[gcc(refs/users/meissner/heads/work019)] Power10: Add PCREL_OPT for loads.
Michael Meissner
meissner@gcc.gnu.org
Wed Sep 30 20:06:36 GMT 2020
https://gcc.gnu.org/g:914962f217914e8a4d41c1b3c033422c615b5acb
commit 914962f217914e8a4d41c1b3c033422c615b5acb
Author: Michael Meissner <meissner@linux.ibm.com>
Date: Wed Sep 30 16:06:02 2020 -0400
Power10: Add PCREL_OPT for loads.
gcc/
2020-09-30 Michael Meissner <meissner@linux.ibm.com>
* config.gcc (powerpc*-*-*): Add pcrel-opt.o.
(rs6000*-*-*): Add pcrel-opt.o.
* config/rs6000/pcrel-opt.c: New file.
* config/rs6000/pcrel-opt.md: New file.
* config/rs6000/predicates.md (d_form_memory): New predicate.
* config/rs6000/rs6000-cpus.def (OTHER_POWER10_MASKS): Add
-mpcrel-opt.
(POWERPC_MASKS): Add -mpcrel-opt.
* config/rs6000/rs6000-passes.def: Add comment for existing power8
swaps pass. Add PCREL_OPT pass.
* config/rs6000/rs6000-protos.h (reg_to_non_prefixed): New
declaration.
(offsettable_non_prefixed_memory): New declaration.
(output_pcrel_opt_reloc): New declaration.
(make_pass_pcrel_opt): New declaration.
* config/rs6000/rs6000.c (reg_to_non_prefixed): Make function
globally visible.
(rs6000_option_override_internal): Add support for -mpcrel-opt.
(rs6000_delegitimize_address): Add support for the PCREL_OPT
addresses.
(rs6000_opt_masks): Add -mpcrel-opt.
(offsettable_non_prefixed_memory): New helper function.
(rs6000_asm_output_opcode): Reset prefixed flag after first use.
(output_pcrel_opt_reloc): New function.
* config/rs6000/rs6000.md (loads_extern_addr): New insn
attribute.
(pcrel_extern_addr): Set loads_extern_addr attribute.
(toplevel): Include pcrel-opt.md.
* config/rs6000/rs6000.opt (-mpcrel-opt): New option.
* config/rs6000/t-rs6000 (pcrel-opt.o): Add build rules.
(MD_INCLUDES): Add pcrel-opt.md
Diff:
---
gcc/config.gcc | 6 +-
gcc/config/rs6000/pcrel-opt.c | 590 ++++++++++++++++++++++++++++++++++++
gcc/config/rs6000/pcrel-opt.md | 256 ++++++++++++++++
gcc/config/rs6000/predicates.md | 23 ++
gcc/config/rs6000/rs6000-cpus.def | 2 +
gcc/config/rs6000/rs6000-passes.def | 8 +
gcc/config/rs6000/rs6000-protos.h | 4 +
gcc/config/rs6000/rs6000.c | 105 ++++++-
gcc/config/rs6000/rs6000.md | 8 +-
gcc/config/rs6000/rs6000.opt | 4 +
gcc/config/rs6000/t-rs6000 | 7 +-
11 files changed, 1004 insertions(+), 9 deletions(-)
diff --git a/gcc/config.gcc b/gcc/config.gcc
index 2d0cfde284b..fabe4678c1e 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -507,7 +507,7 @@ or1k*-*-*)
;;
powerpc*-*-*)
cpu_type=rs6000
- extra_objs="rs6000-string.o rs6000-p8swap.o rs6000-logue.o rs6000-call.o"
+ extra_objs="rs6000-string.o rs6000-p8swap.o rs6000-logue.o rs6000-call.o pcrel-opt.o"
extra_headers="ppc-asm.h altivec.h htmintrin.h htmxlintrin.h"
extra_headers="${extra_headers} bmi2intrin.h bmiintrin.h"
extra_headers="${extra_headers} xmmintrin.h mm_malloc.h emmintrin.h"
@@ -522,6 +522,7 @@ powerpc*-*-*)
esac
extra_options="${extra_options} g.opt fused-madd.opt rs6000/rs6000-tables.opt"
target_gtfiles="$target_gtfiles \$(srcdir)/config/rs6000/rs6000-logue.c \$(srcdir)/config/rs6000/rs6000-call.c"
+ target_gtfiles="$target_gtfiles \$(srcdir)/config/rs6000/pcrel-opt.c"
;;
pru-*-*)
cpu_type=pru
@@ -533,8 +534,9 @@ riscv*)
;;
rs6000*-*-*)
extra_options="${extra_options} g.opt fused-madd.opt rs6000/rs6000-tables.opt"
- extra_objs="rs6000-string.o rs6000-p8swap.o rs6000-logue.o rs6000-call.o"
+ extra_objs="rs6000-string.o rs6000-p8swap.o rs6000-logue.o rs6000-call.o pcrel-opt.o"
target_gtfiles="$target_gtfiles \$(srcdir)/config/rs6000/rs6000-logue.c \$(srcdir)/config/rs6000/rs6000-call.c"
+ target_gtfiles="$target_gtfiles \$(srcdir)/config/rs6000/pcrel-opt.c"
;;
sparc*-*-*)
cpu_type=sparc
diff --git a/gcc/config/rs6000/pcrel-opt.c b/gcc/config/rs6000/pcrel-opt.c
new file mode 100644
index 00000000000..f831853c90b
--- /dev/null
+++ b/gcc/config/rs6000/pcrel-opt.c
@@ -0,0 +1,590 @@
+/* Subroutines used support the pc-relative linker optimization.
+ Copyright (C) 2020 Free Software Foundation, Inc.
+
+ 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/>. */
+
+/* This file implements a RTL pass that looks for pc-relative loads of the
+ address of an external variable using the PCREL_GOT relocation and a single
+ load that uses that external address. If that is found we create the
+ PCREL_OPT relocation to possibly convert:
+
+ pld addr_reg,var@pcrel@got
+
+ <possibly other insns that do not use 'addr_reg' or 'data_reg'>
+
+ lwz data_reg,0(addr_reg)
+
+ into:
+
+ plwz data_reg,var@pcrel
+
+ <possibly other insns that do not use 'addr_reg' or 'data_reg'>
+
+ nop
+
+ If the variable is not defined in the main program or the code using it is
+ not in the main program, the linker put the address in the .got section and
+ do:
+
+ .section .got
+ .Lvar_got:
+ .dword var
+
+ .section .text
+ pld addr_reg,.Lvar_got@pcrel
+
+ <possibly other insns that do not use 'addr_reg' or 'data_reg'>
+
+ lwz data_reg,0(addr_reg)
+
+ We only look for a single usage in the basic block where the external
+ address is loaded. Multiple uses or references in another basic block will
+ force us to not use the PCREL_OPT relocation. */
+
+#define IN_TARGET_CODE 1
+
+#include "config.h"
+#include "system.h"
+#include "coretypes.h"
+#include "backend.h"
+#include "rtl.h"
+#include "tree.h"
+#include "memmodel.h"
+#include "expmed.h"
+#include "optabs.h"
+#include "recog.h"
+#include "df.h"
+#include "tm_p.h"
+#include "ira.h"
+#include "print-tree.h"
+#include "varasm.h"
+#include "explow.h"
+#include "expr.h"
+#include "output.h"
+#include "tree-pass.h"
+#include "rtx-vector-builder.h"
+#include "print-rtl.h"
+#include "insn-attr.h"
+#include "insn-codes.h"
+
+/* Various counters. */
+static struct {
+ unsigned long extern_addrs;
+ unsigned long loads;
+ unsigned long adjacent_loads;
+ unsigned long failed_loads;
+} counters;
+
+/* Return a marker to identify the PCREL_OPT load address and load
+ instruction. We use a constant integer which is added to ".Lpcrel" to make
+ the label. */
+
+static rtx
+pcrel_opt_next_marker (void)
+{
+ static unsigned int pcrel_opt_next_num;
+
+ pcrel_opt_next_num++;
+ return GEN_INT (pcrel_opt_next_num);
+}
+
+/* Optimize a PC-relative load address to be used in a load.
+
+ If the sequence of insns is safe to use the PCREL_OPT optimization (i.e. no
+ additional references to the address register, the address register dies at
+ the load, and no references to the load), convert insns of the form:
+
+ (set (reg:DI addr)
+ (symbol_ref:DI "ext_symbol"))
+
+ ...
+
+ (set (reg:<MODE> value)
+ (mem:<MODE> (reg:DI addr)))
+
+ into:
+
+ (parallel [(set (reg:DI addr)
+ (unspec:<MODE> [(symbol_ref:DI "ext_symbol")
+ (const_int label_num)
+ (const_int 0)]
+ UNSPEC_PCREL_OPT_LD_ADDR))
+ (set (reg:DI data)
+ (unspec:DI [(const_int 0)]
+ UNSPEC_PCREL_OPT_LD_ADDR))])
+
+ ...
+
+ (parallel [(set (reg:<MODE>)
+ (unspec:<MODE> [(mem:<MODE> (reg:DI addr))
+ (reg:DI data)
+ (const_int label_num)]
+ UNSPEC_PCREL_OPT_LD_RELOC))
+ (clobber (reg:DI addr))])
+
+ If the register being loaded is the same register that was used to hold the
+ external address, we generate the following insn instead:
+
+ (set (reg:DI data)
+ (unspec:DI [(symbol_ref:DI "ext_symbol")
+ (const_int label_num)
+ (const_int 1)]
+ UNSPEC_PCREL_OPT_LD_ADDR))
+
+ In the first insn, we set both the address of the external variable, and
+ mark that the variable being loaded both are created in that insn, and are
+ consumed in the second insn. It doesn't matter what mode the register that
+ we will ultimately do the load into, so we use DImode. We just need to mark
+ that both registers may be set in the first insn, and will be used in the
+ second insn.
+
+ The UNSPEC_PCREL_OPT_LD_ADDR insn will generate the load address plus
+ a definition of a label (.Lpcrel<n>), while the UNSPEC_PCREL_OPT_LD_RELOC
+ insn will generate the .reloc to tell the linker to tie the load address and
+ load using that address together.
+
+ pld b,ext_symbol@got@pcrel
+ .Lpcrel1:
+
+ ...
+
+ .reloc .Lpcrel1-8,R_PPC64_PCREL_OPT,.-(.Lpcrel1-8)
+ lwz r,0(b)
+
+ If ext_symbol is defined in another object file in the main program and we
+ are linking the main program, the linker will convert the above instructions
+ to:
+
+ plwz r,ext_symbol@got@pcrel
+
+ ...
+
+ nop */
+
+static void
+pcrel_opt_load (rtx_insn *addr_insn, /* insn loading address. */
+ rtx_insn *load_insn) /* insn using address. */
+{
+ rtx addr_set = PATTERN (addr_insn);
+ gcc_assert (GET_CODE (addr_set) == SET);
+
+ rtx addr_reg = SET_DEST (addr_set);
+ gcc_assert (base_reg_operand (addr_reg, Pmode));
+
+ rtx addr_symbol = SET_SRC (addr_set);
+ gcc_assert (pcrel_external_address (addr_symbol, Pmode));
+
+ rtx load_set = PATTERN (load_insn);
+ gcc_assert (GET_CODE (load_set) == SET);
+
+ /* Make sure there are no references to the register being loaded inbetween
+ the two insns. */
+ rtx reg = SET_DEST (load_set);
+ if (!register_operand (reg, GET_MODE (reg))
+ || reg_used_between_p (reg, addr_insn, load_insn)
+ || reg_set_between_p (reg, addr_insn, load_insn))
+ return;
+
+ rtx mem = SET_SRC (load_set);
+ machine_mode reg_mode = GET_MODE (reg);
+ machine_mode mem_mode = GET_MODE (mem);
+ rtx mem_inner = mem;
+ unsigned int reg_regno = reg_or_subregno (reg);
+
+ /* LWA is a DS format instruction, but LWZ is a D format instruction. We use
+ DImode for the mode to force checking whether the bottom 2 bits are 0.
+ However FPR and vector registers uses the LFIWAX/LXSIWAX instructions
+ which only have indexed forms. */
+ if (GET_CODE (mem) == SIGN_EXTEND && GET_MODE (XEXP (mem, 0)) == SImode)
+ {
+ if (!INT_REGNO_P (reg_regno))
+ return;
+
+ mem_inner = XEXP (mem, 0);
+ mem_mode = DImode;
+ }
+
+ else if (GET_CODE (mem) == SIGN_EXTEND
+ || GET_CODE (mem) == ZERO_EXTEND
+ || GET_CODE (mem) == FLOAT_EXTEND)
+ {
+ mem_inner = XEXP (mem, 0);
+ mem_mode = GET_MODE (mem_inner);
+ }
+
+ if (!MEM_P (mem_inner))
+ return;
+
+ /* If the address isn't a non-prefixed offsettable instruction, we can't do
+ the optimization. */
+ if (!offsettable_non_prefixed_memory (reg, mem_mode, mem_inner))
+ return;
+
+ /* Allocate a new PC-relative label, and update the load external address
+ insn.
+
+ If the register being loaded is different from the address register, we
+ need to indicate both registers are set at the load of the address.
+
+ (parallel [(set (reg load)
+ (unspec [(symbol_ref addr_symbol)
+ (const_int label_num)]
+ UNSPEC_PCREL_OPT_LD_ADDR))
+ (set (reg addr)
+ (unspec [(const_int 0)]
+ UNSPEC_PCREL_OPT_LD_ADDR))])
+
+ If the register being loaded is the same as the address register, we use
+ an alternate form:
+
+ (set (reg load)
+ (unspec [(symbol_ref addr_symbol)
+ (const_int label_num)]
+ UNSPEC_PCREL_OPT_LD_ADDR_SAME_REG)) */
+ unsigned int addr_regno = reg_or_subregno (addr_reg);
+ rtx label_num = pcrel_opt_next_marker ();
+ rtx reg_di = gen_rtx_REG (DImode, reg_regno);
+ rtx addr_pattern;
+
+ /* Create the load address, either using the pattern with an explicit clobber
+ if the address register is not the same as the register being loaded, or
+ using the pattern that requires the address register to be the address
+ loaded. */
+ if (addr_regno != reg_regno)
+ addr_pattern = gen_pcrel_opt_ld_addr (addr_reg, addr_symbol, label_num,
+ reg_di);
+ else
+ addr_pattern = gen_pcrel_opt_ld_addr_same_reg (addr_reg, addr_symbol,
+ label_num);
+
+ validate_change (addr_insn, &PATTERN (addr_insn), addr_pattern, true);
+
+ /* Update the load insn. If the mem had a sign/zero/float extend, add that
+ also after doing the UNSPEC. Add an explicit clobber of the external
+ address register just to make it clear that the address register dies.
+
+ (parallel [(set (reg:<MODE> data)
+ (unspec:<MODE> [(mem (addr_reg)
+ (reg:DI data)
+ (const_int label_num)]
+ UNSPEC_PCREL_OPT_LD_RELOC))
+ (clobber (reg:DI addr_reg))]) */
+ rtvec v_load = gen_rtvec (3, mem_inner, reg_di, label_num);
+ rtx new_load = gen_rtx_UNSPEC (GET_MODE (mem_inner), v_load,
+ UNSPEC_PCREL_OPT_LD_RELOC);
+
+ if (GET_CODE (mem) != GET_CODE (mem_inner))
+ new_load = gen_rtx_fmt_e (GET_CODE (mem), reg_mode, new_load);
+
+ rtx new_load_set = gen_rtx_SET (reg, new_load);
+ rtx load_clobber = gen_rtx_CLOBBER (VOIDmode,
+ (addr_regno == reg_regno
+ ? gen_rtx_SCRATCH (Pmode)
+ : addr_reg));
+ rtx new_load_pattern
+ = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (2, new_load_set, load_clobber));
+
+ validate_change (load_insn, &PATTERN (load_insn), new_load_pattern, true);
+
+ /* Note whether the changes were sucessful or not. */
+ if (apply_change_group ())
+ {
+ /* PCREL_OPT load optimization succeeded. */
+ counters.loads++;
+ if (next_nonnote_insn (addr_insn) == load_insn)
+ counters.adjacent_loads++;
+
+ if (dump_file)
+ fprintf (dump_file,
+ "PCREL_OPT load (addr insn = %d, use insn = %d).\n",
+ INSN_UID (addr_insn),
+ INSN_UID (load_insn));
+ }
+ else
+ {
+ /* PCREL_OPT load optimization did not succeed. */
+ counters.failed_loads++;
+ if (dump_file)
+ fprintf (dump_file,
+ "PCREL_OPT load failed (addr insn = %d, use insn = %d).\n",
+ INSN_UID (addr_insn),
+ INSN_UID (load_insn));
+ }
+
+ return;
+}
+
+/* Given an insn with that loads up a base register with the address of an
+ external symbol, see if we can optimize it with the PCREL_OPT
+ optimization. */
+
+static void
+pcrel_opt_address (rtx_insn *addr_insn)
+{
+ counters.extern_addrs++;
+
+ /* Do some basic validation. */
+ rtx addr_set = PATTERN (addr_insn);
+ if (GET_CODE (addr_set) != SET)
+ return;
+
+ rtx addr_reg = SET_DEST (addr_set);
+ rtx addr_symbol = SET_SRC (addr_set);
+
+ if (!base_reg_operand (addr_reg, Pmode)
+ || !pcrel_external_address (addr_symbol, Pmode))
+ return;
+
+ /* The address register must have exactly one definition. */
+ struct df_insn_info *insn_info = DF_INSN_INFO_GET (addr_insn);
+ if (!insn_info)
+ return;
+
+ df_ref def = df_single_def (insn_info);
+ if (!def)
+ return;
+
+ /* Is there only one use? */
+ df_link *chain = DF_REF_CHAIN (def);
+ if (!chain || chain->next)
+ return;
+
+ /* Get the insn of the possible load. */
+ df_ref use = chain->ref;
+ if (!use)
+ return;
+
+ rtx_insn *use_insn = DF_REF_INSN (use);
+
+ /* The use instruction must be a single non-prefixed instruction. */
+ if (get_attr_length (use_insn) != 4)
+ return;
+
+ /* The address and the memory operation must be in the same basic block. */
+ if (BLOCK_FOR_INSN (use_insn) != BLOCK_FOR_INSN (addr_insn))
+ return;
+
+ /* If this isn't a simple SET, skip doing the optimization. */
+ if (GET_CODE (PATTERN (use_insn)) != SET)
+ return;
+
+ /* Check the insns between loading the address and its use to classify what
+ type of insn it is. */
+ bool load_insns_found = false;
+ bool store_insns_found = false;
+ bool do_pcrel_opt = true;
+ rtx_insn *insn;
+ rtx_insn *last_insn_in_bb = BB_END (BLOCK_FOR_INSN (use_insn));
+
+
+ for (insn = NEXT_INSN (addr_insn);
+ insn != use_insn && do_pcrel_opt;
+ insn = NEXT_INSN (insn))
+ {
+ /* If we see things like labels, calls, etc. don't do the PCREL_OPT
+ optimization. */
+ if (!insn
+ || LABEL_P (insn)
+ || JUMP_P (insn)
+ || CALL_P (insn)
+ || BARRIER_P (insn))
+ {
+ do_pcrel_opt = false;
+ break;
+ }
+
+ /* For a normal insn, see if it is a load or store. */
+ if (NONDEBUG_INSN_P (insn)
+ && GET_CODE (PATTERN (insn)) != USE
+ && GET_CODE (PATTERN (insn)) != CLOBBER)
+ {
+ switch (get_attr_type (insn))
+ {
+ /* While load of the external address is a 'load' for scheduling
+ purposes, it should be safe to allow loading other external
+ addresses between the load of the external address we are
+ currently looking at and the load or store using that
+ address. */
+ case TYPE_LOAD:
+ if (get_attr_loads_extern_addr (insn) != LOADS_EXTERN_ADDR_YES)
+ load_insns_found = true;
+ break;
+
+ case TYPE_FPLOAD:
+ case TYPE_VECLOAD:
+ load_insns_found = true;
+ break;
+
+ case TYPE_STORE:
+ case TYPE_FPSTORE:
+ case TYPE_VECSTORE:
+ store_insns_found = true;
+ break;
+
+ /* Don't do the optimization through atomic operations. */
+ case TYPE_LOAD_L:
+ case TYPE_STORE_C:
+ case TYPE_HTM:
+ case TYPE_HTMSIMPLE:
+ do_pcrel_opt = false;
+ break;
+
+ default:
+ break;
+ }
+ }
+
+ /* If this is the last insn in the basic block, and we haven't found the
+ load, exit. */
+ if (insn == last_insn_in_bb)
+ {
+ do_pcrel_opt = false;
+ break;
+ }
+ }
+
+ /* Don't do the optimization if something went wrong. */
+ if (!do_pcrel_opt)
+ return;
+
+ /* Is this a load? */
+ switch (get_attr_type (use_insn))
+ {
+ /* Don't do the PCREL_OPT load optimization if there was a store
+ operation. Perhaps the store might be to the global variable through
+ a pointer. */
+ case TYPE_LOAD:
+ case TYPE_FPLOAD:
+ case TYPE_VECLOAD:
+ if (store_insns_found)
+ break;
+
+ pcrel_opt_load (addr_insn, use_insn);
+ break;
+
+ /* If the use is not a load, just skip the optimization. */
+ default:
+ break;
+ }
+
+ return;
+}
+
+/* Optimize pcrel external variable references. */
+
+static unsigned int
+pcrel_opt_pass (function *fun)
+{
+ basic_block bb;
+ rtx_insn *insn, *curr_insn = 0;
+
+ memset ((char *) &counters, '\0', sizeof (counters));
+
+ /* Dataflow analysis for use-def chains. */
+ df_set_flags (DF_RD_PRUNE_DEAD_DEFS);
+ df_chain_add_problem (DF_DU_CHAIN);
+ df_note_add_problem ();
+ df_analyze ();
+ df_set_flags (DF_DEFER_INSN_RESCAN | DF_LR_RUN_DCE);
+
+ if (dump_file)
+ fprintf (dump_file, "\n");
+
+ /* Look at each basic block to see if there is a load of an external
+ variable's external address, and a single load using that external
+ address. */
+ FOR_ALL_BB_FN (bb, fun)
+ {
+ FOR_BB_INSNS_SAFE (bb, insn, curr_insn)
+ {
+ if (NONJUMP_INSN_P (insn)
+ && single_set (insn)
+ && get_attr_loads_extern_addr (insn) == LOADS_EXTERN_ADDR_YES)
+ pcrel_opt_address (insn);
+ }
+ }
+
+ if (dump_file)
+ {
+ fprintf (dump_file,
+ "\n# of load(s) of an address of an external symbol = %lu\n",
+ counters.extern_addrs);
+
+ fprintf (dump_file, "# of PCREL_OPT load(s) = %lu (adjacent %lu)\n",
+ counters.loads, counters.adjacent_loads);
+
+ if (counters.failed_loads)
+ fprintf (dump_file, "# of failed PCREL_OPT load(s) = %lu\n",
+ counters.failed_loads);
+
+ fprintf (dump_file, "\n");
+ }
+
+ df_remove_problem (df_chain);
+ df_process_deferred_rescans ();
+ df_set_flags (DF_RD_PRUNE_DEAD_DEFS | DF_LR_RUN_DCE);
+ df_analyze ();
+ return 0;
+}
+
+/* Optimize pc-relative references for the new PCREL_OPT pass. */
+const pass_data pass_data_pcrel_opt =
+{
+ RTL_PASS, /* type. */
+ "pcrel_opt", /* 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. */
+};
+
+/* Pass data structures. */
+class pcrel_opt : public rtl_opt_pass
+{
+public:
+ pcrel_opt (gcc::context *ctxt)
+ : rtl_opt_pass (pass_data_pcrel_opt, ctxt)
+ {}
+
+ ~pcrel_opt (void)
+ {}
+
+ /* opt_pass methods: */
+ virtual bool gate (function *)
+ {
+ return (TARGET_PCREL && TARGET_PCREL_OPT && optimize);
+ }
+
+ virtual unsigned int execute (function *fun)
+ {
+ return pcrel_opt_pass (fun);
+ }
+
+ opt_pass *clone ()
+ {
+ return new pcrel_opt (m_ctxt);
+ }
+};
+
+rtl_opt_pass *
+make_pass_pcrel_opt (gcc::context *ctxt)
+{
+ return new pcrel_opt (ctxt);
+}
diff --git a/gcc/config/rs6000/pcrel-opt.md b/gcc/config/rs6000/pcrel-opt.md
new file mode 100644
index 00000000000..70d4d8911b6
--- /dev/null
+++ b/gcc/config/rs6000/pcrel-opt.md
@@ -0,0 +1,256 @@
+;; Machine description for the PCREL_OPT optimization.
+;; Copyright (C) 2020 Free Software Foundation, Inc.
+;; Contributed by Michael Meissner (meissner@linux.ibm.com)
+
+;; 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/>.
+
+;; Support for the PCREL_OPT optimization. PCREL_OPT looks for instances where
+;; an external variable is used only once, either for reading or for writing.
+;;
+;; If we are optimizing a single read, normally the code would look like:
+;;
+;; (set (reg:DI <ptr>)
+;; (symbol_ref:DI "<extern_addr>")) # <data> is currently dead
+;;
+;; ... # insns do not need to be adjacent
+;;
+;; (set (reg:SI <data>)
+;; (mem:SI (reg:DI <xxx>))) # <ptr> dies with this insn
+;;
+;; We transform this into:
+;;
+;; (parallel [(set (reg:DI <ptr>)
+;; (unspec:SI [(symbol_ref:DI <extern_addr>)
+;; (const_int <marker>)]
+;; UNSPEC_PCREL_OPT_LD_ADDR))
+;; (set (reg:DI <data>)
+;; (unspec:DI [(const_int 0)]
+;; UNSPEC_PCREL_OPT_LD_ADDR))])
+;;
+;; ...
+;;
+;; (parallel [(set (reg:SI <data>)
+;; (unspec:SI [(mem:SI (reg:DI <ptr>))
+;; (reg:DI <data>)
+;; (const_int <marker>)]
+;; UNSPEC_PCREL_OPT_LD))
+;; (clobber (reg:DI <ptr>))])
+;;
+;; The marker is an integer constant that links the load of the external
+;; address to the load of the actual variable.
+;;
+;; In the first insn, we set both the address of the external variable, and
+;; mark that the variable being loaded both are created in that insn, and are
+;; consumed in the second insn. It doesn't matter what mode the register that
+;; we will ultimately do the load into, so we use DImode. We just need to mark
+;; that both registers may be set in the first insn, and will be used in the
+;; second insn.
+;;
+;; Since we use UNSPEC's and link both the the register holding the external
+;; address and the value being loaded, it should prevent other passes from
+;; modifying it.
+;;
+;; If the register being loaded is the same as the base register, we use an
+;; alternate form of the insns.
+;;
+;; (set (reg:DI <data_ptr>)
+;; (unspec:DI [(symbol_ref:DI <extern_addr>)
+;; (const_int <marker>)]
+;; UNSPEC_PCREL_OPT_LD_ADDR_SAME_REG))
+;;
+;; ...
+;;
+;; (parallel [(set (reg:SI <data>)
+;; (unspec:SI [(mem:SI (reg:DI <ptr>))
+;; (reg:DI <data>)
+;; (const_int <marker>)]
+;; UNSPEC_PCREL_OPT_LD))
+;; (clobber (reg:DI <ptr>))])
+
+(define_c_enum "unspec"
+ [UNSPEC_PCREL_OPT_LD_ADDR
+ UNSPEC_PCREL_OPT_LD_ADDR_SAME_REG
+ UNSPEC_PCREL_OPT_LD_RELOC])
+
+;; Modes that are supported for PCREL_OPT
+(define_mode_iterator PO [QI HI SI DI TI SF DF KF
+ V1TI V2DI V4SI V8HI V16QI V2DF V4SF
+ (TF "TARGET_FLOAT128_TYPE && TARGET_IEEEQUAD")])
+
+;; Vector modes for PCREL_OPT
+(define_mode_iterator PO_VECT [TI KF V1TI V2DI V4SI V8HI V16QI V2DF V4SF
+ (TF "TARGET_FLOAT128_TYPE && TARGET_IEEEQUAD")])
+
+;; Insn for loading the external address, where the register being loaded is not
+;; the same as the register being loaded with the data.
+(define_insn "pcrel_opt_ld_addr"
+ [(set (match_operand:DI 0 "base_reg_operand" "=&b,&b")
+ (unspec:DI [(match_operand:DI 1 "pcrel_external_address")
+ (match_operand 2 "const_int_operand" "n,n")]
+ UNSPEC_PCREL_OPT_LD_ADDR))
+ (set (match_operand:DI 3 "gpc_reg_operand" "=r,wa")
+ (unspec:DI [(const_int 0)]
+ UNSPEC_PCREL_OPT_LD_ADDR))]
+ "TARGET_PCREL_OPT
+ && reg_or_subregno (operands[0]) != reg_or_subregno (operands[3])"
+ "ld %0,%a1\n.Lpcrel%2:"
+ [(set_attr "prefixed" "yes")
+ (set_attr "type" "load")
+ (set_attr "loads_extern_addr" "yes")])
+
+;; Alternate form of loading up the external address that is the same register
+;; as the final load.
+(define_insn "pcrel_opt_ld_addr_same_reg"
+ [(set (match_operand:DI 0 "base_reg_operand" "=b")
+ (unspec:DI [(match_operand:DI 1 "pcrel_external_address")
+ (match_operand 2 "const_int_operand" "n")]
+ UNSPEC_PCREL_OPT_LD_ADDR_SAME_REG))]
+ "TARGET_PCREL_OPT"
+ "ld %0,%a1\n.Lpcrel%2:"
+ [(set_attr "prefixed" "yes")
+ (set_attr "type" "load")
+ (set_attr "loads_extern_addr" "yes")])
+
+;; PCREL_OPT modes that are optimized for loading or storing GPRs.
+(define_mode_iterator PO_GPR [QI HI SI DI SF DF])
+
+(define_mode_attr PO_GPR_LD [(QI "lbz")
+ (HI "lhz")
+ (SI "lwz")
+ (SF "lwz")
+ (DI "ld")
+ (DF "ld")])
+
+;; PCREL_OPT load operation of GPRs. Operand 4 (the register used to hold the
+;; address of the external symbol) is SCRATCH if the same register is used for
+;; the normal load.
+(define_insn "*pcrel_opt_ld<mode>_gpr"
+ [(parallel [(set (match_operand:PO_GPR 0 "int_reg_operand" "+r")
+ (unspec:PO_GPR [(match_operand:PO_GPR 1 "d_form_memory" "o")
+ (match_operand:DI 2 "int_reg_operand" "0")
+ (match_operand 3 "const_int_operand" "n")]
+ UNSPEC_PCREL_OPT_LD_RELOC))
+ (clobber (match_scratch:DI 4 "=bX"))])]
+ "TARGET_PCREL_OPT
+ && (GET_CODE (operands[4]) == SCRATCH
+ || reg_mentioned_p (operands[4], operands[1]))"
+{
+ output_pcrel_opt_reloc (operands[3]);
+ return "<PO_GPR_LD> %0,%1";
+}
+ [(set_attr "type" "load")])
+
+;; PCREL_OPT load with sign/zero extension
+(define_insn "*pcrel_opt_ldsi_<u><mode>_gpr"
+ [(set (match_operand:EXTSI 0 "int_reg_operand" "+r")
+ (any_extend:EXTSI
+ (unspec:SI [(match_operand:SI 1 "d_form_memory" "o")
+ (match_operand:DI 2 "int_reg_operand" "0")
+ (match_operand 3 "const_int_operand" "n")]
+ UNSPEC_PCREL_OPT_LD_RELOC)))
+ (clobber (match_scratch:DI 4 "=bX"))]
+ "TARGET_PCREL_OPT"
+{
+ output_pcrel_opt_reloc (operands[3]);
+ return "lw<az> %0,%1";
+}
+ [(set_attr "type" "load")])
+
+(define_insn "*pcrel_opt_ldhi_<u><mode>_gpr"
+ [(set (match_operand:EXTHI 0 "int_reg_operand" "+r")
+ (any_extend:EXTHI
+ (unspec:HI [(match_operand:HI 1 "d_form_memory" "o")
+ (match_operand:DI 2 "int_reg_operand" "0")
+ (match_operand 3 "const_int_operand" "n")]
+ UNSPEC_PCREL_OPT_LD_RELOC)))
+ (clobber (match_scratch:DI 4 "=bX"))]
+ "TARGET_PCREL_OPT"
+{
+ output_pcrel_opt_reloc (operands[3]);
+ return "lh<az> %0,%1";
+}
+ [(set_attr "type" "load")])
+
+(define_insn "*pcrel_opt_ldqi_u<mode>_gpr"
+ [(set (match_operand:EXTQI 0 "int_reg_operand" "+r")
+ (zero_extend:EXTQI
+ (unspec:QI [(match_operand:QI 1 "d_form_memory" "o")
+ (match_operand:DI 2 "int_reg_operand" "0")
+ (match_operand 3 "const_int_operand" "n")]
+ UNSPEC_PCREL_OPT_LD_RELOC)))
+ (clobber (match_scratch:DI 4 "=bX"))]
+ "TARGET_PCREL_OPT"
+{
+ output_pcrel_opt_reloc (operands[3]);
+ return "lbz %0,%1";
+}
+ [(set_attr "type" "load")])
+
+;; Scalar types that can be optimized by loading them into floating point
+;; or Altivec registers.
+(define_mode_iterator PO_FP [DI DF SF])
+
+;; Load instructions to load up scalar floating point or 64-bit integer values
+;; into floating point registers or Altivec registers.
+(define_mode_attr PO_FPR_LD [(DI "lfd") (DF "lfd") (SF "lfs")])
+(define_mode_attr PO_AVX_LD [(DI "lxsd") (DF "lxsd") (SF "lxssp")])
+
+;; PCREL_OPT load operation of scalar DF/DI/SF into vector registers.
+(define_insn "*pcrel_opt_ld<mode>_vsx"
+ [(set (match_operand:PO_FP 0 "vsx_register_operand" "+d,v")
+ (unspec:PO_FP [(match_operand:PO_FP 1 "d_form_memory" "o,o")
+ (match_operand:DI 2 "vsx_register_operand" "0,0")
+ (match_operand 3 "const_int_operand" "n,n")]
+ UNSPEC_PCREL_OPT_LD_RELOC))
+ (clobber (match_operand:DI 4 "base_reg_operand" "=b,b"))]
+ "TARGET_PCREL_OPT"
+{
+ output_pcrel_opt_reloc (operands[3]);
+ return which_alternative ? "<PO_AVX_LD> %0,%1" : "<PO_FPR_LD> %0,%1";
+}
+ [(set_attr "type" "fpload")])
+
+;; PCREL_OPT optimization extending SFmode to DFmode via a load.
+(define_insn "*pcrel_opt_ldsf_df"
+ [(set (match_operand:DF 0 "vsx_register_operand" "+d,v")
+ (float_extend:DF
+ (unspec:SF [(match_operand:SF 1 "d_form_memory" "o,o")
+ (match_operand:DI 2 "vsx_register_operand" "0,0")
+ (match_operand 3 "const_int_operand" "n,n")]
+ UNSPEC_PCREL_OPT_LD_RELOC)))
+ (clobber (match_operand:DI 4 "base_reg_operand" "=b,b"))]
+ "TARGET_PCREL_OPT"
+{
+ output_pcrel_opt_reloc (operands[3]);
+ return which_alternative ? "lxssp %0,%1" : "lfs %0,%1";
+}
+ [(set_attr "type" "fpload")])
+
+;; PCREL_OPT load operation of vector/float128 types into vector registers.
+(define_insn "*pcrel_opt_ld<mode>"
+ [(set (match_operand:PO_VECT 0 "vsx_register_operand" "+wa")
+ (unspec:PO_VECT [(match_operand:PO_VECT 1 "d_form_memory" "o")
+ (match_operand:DI 2 "vsx_register_operand" "0")
+ (match_operand 3 "const_int_operand" "n")]
+ UNSPEC_PCREL_OPT_LD_RELOC))
+ (clobber (match_operand:DI 4 "base_reg_operand" "=b"))]
+ "TARGET_PCREL_OPT"
+{
+ output_pcrel_opt_reloc (operands[3]);
+ return "lxv %x0,%1";
+}
+ [(set_attr "type" "vecload")])
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 4c2fe7fa312..9610587e1c1 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -1876,3 +1876,26 @@
{
return address_is_prefixed (XEXP (op, 0), mode, NON_PREFIXED_DEFAULT);
})
+
+;; Return true if the operand is a valid memory operand with an offsettable
+;; address that could be merged with the load of a PC-relative external address
+;; with the PCREL_OPT optimization. We don't check here whether or not the
+;; offset needs to be used in a DS-FORM (bottom 2 bits 0) or DQ-FORM (bottom 4
+;; bits 0) instruction.
+(define_predicate "d_form_memory"
+ (match_code "mem")
+{
+ if (!memory_operand (op, mode))
+ return false;
+
+ rtx addr = XEXP (op, 0);
+
+ if (REG_P (addr) || SUBREG_P (addr))
+ return true;
+
+ if (GET_CODE (addr) != PLUS)
+ return false;
+
+ return (base_reg_operand (XEXP (addr, 0), Pmode)
+ && satisfies_constraint_I (XEXP (addr, 1)));
+})
diff --git a/gcc/config/rs6000/rs6000-cpus.def b/gcc/config/rs6000/rs6000-cpus.def
index 8d2c1ffd6cf..d3f72d77a6e 100644
--- a/gcc/config/rs6000/rs6000-cpus.def
+++ b/gcc/config/rs6000/rs6000-cpus.def
@@ -78,6 +78,7 @@
/* Flags that need to be turned off if -mno-power10. */
#define OTHER_POWER10_MASKS (OPTION_MASK_MMA \
| OPTION_MASK_PCREL \
+ | OPTION_MASK_PCREL_OPT \
| OPTION_MASK_PREFIXED)
#define ISA_3_1_MASKS_SERVER (ISA_3_0_MASKS_SERVER \
@@ -142,6 +143,7 @@
| OPTION_MASK_P9_MISC \
| OPTION_MASK_P9_VECTOR \
| OPTION_MASK_PCREL \
+ | OPTION_MASK_PCREL_OPT \
| OPTION_MASK_POPCNTB \
| OPTION_MASK_POPCNTD \
| OPTION_MASK_POWERPC64 \
diff --git a/gcc/config/rs6000/rs6000-passes.def b/gcc/config/rs6000/rs6000-passes.def
index 5164c526e34..b62244b8df2 100644
--- a/gcc/config/rs6000/rs6000-passes.def
+++ b/gcc/config/rs6000/rs6000-passes.def
@@ -24,4 +24,12 @@ along with GCC; see the file COPYING3. If not see
REPLACE_PASS (PASS, INSTANCE, TGT_PASS)
*/
+ /* Pass to add the appropriate vector swaps on power8 little endian systems.
+ The power8 does not have instructions that automaticaly do the byte swaps
+ for loads and stores. */
INSERT_PASS_BEFORE (pass_cse, 1, pass_analyze_swaps);
+
+ /* Pass to do the PCREL_OPT optimization that combines the load of an
+ external symbol's address along with a single load or store using that
+ address as a base register. */
+ INSERT_PASS_BEFORE (pass_sched2, 1, pass_pcrel_opt);
diff --git a/gcc/config/rs6000/rs6000-protos.h b/gcc/config/rs6000/rs6000-protos.h
index 25fa5dd57cd..75c659971ea 100644
--- a/gcc/config/rs6000/rs6000-protos.h
+++ b/gcc/config/rs6000/rs6000-protos.h
@@ -190,10 +190,13 @@ enum non_prefixed_form {
extern enum insn_form address_to_insn_form (rtx, machine_mode,
enum non_prefixed_form);
+extern enum non_prefixed_form reg_to_non_prefixed (rtx, machine_mode);
+extern bool offsettable_non_prefixed_memory (rtx, machine_mode, rtx);
extern bool prefixed_load_p (rtx_insn *);
extern bool prefixed_store_p (rtx_insn *);
extern bool prefixed_paddi_p (rtx_insn *);
extern void rs6000_asm_output_opcode (FILE *);
+extern void output_pcrel_opt_reloc (rtx);
extern void rs6000_final_prescan_insn (rtx_insn *, rtx [], int);
extern int rs6000_adjust_insn_length (rtx_insn *, int);
@@ -306,6 +309,7 @@ namespace gcc { class context; }
class rtl_opt_pass;
extern rtl_opt_pass *make_pass_analyze_swaps (gcc::context *);
+extern rtl_opt_pass *make_pass_pcrel_opt (gcc::context *);
extern bool rs6000_sum_of_two_registers_p (const_rtx expr);
extern bool rs6000_quadword_masked_address_p (const_rtx exp);
extern rtx rs6000_gen_lvx (enum machine_mode, rtx, rtx);
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 59e39117eb5..d98876b8f7f 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -1175,7 +1175,6 @@ static bool rs6000_secondary_reload_move (enum rs6000_reg_type,
machine_mode,
secondary_reload_info *,
bool);
-static enum non_prefixed_form reg_to_non_prefixed (rtx reg, machine_mode mode);
rtl_opt_pass *make_pass_analyze_swaps (gcc::context*);
/* Hash table stuff for keeping track of TOC entries. */
@@ -4325,6 +4324,14 @@ rs6000_option_override_internal (bool global_init_p)
rs6000_isa_flags &= ~OPTION_MASK_MMA;
}
+ if (!TARGET_PCREL && TARGET_PCREL_OPT)
+ {
+ if ((rs6000_isa_flags_explicit & OPTION_MASK_PCREL_OPT) != 0)
+ error ("%qs requires %qs", "-mpcrel-opt", "-mpcrel");
+
+ rs6000_isa_flags &= ~OPTION_MASK_PCREL_OPT;
+ }
+
if (TARGET_DEBUG_REG || TARGET_DEBUG_TARGET)
rs6000_print_isa_options (stderr, 0, "after subtarget", rs6000_isa_flags);
@@ -8524,8 +8531,46 @@ rs6000_delegitimize_address (rtx orig_x)
{
rtx x, y, offset;
- if (GET_CODE (orig_x) == UNSPEC && XINT (orig_x, 1) == UNSPEC_FUSION_GPR)
- orig_x = XVECEXP (orig_x, 0, 0);
+ /* UNSPEC_FUSION_GPR is created by the peephole2 for power8 fusion. It
+ encodes loading up the high part of the address of a TOC reference along
+ with a load of a GPR using the same base register used for the load. We
+ return the original SYMBOL_REF.
+
+ (set (reg:INT1 <reg>
+ (unspec:INT1 [<combined-address>] UNSPEC_FUSION_GPR)))
+
+ UNSPEC_PCREL_OPT_LD_ADDR is used by the power10 PCREL_OPT pass. These
+ UNSPECs include the external SYMBOL_REF along with the value being loaded.
+ We return the original SYMBOL_REF.
+
+ (parallel [(set (reg:DI <base-reg>)
+ (unspec:DI [(symbol_ref <symbol>)
+ (const_int <marker>)]
+ UNSPEC_PCREL_OPT_LD_ADDR))
+ (set (reg:DI <load-reg>)
+ (unspec:DI [(const_int 0)]
+ UNSPEC_PCREL_OPT_LD_ADDR))])
+
+ UNSPEC_PCREL_OPT_LD_ADDR_SAME_REG is an alternative that is used if the
+ GPR being loaded is the same as the GPR used to hold the external address.
+
+ (set (reg:DI <base-reg>)
+ (unspec:DI [(symbol_ref <symbol>)
+ (const_int <marker>)]
+ UNSPEC_PCREL_OPT_LD_ADDR_SAME_REG)) */
+
+ if (GET_CODE (orig_x) == UNSPEC)
+ switch (XINT (orig_x, 1))
+ {
+ case UNSPEC_FUSION_GPR:
+ case UNSPEC_PCREL_OPT_LD_ADDR:
+ case UNSPEC_PCREL_OPT_LD_ADDR_SAME_REG:
+ orig_x = XVECEXP (orig_x, 0, 0);
+ break;
+
+ default:
+ break;
+ }
orig_x = delegitimize_mem_from_attrs (orig_x);
@@ -23292,6 +23337,7 @@ static struct rs6000_opt_mask const rs6000_opt_masks[] =
{ "mulhw", OPTION_MASK_MULHW, false, true },
{ "multiple", OPTION_MASK_MULTIPLE, false, true },
{ "pcrel", OPTION_MASK_PCREL, false, true },
+ { "pcrel-opt", OPTION_MASK_PCREL_OPT, false, true },
{ "popcntb", OPTION_MASK_POPCNTB, false, true },
{ "popcntd", OPTION_MASK_POPCNTD, false, true },
{ "power8-fusion", OPTION_MASK_P8_FUSION, false, true },
@@ -25391,6 +25437,32 @@ address_to_insn_form (rtx addr,
return INSN_FORM_BAD;
}
+/* Return true if an REG with a given MODE is loaded from or stored into a MEM
+ location uses a non-prefixed offsettable address. This is used to validate
+ the load or store with the PCREL_OPT optimization to make sure it is an
+ instruction that can be optimized.
+
+ We need to specify the MODE separately from the REG to allow for loads that
+ include zero/sign/float extension. */
+
+bool
+offsettable_non_prefixed_memory (rtx reg, machine_mode mode, rtx mem)
+{
+ /* If the instruction is indexed only like LFIWAX/LXSIWAX, it is not
+ offsettable. */
+ enum non_prefixed_form non_prefixed = reg_to_non_prefixed (reg, mode);
+ if (non_prefixed == NON_PREFIXED_X)
+ return false;
+
+ /* Check if this is a non-prefixed offsettable instruction. */
+ rtx addr = XEXP (mem, 0);
+ enum insn_form iform = address_to_insn_form (addr, mode, non_prefixed);
+ return (iform == INSN_FORM_BASE_REG
+ || iform == INSN_FORM_D
+ || iform == INSN_FORM_DS
+ || iform == INSN_FORM_DQ);
+}
+
/* Helper function to see if we're potentially looking at lfs/stfs.
- PARALLEL containing a SET and a CLOBBER
- stfs:
@@ -25449,7 +25521,7 @@ is_lfs_stfs_insn (rtx_insn *insn)
/* Helper function to take a REG and a MODE and turn it into the non-prefixed
instruction format (D/DS/DQ) used for offset memory. */
-static enum non_prefixed_form
+enum non_prefixed_form
reg_to_non_prefixed (rtx reg, machine_mode mode)
{
/* If it isn't a register, use the defaults. */
@@ -25672,11 +25744,34 @@ void
rs6000_asm_output_opcode (FILE *stream)
{
if (next_insn_prefixed_p)
- fprintf (stream, "p");
+ {
+ fprintf (stream, "p");
+
+ /* Reset flag in case there are separate insn lines in the sequence, so
+ the 'p' is only emited for the first line. This shows up when we are
+ doing the PCREL_OPT optimization, in that the label created with %r<n>
+ would have a leading 'p' printed. */
+ next_insn_prefixed_p = false;
+ }
return;
}
+/* Emit the relocation to tie the next instruction to a previous instruction
+ that loads up an external address. This is used to do the PCREL_OPT
+ optimization. Note, the label is generated after the PLD of the got
+ pc-relative address to allow for the assembler to insert NOPs before the PLD
+ instruction. The operand is a constant integer that is the label
+ number. */
+
+void
+output_pcrel_opt_reloc (rtx label_num)
+{
+ rtx operands[1] = { label_num };
+ output_asm_insn (".reloc .Lpcrel%0-8,R_PPC64_PCREL_OPT,.-(.Lpcrel%0-8)",
+ operands);
+}
+
/* Adjust the length of an INSN. LENGTH is the currently-computed length and
should be adjusted to reflect any required changes. This macro is used when
there is some systematic length adjustment required that would be difficult
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index c7bc14b9207..f5b5a017624 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -292,6 +292,10 @@
(const_string "no")))
+;; Whether an insn loads an external address for the PCREL_OPT optimizaton.
+(define_attr "loads_extern_addr" "no,yes"
+ (const_string "no"))
+
;; Return the number of real hardware instructions in a combined insn. If it
;; is 0, just use the length / 4.
(define_attr "num_insns" "" (const_int 0))
@@ -10295,7 +10299,8 @@
"TARGET_PCREL"
"ld %0,%a1"
[(set_attr "prefixed" "yes")
- (set_attr "type" "load")])
+ (set_attr "type" "load")
+ (set_attr "loads_extern_addr" "yes")])
;; TOC register handling.
@@ -14952,3 +14957,4 @@
(include "dfp.md")
(include "crypto.md")
(include "htm.md")
+(include "pcrel-opt.md")
diff --git a/gcc/config/rs6000/rs6000.opt b/gcc/config/rs6000/rs6000.opt
index b2a70e88ca8..d1719bfd2a0 100644
--- a/gcc/config/rs6000/rs6000.opt
+++ b/gcc/config/rs6000/rs6000.opt
@@ -586,6 +586,10 @@ mpcrel
Target Report Mask(PCREL) Var(rs6000_isa_flags)
Generate (do not generate) pc-relative memory addressing.
+mpcrel-opt
+Target Undocumented Mask(PCREL_OPT) Var(rs6000_isa_flags)
+Generate (do not generate) pc-relative memory optimizations for externals.
+
mmma
Target Report Mask(MMA) Var(rs6000_isa_flags)
Generate (do not generate) MMA instructions.
diff --git a/gcc/config/rs6000/t-rs6000 b/gcc/config/rs6000/t-rs6000
index 1ddb5729cb2..a617276484e 100644
--- a/gcc/config/rs6000/t-rs6000
+++ b/gcc/config/rs6000/t-rs6000
@@ -23,6 +23,10 @@ TM_H += $(srcdir)/config/rs6000/rs6000-cpus.def
TM_H += $(srcdir)/config/rs6000/rs6000-modes.h
PASSES_EXTRA += $(srcdir)/config/rs6000/rs6000-passes.def
+pcrel-opt.o: $(srcdir)/config/rs6000/pcrel-opt.c
+ $(COMPILE) $<
+ $(POSTCOMPILE)
+
rs6000-c.o: $(srcdir)/config/rs6000/rs6000-c.c
$(COMPILE) $<
$(POSTCOMPILE)
@@ -86,4 +90,5 @@ MD_INCLUDES = $(srcdir)/config/rs6000/rs64.md \
$(srcdir)/config/rs6000/mma.md \
$(srcdir)/config/rs6000/crypto.md \
$(srcdir)/config/rs6000/htm.md \
- $(srcdir)/config/rs6000/dfp.md
+ $(srcdir)/config/rs6000/dfp.md \
+ $(srcdir)/config/rs6000/pcrel-opt.md
More information about the Gcc-cvs
mailing list