - 1). */
> + tree last_index = gimple_build (&stmts, PLUS_EXPR, TREE_TYPE (len),
> + len, bias_minus_one);
> +
> + /* This needs to implement extraction of the first index, but not sure
> + how the LEN stuff works. At the moment we shouldn't get here since
> + there's no LEN support for early breaks. But guard this so there's
> + no incorrect codegen. */
> + gcc_assert (!LOOP_VINFO_EARLY_BREAKS (loop_vinfo));
> +
> + /* SCALAR_RES = VEC_EXTRACT <VEC_LHS, LEN + BIAS - 1>. */
> + tree scalar_res
> + = gimple_build (&stmts, CFN_VEC_EXTRACT, TREE_TYPE (vectype),
> + vec_lhs_phi, last_index);
> +
> + /* Convert the extracted vector element to the scalar type. */
> + new_tree = gimple_convert (&stmts, lhs_type, scalar_res);
> + }
> + else if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo))
> + {
> + /* Emit:
> +
> + SCALAR_RES = EXTRACT_LAST <VEC_LHS, MASK>
> +
> + where VEC_LHS is the vectorized live-out result and MASK is
> + the loop mask for the final iteration. */
> + gcc_assert (!slp_node);
> + tree scalar_type = TREE_TYPE (STMT_VINFO_VECTYPE (stmt_info));
> + gimple_seq tem = NULL;
> + gimple_stmt_iterator gsi = gsi_last (tem);
> + tree mask = vect_get_loop_mask (loop_vinfo, &gsi,
> + &LOOP_VINFO_MASKS (loop_vinfo),
> + 1, vectype, 0);
> + tree scalar_res;
> +
> + /* For an inverted control flow with early breaks we want EXTRACT_FIRST
> + instead of EXTRACT_LAST. Emulate by reversing the vector and mask. */
> + if (restart_loop && LOOP_VINFO_EARLY_BREAKS (loop_vinfo))
> + {
> + /* First create the permuted mask. */
> + tree perm_mask = perm_mask_for_reverse (TREE_TYPE (mask));
> + tree perm_dest = copy_ssa_name (mask);
> + gimple *perm_stmt
> + = gimple_build_assign (perm_dest, VEC_PERM_EXPR, mask,
> + mask, perm_mask);
> + vect_finish_stmt_generation (loop_vinfo, stmt_info, perm_stmt,
> + &gsi);
> + mask = perm_dest;
> +
> + /* Then permute the vector contents. */
> + tree perm_elem = perm_mask_for_reverse (vectype);
> + perm_dest = copy_ssa_name (vec_lhs_phi);
> + perm_stmt
> + = gimple_build_assign (perm_dest, VEC_PERM_EXPR, vec_lhs_phi,
> + vec_lhs_phi, perm_elem);
> + vect_finish_stmt_generation (loop_vinfo, stmt_info, perm_stmt,
> + &gsi);
> + vec_lhs_phi = perm_dest;
> + }
> +
> + gimple_seq_add_seq (&stmts, tem);
> +
> + scalar_res = gimple_build (&stmts, CFN_EXTRACT_LAST, scalar_type,
> + mask, vec_lhs_phi);
> +
> + /* Convert the extracted vector element to the scalar type. */
> + new_tree = gimple_convert (&stmts, lhs_type, scalar_res);
> + }
> + else
> + {
> + tree bftype = TREE_TYPE (vectype);
> + if (VECTOR_BOOLEAN_TYPE_P (vectype))
> + bftype = build_nonstandard_integer_type (tree_to_uhwi (bitsize), 1);
> + new_tree = build3 (BIT_FIELD_REF, bftype, vec_lhs_phi, bitsize,
> bitstart);
> + new_tree = force_gimple_operand (fold_convert (lhs_type, new_tree),
> + &stmts, true, NULL_TREE);
> + }
> +
> + *exit_gsi = gsi_after_labels (exit_bb);
> + if (stmts)
> + gsi_insert_seq_before (exit_gsi, stmts, GSI_SAME_STMT);
> +
> + return new_tree;
> +}
> +
> +/* Find the edge that's the final one in the path from SRC to DEST and
> + return it. This edge must exist in at most one forwarder edge between.
> */
> +
> +static edge
> +find_connected_edge (edge src, basic_block dest)
> +{
> + if (src->dest == dest)
> + return src;
> +
> + edge e;
> + edge_iterator ei;
> +
> + FOR_EACH_EDGE (e, ei, dest->preds)
> + {
> + if (src->dest == e->src)
> + return e;
> + }
isn't that just find_edge (src->dest, dest)?
> + return NULL;
> +}
> +
> /* Function vectorizable_live_operation.
>
> STMT_INFO computes a value that is used outside the loop. Check if
> @@ -10505,7 +10690,8 @@ vectorizable_live_operation (vec_info *vinfo,
> stmt_vec_info stmt_info,
> int vec_entry = 0;
> poly_uint64 vec_index = 0;
>
> - gcc_assert (STMT_VINFO_LIVE_P (stmt_info));
> + gcc_assert (STMT_VINFO_LIVE_P (stmt_info)
> + || LOOP_VINFO_EARLY_BREAKS (loop_vinfo));
>
> /* If a stmt of a reduction is live, vectorize it via
> vect_create_epilog_for_reduction. vectorizable_reduction assessed
> @@ -10530,8 +10716,22 @@ vectorizable_live_operation (vec_info *vinfo,
> stmt_vec_info stmt_info,
> if (STMT_VINFO_REDUC_TYPE (reduc_info) == FOLD_LEFT_REDUCTION
> || STMT_VINFO_REDUC_TYPE (reduc_info) == EXTRACT_LAST_REDUCTION)
> return true;
> +
> + /* If early break we only have to materialize the reduction on the
> merge
> + block, but we have to find an alternate exit first. */
> + if (LOOP_VINFO_EARLY_BREAKS (loop_vinfo))
> + {
> + for (auto exit : get_loop_exit_edges (LOOP_VINFO_LOOP (loop_vinfo)))
> + if (exit != LOOP_VINFO_IV_EXIT (loop_vinfo))
> + vect_create_epilog_for_reduction (loop_vinfo, stmt_info,
> + slp_node, slp_node_instance,
> + exit, false);
Hmm, for each one. But we only need a single reduction epilogue, no?
In the merge block?
> + }
> +
> vect_create_epilog_for_reduction (loop_vinfo, stmt_info, slp_node,
> - slp_node_instance);
> + slp_node_instance,
> + LOOP_VINFO_IV_EXIT (loop_vinfo));
> +
> return true;
> }
>
> @@ -10683,103 +10883,63 @@ vectorizable_live_operation (vec_info *vinfo,
> stmt_vec_info stmt_info,
> lhs' = new_tree; */
>
> class loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
> - basic_block exit_bb = LOOP_VINFO_IV_EXIT (loop_vinfo)->dest;
> - gcc_assert (single_pred_p (exit_bb));
> -
> - tree vec_lhs_phi = copy_ssa_name (vec_lhs);
> - gimple *phi = create_phi_node (vec_lhs_phi, exit_bb);
> - SET_PHI_ARG_DEF (phi, LOOP_VINFO_IV_EXIT (loop_vinfo)->dest_idx,
> vec_lhs);
> -
> - gimple_seq stmts = NULL;
> - tree new_tree;
> - if (LOOP_VINFO_FULLY_WITH_LENGTH_P (loop_vinfo))
> - {
> - /* Emit:
> -
> - SCALAR_RES = VEC_EXTRACT <VEC_LHS, LEN + BIAS - 1>
> -
> - where VEC_LHS is the vectorized live-out result and MASK is
> - the loop mask for the final iteration. */
> - gcc_assert (ncopies == 1 && !slp_node);
> - gimple_seq tem = NULL;
> - gimple_stmt_iterator gsi = gsi_last (tem);
> - tree len
> - = vect_get_loop_len (loop_vinfo, &gsi,
> - &LOOP_VINFO_LENS (loop_vinfo),
> - 1, vectype, 0, 0);
> -
> - /* BIAS - 1. */
> - signed char biasval = LOOP_VINFO_PARTIAL_LOAD_STORE_BIAS (loop_vinfo);
> - tree bias_minus_one
> - = int_const_binop (MINUS_EXPR,
> - build_int_cst (TREE_TYPE (len), biasval),
> - build_one_cst (TREE_TYPE (len)));
> -
> - /* LAST_INDEX = LEN + (BIAS - 1). */
> - tree last_index = gimple_build (&stmts, PLUS_EXPR, TREE_TYPE (len),
> - len, bias_minus_one);
> -
> - /* SCALAR_RES = VEC_EXTRACT <VEC_LHS, LEN + BIAS - 1>. */
> - tree scalar_res
> - = gimple_build (&stmts, CFN_VEC_EXTRACT, TREE_TYPE (vectype),
> - vec_lhs_phi, last_index);
> -
> - /* Convert the extracted vector element to the scalar type. */
> - new_tree = gimple_convert (&stmts, lhs_type, scalar_res);
> - }
> - else if (LOOP_VINFO_FULLY_MASKED_P (loop_vinfo))
> - {
> - /* Emit:
> -
> - SCALAR_RES = EXTRACT_LAST <VEC_LHS, MASK>
> -
> - where VEC_LHS is the vectorized live-out result and MASK is
> - the loop mask for the final iteration. */
> - gcc_assert (ncopies == 1 && !slp_node);
> - tree scalar_type = TREE_TYPE (STMT_VINFO_VECTYPE (stmt_info));
> - gimple_seq tem = NULL;
> - gimple_stmt_iterator gsi = gsi_last (tem);
> - tree mask = vect_get_loop_mask (loop_vinfo, &gsi,
> - &LOOP_VINFO_MASKS (loop_vinfo),
> - 1, vectype, 0);
> - gimple_seq_add_seq (&stmts, tem);
> - tree scalar_res = gimple_build (&stmts, CFN_EXTRACT_LAST, scalar_type,
> - mask, vec_lhs_phi);
> -
> - /* Convert the extracted vector element to the scalar type. */
> - new_tree = gimple_convert (&stmts, lhs_type, scalar_res);
> - }
> - else
> - {
> - tree bftype = TREE_TYPE (vectype);
> - if (VECTOR_BOOLEAN_TYPE_P (vectype))
> - bftype = build_nonstandard_integer_type (tree_to_uhwi (bitsize), 1);
> - new_tree = build3 (BIT_FIELD_REF, bftype,
> - vec_lhs_phi, bitsize, bitstart);
> - new_tree = force_gimple_operand (fold_convert (lhs_type, new_tree),
> - &stmts, true, NULL_TREE);
> - }
> + /* Check if we have a loop where the chosen exit is not the main exit,
> + in these cases for an early break we restart the iteration the vector
> code
> + did. For the live values we want the value at the start of the
> iteration
> + rather than at the end. */
> + edge main_e = LOOP_VINFO_IV_EXIT (loop_vinfo);
> + bool restart_loop = LOOP_VINFO_EARLY_BREAKS_VECT_PEELED (loop_vinfo);
> + FOR_EACH_IMM_USE_STMT (use_stmt, imm_iter, lhs)
> + if (!is_gimple_debug (use_stmt)
> + && !flow_bb_inside_loop_p (loop, gimple_bb (use_stmt)))
> + {
> + basic_block use_bb = gimple_bb (use_stmt);
> + if (!is_a <gphi *> (use_stmt))
> + continue;
> + for (auto exit_e : get_loop_exit_edges (loop))
> + {
> + /* See if this exit leads to the value. */
> + edge dest_e = find_connected_edge (exit_e, use_bb);
> + if (!dest_e || PHI_ARG_DEF_FROM_EDGE (use_stmt, dest_e) != lhs)
> + continue;
>
> - gimple_stmt_iterator exit_gsi = gsi_after_labels (exit_bb);
> - if (stmts)
> - gsi_insert_seq_before (&exit_gsi, stmts, GSI_SAME_STMT);
> + gimple *tmp_vec_stmt = vec_stmt;
> + tree tmp_vec_lhs = vec_lhs;
> + tree tmp_bitstart = bitstart;
> + /* For early exit where the exit is not in the BB that leads
> + to the latch then we're restarting the iteration in the
> + scalar loop. So get the first live value. */
> + restart_loop = restart_loop || exit_e != main_e;
> + if (restart_loop)
> + {
> + tmp_vec_stmt = STMT_VINFO_VEC_STMTS (stmt_info)[0];
> + tmp_vec_lhs = gimple_get_lhs (tmp_vec_stmt);
> + tmp_bitstart = build_zero_cst (TREE_TYPE (bitstart));
> + }
>
> - /* Remove existing phis that copy from lhs and create copies
> - from new_tree. */
> - gimple_stmt_iterator gsi;
> - for (gsi = gsi_start_phis (exit_bb); !gsi_end_p (gsi);)
> - {
> - gimple *phi = gsi_stmt (gsi);
> - if ((gimple_phi_arg_def (phi, 0) == lhs))
> - {
> - remove_phi_node (&gsi, false);
> - tree lhs_phi = gimple_phi_result (phi);
> - gimple *copy = gimple_build_assign (lhs_phi, new_tree);
> - gsi_insert_before (&exit_gsi, copy, GSI_SAME_STMT);
> - }
> - else
> - gsi_next (&gsi);
> - }
> + gimple_stmt_iterator exit_gsi;
> + tree new_tree
> + = vectorizable_live_operation_1 (loop_vinfo, stmt_info,
> + exit_e, vectype, ncopies,
> + slp_node, bitsize,
> + tmp_bitstart, tmp_vec_lhs,
> + lhs_type, restart_loop,
> + &exit_gsi);
> +
> + /* Use the empty block on the exit to materialize the new stmts
> + so we can use update the PHI here. */
> + if (gimple_phi_num_args (use_stmt) == 1)
> + {
> + auto gsi = gsi_for_stmt (use_stmt);
> + remove_phi_node (&gsi, false);
> + tree lhs_phi = gimple_phi_result (use_stmt);
> + gimple *copy = gimple_build_assign (lhs_phi, new_tree);
> + gsi_insert_before (&exit_gsi, copy, GSI_SAME_STMT);
> + }
> + else
> + SET_PHI_ARG_DEF (use_stmt, dest_e->dest_idx, new_tree);
> + }
> + }
Difficult to see what changed due to the split out, guess it'll be ok.
> /* There a no further out-of-loop uses of lhs by LC-SSA construction.
> */
> FOR_EACH_IMM_USE_STMT (use_stmt, imm_iter, lhs)
> @@ -11797,6 +11957,21 @@ vect_transform_loop (loop_vec_info loop_vinfo,
> gimple *loop_vectorized_call)
> if (dump_enabled_p ())
> dump_printf_loc (MSG_NOTE, vect_location, "transform phi.\n");
> vect_transform_stmt (loop_vinfo, stmt_info, NULL, NULL, NULL);
> + /* If vectorizing early break we must also vectorize the use of
> + the PHIs as a live operation. */
> + if (LOOP_VINFO_EARLY_BREAKS (loop_vinfo)
> + && !STMT_VINFO_LIVE_P (stmt_info)
> + && STMT_VINFO_DEF_TYPE (stmt_info) == vect_induction_def)
> + {
> + if (dump_enabled_p ())
> + dump_printf_loc (MSG_NOTE, vect_location,
> + "----> vectorizing early break reduc or induc phi: %G",
> + (gimple *) phi);
> + bool done
> + = vectorizable_live_operation (loop_vinfo, stmt_info, NULL,
> + NULL, -1, true, NULL);
you should be able to amend can_vectorize_live_stmts instead by
adding || (LOOP_VINFO_EARLY_BREAKS (loop_vinfo) && vect_induction_def),
then we keep it at one place also where we'd handle the SLP case.
> + gcc_assert (done);
> + }
> }
> }
>
> diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
> index
> fe38beb4fa1d9f8593445354f56ba52e10a040cd..f1b6a13395f286f9997530bbe57cda3a00502f8f
> 100644
> --- a/gcc/tree-vect-stmts.cc
> +++ b/gcc/tree-vect-stmts.cc
> @@ -342,6 +342,7 @@ is_simple_and_all_uses_invariant (stmt_vec_info stmt_info,
> - it has uses outside the loop.
> - it has vdefs (it alters memory).
> - control stmts in the loop (except for the exit condition).
> + - it is an induction and we have multiple exits.
>
> CHECKME: what other side effects would the vectorizer allow? */
>
> @@ -399,6 +400,19 @@ vect_stmt_relevant_p (stmt_vec_info stmt_info,
> loop_vec_info loop_vinfo,
> }
> }
>
> + /* Check if it's an induction and multiple exits. In this case there will
> be
> + a usage later on after peeling which is needed for the alternate exit.
> */
> + if (LOOP_VINFO_EARLY_BREAKS (loop_vinfo)
> + && STMT_VINFO_DEF_TYPE (stmt_info) == vect_induction_def)
> + {
> + if (dump_enabled_p ())
> + dump_printf_loc (MSG_NOTE, vect_location,
> + "vec_stmt_relevant_p: induction forced for "
> + "early break.\n");
> + *relevant = vect_used_in_scope;
> +
I think you should instead set *live_p?
> + }
> +
> if (*live_p && *relevant == vect_unused_in_scope
> && !is_simple_and_all_uses_invariant (stmt_info, loop_vinfo))
> {
> @@ -1774,7 +1788,7 @@ compare_step_with_zero (vec_info *vinfo, stmt_vec_info
> stmt_info)
> /* If the target supports a permute mask that reverses the elements in
> a vector of type VECTYPE, return that mask, otherwise return null. */
>
> -static tree
> +tree
> perm_mask_for_reverse (tree vectype)
> {
> poly_uint64 nunits = TYPE_VECTOR_SUBPARTS (vectype);
> diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
> index
> 076a698eb4288f68e81f91923f7e3e8d181ad685..de673ae56eac455c9560a29d7f3792b6c3c49f3b
> 100644
> --- a/gcc/tree-vectorizer.h
> +++ b/gcc/tree-vectorizer.h
> @@ -2227,6 +2227,7 @@ extern bool vect_can_advance_ivs_p (loop_vec_info);
> extern void vect_update_inits_of_drs (loop_vec_info, tree, tree_code);
> extern edge vec_init_loop_exit_info (class loop *);
> extern bool vect_is_loop_exit_latch_pred (edge, class loop *);
> +extern void vect_iv_increment_position (edge, gimple_stmt_iterator *, bool
> *);
>
> /* In tree-vect-stmts.cc. */
> extern tree get_related_vectype_for_scalar_type (machine_mode, tree,
> @@ -2248,6 +2249,7 @@ extern bool vect_is_simple_use (vec_info *,
> stmt_vec_info, slp_tree,
> enum vect_def_type *,
> tree *, stmt_vec_info * = NULL);
> extern bool vect_maybe_update_slp_op_vectype (slp_tree, tree);
> +extern tree perm_mask_for_reverse (tree);
> extern bool supportable_widening_operation (vec_info*, code_helper,
> stmt_vec_info, tree, tree,
> code_helper*, code_helper*,
>
--
Richard Biener <rguent...@suse.de>
SUSE Software Solutions Germany GmbH,
Frankenstrasse 146, 90461 Nuernberg, Germany;
GF: Ivo Totev, Andrew McDonald, Werner Knoblich; (HRB 36809, AG Nuernberg)
