From: Kewen Lin <linkw@linux.ibm.com>
To: gcc-patches@gcc.gnu.org
Cc: richard.guenther@gmail.com, richard.sandiford@arm.com
Subject: [PATCH 09/10] vect: Get rid of vect_model_store_cost
Date: Wed, 13 Sep 2023 22:11:58 -0500 [thread overview]
Message-ID: <b2f2a8081d2ffd2459b0ff161a559e502511d8a5.1694657494.git.linkw@linux.ibm.com> (raw)
In-Reply-To: <cover.1694657494.git.linkw@linux.ibm.com>
This patch is to eventually get rid of vect_model_store_cost,
it adjusts the costing for the remaining memory access types
VMAT_CONTIGUOUS{, _DOWN, _REVERSE} by moving costing close
to the transform code. Note that in vect_model_store_cost,
there is one special handling for vectorizing a store into
the function result, since it's extra penalty and the
transform part doesn't have it, this patch keep it alone.
gcc/ChangeLog:
* tree-vect-stmts.cc (vect_model_store_cost): Remove.
(vectorizable_store): Adjust the costing for the remaining memory
access types VMAT_CONTIGUOUS{, _DOWN, _REVERSE}.
---
gcc/tree-vect-stmts.cc | 137 +++++++++++++----------------------------
1 file changed, 44 insertions(+), 93 deletions(-)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index e3ba8077091..3d451c80bca 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -951,81 +951,6 @@ cfun_returns (tree decl)
return false;
}
-/* Function vect_model_store_cost
-
- Models cost for stores. In the case of grouped accesses, one access
- has the overhead of the grouped access attributed to it. */
-
-static void
-vect_model_store_cost (vec_info *vinfo, stmt_vec_info stmt_info, int ncopies,
- vect_memory_access_type memory_access_type,
- dr_alignment_support alignment_support_scheme,
- int misalignment,
- vec_load_store_type vls_type, slp_tree slp_node,
- stmt_vector_for_cost *cost_vec)
-{
- gcc_assert (memory_access_type != VMAT_GATHER_SCATTER
- && memory_access_type != VMAT_ELEMENTWISE
- && memory_access_type != VMAT_STRIDED_SLP
- && memory_access_type != VMAT_LOAD_STORE_LANES
- && memory_access_type != VMAT_CONTIGUOUS_PERMUTE);
-
- unsigned int inside_cost = 0, prologue_cost = 0;
-
- /* ??? Somehow we need to fix this at the callers. */
- if (slp_node)
- ncopies = SLP_TREE_NUMBER_OF_VEC_STMTS (slp_node);
-
- if (vls_type == VLS_STORE_INVARIANT)
- {
- if (!slp_node)
- prologue_cost += record_stmt_cost (cost_vec, 1, scalar_to_vec,
- stmt_info, 0, vect_prologue);
- }
-
-
- /* Costs of the stores. */
- vect_get_store_cost (vinfo, stmt_info, ncopies, alignment_support_scheme,
- misalignment, &inside_cost, cost_vec);
-
- /* When vectorizing a store into the function result assign
- a penalty if the function returns in a multi-register location.
- In this case we assume we'll end up with having to spill the
- vector result and do piecewise loads as a conservative estimate. */
- tree base = get_base_address (STMT_VINFO_DATA_REF (stmt_info)->ref);
- if (base
- && (TREE_CODE (base) == RESULT_DECL
- || (DECL_P (base) && cfun_returns (base)))
- && !aggregate_value_p (base, cfun->decl))
- {
- rtx reg = hard_function_value (TREE_TYPE (base), cfun->decl, 0, 1);
- /* ??? Handle PARALLEL in some way. */
- if (REG_P (reg))
- {
- int nregs = hard_regno_nregs (REGNO (reg), GET_MODE (reg));
- /* Assume that a single reg-reg move is possible and cheap,
- do not account for vector to gp register move cost. */
- if (nregs > 1)
- {
- /* Spill. */
- prologue_cost += record_stmt_cost (cost_vec, ncopies,
- vector_store,
- stmt_info, 0, vect_epilogue);
- /* Loads. */
- prologue_cost += record_stmt_cost (cost_vec, ncopies * nregs,
- scalar_load,
- stmt_info, 0, vect_epilogue);
- }
- }
- }
-
- if (dump_enabled_p ())
- dump_printf_loc (MSG_NOTE, vect_location,
- "vect_model_store_cost: inside_cost = %d, "
- "prologue_cost = %d .\n", inside_cost, prologue_cost);
-}
-
-
/* Calculate cost of DR's memory access. */
void
vect_get_store_cost (vec_info *, stmt_vec_info stmt_info, int ncopies,
@@ -9223,6 +9148,11 @@ vectorizable_store (vec_info *vinfo,
return true;
}
+ gcc_assert (memory_access_type == VMAT_CONTIGUOUS
+ || memory_access_type == VMAT_CONTIGUOUS_DOWN
+ || memory_access_type == VMAT_CONTIGUOUS_PERMUTE
+ || memory_access_type == VMAT_CONTIGUOUS_REVERSE);
+
unsigned inside_cost = 0, prologue_cost = 0;
auto_vec<tree> result_chain (group_size);
auto_vec<tree, 1> vec_oprnds;
@@ -9257,10 +9187,9 @@ vectorizable_store (vec_info *vinfo,
that there is no interleaving, DR_GROUP_SIZE is 1,
and only one iteration of the loop will be executed. */
op = vect_get_store_rhs (next_stmt_info);
- if (costing_p
- && memory_access_type == VMAT_CONTIGUOUS_PERMUTE)
+ if (costing_p)
update_prologue_cost (&prologue_cost, op);
- else if (!costing_p)
+ else
{
vect_get_vec_defs_for_operand (vinfo, next_stmt_info,
ncopies, op,
@@ -9352,10 +9281,9 @@ vectorizable_store (vec_info *vinfo,
{
if (costing_p)
{
- if (memory_access_type == VMAT_CONTIGUOUS_PERMUTE)
- vect_get_store_cost (vinfo, stmt_info, 1,
- alignment_support_scheme, misalignment,
- &inside_cost, cost_vec);
+ vect_get_store_cost (vinfo, stmt_info, 1,
+ alignment_support_scheme, misalignment,
+ &inside_cost, cost_vec);
if (!slp)
{
@@ -9550,18 +9478,41 @@ vectorizable_store (vec_info *vinfo,
if (costing_p)
{
- if (memory_access_type == VMAT_CONTIGUOUS_PERMUTE)
- {
- if (dump_enabled_p ())
- dump_printf_loc (MSG_NOTE, vect_location,
- "vect_model_store_cost: inside_cost = %d, "
- "prologue_cost = %d .\n",
- inside_cost, prologue_cost);
+ /* When vectorizing a store into the function result assign
+ a penalty if the function returns in a multi-register location.
+ In this case we assume we'll end up with having to spill the
+ vector result and do piecewise loads as a conservative estimate. */
+ tree base = get_base_address (STMT_VINFO_DATA_REF (stmt_info)->ref);
+ if (base
+ && (TREE_CODE (base) == RESULT_DECL
+ || (DECL_P (base) && cfun_returns (base)))
+ && !aggregate_value_p (base, cfun->decl))
+ {
+ rtx reg = hard_function_value (TREE_TYPE (base), cfun->decl, 0, 1);
+ /* ??? Handle PARALLEL in some way. */
+ if (REG_P (reg))
+ {
+ int nregs = hard_regno_nregs (REGNO (reg), GET_MODE (reg));
+ /* Assume that a single reg-reg move is possible and cheap,
+ do not account for vector to gp register move cost. */
+ if (nregs > 1)
+ {
+ /* Spill. */
+ prologue_cost
+ += record_stmt_cost (cost_vec, ncopies, vector_store,
+ stmt_info, 0, vect_epilogue);
+ /* Loads. */
+ prologue_cost
+ += record_stmt_cost (cost_vec, ncopies * nregs, scalar_load,
+ stmt_info, 0, vect_epilogue);
+ }
+ }
}
- else
- vect_model_store_cost (vinfo, stmt_info, ncopies, memory_access_type,
- alignment_support_scheme, misalignment, vls_type,
- slp_node, cost_vec);
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "vect_model_store_cost: inside_cost = %d, "
+ "prologue_cost = %d .\n",
+ inside_cost, prologue_cost);
}
return true;
--
2.31.1
next prev parent reply other threads:[~2023-09-14 3:12 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-14 3:11 [PATCH 00/10] vect: Move costing next to the transform for vect store Kewen Lin
2023-09-14 3:11 ` [PATCH 01/10] vect: Ensure vect store is supported for some VMAT_ELEMENTWISE case Kewen Lin
2023-09-27 11:22 ` Richard Biener
2023-09-14 3:11 ` [PATCH 02/10] vect: Move vect_model_store_cost next to the transform in vectorizable_store Kewen Lin
2023-09-27 11:23 ` Richard Biener
2023-09-14 3:11 ` [PATCH 03/10] vect: Adjust vectorizable_store costing on VMAT_GATHER_SCATTER Kewen Lin
2023-09-27 11:24 ` Richard Biener
2023-09-14 3:11 ` [PATCH 04/10] vect: Simplify costing on vectorizable_scan_store Kewen Lin
2023-09-27 11:25 ` Richard Biener
2023-09-14 3:11 ` [PATCH 05/10] vect: Adjust vectorizable_store costing on VMAT_ELEMENTWISE and VMAT_STRIDED_SLP Kewen Lin
2023-09-27 11:26 ` Richard Biener
2023-09-14 3:11 ` [PATCH 06/10] vect: Adjust vectorizable_store costing on VMAT_LOAD_STORE_LANES Kewen Lin
2023-09-27 11:27 ` Richard Biener
2023-09-14 3:11 ` [PATCH 07/10] vect: Adjust vectorizable_store costing on VMAT_CONTIGUOUS_PERMUTE Kewen Lin
2023-09-27 11:28 ` Richard Biener
2023-09-14 3:11 ` [PATCH/RFC 08/10] aarch64: Don't use CEIL for vector_store in aarch64_stp_sequence_cost Kewen Lin
2023-09-18 8:41 ` Richard Sandiford
2023-09-18 8:53 ` Richard Biener
2023-09-20 2:40 ` Kewen.Lin
2023-09-14 3:11 ` Kewen Lin [this message]
2023-09-27 11:29 ` [PATCH 09/10] vect: Get rid of vect_model_store_cost Richard Biener
2023-09-14 3:11 ` [PATCH 10/10] vect: Consider vec_perm costing for VMAT_CONTIGUOUS_REVERSE Kewen Lin
2023-09-27 11:30 ` Richard Biener
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=b2f2a8081d2ffd2459b0ff161a559e502511d8a5.1694657494.git.linkw@linux.ibm.com \
--to=linkw@linux.ibm.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=richard.guenther@gmail.com \
--cc=richard.sandiford@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).