Hi!
Before we start looking into enabling certain 'pass_postreload' passes
for nvptx, as we've been discussing in
<https://inbox.sourceware.org/007a01dac921$82d0d9c0$88728d40$@nextmovesoftware.com>
"nvptx vs. [PATCH] Add a late-combine pass [PR106594]", let's first
document the (not quite obvious) status quo:
On 2014-10-20T16:24:43+0200, Bernd Schmidt <ber...@codesourcery.com> wrote:
> This stops most of the post-regalloc passes to be run if the target
> doesn't want register allocation. I'd previously moved them all out of
> postreload to the toplevel, but Jakub (I think) pointed out that the
> idea is not to run them to avoid crashes if reload fails e.g. for an
> invalid asm. So I've made a new container pass.
OK to push "Document 'pass_postreload' vs. 'pass_late_compilation'", see
attached?
Grüße
Thomas
> A later patch will make thread_prologue_and_epilogue_insns callable from
> the backend.
>
>
> Bernd
>
> gcc/
> * passes.def (pass_compute_alignments, pass_duplicate_computed_gotos,
> pass_variable_tracking, pass_free_cfg, pass_machine_reorg,
> pass_cleanup_barriers, pass_delay_slots,
> pass_split_for_shorten_branches, pass_convert_to_eh_region_ranges,
> pass_shorten_branches, pass_est_nothrow_function_flags,
> pass_dwarf2_frame, pass_final): Move outside of pass_postreload and
> into pass_late_compilation.
> (pass_late_compilation): Add.
> * passes.c (pass_data_late_compilation, pass_late_compilation,
> make_pass_late_compilation): New.
> * timevar.def (TV_LATE_COMPILATION): New.
>
> ------------------------------------------------------------------------
> Index: gcc/passes.def
> ===================================================================
> --- gcc/passes.def.orig
> +++ gcc/passes.def
> @@ -415,6 +415,9 @@ along with GCC; see the file COPYING3.
> NEXT_PASS (pass_split_before_regstack);
> NEXT_PASS (pass_stack_regs_run);
> POP_INSERT_PASSES ()
> + POP_INSERT_PASSES ()
> + NEXT_PASS (pass_late_compilation);
> + PUSH_INSERT_PASSES_WITHIN (pass_late_compilation)
> NEXT_PASS (pass_compute_alignments);
> NEXT_PASS (pass_variable_tracking);
> NEXT_PASS (pass_free_cfg);
> Index: gcc/passes.c
> ===================================================================
> --- gcc/passes.c.orig
> +++ gcc/passes.c
> @@ -569,6 +569,44 @@ make_pass_postreload (gcc::context *ctxt
> return new pass_postreload (ctxt);
> }
>
> +namespace {
> +
> +const pass_data pass_data_late_compilation =
> +{
> + RTL_PASS, /* type */
> + "*all-late_compilation", /* name */
> + OPTGROUP_NONE, /* optinfo_flags */
> + TV_LATE_COMPILATION, /* tv_id */
> + PROP_rtl, /* properties_required */
> + 0, /* properties_provided */
> + 0, /* properties_destroyed */
> + 0, /* todo_flags_start */
> + 0, /* todo_flags_finish */
> +};
> +
> +class pass_late_compilation : public rtl_opt_pass
> +{
> +public:
> + pass_late_compilation (gcc::context *ctxt)
> + : rtl_opt_pass (pass_data_late_compilation, ctxt)
> + {}
> +
> + /* opt_pass methods: */
> + virtual bool gate (function *)
> + {
> + return reload_completed || targetm.no_register_allocation;
> + }
> +
> +}; // class pass_late_compilation
> +
> +} // anon namespace
> +
> +static rtl_opt_pass *
> +make_pass_late_compilation (gcc::context *ctxt)
> +{
> + return new pass_late_compilation (ctxt);
> +}
> +
>
>
> /* Set the static pass number of pass PASS to ID and record that
> Index: gcc/timevar.def
> ===================================================================
> --- gcc/timevar.def.orig
> +++ gcc/timevar.def
> @@ -270,6 +270,7 @@ DEFTIMEVAR (TV_EARLY_LOCAL , "early
> DEFTIMEVAR (TV_OPTIMIZE , "unaccounted optimizations")
> DEFTIMEVAR (TV_REST_OF_COMPILATION , "rest of compilation")
> DEFTIMEVAR (TV_POSTRELOAD , "unaccounted post reload")
> +DEFTIMEVAR (TV_LATE_COMPILATION , "unaccounted late compilation")
> DEFTIMEVAR (TV_REMOVE_UNUSED , "remove unused locals")
> DEFTIMEVAR (TV_ADDRESS_TAKEN , "address taken")
> DEFTIMEVAR (TV_TODO , "unaccounted todo")
>From 7f708dd9774773e704cb06b7a6f296927f9057df Mon Sep 17 00:00:00 2001
From: Thomas Schwinge <tschwi...@baylibre.com>
Date: Fri, 28 Jun 2024 16:04:18 +0200
Subject: [PATCH] Document 'pass_postreload' vs. 'pass_late_compilation'
See Subversion r217124 (Git commit 433e4164339f18d0b8798968444a56b681b5232c)
"Reorganize post-ra pipeline for targets without register allocation".
gcc/
* passes.cc: Document 'pass_postreload' vs. 'pass_late_compilation'.
* passes.def: Likewise.
---
gcc/passes.cc | 14 +++++++++++++-
gcc/passes.def | 3 +++
2 files changed, 16 insertions(+), 1 deletion(-)
diff --git a/gcc/passes.cc b/gcc/passes.cc
index d3648a24b58..e444b462113 100644
--- a/gcc/passes.cc
+++ b/gcc/passes.cc
@@ -660,6 +660,10 @@ make_pass_rest_of_compilation (gcc::context *ctxt)
namespace {
+/* A container pass (only) for '!targetm.no_register_allocation' targets, for
+ passes to run if reload completed (..., but not run them if it failed, for
+ example for an invalid 'asm'). See also 'pass_late_compilation'. */
+
const pass_data pass_data_postreload =
{
RTL_PASS, /* type */
@@ -681,7 +685,12 @@ public:
{}
/* opt_pass methods: */
- bool gate (function *) final override { return reload_completed; }
+ bool gate (function *) final override
+ {
+ if (reload_completed)
+ gcc_checking_assert (!targetm.no_register_allocation);
+ return reload_completed;
+ }
}; // class pass_postreload
@@ -695,6 +704,9 @@ make_pass_postreload (gcc::context *ctxt)
namespace {
+/* A container pass like 'pass_postreload', but for passes to run also for
+ 'targetm.no_register_allocation' targets. */
+
const pass_data pass_data_late_compilation =
{
RTL_PASS, /* type */
diff --git a/gcc/passes.def b/gcc/passes.def
index 61ca210822a..72198bc4c4e 100644
--- a/gcc/passes.def
+++ b/gcc/passes.def
@@ -507,6 +507,9 @@ along with GCC; see the file COPYING3. If not see
NEXT_PASS (pass_early_remat);
NEXT_PASS (pass_ira);
NEXT_PASS (pass_reload);
+ /* In the following, some passes are tied to 'pass_postreload' and others
+ to 'pass_late_compilation'. The difference is that the latter also
+ run for 'targetm.no_register_allocation' targets. */
NEXT_PASS (pass_postreload);
PUSH_INSERT_PASSES_WITHIN (pass_postreload)
NEXT_PASS (pass_postreload_cse);
--
2.34.1
