@@ -1685,6 +1685,7 @@ OBJS = \
statistics.o \
stmt.o \
stor-layout.o \
+ avoid-store-forwarding.o \
store-motion.o \
streamer-hooks.o \
stringpool.o \
new file mode 100644
@@ -0,0 +1,597 @@
+/* Avoid store forwarding optimization pass.
+ Copyright (C) 2024 Free Software Foundation, Inc.
+ Contributed by VRULL GmbH.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify it
+ under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful, but
+ WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with GCC; see the file COPYING3. If not see
+ <http://www.gnu.org/licenses/>. */
+
+#include "avoid-store-forwarding.h"
+#include "config.h"
+#include "system.h"
+#include "coretypes.h"
+#include "backend.h"
+#include "target.h"
+#include "rtl.h"
+#include "alias.h"
+#include "rtlanal.h"
+#include "tree-pass.h"
+#include "cselib.h"
+#include "predict.h"
+#include "insn-config.h"
+#include "expmed.h"
+#include "recog.h"
+#include "regset.h"
+#include "df.h"
+#include "expr.h"
+#include "memmodel.h"
+#include "emit-rtl.h"
+#include "vec.h"
+
+/* This pass tries to detect and avoid cases of store forwarding.
+ On many processors there is a large penalty when smaller stores are
+ forwarded to larger loads. The idea used to avoid the stall is to move
+ the store after the load and in addition emit a bit insert sequence so
+ the load register has the correct value. For example the following:
+
+ strb w2, [x1, 1]
+ ldr x0, [x1]
+
+ Will be transformed to:
+
+ ldr x0, [x1]
+ strb w2, [x1]
+ bfi x0, x2, 0, 8
+*/
+
+namespace {
+
+const pass_data pass_data_avoid_store_forwarding =
+{
+ RTL_PASS, /* type. */
+ "avoid_store_forwarding", /* name. */
+ OPTGROUP_NONE, /* optinfo_flags. */
+ TV_NONE, /* tv_id. */
+ 0, /* properties_required. */
+ 0, /* properties_provided. */
+ 0, /* properties_destroyed. */
+ 0, /* todo_flags_start. */
+ TODO_df_finish /* todo_flags_finish. */
+};
+
+class pass_rtl_avoid_store_forwarding : public rtl_opt_pass
+{
+public:
+ pass_rtl_avoid_store_forwarding (gcc::context *ctxt)
+ : rtl_opt_pass (pass_data_avoid_store_forwarding, ctxt)
+ {}
+
+ /* opt_pass methods: */
+ virtual bool gate (function *)
+ {
+ return flag_avoid_store_forwarding && optimize >= 1
+ && optimize_insn_for_speed_p ();
+ }
+
+ virtual unsigned int execute (function *) override;
+}; // class pass_rtl_avoid_store_forwarding
+
+static unsigned int stats_sf_detected = 0;
+static unsigned int stats_sf_avoided = 0;
+
+/* If expr is a SET that reads from memory then return the RTX for it's MEM
+ argument, otherwise return NULL. Allows MEM to be zero/sign extended. */
+
+static rtx
+get_load_mem (rtx expr)
+{
+ if (!expr)
+ return NULL_RTX;
+
+ rtx mem = SET_SRC (expr);
+
+ if (GET_CODE (mem) == ZERO_EXTEND
+ || GET_CODE (mem) == SIGN_EXTEND)
+ mem = XEXP (mem, 0);
+
+ if (MEM_P (mem))
+ return mem;
+ else
+ return NULL_RTX;
+}
+
+/* Return true iff a store to STORE_MEM would write to a sub-region of bytes
+ from what LOAD_MEM would read. If true also store the relative byte offset
+ of the store within the load to OFF_VAL. */
+
+static bool
+is_store_forwarding (rtx store_mem, rtx load_mem, HOST_WIDE_INT *off_val)
+{
+ if (known_ge (GET_MODE_SIZE (GET_MODE (store_mem)),
+ GET_MODE_SIZE (GET_MODE (load_mem))))
+ return false;
+
+ rtx off = simplify_gen_binary (MINUS, GET_MODE (XEXP (store_mem, 0)),
+ XEXP (store_mem, 0), XEXP (load_mem, 0));
+
+ if (CONST_INT_P (off))
+ {
+ *off_val = INTVAL (off);
+ poly_uint64 store_mode_size = GET_MODE_SIZE (GET_MODE (store_mem));
+ poly_uint64 load_mode_size = GET_MODE_SIZE (GET_MODE (load_mem));
+ unsigned HOST_WIDE_INT store_size, load_size;
+ if (store_mode_size.is_constant (&store_size)
+ && load_mode_size.is_constant (&load_size))
+ {
+ gcc_checking_assert (store_size > 0 && load_size > 0);
+ return *off_val >= 0
+ && (store_size + *off_val <= load_size);
+ }
+ }
+
+ return false;
+}
+
+/* Return a bit insertion sequence that would make DEST have the correct value
+ if the store represented by STORE_INFO were to be moved after DEST. */
+
+static rtx_insn *
+generate_bit_insert_sequence (store_fwd_info *store_info, rtx dest,
+ machine_mode load_inner_mode)
+{
+ poly_uint64 store_mode_size
+ = GET_MODE_SIZE (GET_MODE (store_info->store_mem));
+ poly_uint64 load_mode_size = GET_MODE_SIZE (load_inner_mode);
+ unsigned HOST_WIDE_INT store_size = store_mode_size.to_constant ();
+ unsigned HOST_WIDE_INT load_size = load_mode_size.to_constant ();
+ HOST_WIDE_INT bf_offset_bytes;
+
+ if (BYTES_BIG_ENDIAN)
+ bf_offset_bytes = load_size - store_size - store_info->offset;
+ else
+ bf_offset_bytes = store_info->offset;
+
+ start_sequence ();
+ store_bit_field (dest, store_size * BITS_PER_UNIT,
+ bf_offset_bytes * BITS_PER_UNIT, 0, 0,
+ GET_MODE (dest), store_info->mov_reg,
+ false, false);
+
+ rtx_insn *insns = get_insns ();
+ unshare_all_rtl_in_chain (insns);
+ end_sequence ();
+
+ for (rtx_insn *insn = insns; insn; insn = NEXT_INSN (insn))
+ if (contains_mem_rtx_p (PATTERN (insn))
+ || recog_memoized (insn) < 0)
+ return NULL;
+
+ return insns;
+}
+
+/* Given a list of small stores that are forwarded to LOAD_INSN, try to
+ rearrange them so that a store-forwarding penalty doesn't occur. */
+
+static bool
+process_forwardings (vec<store_fwd_info> &stores, rtx_insn *load_insn)
+{
+ rtx load = single_set (load_insn);
+ rtx load_inner = get_load_mem (load);
+ machine_mode load_inner_mode = GET_MODE (load_inner);
+ poly_uint64 load_mode_size = GET_MODE_SIZE (load_inner_mode);
+ HOST_WIDE_INT load_size = load_mode_size.to_constant ();
+
+ /* If the stores cover all the bytes of the load without overlap then we can
+ eliminate the load entirely and use the computed value instead. */
+
+ sbitmap forwarded_bytes = sbitmap_alloc (load_size);
+ bitmap_clear (forwarded_bytes);
+
+ unsigned int i;
+ store_fwd_info* it;
+ FOR_EACH_VEC_ELT (stores, i, it)
+ {
+ poly_uint64 store_mode_size = GET_MODE_SIZE (GET_MODE (it->store_mem));
+ HOST_WIDE_INT store_size = store_mode_size.to_constant ();
+ if (bitmap_bit_in_range_p (forwarded_bytes, it->offset,
+ it->offset + store_size - 1))
+ break;
+ bitmap_set_range (forwarded_bytes, it->offset, store_size);
+ }
+
+ bitmap_not (forwarded_bytes, forwarded_bytes);
+ bool load_elim = bitmap_empty_p (forwarded_bytes);
+
+ stats_sf_detected++;
+
+ if (dump_file)
+ {
+ fprintf (dump_file, "Store forwarding%s detected:\n",
+ (stores.length () > 1) ? "s" : "");
+
+ FOR_EACH_VEC_ELT (stores, i, it)
+ {
+ fprintf (dump_file, "From: ");
+ print_rtl_single (dump_file, it->store_insn);
+ }
+
+ fprintf (dump_file, "To: ");
+ print_rtl_single (dump_file, load_insn);
+
+ if (load_elim)
+ fprintf (dump_file, "(Load elimination candidate)\n");
+ }
+
+ rtx dest;
+ if (load_elim)
+ dest = gen_reg_rtx (load_inner_mode);
+ else
+ dest = SET_DEST (load);
+
+ int move_to_front = -1;
+ int total_cost = 0;
+
+ /* Check if we can emit bit insert instructions for all forwarded stores. */
+ FOR_EACH_VEC_ELT (stores, i, it)
+ {
+ it->mov_reg = gen_reg_rtx (GET_MODE (it->store_mem));
+ rtx_insn *insns = NULL;
+
+ /* If we're eliminating the load then find the store with zero offset
+ and use it as the base register to avoid a bit insert if possible. */
+ if (load_elim && it->offset == 0
+ && validate_subreg (GET_MODE (dest), GET_MODE (it->mov_reg),
+ it->mov_reg, 0))
+ {
+ start_sequence ();
+
+ /* We can use a paradoxical subreg to force this to a wider mode, as
+ the only use will be inserting the bits (i.e., we don't care about
+ the value of the higher bits). */
+ rtx ext0 = gen_rtx_SUBREG (GET_MODE (dest), it->mov_reg, 0);
+ rtx_insn *move0 = emit_move_insn (dest, ext0);
+ if (recog_memoized (move0) >= 0)
+ {
+ insns = get_insns ();
+ move_to_front = (int) i;
+ }
+
+ end_sequence ();
+ }
+
+ if (!insns)
+ insns = generate_bit_insert_sequence (&(*it), dest, load_inner_mode);
+
+ if (!insns)
+ {
+ if (dump_file)
+ {
+ fprintf (dump_file, "Failed due to: ");
+ print_rtl_single (dump_file, it->store_insn);
+ }
+ return false;
+ }
+
+ total_cost += seq_cost (insns, true);
+ it->bits_insert_insns = insns;
+ }
+
+ if (load_elim)
+ total_cost -= COSTS_N_INSNS (1);
+
+ if (targetm.avoid_store_forwarding_p)
+ {
+ /* If a target-specific hook exists to decide profitability of the
+ specific store-forwarding instance then use that as it should be
+ the most accurate. */
+ if (!targetm.avoid_store_forwarding_p (stores, load_inner, total_cost,
+ load_elim))
+ {
+ if (dump_file)
+ fprintf (dump_file, "Not transformed due to target decision.\n");
+
+ return false;
+ }
+ }
+ else
+ {
+ /* Otherwise use a simple cost heurstic base on
+ param_store_forwarding_max_distance. In general the distance should
+ be somewhat correlated to the store forwarding penalty; if the penalty
+ is large then it is justified to increase the window size. Use this
+ to reject sequences that are clearly unprofitable. */
+ int max_cost = COSTS_N_INSNS (param_store_forwarding_max_distance / 2);
+ if (total_cost > max_cost)
+ {
+ if (dump_file)
+ fprintf (dump_file, "Not transformed due to cost: %d > %d.\n",
+ total_cost, max_cost);
+
+ return false;
+ }
+ }
+
+ /* If we have a move instead of bit insert, it needs to be emitted first in
+ the resulting sequence. */
+ if (move_to_front != -1)
+ {
+ store_fwd_info copy = stores[move_to_front];
+ stores.safe_push (copy);
+ stores.ordered_remove (move_to_front);
+ }
+
+ if (load_elim)
+ {
+ machine_mode outter_mode = GET_MODE (SET_DEST (load));
+ rtx_code extend = ZERO_EXTEND;
+ if (outter_mode != load_inner_mode)
+ extend = GET_CODE (SET_SRC (load));
+
+ start_sequence ();
+ rtx load_value = simplify_gen_unary (extend, outter_mode, dest,
+ load_inner_mode);
+ rtx load_move = gen_move_insn (SET_DEST (load), load_value);
+ rtx_insn *insn = emit_insn (load_move);
+ rtx_insn *seq = get_insns ();
+ end_sequence ();
+
+ if (recog_memoized (insn) < 0)
+ return false;
+
+ df_insn_rescan (emit_insn_after (seq, load_insn));
+ }
+
+ if (dump_file)
+ {
+ fprintf (dump_file, "Store forwarding%s avoided with bit inserts:\n",
+ (stores.length () > 1) ? "s" : "");
+
+ FOR_EACH_VEC_ELT (stores, i, it)
+ {
+ if (stores.length () > 1)
+ {
+ fprintf (dump_file, "For: ");
+ print_rtl_single (dump_file, it->store_insn);
+ }
+
+ fprintf (dump_file, "With sequence:\n");
+
+ for (rtx_insn *insn = it->bits_insert_insns; insn;
+ insn = NEXT_INSN (insn))
+ {
+ fprintf (dump_file, " ");
+ print_rtl_single (dump_file, insn);
+ }
+ }
+ }
+
+ stats_sf_avoided++;
+
+ FOR_EACH_VEC_ELT (stores, i, it)
+ {
+ /* Emit code that updated the loaded value to account for the
+ missing store. */
+ df_insn_rescan (emit_insn_after (it->bits_insert_insns, load_insn));
+ }
+
+ FOR_EACH_VEC_ELT (stores, i, it)
+ {
+ rtx store_set = single_set (it->store_insn);
+ /* Create a register move at the store's original position to save the
+ stored value. */
+ rtx mov1 = gen_move_insn (it->mov_reg, SET_SRC (store_set));
+ df_insn_rescan (emit_insn_before (mov1, it->store_insn));
+ /* Create a new store after the load with the saved original value.
+ This avoids the forwarding stall. */
+ rtx mov2 = gen_move_insn (SET_DEST (store_set), it->mov_reg);
+ df_insn_rescan (emit_insn_after (mov2, load_insn));
+ /* Done, delete the original store. */
+ set_insn_deleted (it->store_insn);
+ }
+
+ df_insn_rescan (load_insn);
+
+ if (load_elim)
+ set_insn_deleted (load_insn);
+
+ return true;
+}
+
+/* Process BB for expensive store forwardings. */
+
+static void
+avoid_store_forwarding (basic_block bb)
+{
+ auto_vec<store_fwd_info, 8> store_exprs;
+ rtx_insn *insn;
+ unsigned int insn_cnt = 0;
+
+ FOR_BB_INSNS (bb, insn)
+ {
+ if (!NONDEBUG_INSN_P (insn))
+ continue;
+
+ rtx set = single_set (insn);
+
+ /* Store forwarding issues are unlikely if we cross a call.
+ Clear store forwarding candidates if we can't deal with INSN. */
+ if (CALL_P (insn) || !set || volatile_refs_p (set)
+ || GET_MODE (SET_DEST (set)) == BLKmode
+ || (MEM_P (SET_DEST (set)) && MEM_P (SET_SRC (set))))
+ {
+ store_exprs.truncate (0);
+ continue;
+ }
+
+ rtx load_mem = get_load_mem (set);
+ int removed_count = 0;
+
+ if (MEM_P (SET_DEST (set)))
+ {
+ /* Record store forwarding candidate. */
+ store_fwd_info info;
+ info.store_insn = insn;
+ info.store_mem = SET_DEST (set);
+ info.insn_cnt = insn_cnt;
+ info.remove = false;
+ info.forwarded = false;
+ store_exprs.safe_push (info);
+ }
+ else if (load_mem)
+ {
+ /* Process load for possible store forwardings. */
+ auto_vec<store_fwd_info> forwardings;
+ bool partial_forwarding = false;
+ bool remove_rest = false;
+
+ unsigned int i;
+ store_fwd_info *it;
+ FOR_EACH_VEC_ELT_REVERSE (store_exprs, i, it)
+ {
+ rtx store_mem = it->store_mem;
+ HOST_WIDE_INT off_val;
+
+ if (remove_rest)
+ {
+ it->remove = true;
+ removed_count++;
+ }
+ else if (is_store_forwarding (store_mem, load_mem, &off_val))
+ {
+ /* Check if moving this store after the load is legal. */
+ bool write_dep = false;
+ for (unsigned int j = store_exprs.length () - 1; j != i; j--)
+ if (!store_exprs[j].forwarded
+ && output_dependence (store_mem,
+ store_exprs[j].store_mem))
+ {
+ write_dep = true;
+ break;
+ }
+
+ if (!write_dep)
+ {
+ it->forwarded = true;
+ it->offset = off_val;
+ forwardings.safe_push (*it);
+ }
+ else
+ partial_forwarding = true;
+
+ it->remove = true;
+ removed_count++;
+ }
+ else if (true_dependence (store_mem, GET_MODE (store_mem),
+ load_mem))
+ {
+ /* We cannot keep a store forwarding candidate if it possibly
+ interferes with this load. */
+ it->remove = true;
+ removed_count++;
+ remove_rest = true;
+ }
+ }
+
+ if (!forwardings.is_empty () && !partial_forwarding)
+ process_forwardings (forwardings, insn);
+ }
+ else
+ {
+ rtx reg = SET_DEST (set);
+
+ while (GET_CODE (reg) == ZERO_EXTRACT
+ || GET_CODE (reg) == STRICT_LOW_PART
+ || GET_CODE (reg) == SUBREG)
+ reg = XEXP (reg, 0);
+
+ /* Drop store forwarding candidates when the address register is
+ overwritten. */
+ if (REG_P (reg))
+ {
+ bool remove_rest = false;
+ unsigned int i;
+ store_fwd_info *it;
+ FOR_EACH_VEC_ELT_REVERSE (store_exprs, i, it)
+ {
+ if (remove_rest
+ || reg_overlap_mentioned_p (reg, it->store_mem))
+ {
+ it->remove = true;
+ removed_count++;
+ remove_rest = true;
+ }
+ }
+ }
+ else
+ {
+ /* We can't understand INSN. */
+ store_exprs.truncate (0);
+ continue;
+ }
+ }
+
+ if (removed_count)
+ {
+ unsigned int i, j;
+ store_fwd_info *it;
+ VEC_ORDERED_REMOVE_IF (store_exprs, i, j, it, it->remove);
+ }
+
+ /* Don't consider store forwarding if the RTL instruction distance is
+ more than PARAM_STORE_FORWARDING_MAX_DISTANCE. */
+ if (!store_exprs.is_empty ()
+ && (store_exprs[0].insn_cnt
+ + param_store_forwarding_max_distance <= insn_cnt))
+ store_exprs.ordered_remove (0);
+
+ insn_cnt++;
+ }
+}
+
+unsigned int
+pass_rtl_avoid_store_forwarding::execute (function *fn)
+{
+ df_set_flags (DF_DEFER_INSN_RESCAN);
+ df_note_add_problem ();
+
+ init_alias_analysis ();
+ cselib_init (CSELIB_RECORD_MEMORY | CSELIB_PRESERVE_CONSTANTS);
+
+ stats_sf_detected = 0;
+ stats_sf_avoided = 0;
+
+ basic_block bb;
+ FOR_EACH_BB_FN (bb, fn)
+ avoid_store_forwarding (bb);
+
+ end_alias_analysis ();
+ cselib_finish ();
+ df_analyze ();
+
+ statistics_counter_event (fn, "Store forwardings detected: ",
+ stats_sf_detected);
+ statistics_counter_event (fn, "Store forwardings avoided: ",
+ stats_sf_detected);
+
+ return 0;
+}
+
+} // anon namespace.
+
+rtl_opt_pass *
+make_pass_rtl_avoid_store_forwarding (gcc::context *ctxt)
+{
+ return new pass_rtl_avoid_store_forwarding (ctxt);
+}
new file mode 100644
@@ -0,0 +1,50 @@
+/* Avoid store forwarding optimization pass.
+ Copyright (C) 2024 Free Software Foundation, Inc.
+ Contributed by VRULL GmbH.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify it
+ under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3, or (at your option)
+ any later version.
+
+ GCC is distributed in the hope that it will be useful, but
+ WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with GCC; see the file COPYING3. If not see
+ <http://www.gnu.org/licenses/>. */
+
+#ifndef GCC_AVOID_STORE_FORWARDING_H
+#define GCC_AVOID_STORE_FORWARDING_H
+
+#include "config.h"
+#include "system.h"
+#include "coretypes.h"
+#include "backend.h"
+#include "rtl.h"
+
+struct store_fwd_info
+{
+ /* The store instruction that is a store forwarding candidate. */
+ rtx_insn *store_insn;
+ /* SET_DEST (single_set (store_insn)). */
+ rtx store_mem;
+ /* The temporary that will hold the stored value at the original store
+ position. */
+ rtx mov_reg;
+ /* The instruction sequence that inserts the stored value's bits at the
+ appropriate position in the loaded value. */
+ rtx_insn *bits_insert_insns;
+ /* The byte offset for the store's position within the load. */
+ HOST_WIDE_INT offset;
+
+ unsigned int insn_cnt;
+ bool remove;
+ bool forwarded;
+};
+
+#endif /* GCC_AVOID_STORE_FORWARDING_H */
@@ -1747,6 +1747,10 @@ fgcse-sm
Common Var(flag_gcse_sm) Init(0) Optimization
Perform store motion after global common subexpression elimination.
+favoid-store-forwarding
+Common Var(flag_avoid_store_forwarding) Init(0) Optimization
+Try to avoid store forwarding.
+
fgcse-las
Common Var(flag_gcse_las) Init(0) Optimization
Perform redundant load after store elimination in global common subexpression
@@ -12717,6 +12717,15 @@ loop unrolling.
This option is enabled by default at optimization levels @option{-O1},
@option{-O2}, @option{-O3}, @option{-Os}.
+@opindex favoid-store-forwarding
+@item -favoid-store-forwarding
+@itemx -fno-avoid-store-forwarding
+Many CPUs will stall for many cycles when a load partially depends on previous
+smaller stores. This pass tries to detect such cases and avoid the penalty by
+changing the order of the load and store and then fixing up the loaded value.
+
+Disabled by default.
+
@opindex ffp-contract
@item -ffp-contract=@var{style}
@option{-ffp-contract=off} disables floating-point expression contraction.
@@ -925,6 +925,14 @@ and addressing mode selection. The pass is run twice, with values
being propagated into loops only on the second run. The code is
located in @file{fwprop.cc}.
+@item Store forwarding avoidance
+
+This pass attempts to reduce the overhead of store to load forwarding.
+It detects when a load reads from one or more previous smaller stores and
+then rearranges them so that the stores are done after the load. The loaded
+value is adjusted with a series of bit insert instructions so that it stays
+the same. The code is located in @file{avoid-store-forwarding.cc}.
+
@item Common subexpression elimination
This pass removes redundant computation within basic blocks, and
@@ -7330,6 +7330,15 @@ the @code{POLY_VALUE_MIN}, @code{POLY_VALUE_MAX} and
implementation returns the lowest possible value of @var{val}.
@end deftypefn
+@deftypefn {Target Hook} bool TARGET_AVOID_STORE_FORWARDING_P (vec<store_fwd_info>, @var{rtx}, @var{int}, @var{bool})
+This hook, if defined, enables the use of the avoid-store-forwarding pass.
+Given a list of stores and a load instruction that reads from the location
+of the stores, this hook decides if it's profitable to emit additional code
+to avoid a potential store forwarding stall. The additional instructions
+needed, the sequence cost and additional relevant information is given in
+the arguments so that the target can make an informed decision.
+@end deftypefn
+
@node Scheduling
@section Adjusting the Instruction Scheduler
@@ -4741,6 +4741,8 @@ Define this macro if a non-short-circuit operation produced by
@hook TARGET_ESTIMATED_POLY_VALUE
+@hook TARGET_AVOID_STORE_FORWARDING_P
+
@node Scheduling
@section Adjusting the Instruction Scheduler
@@ -1032,6 +1032,10 @@ Allow the store merging pass to introduce unaligned stores if it is legal to do
Common Joined UInteger Var(param_store_merging_max_size) Init(65536) IntegerRange(1, 65536) Param Optimization
Maximum size of a single store merging region in bytes.
+-param=store-forwarding-max-distance=
+Common Joined UInteger Var(param_store_forwarding_max_distance) Init(10) IntegerRange(1, 1000) Param Optimization
+Maximum number of instruction distance that a small store forwarded to a larger load may stall.
+
-param=switch-conversion-max-branch-ratio=
Common Joined UInteger Var(param_switch_conversion_branch_ratio) Init(8) IntegerRange(1, 65536) Param Optimization
The maximum ratio between array size and switch branches for a switch conversion to take place.
@@ -507,6 +507,7 @@ along with GCC; see the file COPYING3. If not see
NEXT_PASS (pass_sms);
NEXT_PASS (pass_live_range_shrinkage);
NEXT_PASS (pass_sched);
+ NEXT_PASS (pass_rtl_avoid_store_forwarding);
NEXT_PASS (pass_early_remat);
NEXT_PASS (pass_ira);
NEXT_PASS (pass_reload);
@@ -6934,6 +6934,17 @@ HOOK_VECTOR_END (shrink_wrap)
#undef HOOK_PREFIX
#define HOOK_PREFIX "TARGET_"
+DEFHOOK
+(avoid_store_forwarding_p,
+ "This hook, if defined, enables the use of the avoid-store-forwarding pass.\n\
+Given a list of stores and a load instruction that reads from the location\n\
+of the stores, this hook decides if it's profitable to emit additional code\n\
+to avoid a potential store forwarding stall. The additional instructions\n\
+needed, the sequence cost and additional relevant information is given in\n\
+the arguments so that the target can make an informed decision.",
+ bool, (vec<store_fwd_info>, rtx, int, bool),
+ NULL)
+
/* Determine the type of unwind info to emit for debugging. */
DEFHOOK
(debug_unwind_info,
@@ -165,6 +165,9 @@ class function_arg_info;
/* This is defined in function-abi.h. */
class predefined_function_abi;
+/* This is defined in avoid-store-forwarding.h . */
+struct store_fwd_info;
+
/* These are defined in tree-vect-stmts.cc. */
extern tree stmt_vectype (class _stmt_vec_info *);
extern bool stmt_in_inner_loop_p (class vec_info *, class _stmt_vec_info *);
new file mode 100644
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -favoid-store-forwarding -fdump-rtl-avoid_store_forwarding" } */
+
+typedef union {
+ char arr_8[8];
+ long long_value;
+} DataUnion;
+
+long ssll_1 (DataUnion *data, char x)
+{
+ data->arr_8[0] = x;
+ return data->long_value;
+}
+
+long ssll_2 (DataUnion *data, char x)
+{
+ data->arr_8[1] = x;
+ return data->long_value;
+}
+
+long ssll_3 (DataUnion *data, char x)
+{
+ data->arr_8[7] = x;
+ return data->long_value;
+}
+
+/* { dg-final { scan-rtl-dump-times "Store forwarding detected" 3 "avoid_store_forwarding" } } */
+/* { dg-final { scan-rtl-dump-times "Store forwarding avoided" 3 "avoid_store_forwarding" } } */
new file mode 100644
@@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -favoid-store-forwarding -fdump-rtl-avoid_store_forwarding" } */
+
+typedef union {
+ char arr_8[8];
+ int long_value;
+} DataUnion1;
+
+long no_ssll_1 (DataUnion1 *data, char x)
+{
+ data->arr_8[4] = x;
+ return data->long_value;
+}
+
+long no_ssll_2 (DataUnion1 *data, char x)
+{
+ data->arr_8[5] = x;
+ return data->long_value;
+}
+
+typedef union {
+ char arr_8[8];
+ short long_value[4];
+} DataUnion2;
+
+long no_ssll_3 (DataUnion2 *data, char x)
+{
+ data->arr_8[4] = x;
+ return data->long_value[1];
+}
+
+long no_ssll_4 (DataUnion2 *data, char x)
+{
+ data->arr_8[0] = x;
+ return data->long_value[1];
+}
+
+/* { dg-final { scan-rtl-dump-times "Store forwarding detected" 0 "avoid_store_forwarding" } } */
+/* { dg-final { scan-rtl-dump-times "Store forwarding avoided" 0 "avoid_store_forwarding" } } */
new file mode 100644
@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -favoid-store-forwarding -fdump-rtl-avoid_store_forwarding" } */
+
+typedef union {
+ char arr_8[8];
+ long long_value;
+} DataUnion;
+
+long ssll_multi_1 (DataUnion *data, char x)
+{
+ data->arr_8[0] = x;
+ data->arr_8[2] = x;
+ return data->long_value;
+}
+
+long ssll_multi_2 (DataUnion *data, char x)
+{
+ data->arr_8[0] = x;
+ data->arr_8[1] = 11;
+ return data->long_value;
+}
+
+long ssll_multi_3 (DataUnion *data, char x, short y)
+{
+ data->arr_8[1] = x;
+ __builtin_memcpy(data->arr_8 + 4, &y, sizeof(short));
+ return data->long_value;
+}
+
+/* { dg-final { scan-rtl-dump-times "Store forwardings detected" 3 "avoid_store_forwarding" } } */
+/* { dg-final { scan-rtl-dump-times "Store forwardings avoided" 3 "avoid_store_forwarding" } } */
new file mode 100644
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -favoid-store-forwarding -fdump-rtl-avoid_store_forwarding" } */
+
+typedef int v4si __attribute__ ((vector_size (16)));
+
+typedef union {
+ char arr_16[16];
+ v4si vec_value;
+} DataUnion;
+
+v4si ssll_vect_1 (DataUnion *data, char x)
+{
+ data->arr_16[0] = x;
+ return data->vec_value;
+}
+
+v4si ssll_vect_2 (DataUnion *data, int x)
+{
+ __builtin_memcpy(data->arr_16 + 4, &x, sizeof(int));
+ return data->vec_value;
+}
+
+/* { dg-final { scan-rtl-dump-times "Store forwarding detected" 2 "avoid_store_forwarding" } } */
new file mode 100644
@@ -0,0 +1,38 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2 -favoid-store-forwarding -fdump-rtl-avoid_store_forwarding" } */
+
+typedef float v4f __attribute__ ((vector_size (16)));
+
+typedef union {
+ float arr_2[4];
+ long long_value;
+ __int128 longlong_value;
+ v4f vec_value;
+} DataUnion;
+
+long ssll_load_elim_1 (DataUnion *data, float x)
+{
+ data->arr_2[0] = x;
+ data->arr_2[1] = 0.0f;
+ return data->long_value;
+}
+
+__int128 ssll_load_elim_2 (DataUnion *data, float x)
+{
+ data->arr_2[0] = x;
+ data->arr_2[1] = 0.0f;
+ data->arr_2[2] = x;
+ data->arr_2[3] = 0.0f;
+ return data->longlong_value;
+}
+
+v4f ssll_load_elim_3 (DataUnion *data, float x)
+{
+ data->arr_2[3] = x;
+ data->arr_2[2] = x;
+ data->arr_2[1] = x;
+ data->arr_2[0] = x;
+ return data->vec_value;
+}
+
+/* { dg-final { scan-rtl-dump-times "Store forwardings detected" 3 "avoid_store_forwarding" } } */
@@ -571,6 +571,7 @@ extern rtl_opt_pass *make_pass_rtl_dse3 (gcc::context *ctxt);
extern rtl_opt_pass *make_pass_rtl_cprop (gcc::context *ctxt);
extern rtl_opt_pass *make_pass_rtl_pre (gcc::context *ctxt);
extern rtl_opt_pass *make_pass_rtl_hoist (gcc::context *ctxt);
+extern rtl_opt_pass *make_pass_rtl_avoid_store_forwarding (gcc::context *ctxt);
extern rtl_opt_pass *make_pass_rtl_store_motion (gcc::context *ctxt);
extern rtl_opt_pass *make_pass_cse_after_global_opts (gcc::context *ctxt);
extern rtl_opt_pass *make_pass_rtl_ifcvt (gcc::context *ctxt);