diff options
author | Richard Sandiford <richard.sandiford@arm.com> | 2021-11-30 09:52:29 +0000 |
---|---|---|
committer | Richard Sandiford <richard.sandiford@arm.com> | 2021-11-30 09:52:29 +0000 |
commit | 10833849b55401a52f2334eb032a70beb688e9fc (patch) | |
tree | a2556da822f071f9f927e85f9f4ecb668bac4d07 /gcc/tree-vect-stmts.c | |
parent | 6f798618c070e2ca505e39c3fcc0c3ca478ac81b (diff) | |
download | gcc-10833849b55401a52f2334eb032a70beb688e9fc.zip gcc-10833849b55401a52f2334eb032a70beb688e9fc.tar.gz gcc-10833849b55401a52f2334eb032a70beb688e9fc.tar.bz2 |
vect: Support gather loads with SLP
This patch adds SLP support for IFN_GATHER_LOAD. Like the SLP
support for IFN_MASK_LOAD, it works by treating only some of the
arguments as child nodes. Unlike IFN_MASK_LOAD, it requires the
other arguments (base, scale, and extension type) to be the same
for all calls in the group. It does not require/expect the loads
to be in a group (which probably wouldn't make sense for gathers).
I was worried about the possible alias effect of moving gathers
around to be part of the same SLP group. The patch therefore
makes vect_analyze_data_ref_dependence treat gathers and scatters
as a top-level concern, punting if the accesses aren't completely
independent and if the user hasn't told us that a particular
VF is safe. I think in practice we already punted in the same
circumstances; the idea is just to make it more explicit.
gcc/
PR tree-optimization/102467
* doc/sourcebuild.texi (vect_gather_load_ifn): Document.
* tree-vect-data-refs.c (vect_analyze_data_ref_dependence):
Commonize safelen handling. Punt for anything involving
gathers and scatters unless safelen says otherwise.
* tree-vect-slp.c (arg1_map): New variable.
(vect_get_operand_map): Handle IFN_GATHER_LOAD.
(vect_build_slp_tree_1): Likewise.
(vect_build_slp_tree_2): Likewise.
(compatible_calls_p): If vect_get_operand_map returns nonnull,
check that any skipped arguments are equal.
(vect_slp_analyze_node_operations_1): Tighten reduction check.
* tree-vect-stmts.c (check_load_store_for_partial_vectors): Take
an ncopies argument.
(vect_get_gather_scatter_ops): Take slp_node and ncopies arguments.
Handle SLP nodes.
(vectorizable_store, vectorizable_load): Adjust accordingly.
gcc/testsuite/
* lib/target-supports.exp
(check_effective_target_vect_gather_load_ifn): New target test.
* gcc.dg/vect/vect-gather-1.c: New test.
* gcc.dg/vect/vect-gather-2.c: Likewise.
* gcc.target/aarch64/sve/gather_load_11.c: Likewise.
Diffstat (limited to 'gcc/tree-vect-stmts.c')
-rw-r--r-- | gcc/tree-vect-stmts.c | 26 |
1 files changed, 14 insertions, 12 deletions
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c index 101f61f..06da5a9 100644 --- a/gcc/tree-vect-stmts.c +++ b/gcc/tree-vect-stmts.c @@ -1674,6 +1674,7 @@ check_load_store_for_partial_vectors (loop_vec_info loop_vinfo, tree vectype, int group_size, vect_memory_access_type memory_access_type, + unsigned int ncopies, gather_scatter_info *gs_info, tree scalar_mask) { @@ -1698,7 +1699,6 @@ check_load_store_for_partial_vectors (loop_vec_info loop_vinfo, tree vectype, LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo) = false; return; } - unsigned int ncopies = vect_get_num_copies (loop_vinfo, vectype); vect_record_loop_mask (loop_vinfo, masks, ncopies, vectype, scalar_mask); return; } @@ -1721,7 +1721,6 @@ check_load_store_for_partial_vectors (loop_vec_info loop_vinfo, tree vectype, LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo) = false; return; } - unsigned int ncopies = vect_get_num_copies (loop_vinfo, vectype); vect_record_loop_mask (loop_vinfo, masks, ncopies, vectype, scalar_mask); return; } @@ -2963,6 +2962,7 @@ vect_build_gather_load_calls (vec_info *vinfo, stmt_vec_info stmt_info, static void vect_get_gather_scatter_ops (loop_vec_info loop_vinfo, class loop *loop, stmt_vec_info stmt_info, + slp_tree slp_node, unsigned int ncopies, gather_scatter_info *gs_info, tree *dataref_ptr, vec<tree> *vec_offset) { @@ -2975,10 +2975,12 @@ vect_get_gather_scatter_ops (loop_vec_info loop_vinfo, new_bb = gsi_insert_seq_on_edge_immediate (pe, stmts); gcc_assert (!new_bb); } - unsigned ncopies = vect_get_num_copies (loop_vinfo, gs_info->offset_vectype); - vect_get_vec_defs_for_operand (loop_vinfo, stmt_info, ncopies, - gs_info->offset, vec_offset, - gs_info->offset_vectype); + if (slp_node) + vect_get_slp_defs (SLP_TREE_CHILDREN (slp_node)[0], vec_offset); + else + vect_get_vec_defs_for_operand (loop_vinfo, stmt_info, ncopies, + gs_info->offset, vec_offset, + gs_info->offset_vectype); } /* Prepare to implement a grouped or strided load or store using @@ -7484,7 +7486,7 @@ vectorizable_store (vec_info *vinfo, && LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo)) check_load_store_for_partial_vectors (loop_vinfo, vectype, vls_type, group_size, memory_access_type, - &gs_info, mask); + ncopies, &gs_info, mask); if (slp_node && !vect_maybe_update_slp_op_vectype (SLP_TREE_CHILDREN (slp_node)[0], @@ -8147,8 +8149,8 @@ vectorizable_store (vec_info *vinfo, else if (STMT_VINFO_GATHER_SCATTER_P (stmt_info)) { vect_get_gather_scatter_ops (loop_vinfo, loop, stmt_info, - &gs_info, &dataref_ptr, - &vec_offsets); + slp_node, ncopies, &gs_info, + &dataref_ptr, &vec_offsets); vec_offset = vec_offsets[0]; } else @@ -8827,7 +8829,7 @@ vectorizable_load (vec_info *vinfo, && LOOP_VINFO_CAN_USE_PARTIAL_VECTORS_P (loop_vinfo)) check_load_store_for_partial_vectors (loop_vinfo, vectype, VLS_LOAD, group_size, memory_access_type, - &gs_info, mask); + ncopies, &gs_info, mask); if (dump_enabled_p () && memory_access_type != VMAT_ELEMENTWISE @@ -9445,8 +9447,8 @@ vectorizable_load (vec_info *vinfo, else if (STMT_VINFO_GATHER_SCATTER_P (stmt_info)) { vect_get_gather_scatter_ops (loop_vinfo, loop, stmt_info, - &gs_info, &dataref_ptr, - &vec_offsets); + slp_node, ncopies, &gs_info, + &dataref_ptr, &vec_offsets); } else dataref_ptr |