From: kugan <kugan.vivekanandarajah@linaro.org>
To: Bin Cheng <Bin.Cheng@arm.com>,
"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Cc: nd <nd@arm.com>
Subject: Re: [PATCH GCC][4/5]Improve loop distribution to handle hmmer
Date: Thu, 08 Jun 2017 02:48:00 -0000 [thread overview]
Message-ID: <2df529ae-803d-f955-cc6e-494a13ab7d6a@linaro.org> (raw)
In-Reply-To: <VI1PR0802MB2176D6EF8010E74F69340CD1E7F70@VI1PR0802MB2176.eurprd08.prod.outlook.com>
Hi Bin,
> +
> +/* In reduced dependence graph RDG for loop distribution, return true if
> + dependence between references DR1 and DR2 may create dependence cycle
> + and such dependence cycle can't be resolved by runtime alias check. */
> +
> +static bool
> +possible_data_dep_cycle_p (struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table,
> + data_reference_p dr1, data_reference_p dr2)
This name seems to be misleading a bit. It is basically dependence test
? Of course this can lead to a cycle but looks like possible_data_dep_p
would be better.
> +{
> + struct data_dependence_relation *ddr;
> +
> + /* Re-shuffle data-refs to be in topological order. */
> + if (rdg_vertex_for_stmt (rdg, DR_STMT (dr1))
> + > rdg_vertex_for_stmt (rdg, DR_STMT (dr2)))
> + std::swap (dr1, dr2);
> +
> + ddr = get_ddr (rdg, ddr_table, dr1, dr2);
> +
> + /* In case something goes wrong in data dependence analysis. */
> + if (ddr == NULL)
> + return true;
> + /* In case of no data dependence. */
> + else if (DDR_ARE_DEPENDENT (ddr) == chrec_known)
> + return false;
> + /* Or the data dependence can be resolved by compilation time alias
> + check. */
> + else if (!alias_sets_conflict_p (get_alias_set (DR_REF (dr1)),
> + get_alias_set (DR_REF (dr2))))
> + return false;
> + /* For unknown data dependence or known data dependence which can't be
> + expressed in classic distance vector, we check if it can be resolved
> + by runtime alias check. If yes, we still consider data dependence
> + as won't introduce data dependence cycle. */
> + else if (DDR_ARE_DEPENDENT (ddr) == chrec_dont_know
> + || DDR_NUM_DIST_VECTS (ddr) == 0)
You have already handled chrec_known above. Can you still have known
data dependence which can't be expressed in classic distance vector ?
> + return !runtime_alias_check_p (ddr, NULL, true);
> + else if (DDR_NUM_DIST_VECTS (ddr) > 1)
> + return true;
> + else if (DDR_REVERSED_P (ddr)
> + || lambda_vector_zerop (DDR_DIST_VECT (ddr, 0), 1))
> + return false;
> +
> + return true;
> +}
>
> /* Returns a partition with all the statements needed for computing
> the vertex V of the RDG, also including the loop exit conditions. */
>
> static partition *
> -build_rdg_partition_for_vertex (struct graph *rdg, int v)
> +build_rdg_partition_for_vertex (struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table, int v)
> {
> partition *partition = partition_alloc (NULL, NULL);
> auto_vec<int, 3> nodes;
> - unsigned i;
> + unsigned i, j;
> int x;
> + data_reference_p dr, dr1, dr2;
>
> graphds_dfs (rdg, &v, 1, &nodes, false, NULL);
>
> @@ -1005,8 +1262,43 @@ build_rdg_partition_for_vertex (struct graph *rdg, int v)
> bitmap_set_bit (partition->stmts, x);
> bitmap_set_bit (partition->loops,
> loop_containing_stmt (RDG_STMT (rdg, x))->num);
> +
> + for (j = 0; RDG_DATAREFS (rdg, x).iterate (j, &dr); ++j)
> + {
> + /* Partition can only be executed sequentially if there is any
> + unknown data reference. */
> + if (!DR_BASE_ADDRESS (dr) || !DR_OFFSET (dr)
> + || !DR_INIT (dr) || !DR_STEP (dr))
> + partition->type = PTYPE_SEQUENTIAL;
> +
> + if (DR_IS_READ (dr))
> + partition->reads.safe_push (dr);
> + else
> + partition->writes.safe_push (dr);
> + }
> }
>
> + if (partition->type == PTYPE_SEQUENTIAL)
> + return partition;
> +
> + /* Further check if any data dependence prevents us from executing the
> + partition parallelly. */
> + for (i = 0; partition->reads.iterate (i, &dr1); ++i)
> + for (j = 0; partition->writes.iterate (j, &dr2); ++j)
> + if (possible_data_dep_cycle_p (rdg, ddr_table, dr1, dr2))
> + {
> + partition->type = PTYPE_SEQUENTIAL;
> + return partition;
> + }
> +
> + for (i = 0; partition->writes.iterate (i, &dr1); ++i)
> + for (j = i + 1; partition->writes.iterate (j, &dr2); ++j)
> + if (possible_data_dep_cycle_p (rdg, ddr_table, dr1, dr2))
> + {
> + partition->type = PTYPE_SEQUENTIAL;
> + return partition;
> + }
> +
> return partition;
> }
>
> @@ -1014,7 +1306,9 @@ build_rdg_partition_for_vertex (struct graph *rdg, int v)
> For the moment we detect only the memset zero pattern. */
>
> static void
> -classify_partition (loop_p loop, struct graph *rdg, partition *partition)
> +classify_partition (loop_p loop, struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table,
> + partition *partition, bitmap stmt_in_all_partitions)
> {
> bitmap_iterator bi;
> unsigned i;
> @@ -1022,6 +1316,7 @@ classify_partition (loop_p loop, struct graph *rdg, partition *partition)
> data_reference_p single_load, single_store;
> bool volatiles_p = false;
> bool plus_one = false;
> + bool has_reduction = false;
>
> partition->kind = PKIND_NORMAL;
> partition->main_dr = NULL;
> @@ -1036,16 +1331,24 @@ classify_partition (loop_p loop, struct graph *rdg, partition *partition)
> if (gimple_has_volatile_ops (stmt))
> volatiles_p = true;
>
> - /* If the stmt has uses outside of the loop mark it as reduction. */
> + /* If the stmt is not included by all partitions and there is uses
> + outside of the loop, then mark the partition as reduction. */
> if (stmt_has_scalar_dependences_outside_loop (loop, stmt))
> {
> - partition->reduction_p = true;
> - return;
> + if (!bitmap_bit_p (stmt_in_all_partitions, i))
> + {
> + partition->reduction_p = true;
> + return;
> + }
> + has_reduction = true;
> }
> }
>
> /* Perform general partition disqualification for builtins. */
> if (volatiles_p
> + /* Simple workaround to prevent classifying the partition as builtin
> + if it contains any use outside of loop. */
> + || has_reduction
> || !flag_tree_loop_distribute_patterns)
> return;
>
> @@ -1143,44 +1446,27 @@ classify_partition (loop_p loop, struct graph *rdg, partition *partition)
> return;
> /* Now check that if there is a dependence this dependence is
> of a suitable form for memmove. */
> - vec<loop_p> loops = vNULL;
> - ddr_p ddr;
> - loops.safe_push (loop);
> - ddr = initialize_data_dependence_relation (single_load, single_store,
> - loops);
> - compute_affine_dependence (ddr, loop);
> + ddr_p ddr = get_ddr (rdg, ddr_table, single_load, single_store);
> if (DDR_ARE_DEPENDENT (ddr) == chrec_dont_know)
> - {
> - free_dependence_relation (ddr);
> - loops.release ();
> - return;
> - }
> + return;
> +
> if (DDR_ARE_DEPENDENT (ddr) != chrec_known)
> {
> if (DDR_NUM_DIST_VECTS (ddr) == 0)
> - {
> - free_dependence_relation (ddr);
> - loops.release ();
> - return;
> - }
> + return;
> +
> lambda_vector dist_v;
> FOR_EACH_VEC_ELT (DDR_DIST_VECTS (ddr), i, dist_v)
> {
> int dist = dist_v[index_in_loop_nest (loop->num,
> DDR_LOOP_NEST (ddr))];
> if (dist > 0 && !DDR_REVERSED_P (ddr))
> - {
> - free_dependence_relation (ddr);
> - loops.release ();
> - return;
> - }
> + return;
> }
> partition->kind = PKIND_MEMMOVE;
> }
> else
> partition->kind = PKIND_MEMCPY;
> - free_dependence_relation (ddr);
> - loops.release ();
> partition->main_dr = single_store;
> partition->secondary_dr = single_load;
> partition->niter = nb_iter;
> @@ -1188,30 +1474,16 @@ classify_partition (loop_p loop, struct graph *rdg, partition *partition)
> }
> }
>
> -/* For a data reference REF, return the declaration of its base
> - address or NULL_TREE if the base is not determined. */
> -
> -static tree
> -ref_base_address (data_reference_p dr)
> -{
> - tree base_address = DR_BASE_ADDRESS (dr);
> - if (base_address
> - && TREE_CODE (base_address) == ADDR_EXPR)
> - return TREE_OPERAND (base_address, 0);
> -
> - return base_address;
> -}
> -
> -/* Returns true when PARTITION1 and PARTITION2 have similar memory
> - accesses in RDG. */
> +/* Returns true when PARTITION1 and PARTITION2 share the same memory
> + accesses in RDG. This is a simple data reuse cost model. */
>
> static bool
> -similar_memory_accesses (struct graph *rdg, partition *partition1,
> - partition *partition2)
> +share_memory_accesses (struct graph *rdg,
> + partition *partition1, partition *partition2)
> {
> - unsigned i, j, k, l;
> - bitmap_iterator bi, bj;
> - data_reference_p ref1, ref2;
> + unsigned i, j;
> + data_reference_p dr1, dr2;
> + bitmap_iterator bi;
>
> /* First check whether in the intersection of the two partitions are
> any loads or stores. Common loads are the situation that happens
> @@ -1221,24 +1493,69 @@ similar_memory_accesses (struct graph *rdg, partition *partition1,
> || RDG_MEM_READS_STMT (rdg, i))
> return true;
>
> - /* Then check all data-references against each other. */
> - EXECUTE_IF_SET_IN_BITMAP (partition1->stmts, 0, i, bi)
> - if (RDG_MEM_WRITE_STMT (rdg, i)
> - || RDG_MEM_READS_STMT (rdg, i))
> - EXECUTE_IF_SET_IN_BITMAP (partition2->stmts, 0, j, bj)
> - if (RDG_MEM_WRITE_STMT (rdg, j)
> - || RDG_MEM_READS_STMT (rdg, j))
> - {
> - FOR_EACH_VEC_ELT (RDG_DATAREFS (rdg, i), k, ref1)
> - {
> - tree base1 = ref_base_address (ref1);
> - if (base1)
> - FOR_EACH_VEC_ELT (RDG_DATAREFS (rdg, j), l, ref2)
> - if (base1 == ref_base_address (ref2))
> - return true;
> - }
> - }
> + for (i = 0; partition1->reads.iterate (i, &dr1); ++i)
> + {
> + if (!DR_BASE_ADDRESS (dr1)
> + || !DR_OFFSET (dr1) || !DR_INIT (dr1) || !DR_STEP (dr1))
> + continue;
> +
> + for (j = 0; partition2->reads.iterate (j, &dr2); ++j)
> + {
> + if (!DR_BASE_ADDRESS (dr2)
> + || !DR_OFFSET (dr2) || !DR_INIT (dr2) || !DR_STEP (dr2))
> + continue;
> +
> + if (operand_equal_p (DR_BASE_ADDRESS (dr1), DR_BASE_ADDRESS (dr2), 0)
> + && operand_equal_p (DR_OFFSET (dr1), DR_OFFSET (dr2), 0)
> + && operand_equal_p (DR_INIT (dr1), DR_INIT (dr2), 0)
> + && operand_equal_p (DR_STEP (dr1), DR_STEP (dr2), 0))
> + return true;
> + }
> + for (j = 0; partition2->writes.iterate (j, &dr2); ++j)
> + {
> + if (!DR_BASE_ADDRESS (dr2)
> + || !DR_OFFSET (dr2) || !DR_INIT (dr2) || !DR_STEP (dr2))
> + continue;
> +
> + if (operand_equal_p (DR_BASE_ADDRESS (dr1), DR_BASE_ADDRESS (dr2), 0)
> + && operand_equal_p (DR_OFFSET (dr1), DR_OFFSET (dr2), 0)
> + && operand_equal_p (DR_INIT (dr1), DR_INIT (dr2), 0)
> + && operand_equal_p (DR_STEP (dr1), DR_STEP (dr2), 0))
> + return true;
> + }
> + }
> +
> + for (i = 0; partition1->writes.iterate (i, &dr1); ++i)
> + {
> + if (!DR_BASE_ADDRESS (dr1)
> + || !DR_OFFSET (dr1) || !DR_INIT (dr1) || !DR_STEP (dr1))
> + continue;
> +
> + for (j = 0; partition2->reads.iterate (j, &dr2); ++j)
> + {
> + if (!DR_BASE_ADDRESS (dr2)
> + || !DR_OFFSET (dr2) || !DR_INIT (dr2) || !DR_STEP (dr2))
> + continue;
>
> + if (operand_equal_p (DR_BASE_ADDRESS (dr1), DR_BASE_ADDRESS (dr2), 0)
> + && operand_equal_p (DR_OFFSET (dr1), DR_OFFSET (dr2), 0)
> + && operand_equal_p (DR_INIT (dr1), DR_INIT (dr2), 0)
> + && operand_equal_p (DR_STEP (dr1), DR_STEP (dr2), 0))
> + return true;
> + }
> + for (j = 0; partition2->writes.iterate (j, &dr2); ++j)
> + {
> + if (!DR_BASE_ADDRESS (dr2)
> + || !DR_OFFSET (dr2) || !DR_INIT (dr2) || !DR_STEP (dr2))
> + continue;
> +
> + if (operand_equal_p (DR_BASE_ADDRESS (dr1), DR_BASE_ADDRESS (dr2), 0)
> + && operand_equal_p (DR_OFFSET (dr1), DR_OFFSET (dr2), 0)
> + && operand_equal_p (DR_INIT (dr1), DR_INIT (dr2), 0)
> + && operand_equal_p (DR_STEP (dr1), DR_STEP (dr2), 0))
> + return true;
> + }
> + }
> return false;
> }
>
> @@ -1248,8 +1565,10 @@ similar_memory_accesses (struct graph *rdg, partition *partition1,
>
> static void
> rdg_build_partitions (struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table,
> vec<gimple *> starting_stmts,
> - vec<partition *> *partitions)
> + vec<partition *> *partitions,
> + bitmap stmt_in_all_partitions)
> {
> auto_bitmap processed;
> int i;
> @@ -1261,20 +1580,22 @@ rdg_build_partitions (struct graph *rdg,
>
> if (dump_file && (dump_flags & TDF_DETAILS))
> fprintf (dump_file,
> - "ldist asked to generate code for vertex %d\n", v);
> + "LDist asked to generate code for vertex %d\n", v);
>
> /* If the vertex is already contained in another partition so
> is the partition rooted at it. */
> if (bitmap_bit_p (processed, v))
> continue;
>
> - partition *partition = build_rdg_partition_for_vertex (rdg, v);
> + partition *partition = build_rdg_partition_for_vertex (rdg, ddr_table, v);
> bitmap_ior_into (processed, partition->stmts);
> + bitmap_and_into (stmt_in_all_partitions, partition->stmts);
>
> if (dump_file && (dump_flags & TDF_DETAILS))
> {
> - fprintf (dump_file, "ldist useful partition:\n");
> - dump_bitmap (dump_file, partition->stmts);
> + fprintf (dump_file, "LDist creates useful %s partition:\n",
> + partition->type == PTYPE_PARALLEL ? "parallel" : "sequent");
> + bitmap_print (dump_file, partition->stmts, " ", "\n");
> }
>
> partitions->safe_push (partition);
> @@ -1365,12 +1686,15 @@ partition_contains_all_rw (struct graph *rdg,
> }
>
> /* Compute partition dependence created by the data references in DRS1
> - and DRS2 and modify and return DIR according to that. */
> + and DRS2 and modify and return DIR according to that. If additional
> + dependence is introduced by possible alias between data references,
> + we record such data dependence relations in ALIAS_DDRS. */
>
> static int
> -pg_add_dependence_edges (struct graph *rdg, vec<loop_p> loops, int dir,
> +pg_add_dependence_edges (struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table, int dir,
> vec<data_reference_p> drs1,
> - vec<data_reference_p> drs2)
> + vec<data_reference_p> drs2, vec<ddr_p> *alias_ddrs)
> {
> data_reference_p dr1, dr2;
>
> @@ -1380,26 +1704,40 @@ pg_add_dependence_edges (struct graph *rdg, vec<loop_p> loops, int dir,
> for (int jj = 0; drs2.iterate (jj, &dr2); ++jj)
> {
> data_reference_p saved_dr1 = dr1;
> - int this_dir = 1;
> + int res, this_dir = 1;
> ddr_p ddr;
> - /* Re-shuffle data-refs to be in dominator order. */
> + /* Re-shuffle data-refs to be in topological order. */
> if (rdg_vertex_for_stmt (rdg, DR_STMT (dr1))
> > rdg_vertex_for_stmt (rdg, DR_STMT (dr2)))
> {
> std::swap (dr1, dr2);
> this_dir = -this_dir;
> }
> - ddr = initialize_data_dependence_relation (dr1, dr2, loops);
> - compute_affine_dependence (ddr, loops[0]);
> + ddr = get_ddr (rdg, ddr_table, dr1, dr2);
> if (DDR_ARE_DEPENDENT (ddr) == chrec_dont_know)
> - this_dir = 2;
> + {
> + res = data_ref_compare_tree (DR_BASE_ADDRESS (dr1),
> + DR_BASE_ADDRESS (dr2));
> + /* Be conservative. If data references are not well analyzed, or
> + the two data references have the same base address and offset,
> + add dependence and consider it alias to each other. In other
> + words, the dependence can not be resolved by runtime alias
> + check. */
> + if (!DR_BASE_ADDRESS (dr1) || !DR_OFFSET (dr1) || !DR_INIT (dr1)
> + || !DR_BASE_ADDRESS (dr2) || !DR_OFFSET (dr2) || !DR_INIT (dr2)
> + || !DR_STEP (dr1) || !tree_fits_uhwi_p (DR_STEP (dr1))
> + || !DR_STEP (dr2) || !tree_fits_uhwi_p (DR_STEP (dr2))
> + || res == 0)
> + this_dir = 2;
> + /* If it's possible to do runtime alias check, simply record the
> + ddr. */
> + else if (alias_ddrs != NULL)
> + alias_ddrs->safe_push (ddr);
If alias_ddrs is not passed (i.e. NULL), shouldn't this_ddr = 2. May be
add an assert for alias_ddrs ?
> + }
> else if (DDR_ARE_DEPENDENT (ddr) == NULL_TREE)
> {
> if (DDR_REVERSED_P (ddr))
> - {
> - std::swap (dr1, dr2);
> - this_dir = -this_dir;
> - }
> + this_dir = -this_dir;
> /* Known dependences can still be unordered througout the
> iteration space, see gcc.dg/tree-ssa/ldist-16.c. */
> if (DDR_NUM_DIST_VECTS (ddr) != 1)
> @@ -1407,16 +1745,13 @@ pg_add_dependence_edges (struct graph *rdg, vec<loop_p> loops, int dir,
> /* If the overlap is exact preserve stmt order. */
> else if (lambda_vector_zerop (DDR_DIST_VECT (ddr, 0), 1))
> ;
> + /* Else as the distance vector is lexicographic positive
> + swap the dependence direction. */
> else
> - {
> - /* Else as the distance vector is lexicographic positive
> - swap the dependence direction. */
> - this_dir = -this_dir;
> - }
> + this_dir = -this_dir;
> }
> else
> this_dir = 0;
> - free_dependence_relation (ddr);
> if (this_dir == 2)
> return 2;
> else if (dir == 0)
> @@ -1439,6 +1774,663 @@ pgcmp (const void *v1_, const void *v2_)
> return v2->post - v1->post;
> }
>
> +/* Given loop nest LOOPS and its reduced dependence graph RDG for loop
> + distribution, compute data dependence relations for all data refs in
> + DATAREFS. Record dependence relation in DEPENDENCES and DDR_TABLE. */
> +
> +static void
> +rdg_compute_data_dependence (struct graph *rdg, vec<loop_p> loops,
> + vec<data_reference_p> *datarefs,
> + vec<ddr_p> *dependences,
> + hash_table<ddr_entry_hasher> *ddr_table)
> +{
> + int i, j;
> + data_reference_p a, b;
> + struct data_dependence_relation *ddr;
> +
> + FOR_EACH_VEC_ELT ((*datarefs), i, a)
> + for (j = i + 1; datarefs->iterate (j, &b); j++)
> + if (DR_IS_WRITE (a) || DR_IS_WRITE (b))
> + {
> + ddr = initialize_data_dependence_relation (a, b, loops);
> + compute_affine_dependence (ddr, loops[0]);
> + dependences->safe_push (ddr);
> + /* Record data dependence relation in hash table for later
> + because it will be used multiple times. */
> + record_ddr (rdg, ddr_table, a, b, ddr);
> + }
> +}
> +
> +/* Data attached to vertices of partition dependence graph. */
> +struct pg_vdata
> +{
> + /* ID of the corresponding partition. */
> + int id;
> + /* The partition. */
> + struct partition *partition;
> +};
> +
> +/* Data attached to edges of partition dependence graph. */
> +struct pg_edata
> +{
> + /* If the dependence edge can be resolved by runtime alias check,
> + this vector contains data dependence relations for runtime alias
> + check. On the other hand, if the dependence edge is introduced
> + because of compilation time known data dependence, this vector
> + is contains nothing. */
> + vec<ddr_p> alias_ddrs;
> +};
> +
> +/* Callback data for traversing edges in graph. */
> +struct pg_edge_callback_data
> +{
> + /* Bitmap contains strong connected components should be merged. */
> + bitmap sccs_to_merge;
> + /* Array constains component information for all vertices. */
> + int *vertices_component;
> + /* Vector to record all data dependence relations which are needed
> + to break strong connected components by runtime alias checks. */
> + vec<ddr_p> *alias_ddrs;
> +};
> +
> +/* Initialize vertice's data for partition dependence graph PG with
> + PARTITIONS. */
> +static void
> +init_partition_graph_vertices (struct graph *pg,
> + vec<struct partition *> *partitions)
> +{
> + int i;
> + partition *partition;
> + struct pg_vdata *data;
> +
> + for (i = 0; partitions->iterate (i, &partition); ++i)
> + {
> + data = new pg_vdata;
> + pg->vertices[i].data = data;
> + data->id = i;
> + data->partition = partition;
> + }
> +}
> +
> +/* Add edge <I, J> to partition dependence graph PG. Attach vector of data
> + dependence relations to the EDGE if DDRS isn't NULL. */
> +
> +static void
> +add_partition_graph_edge (struct graph *pg, int i, int j, vec<ddr_p> *ddrs)
> +{
> + struct graph_edge *e = add_edge (pg, i, j);
> +
> + /* If the edge is attached with data dependence relations, it means this
> + dependence edge can be resolved by runtime alias checks. */
> + if (ddrs != NULL)
> + {
> + struct pg_edata *data = new pg_edata;
> +
> + gcc_assert (ddrs->length () > 0);
> + e->data = data;
> + data->alias_ddrs = vNULL;
> + data->alias_ddrs.safe_splice (*ddrs);
> + }
> +}
> +
> +/* Callback function for graph travesal algorithm. It returns true
> + if edge E shouldn't be considered in graph when traversing it. */
> +
> +static bool
> +pg_skip_alias_edge (struct graph_edge *e)
> +{
> + struct pg_edata *data = (struct pg_edata *)e->data;
> + return (data != NULL && data->alias_ddrs.length () > 0);
> +}
> +
> +/* Callback function freeing data attached to edge E of graph. */
> +
> +static void
> +free_partition_graph_edata_cb (struct graph *, struct graph_edge *e, void *)
> +{
> + if (e->data != NULL)
> + {
> + struct pg_edata *data = (struct pg_edata *)e->data;
> + data->alias_ddrs.release ();
> + delete data;
> + }
> +}
> +
> +/* Free data attached to vertice of partition dependence graph PG. */
> +
> +static void
> +free_partition_graph_vdata (struct graph *pg)
> +{
> + int i;
> + struct pg_vdata *data;
> +
> + for (i = 0; i < pg->n_vertices; ++i)
> + {
> + data = (struct pg_vdata *)pg->vertices[i].data;
> + delete data;
> + }
> +}
> +
> +/* Build and return partition dependence graph for PARTITIONS. RDG is
> + reduced dependence graph for the loop to be distributed. DDR_TABLE
> + is hash table contains all data dependence relations. ALIAS_DDRS is
> + a data dependence relations vector for temporary use. If ALIAS_DDRS
> + is NULL, dependence which can be resolved by runtime alias check will
> + not be considered, vice versa. */
> +
> +static struct graph *
> +build_partition_graph (struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table,
> + vec<struct partition *> *partitions,
> + vec<ddr_p> *alias_ddrs)
Why do you pass alias_ddrs to this. alias_ddrs does not pass any data or
return any. It can be defined in the function and used there. If you are
using this to indicate runtime alias check should be considered, you can
define a different bool for that ?
> +{
> + int i, j;
> + struct partition *partition1, *partition2;
> + graph *pg = new_graph (partitions->length ());
> +
> + init_partition_graph_vertices (pg, partitions);
> +
> + for (i = 0; partitions->iterate (i, &partition1); ++i)
> + {
> + for (j = i + 1; partitions->iterate (j, &partition2); ++j)
> + {
> + /* dependence direction - 0 is no dependence, -1 is back,
> + 1 is forth, 2 is both (we can stop then, merging will occur). */
> + int dir = 0;
> +
> + /* If the first partition has reduction, add back edge; if the
> + second partition has reduction, add forth edge. This makes
> + sure that reduction partition will be sorted as the last one. */
> + if (partition_reduction_p (partition1))
> + dir = -1;
> + else if (partition_reduction_p (partition2))
> + dir = 1;
> +
> + /* Cleanup the temporary vector. */
> + if (alias_ddrs != NULL)
> + alias_ddrs->truncate (0);
> +
> + dir = pg_add_dependence_edges (rdg, ddr_table, dir,
> + partition1->writes,
> + partition2->reads, alias_ddrs);
> + if (dir != 2)
> + dir = pg_add_dependence_edges (rdg, ddr_table, dir,
> + partition1->reads,
> + partition2->writes, alias_ddrs);
> + if (dir != 2)
> + dir = pg_add_dependence_edges (rdg, ddr_table, dir,
> + partition1->writes,
> + partition2->writes, alias_ddrs);
> +
> + /* Add edge to partition graph if there exists dependence. There
> + are two types of edges. One type edge is caused by compilation
> + time know dependence, this type can not be resolved by runtime
> + alias check. The other type can be resolved by runtime alias
> + check. */
> + if (dir == 1 || dir == 2
> + || (alias_ddrs != NULL && alias_ddrs->length () > 0))
> + {
> + /* Attach data dependence relations to edge that can be resolved
> + by runtime alias check. */
> + bool alias_edge_p = (dir != 1 && dir != 2);
> + add_partition_graph_edge (pg, i, j,
> + (alias_edge_p) ? alias_ddrs : NULL);
> + }
> + if (dir == -1 || dir == 2
> + || (alias_ddrs != NULL && alias_ddrs->length () > 0))
> + {
> + /* Attach data dependence relations to edge that can be resolved
> + by runtime alias check. */
> + bool alias_edge_p = (dir != -1 && dir != 2);
> + add_partition_graph_edge (pg, j, i,
> + (alias_edge_p) ? alias_ddrs : NULL);
> + }
> + }
> + }
> + return pg;
> +}
> +
> +/* Sort partitions in PG by post order and store them in PARTITIONS. */
> +
> +static void
> +sort_partitions_by_post_order (struct graph *pg,
> + vec<struct partition *> *partitions)
> +{
> + int i;
> + struct pg_vdata *data;
> +
> + /* Now order the remaining nodes in postorder. */
> + qsort (pg->vertices, pg->n_vertices, sizeof (vertex), pgcmp);
> + partitions->truncate (0);
> + for (i = 0; i < pg->n_vertices; ++i)
> + {
> + data = (struct pg_vdata *)pg->vertices[i].data;
> + if (data->partition)
> + partitions->safe_push (data->partition);
> + }
> +}
> +
> +/* Given reduced dependence graph RDG and data dependences in DDR_TABLE,
> + merge strong connected components of PARTITIONS. ALIAS_DDRS is a data
> + dependence relations vector for temporary use. If ALIAS_DDRS is NULL,
> + dependence which can be resolved by runtime alias check will not be
> + considered in building dependence graph for partitions, vice versa. */
> +
> +static void
> +merge_dep_scc_partitions (struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table,
> + vec<struct partition *> *partitions,
> + vec<ddr_p> *alias_ddrs)
> +{
> + struct partition *partition1, *partition2;
> + struct pg_vdata *data;
> + graph *pg = build_partition_graph (rdg, ddr_table, partitions, alias_ddrs);
> + int i, j, num_sccs = graphds_scc (pg, NULL);
> +
> + /* Strong connected compoenent means dependence cycle, we cannot distribute
> + them. So fuse them together. */
> + if ((unsigned) num_sccs < partitions->length ())
> + {
> + for (i = 0; i < num_sccs; ++i)
> + {
> + for (j = 0; partitions->iterate (j, &partition1); ++j)
> + if (pg->vertices[j].component == i)
> + break;
> + for (j = j + 1; partitions->iterate (j, &partition2); ++j)
> + if (pg->vertices[j].component == i)
> + {
> + partition_merge_into (partition1, partition2, FUSE_SAME_SCC);
> + (*partitions)[j] = NULL;
> + partition_free (partition2);
> + data = (struct pg_vdata *)pg->vertices[j].data;
> + data->partition = NULL;
> + }
> + }
> + sort_partitions_by_post_order (pg, partitions);
> + }
> + gcc_assert (partitions->length () == (unsigned)num_sccs);
> + free_partition_graph_vdata (pg);
> + free_graph (pg);
> +}
> +
> +/* Callback function for traversing edge E in graph G. DATA is private
> + callback data. */
> +
> +static void
> +pg_collect_alias_ddrs (struct graph *g, struct graph_edge *e, void *data)
> +{
> + int i, j, component;
> + struct pg_edge_callback_data *cbdata;
> + struct pg_edata *edata = (struct pg_edata *) e->data;
> +
> + /* If the edge doesn't have attached data dependence, it represents
> + compilation time known dependences. This type dependence cannot
> + be resolved by runtime alias check. */
> + if (edata == NULL || edata->alias_ddrs.length () == 0)
> + return;
> +
> + cbdata = (struct pg_edge_callback_data *) data;
> + i = e->src;
> + j = e->dest;
> + component = cbdata->vertices_component[i];
> + /* Vertices are topologically sorted according to compilation time
> + known dependences, so we can break strong connected components
> + by removing edges of the opposite direction, i.e, edges pointing
> + from vertice with smaller post number to vertice with bigger post
> + number. */
> + if (g->vertices[i].post < g->vertices[j].post
> + /* We only need to remove edges connecting vertices in the same
> + strong connected component to break it. */
> + && component == cbdata->vertices_component[j]
> + /* Check if we want to break the strong connected component or not. */
> + && !bitmap_bit_p (cbdata->sccs_to_merge, component))
> + cbdata->alias_ddrs->safe_splice (edata->alias_ddrs);
> +}
> +
> +/* This is the main function breaking strong conected components in
> + PARTITIONS giving reduced depdendence graph RDG and data dependences
> + in DDR_TABLE. Store data dependence relations for runtime alias
> + check in ALIAS_DDRS. */
> +
> +static void
> +break_alias_scc_partitions (struct graph *rdg,
> + hash_table<ddr_entry_hasher> *ddr_table,
> + vec<struct partition *> *partitions,
> + vec<ddr_p> *alias_ddrs)
I am not sure I understand this. When you are in
pg_add_dependence_edges, when you record alias_ddrs for runtime checking
you set this_dur io 1. That means you have broken the dpendency there
itself. Were you planning to keep this_dir = 2 and break the dependency
here ?
Thanks,
Kugan
> +{
> + int i, j, num_sccs, num_sccs_no_alias;
> + /* Build partition dependence graph. */
> + graph *pg = build_partition_graph (rdg, ddr_table, partitions, alias_ddrs);
> +
> + alias_ddrs->truncate (0);
> + /* Find strong connected components in the graph, with all dependence edges
> + considered. */
> + num_sccs = graphds_scc (pg, NULL);
> + /* All SCCs now can be broken by runtime alias checks because SCCs caused by
> + compilation time known dependences are merged before this function. */
> + if ((unsigned) num_sccs < partitions->length ())
> + {
> + struct pg_edge_callback_data cbdata;
> + auto_bitmap sccs_to_merge;
> + auto_vec<enum partition_type> scc_types;
> + struct partition *partition, *first;
> +
> + /* If all paritions in a SCC has the same type, we can simply merge the
> + SCC. This loop finds out such SCCS and record them in bitmap. */
> + bitmap_set_range (sccs_to_merge, 0, (unsigned) num_sccs);
> + for (i = 0; i < num_sccs; ++i)
> + {
> + for (j = 0; partitions->iterate (j, &first); ++j)
> + if (pg->vertices[j].component == i)
> + break;
> + for (++j; partitions->iterate (j, &partition); ++j)
> + {
> + if (pg->vertices[j].component != i)
> + continue;
> +
> + if (first->type != partition->type)
> + {
> + bitmap_clear_bit (sccs_to_merge, i);
> + break;
> + }
> + }
> + }
> +
> + /* Initialize callback data for traversing. */
> + cbdata.sccs_to_merge = sccs_to_merge;
> + cbdata.alias_ddrs = alias_ddrs;
> + cbdata.vertices_component = XNEWVEC (int, pg->n_vertices);
> + /* Record the component information which will be corrupted by next
> + graph scc finding call. */
> + for (i = 0; i < pg->n_vertices; ++i)
> + cbdata.vertices_component[i] = pg->vertices[i].component;
> +
> + /* Collect data dependences for runtime alias checks to break SCCs. */
> + if (bitmap_count_bits (sccs_to_merge) != (unsigned) num_sccs)
> + {
> + /* Run SCC finding algorithm again, with alias dependence edges
> + skipped. This is to topologically sort paritions according to
> + compilation time known dependence. Note the topological order
> + is stored in the form of pg's post order number. */
> + num_sccs_no_alias = graphds_scc (pg, NULL, pg_skip_alias_edge);
> + gcc_assert (partitions->length () == (unsigned) num_sccs_no_alias);
> + /* With topological order, we can construct two subgraphs L and R.
> + L contains edge <x, y> where x < y in terms of post order, while
> + R contains edge <x, y> where x > y. Edges for compilation time
> + known dependence all fall in R, so we break SCCs by removing all
> + (alias) edges of in subgraph L. */
> + for_each_edge (pg, pg_collect_alias_ddrs, &cbdata);
> + }
> +
> + /* For SCC that doesn't need to be broken, merge it. */
> + for (i = 0; i < num_sccs; ++i)
> + {
> + if (!bitmap_bit_p (sccs_to_merge, i))
> + continue;
> +
> + for (j = 0; partitions->iterate (j, &first); ++j)
> + if (cbdata.vertices_component[j] == i)
> + break;
> + for (++j; partitions->iterate (j, &partition); ++j)
> + {
> + struct pg_vdata *data;
> +
> + if (cbdata.vertices_component[j] != i)
> + continue;
> +
> + partition_merge_into (first, partition, FUSE_SAME_SCC);
> + (*partitions)[j] = NULL;
> + partition_free (partition);
> + data = (struct pg_vdata *)pg->vertices[j].data;
> + gcc_assert (data->id == j);
> + data->partition = NULL;
> + }
> + }
> + }
> +
> + sort_partitions_by_post_order (pg, partitions);
> + free_partition_graph_vdata (pg);
> + for_each_edge (pg, free_partition_graph_edata_cb, NULL);
> + free_graph (pg);
> +
> + if (dump_file && (dump_flags & TDF_DETAILS))
> + {
> + fprintf (dump_file, "Possible alias data dependence to break:\n");
> + dump_data_dependence_relations (dump_file, *alias_ddrs);
> + }
> +}
> +
> +/* Compute and return an expression whose value is the segment length which
> + will be accessed by DR in NITERS iterations. */
> +
> +static tree
> +data_ref_segment_size (struct data_reference *dr, tree niters)
> +{
> + tree segment_length;
> +
> + if (integer_zerop (DR_STEP (dr)))
> + segment_length = TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (dr)));
> + else
> + segment_length = size_binop (MULT_EXPR,
> + fold_convert (sizetype, DR_STEP (dr)),
> + fold_convert (sizetype, niters));
> +
> + return segment_length;
> +}
> +
> +/* Return true if LOOP's latch is dominated by statement for data reference
> + DR. */
> +
> +static inline bool
> +latch_dominated_by_data_ref (struct loop *loop, data_reference *dr)
> +{
> + return dominated_by_p (CDI_DOMINATORS, single_exit (loop)->src,
> + gimple_bb (DR_STMT (dr)));
> +}
> +
> +/* Compute alias check pairs and store them in COMP_ALIAS_PAIRS for LOOP's
> + data dependence relations ALIAS_DDRS. */
> +
> +static void
> +compute_alias_check_pairs (struct loop *loop, vec<ddr_p> *alias_ddrs,
> + vec<dr_with_seg_len_pair_t> *comp_alias_pairs)
> +{
> + unsigned int i;
> + unsigned HOST_WIDE_INT factor = 1;
> + tree niters_plus_one, niters = number_of_latch_executions (loop);
> +
> + gcc_assert (niters != NULL_TREE && niters != chrec_dont_know);
> + niters = fold_convert (sizetype, niters);
> + niters_plus_one = size_binop (PLUS_EXPR, niters, size_one_node);
> +
> + if (dump_file && (dump_flags & TDF_DETAILS))
> + fprintf (dump_file, "Creating alias check pairs:\n");
> +
> + /* Iterate all data dependence relations and compute alias check pairs. */
> + for (i = 0; i < alias_ddrs->length (); i++)
> + {
> + ddr_p ddr = (*alias_ddrs)[i];
> + struct data_reference *dr_a = DDR_A (ddr);
> + struct data_reference *dr_b = DDR_B (ddr);
> + tree seg_length_a, seg_length_b;
> + int comp_res = data_ref_compare_tree (DR_BASE_ADDRESS (dr_a),
> + DR_BASE_ADDRESS (dr_b));
> +
> + if (comp_res == 0)
> + comp_res = data_ref_compare_tree (DR_OFFSET (dr_a), DR_OFFSET (dr_b));
> + gcc_assert (comp_res != 0);
> +
> + if (latch_dominated_by_data_ref (loop, dr_a))
> + seg_length_a = data_ref_segment_size (dr_a, niters_plus_one);
> + else
> + seg_length_a = data_ref_segment_size (dr_a, niters);
> +
> + if (latch_dominated_by_data_ref (loop, dr_b))
> + seg_length_b = data_ref_segment_size (dr_b, niters_plus_one);
> + else
> + seg_length_b = data_ref_segment_size (dr_b, niters);
> +
> + dr_with_seg_len_pair_t dr_with_seg_len_pair
> + (dr_with_seg_len (dr_a, seg_length_a),
> + dr_with_seg_len (dr_b, seg_length_b));
> +
> + /* Canonicalize pairs by sorting the two DR members. */
> + if (comp_res > 0)
> + std::swap (dr_with_seg_len_pair.first, dr_with_seg_len_pair.second);
> +
> + comp_alias_pairs->safe_push (dr_with_seg_len_pair);
> + }
> +
> + if (tree_fits_uhwi_p (niters))
> + factor = tree_to_uhwi (niters);
> +
> + /* Prune alias check pairs. */
> + prune_runtime_alias_test_list (comp_alias_pairs, factor);
> + if (dump_file && (dump_flags & TDF_DETAILS))
> + fprintf (dump_file,
> + "Improved number of alias checks from %d to %d\n",
> + alias_ddrs->length (), comp_alias_pairs->length ());
> +}
> +
> +/* Given data dependence relations in ALIAS_DDRS, generate runtime alias
> + checks and version LOOP under condition of these runtime alias checks. */
> +
> +static void
> +version_loop_by_alias_check (struct loop *loop, vec<ddr_p> *alias_ddrs)
> +{
> + unsigned then_prob, else_prob, then_scale, else_scale;
> + basic_block cond_bb;
> + struct loop *nloop;
> + tree lhs, arg0, cond_expr = NULL_TREE;
> + gimple_seq cond_stmts = NULL;
> + gimple *stmt;
> + auto_vec<dr_with_seg_len_pair_t> comp_alias_pairs;
> +
> + /* Generate code for runtime alias checks if necessary. */
> + if (alias_ddrs->length () > 0)
> + {
> + compute_alias_check_pairs (loop, alias_ddrs, &comp_alias_pairs);
> + create_runtime_alias_checks (loop, &comp_alias_pairs, &cond_expr);
> + cond_expr = force_gimple_operand_1 (cond_expr, &cond_stmts,
> + is_gimple_condexpr, NULL_TREE);
> + then_prob = 9 * REG_BR_PROB_BASE / 10;
> + else_prob = REG_BR_PROB_BASE - then_prob;
> + then_scale = 9 * REG_BR_PROB_BASE / 10;
> + else_scale = REG_BR_PROB_BASE - then_scale;
> + }
> + else
> + {
> + cond_expr = boolean_true_node;
> + /* Use REG_BR_PROB_BASE for both branches since only one branch
> + will be kept in the end. */
> + then_prob = REG_BR_PROB_BASE;
> + else_prob = REG_BR_PROB_BASE;
> + then_scale = REG_BR_PROB_BASE;
> + else_scale = REG_BR_PROB_BASE;
> + }
> +
> + /* Depend on vectorizer to fold IFN_LOOP_DIST_ALIAS. */
> + if (flag_tree_loop_vectorize)
> + {
> + /* Generate internal function call for loop distribution alias check. */
> + arg0 = build_int_cst (integer_type_node, loop->num);
> + stmt = gimple_build_call_internal (IFN_LOOP_DIST_ALIAS,
> + 2, arg0, cond_expr);
> + lhs = make_ssa_name (boolean_type_node);
> + gimple_call_set_lhs (stmt, lhs);
> + gimple_seq_add_stmt (&cond_stmts, stmt);
> + }
> + else
> + lhs = cond_expr;
> +
> + if (dump_file && (dump_flags & TDF_DETAILS))
> + fprintf (dump_file,
> + "Version loop <%d> with runtime alias check\n", loop->num);
> +
> + initialize_original_copy_tables ();
> + nloop = loop_version (loop, lhs, &cond_bb, then_prob,
> + else_prob, then_scale, else_scale, true);
> + free_original_copy_tables ();
> + nloop->aux = (void *)nloop;
> + /* Record the original loop number in newly generated loops. */
> + nloop->ldist_alias_id = loop->num;
> + nloop->dont_vectorize = true;
> + nloop->force_vectorize = false;
> +
> + if (cond_stmts)
> + {
> + gimple_stmt_iterator cond_gsi = gsi_last_bb (cond_bb);
> + gsi_insert_seq_before (&cond_gsi, cond_stmts, GSI_SAME_STMT);
> + }
> + update_ssa (TODO_update_ssa);
> +}
> +
> +/* Return true if loop versioning is needed to distrubute PARTITIONS.
> + ALIAS_DDRS are data dependence relations for runtime alias check. */
> +
> +static inline bool
> +version_for_distribution_p (vec<struct partition *> *partitions,
> + vec<ddr_p> *alias_ddrs)
> +{
> + unsigned i;
> + struct partition *partition;
> +
> + /* No need to version loop if we have only one partition. */
> + if (partitions->length () == 1)
> + return false;
> +
> + /* Need to version loop if runtime alias check is necessary. */
> + if (alias_ddrs->length () > 0)
> + return true;
> +
> + /* Don't version the loop with call to IFN_LOOP_DIST_ALIAS if
> + vectorizer is not enable because no other pass can fold it. */
> + if (!flag_tree_loop_vectorize)
> + return false;
> +
> + /* Don't version loop if any partition is builtin. */
> + for (i = 0; partitions->iterate (i, &partition); ++i)
> + {
> + if (partition->kind != PKIND_NORMAL)
> + break;
> + }
> + return (i == partitions->length ());
> +}
> +
> +/* Fuse all partitions if necessary before finalizing distribution. */
> +
> +static void
> +finalize_partitions (vec<struct partition *> *partitions,
> + vec<ddr_p> *alias_ddrs)
> +{
> + unsigned i;
> + struct partition *a, *partition;
> +
> + if (partitions->length () == 1
> + || alias_ddrs->length () > 0)
> + return;
> +
> + a = (*partitions)[0];
> + if (a->kind != PKIND_NORMAL)
> + return;
> +
> + for (i = 1; partitions->iterate (i, &partition); ++i)
> + {
> + /* Don't fuse if partition has different type or it is a builtin. */
> + if (partition->type != a->type
> + || partition->kind != PKIND_NORMAL)
> + return;
> + }
> +
> + /* Fuse all partitions. */
> + for (i = 1; partitions->iterate (i, &partition); ++i)
> + {
> + partition_merge_into (a, partition, FUSE_FINALIZE);
> + partition_free (partition);
> + }
> + partitions->truncate (1);
> +}
> +
> /* Distributes the code from LOOP in such a way that producer
> statements are placed before consumer statements. Tries to separate
> only the statements from STMTS into separate loops.
> @@ -1453,8 +2445,6 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> partition *partition;
> bool any_builtin;
> int i, nbp;
> - graph *pg = NULL;
> - int num_sccs = 1;
>
> *destroy_p = false;
> *nb_calls = 0;
> @@ -1462,7 +2452,9 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> if (!find_loop_nest (loop, &loop_nest))
> return 0;
>
> - rdg = build_rdg (loop_nest, cd);
> + vec<data_reference_p> datarefs;
> + datarefs.create (10);
> + rdg = build_rdg (loop_nest, cd, &datarefs);
> if (!rdg)
> {
> if (dump_file && (dump_flags & TDF_DETAILS))
> @@ -1470,19 +2462,35 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> "Loop %d not distributed: failed to build the RDG.\n",
> loop->num);
>
> + free_data_refs (datarefs);
> return 0;
> }
>
> if (dump_file && (dump_flags & TDF_DETAILS))
> dump_rdg (dump_file, rdg);
>
> + auto_vec<ddr_p> alias_ddrs;
> + vec<ddr_p> dependences;
> + dependences.create (10);
> + hash_table<ddr_entry_hasher> ddr_table (15);
> + rdg_compute_data_dependence (rdg, loop_nest, &datarefs,
> + &dependences, &ddr_table);
> +
> + /* We can't do runtime alias check if niter is unknown for loop. */
> + tree niters = number_of_latch_executions (loop);
> + bool rt_alias_check_p = (niters != NULL_TREE && niters != chrec_dont_know);
> +
> + auto_bitmap stmt_in_all_partitions;
> auto_vec<struct partition *, 3> partitions;
> - rdg_build_partitions (rdg, stmts, &partitions);
> + bitmap_set_range (stmt_in_all_partitions, 0, rdg->n_vertices);
> + rdg_build_partitions (rdg, &ddr_table, stmts,
> + &partitions, stmt_in_all_partitions);
>
> any_builtin = false;
> FOR_EACH_VEC_ELT (partitions, i, partition)
> {
> - classify_partition (loop, rdg, partition);
> + classify_partition (loop, rdg, &ddr_table,
> + partition, stmt_in_all_partitions);
> any_builtin |= partition_builtin_p (partition);
> }
>
> @@ -1508,13 +2516,7 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> for (++i; partitions.iterate (i, &partition); ++i)
> if (!partition_builtin_p (partition))
> {
> - if (dump_file && (dump_flags & TDF_DETAILS))
> - {
> - fprintf (dump_file, "fusing non-builtin partitions\n");
> - dump_bitmap (dump_file, into->stmts);
> - dump_bitmap (dump_file, partition->stmts);
> - }
> - partition_merge_into (into, partition);
> + partition_merge_into (into, partition, FUSE_NON_BUILTIN);
> partitions.unordered_remove (i);
> partition_free (partition);
> i--;
> @@ -1530,21 +2532,14 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> for (i = i + 1; partitions.iterate (i, &partition); ++i)
> if (partition_reduction_p (partition))
> {
> - if (dump_file && (dump_flags & TDF_DETAILS))
> - {
> - fprintf (dump_file, "fusing partitions\n");
> - dump_bitmap (dump_file, into->stmts);
> - dump_bitmap (dump_file, partition->stmts);
> - fprintf (dump_file, "because they have reductions\n");
> - }
> - partition_merge_into (into, partition);
> + partition_merge_into (into, partition, FUSE_REDUCTION);
> partitions.unordered_remove (i);
> partition_free (partition);
> i--;
> }
>
> - /* Apply our simple cost model - fuse partitions with similar
> - memory accesses. */
> + /* Apply our simple cost model - fuse partitions with shared memory
> + accesses. */
> for (i = 0; partitions.iterate (i, &into); ++i)
> {
> bool changed = false;
> @@ -1553,17 +2548,9 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> for (int j = i + 1;
> partitions.iterate (j, &partition); ++j)
> {
> - if (similar_memory_accesses (rdg, into, partition))
> + if (share_memory_accesses (rdg, into, partition))
> {
> - if (dump_file && (dump_flags & TDF_DETAILS))
> - {
> - fprintf (dump_file, "fusing partitions\n");
> - dump_bitmap (dump_file, into->stmts);
> - dump_bitmap (dump_file, partition->stmts);
> - fprintf (dump_file, "because they have similar "
> - "memory accesses\n");
> - }
> - partition_merge_into (into, partition);
> + partition_merge_into (into, partition, FUSE_SHARE_REF);
> partitions.unordered_remove (j);
> partition_free (partition);
> j--;
> @@ -1581,111 +2568,15 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> /* Build the partition dependency graph. */
> if (partitions.length () > 1)
> {
> - pg = new_graph (partitions.length ());
> - struct pgdata {
> - struct partition *partition;
> - vec<data_reference_p> writes;
> - vec<data_reference_p> reads;
> - };
> -#define PGDATA(i) ((pgdata *)(pg->vertices[i].data))
> - for (i = 0; partitions.iterate (i, &partition); ++i)
> - {
> - vertex *v = &pg->vertices[i];
> - pgdata *data = new pgdata;
> - data_reference_p dr;
> - /* FIXME - leaks. */
> - v->data = data;
> - bitmap_iterator bi;
> - unsigned j;
> - data->partition = partition;
> - data->reads = vNULL;
> - data->writes = vNULL;
> - EXECUTE_IF_SET_IN_BITMAP (partition->stmts, 0, j, bi)
> - for (int k = 0; RDG_DATAREFS (rdg, j).iterate (k, &dr); ++k)
> - if (DR_IS_READ (dr))
> - data->reads.safe_push (dr);
> - else
> - data->writes.safe_push (dr);
> - }
> - struct partition *partition1, *partition2;
> - for (i = 0; partitions.iterate (i, &partition1); ++i)
> - for (int j = i + 1; partitions.iterate (j, &partition2); ++j)
> - {
> - /* dependence direction - 0 is no dependence, -1 is back,
> - 1 is forth, 2 is both (we can stop then, merging will occur). */
> - int dir = 0;
> - dir = pg_add_dependence_edges (rdg, loop_nest, dir,
> - PGDATA(i)->writes,
> - PGDATA(j)->reads);
> - if (dir != 2)
> - dir = pg_add_dependence_edges (rdg, loop_nest, dir,
> - PGDATA(i)->reads,
> - PGDATA(j)->writes);
> - if (dir != 2)
> - dir = pg_add_dependence_edges (rdg, loop_nest, dir,
> - PGDATA(i)->writes,
> - PGDATA(j)->writes);
> - if (dir == 1 || dir == 2)
> - add_edge (pg, i, j);
> - if (dir == -1 || dir == 2)
> - add_edge (pg, j, i);
> - }
> -
> - /* Add edges to the reduction partition (if any) to force it last. */
> - unsigned j;
> - for (j = 0; partitions.iterate (j, &partition); ++j)
> - if (partition_reduction_p (partition))
> - break;
> - if (j < partitions.length ())
> - {
> - for (unsigned i = 0; partitions.iterate (i, &partition); ++i)
> - if (i != j)
> - add_edge (pg, i, j);
> - }
> -
> - /* Compute partitions we cannot separate and fuse them. */
> - num_sccs = graphds_scc (pg, NULL);
> - for (i = 0; i < num_sccs; ++i)
> - {
> - struct partition *first;
> - int j;
> - for (j = 0; partitions.iterate (j, &first); ++j)
> - if (pg->vertices[j].component == i)
> - break;
> - for (j = j + 1; partitions.iterate (j, &partition); ++j)
> - if (pg->vertices[j].component == i)
> - {
> - if (dump_file && (dump_flags & TDF_DETAILS))
> - {
> - fprintf (dump_file, "fusing partitions\n");
> - dump_bitmap (dump_file, first->stmts);
> - dump_bitmap (dump_file, partition->stmts);
> - fprintf (dump_file, "because they are in the same "
> - "dependence SCC\n");
> - }
> - partition_merge_into (first, partition);
> - partitions[j] = NULL;
> - partition_free (partition);
> - PGDATA (j)->partition = NULL;
> - }
> - }
> -
> - /* Now order the remaining nodes in postorder. */
> - qsort (pg->vertices, pg->n_vertices, sizeof (vertex), pgcmp);
> - partitions.truncate (0);
> - for (i = 0; i < pg->n_vertices; ++i)
> - {
> - pgdata *data = PGDATA (i);
> - if (data->partition)
> - partitions.safe_push (data->partition);
> - data->reads.release ();
> - data->writes.release ();
> - delete data;
> - }
> - gcc_assert (partitions.length () == (unsigned)num_sccs);
> - free_graph (pg);
> + merge_dep_scc_partitions (rdg, &ddr_table, &partitions,
> + rt_alias_check_p ? NULL : &alias_ddrs);
> + alias_ddrs.truncate (0);
> + if (rt_alias_check_p && partitions.length () > 1)
> + break_alias_scc_partitions (rdg, &ddr_table, &partitions, &alias_ddrs);
> }
>
> + finalize_partitions (&partitions, &alias_ddrs);
> +
> nbp = partitions.length ();
> if (nbp == 0
> || (nbp == 1 && !partition_builtin_p (partitions[0]))
> @@ -1695,8 +2586,15 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> goto ldist_done;
> }
>
> + if (version_for_distribution_p (&partitions, &alias_ddrs))
> + version_loop_by_alias_check (loop, &alias_ddrs);
> +
> if (dump_file && (dump_flags & TDF_DETAILS))
> - dump_rdg_partitions (dump_file, partitions);
> + {
> + fprintf (dump_file,
> + "distribute loop <%d> into partitions:\n", loop->num);
> + dump_rdg_partitions (dump_file, partitions);
> + }
>
> FOR_EACH_VEC_ELT (partitions, i, partition)
> {
> @@ -1706,7 +2604,9 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
> }
>
> ldist_done:
> -
> + free_data_refs (datarefs);
> + free_dependence_relations (dependences);
> + ddr_table.empty ();
> FOR_EACH_VEC_ELT (partitions, i, partition)
> partition_free (partition);
>
> @@ -1758,6 +2658,22 @@ pass_loop_distribution::execute (function *fun)
> control_dependences *cd = NULL;
> auto_vec<loop_p> loops_to_be_destroyed;
>
> + /* Compute topological order for basic blocks. Topological order is
> + needed because data dependence is computed for data references in
> + lexicographical order */
> + if (bb_top_order_index == NULL)
> + {
> + int *rpo = XNEWVEC (int, last_basic_block_for_fn (cfun));
> +
> + bb_top_order_index = XNEWVEC (int, last_basic_block_for_fn (cfun));
> + bb_top_order_index_size
> + = pre_and_rev_post_order_compute_fn (cfun, NULL, rpo, true);
> + for (int i = 0; i < bb_top_order_index_size; i++)
> + bb_top_order_index[rpo[i]] = i;
> +
> + free (rpo);
> + }
> +
> FOR_ALL_BB_FN (bb, fun)
> {
> gimple_stmt_iterator gsi;
> @@ -1767,6 +2683,9 @@ pass_loop_distribution::execute (function *fun)
> gimple_set_uid (gsi_stmt (gsi), -1);
> }
>
> + FOR_EACH_LOOP (loop, LI_ONLY_INNERMOST)
> + loop->aux = NULL;
> +
> /* We can at the moment only distribute non-nested loops, thus restrict
> walking to innermost loops. */
> FOR_EACH_LOOP (loop, LI_ONLY_INNERMOST)
> @@ -1776,6 +2695,10 @@ pass_loop_distribution::execute (function *fun)
> int num = loop->num;
> unsigned int i;
>
> + /* Skip distributed loops. */
> + if (loop->aux != NULL)
> + continue;
> +
> /* If the loop doesn't have a single exit we will fail anyway,
> so do that early. */
> if (!single_exit (loop))
> @@ -1862,16 +2785,26 @@ out:
> fprintf (dump_file, "Loop %d is the same.\n", num);
> }
>
> + FOR_EACH_LOOP (loop, LI_ONLY_INNERMOST)
> + loop->aux = NULL;
> +
> if (cd)
> delete cd;
>
> + if (bb_top_order_index != NULL)
> + {
> + free (bb_top_order_index);
> + bb_top_order_index = NULL;
> + bb_top_order_index_size = 0;
> + }
> +
> if (changed)
> {
> /* Destroy loop bodies that could not be reused. Do this late as we
> otherwise can end up refering to stale data in control dependences. */
> unsigned i;
> FOR_EACH_VEC_ELT (loops_to_be_destroyed, i, loop)
> - destroy_loop (loop);
> + destroy_loop (loop);
>
> /* Cached scalar evolutions now may refer to wrong or non-existing
> loops. */
> diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c
> index 1bef2e4..0d83d33 100644
> --- a/gcc/tree-vectorizer.c
> +++ b/gcc/tree-vectorizer.c
> @@ -469,6 +469,63 @@ fold_loop_vectorized_call (gimple *g, tree value)
> }
> }
>
> +/* If LOOP has been versioned during loop distribution, return the internal
> + call guarding it. */
> +
> +static gimple *
> +vect_loop_dist_alias_call (struct loop *loop)
> +{
> + gimple_stmt_iterator gsi;
> + gimple *g;
> + basic_block bb = loop_preheader_edge (loop)->src;
> + struct loop *outer_loop = bb->loop_father;
> +
> + /* Look upward in dominance tree. */
> + for (; bb != ENTRY_BLOCK_PTR_FOR_FN (cfun) && bb->loop_father == outer_loop;
> + bb = get_immediate_dominator (CDI_DOMINATORS, bb))
> + {
> + g = last_stmt (bb);
> + if (g == NULL || gimple_code (g) != GIMPLE_COND)
> + continue;
> +
> + gsi = gsi_for_stmt (g);
> + gsi_prev (&gsi);
> + if (gsi_end_p (gsi))
> + continue;
> +
> + g = gsi_stmt (gsi);
> + /* The guarding internal function call must have the same distribution
> + alias id. */
> + if (gimple_call_internal_p (g, IFN_LOOP_DIST_ALIAS)
> + && (tree_to_shwi (gimple_call_arg (g, 0)) == loop->ldist_alias_id))
> + return g;
> + }
> + return NULL;
> +}
> +
> +/* Fold LOOP_DIST_ALIAS internal call stmt according to KEEP_P and update
> + any immediate uses of it's LHS. Stmt is folded to its second argument
> + if KEEP_P is true, otherwise to boolean_false_node. */
> +
> +static void
> +fold_loop_dist_alias_call (gimple *g, bool keep_p)
> +{
> + tree lhs = gimple_call_lhs (g);
> + use_operand_p use_p;
> + imm_use_iterator iter;
> + gimple *use_stmt;
> + gimple_stmt_iterator gsi = gsi_for_stmt (g);
> + tree folded_value = keep_p ? gimple_call_arg (g, 1) : boolean_false_node;
> +
> + update_call_from_tree (&gsi, folded_value);
> + FOR_EACH_IMM_USE_STMT (use_stmt, iter, lhs)
> + {
> + FOR_EACH_IMM_USE_ON_STMT (use_p, iter)
> + SET_USE (use_p, folded_value);
> + update_stmt (use_stmt);
> + }
> +}
> +
> /* Set the uids of all the statements in basic blocks inside loop
> represented by LOOP_VINFO. LOOP_VECTORIZED_CALL is the internal
> call guarding the loop which has been if converted. */
> @@ -595,7 +652,7 @@ vectorize_loops (void)
> else
> {
> loop_vec_info loop_vinfo, orig_loop_vinfo;
> - gimple *loop_vectorized_call;
> + gimple *loop_vectorized_call, *loop_dist_alias_call;
> try_vectorize:
> if (!((flag_tree_loop_vectorize
> && optimize_loop_nest_for_speed_p (loop))
> @@ -603,6 +660,7 @@ vectorize_loops (void)
> continue;
> orig_loop_vinfo = NULL;
> loop_vectorized_call = vect_loop_vectorized_call (loop);
> + loop_dist_alias_call = vect_loop_dist_alias_call (loop);
> vectorize_epilogue:
> vect_location = find_loop_location (loop);
> if (LOCATION_LOCUS (vect_location) != UNKNOWN_LOCATION
> @@ -710,6 +768,12 @@ vectorize_loops (void)
> loop_vectorized_call = NULL;
> ret |= TODO_cleanup_cfg;
> }
> + if (loop_dist_alias_call)
> + {
> + fold_loop_dist_alias_call (loop_dist_alias_call, true);
> + loop_dist_alias_call = NULL;
> + ret |= TODO_cleanup_cfg;
> + }
>
> if (new_loop)
> {
> @@ -743,6 +807,15 @@ vectorize_loops (void)
> {
> fold_loop_vectorized_call (g, boolean_false_node);
> ret |= TODO_cleanup_cfg;
> + g = NULL;
> + }
> + else
> + g = vect_loop_dist_alias_call (loop);
> +
> + if (g)
> + {
> + fold_loop_dist_alias_call (g, false);
> + ret |= TODO_cleanup_cfg;
> }
> }
> }
> -- 1.9.1
>
next prev parent reply other threads:[~2017-06-08 2:48 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-02 11:51 Bin Cheng
2017-06-05 4:21 ` Kugan Vivekanandarajah
2017-06-05 9:01 ` Bin.Cheng
2017-06-07 10:03 ` Richard Biener
2017-06-07 10:19 ` Bin.Cheng
2017-06-08 2:48 ` kugan [this message]
2017-06-08 17:35 ` Bin.Cheng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=2df529ae-803d-f955-cc6e-494a13ab7d6a@linaro.org \
--to=kugan.vivekanandarajah@linaro.org \
--cc=Bin.Cheng@arm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=nd@arm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).