From e9d2ae6b9816e61a6148040149c63faa83f54702 Mon Sep 17 00:00:00 2001 From: Richard Sandiford Date: Tue, 5 Dec 2023 09:28:46 +0000 Subject: [PATCH] Allow prologues and epilogues to be inserted later Arm's SME adds a new processor mode called streaming mode. This mode enables some new (matrix-oriented) instructions and disables several existing groups of instructions, such as most Advanced SIMD vector instructions and a much smaller set of SVE instructions. It can also change the current vector length. There are instructions to switch in and out of streaming mode. However, their effect on the ISA and vector length can't be represented directly in RTL, so they need to be emitted late in the pass pipeline, close to md_reorg. It's sometimes the responsibility of the prologue and epilogue to switch modes, which means we need to emit the prologue and epilogue sequences late as well. (This loses shrink-wrapping and scheduling opportunities, but that's a price worth paying.) This patch therefore adds a target hook for forcing prologue and epilogue insertion to happen later in the pipeline. gcc/ * target.def (use_late_prologue_epilogue): New hook. * doc/tm.texi.in: Add TARGET_USE_LATE_PROLOGUE_EPILOGUE. * doc/tm.texi: Regenerate. * passes.def (pass_late_thread_prologue_and_epilogue): New pass. * tree-pass.h (make_pass_late_thread_prologue_and_epilogue): Declare. * function.cc (pass_thread_prologue_and_epilogue::gate): New function. (pass_data_late_thread_prologue_and_epilogue): New pass variable. (pass_late_thread_prologue_and_epilogue): New pass class. (make_pass_late_thread_prologue_and_epilogue): New function. --- gcc/doc/tm.texi | 19 ++++++++++++++++++ gcc/doc/tm.texi.in | 2 ++ gcc/function.cc | 50 ++++++++++++++++++++++++++++++++++++++++++++++ gcc/passes.def | 3 +++ gcc/target.def | 21 +++++++++++++++++++ gcc/tree-pass.h | 2 ++ 6 files changed, 97 insertions(+) diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi index 7c5d2e52360..6709c42a48f 100644 --- a/gcc/doc/tm.texi +++ b/gcc/doc/tm.texi @@ -11879,6 +11879,25 @@ of the if-block in the @code{struct ce_if_block} structure that is pointed to by @var{ce_info}. @end defmac +@deftypefn {Target Hook} bool TARGET_USE_LATE_PROLOGUE_EPILOGUE () +Return true if the current function's prologue and epilogue should +be emitted late in the pass pipeline, instead of at the usual point. + +Normally, the prologue and epilogue sequences are introduced soon after +register allocation is complete. The advantage of this approach is that +it allows the prologue and epilogue instructions to be optimized and +scheduled with other code in the function. However, some targets +require the prologue and epilogue to be the first and last sequences +executed by the function, with no variation allowed. This hook should +return true on such targets. + +The default implementation returns false, which is correct for most +targets. The hook should only return true if there is a specific +target limitation that cannot be described in RTL. For example, +the hook might return true if the prologue and epilogue need to switch +between instruction sets. +@end deftypefn + @deftypefn {Target Hook} void TARGET_MACHINE_DEPENDENT_REORG (void) If non-null, this hook performs a target-specific pass over the instruction stream. The compiler will run it at all optimization levels, diff --git a/gcc/doc/tm.texi.in b/gcc/doc/tm.texi.in index c24493add57..d1d7cfafdca 100644 --- a/gcc/doc/tm.texi.in +++ b/gcc/doc/tm.texi.in @@ -7784,6 +7784,8 @@ of the if-block in the @code{struct ce_if_block} structure that is pointed to by @var{ce_info}. @end defmac +@hook TARGET_USE_LATE_PROLOGUE_EPILOGUE + @hook TARGET_MACHINE_DEPENDENT_REORG @hook TARGET_INIT_BUILTINS diff --git a/gcc/function.cc b/gcc/function.cc index 527ea4807b0..704930160c3 100644 --- a/gcc/function.cc +++ b/gcc/function.cc @@ -84,6 +84,7 @@ along with GCC; see the file COPYING3. If not see #include "function-abi.h" #include "value-range.h" #include "gimple-range.h" +#include "insn-attr.h" /* So we can assign to cfun in this file. */ #undef cfun @@ -6629,6 +6630,11 @@ public: {} /* opt_pass methods: */ + bool gate (function *) final override + { + return !targetm.use_late_prologue_epilogue (); + } + unsigned int execute (function * fun) final override { rest_of_handle_thread_prologue_and_epilogue (fun); @@ -6637,6 +6643,44 @@ public: }; // class pass_thread_prologue_and_epilogue +const pass_data pass_data_late_thread_prologue_and_epilogue = +{ + RTL_PASS, /* type */ + "late_pro_and_epilogue", /* name */ + OPTGROUP_NONE, /* optinfo_flags */ + TV_THREAD_PROLOGUE_AND_EPILOGUE, /* tv_id */ + 0, /* properties_required */ + 0, /* properties_provided */ + 0, /* properties_destroyed */ + 0, /* todo_flags_start */ + ( TODO_df_verify | TODO_df_finish ), /* todo_flags_finish */ +}; + +class pass_late_thread_prologue_and_epilogue : public rtl_opt_pass +{ +public: + pass_late_thread_prologue_and_epilogue (gcc::context *ctxt) + : rtl_opt_pass (pass_data_late_thread_prologue_and_epilogue, ctxt) + {} + + /* opt_pass methods: */ + bool gate (function *) final override + { + return targetm.use_late_prologue_epilogue (); + } + + unsigned int execute (function *fn) final override + { + /* It's not currently possible to have both delay slots and + late prologue/epilogue, since the latter has to run before + the former, and the former won't honor whatever restrictions + the latter is trying to enforce. */ + gcc_assert (!DELAY_SLOTS); + rest_of_handle_thread_prologue_and_epilogue (fn); + return 0; + } +}; // class pass_late_thread_prologue_and_epilogue + } // anon namespace rtl_opt_pass * @@ -6645,6 +6689,12 @@ make_pass_thread_prologue_and_epilogue (gcc::context *ctxt) return new pass_thread_prologue_and_epilogue (ctxt); } +rtl_opt_pass * +make_pass_late_thread_prologue_and_epilogue (gcc::context *ctxt) +{ + return new pass_late_thread_prologue_and_epilogue (ctxt); +} + namespace { const pass_data pass_data_zero_call_used_regs = diff --git a/gcc/passes.def b/gcc/passes.def index 1e1950bdb39..f3139415065 100644 --- a/gcc/passes.def +++ b/gcc/passes.def @@ -533,6 +533,9 @@ along with GCC; see the file COPYING3. If not see NEXT_PASS (pass_stack_regs_run); POP_INSERT_PASSES () POP_INSERT_PASSES () + NEXT_PASS (pass_late_thread_prologue_and_epilogue); + /* No target-independent code motion is allowed beyond this point, + excepting the legacy delayed-branch pass. */ NEXT_PASS (pass_late_compilation); PUSH_INSERT_PASSES_WITHIN (pass_late_compilation) NEXT_PASS (pass_zero_call_used_regs); diff --git a/gcc/target.def b/gcc/target.def index c6562ed40ac..04715028460 100644 --- a/gcc/target.def +++ b/gcc/target.def @@ -4153,6 +4153,27 @@ returns @code{VOIDmode}.", machine_mode, (machine_mode m1, machine_mode m2), default_cc_modes_compatible) +DEFHOOK +(use_late_prologue_epilogue, + "Return true if the current function's prologue and epilogue should\n\ +be emitted late in the pass pipeline, instead of at the usual point.\n\ +\n\ +Normally, the prologue and epilogue sequences are introduced soon after\n\ +register allocation is complete. The advantage of this approach is that\n\ +it allows the prologue and epilogue instructions to be optimized and\n\ +scheduled with other code in the function. However, some targets\n\ +require the prologue and epilogue to be the first and last sequences\n\ +executed by the function, with no variation allowed. This hook should\n\ +return true on such targets.\n\ +\n\ +The default implementation returns false, which is correct for most\n\ +targets. The hook should only return true if there is a specific\n\ +target limitation that cannot be described in RTL. For example,\n\ +the hook might return true if the prologue and epilogue need to switch\n\ +between instruction sets.", + bool, (), + hook_bool_void_false) + /* Do machine-dependent code transformations. Called just before delayed-branch scheduling. */ DEFHOOK diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h index 09e6ada5b2f..4e89dd1aaac 100644 --- a/gcc/tree-pass.h +++ b/gcc/tree-pass.h @@ -616,6 +616,8 @@ extern rtl_opt_pass *make_pass_gcse2 (gcc::context *ctxt); extern rtl_opt_pass *make_pass_split_after_reload (gcc::context *ctxt); extern rtl_opt_pass *make_pass_thread_prologue_and_epilogue (gcc::context *ctxt); +extern rtl_opt_pass *make_pass_late_thread_prologue_and_epilogue (gcc::context + *ctxt); extern rtl_opt_pass *make_pass_zero_call_used_regs (gcc::context *ctxt); extern rtl_opt_pass *make_pass_stack_adjustments (gcc::context *ctxt); extern rtl_opt_pass *make_pass_sched_fusion (gcc::context *ctxt);