From 5603bb17fc40f0d9c667bb24bc2ef041ec69bafb Mon Sep 17 00:00:00 2001 From: Hongyu Wang Date: Tue, 29 Nov 2022 15:17:58 +0800 Subject: [PATCH] [SPR] i386: Only enable small loop unrolling in backend [PR 107692] Followed by the discussion in pr107692, -munroll-only-small-loops Does not turns on/off -funroll-loops, and current check in pass_rtl_unroll_loops::gate would cause -fno-unroll-loops do not take effect. Revert the change about targetm.loop_unroll_adjust and apply the backend option change to strictly follow the rule that -funroll-loops takes full control of loop unrolling, and munroll-only-small-loops just change its behavior to unroll small size loops. gcc/ChangeLog: PR target/107692 * common/config/i386/i386-common.cc (ix86_optimization_table): Enable loop unroll O2, disable -fweb and -frename-registers by default. * config/i386/i386-options.cc (ix86_override_options_after_change): Disable small loop unroll when funroll-loops enabled, reset cunroll_grow_size when it is not explicitly enabled. (ix86_option_override_internal): Call ix86_override_options_after_change instead of calling ix86_recompute_optlev_based_flags and ix86_default_align separately. * config/i386/i386.cc (ix86_loop_unroll_adjust): Adjust unroll factor if -munroll-only-small-loops enabled. * loop-init.cc (pass_rtl_unroll_loops::gate): Do not enable loop unrolling for -O2-speed. (pass_rtl_unroll_loops::execute): Rmove targetm.loop_unroll_adjust check. gcc/testsuite/ChangeLog: PR target/107692 * gcc.dg/guality/loop-1.c: Remove additional option for ia32. * gcc.target/i386/pr86270.c: Add -fno-unroll-loops. * gcc.target/i386/pr93002.c: Likewise. url:https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=8caf155a3d6e23e47bf55068ad23c23d4655a054 --- ...-small-loop-unrolling-in-backend-PR-.patch | 231 ++++++++++++++++++ gcc-12.spec | 7 +- 2 files changed, 237 insertions(+), 1 deletion(-) create mode 100644 0006-i386-Only-enable-small-loop-unrolling-in-backend-PR-.patch diff --git a/0006-i386-Only-enable-small-loop-unrolling-in-backend-PR-.patch b/0006-i386-Only-enable-small-loop-unrolling-in-backend-PR-.patch new file mode 100644 index 0000000..de3995f --- /dev/null +++ b/0006-i386-Only-enable-small-loop-unrolling-in-backend-PR-.patch @@ -0,0 +1,231 @@ +From 5c07825ca0c34dd946a8cfc0325ddb452d7f65c5 Mon Sep 17 00:00:00 2001 +From: Hongyu Wang +Date: Sat, 19 Nov 2022 09:38:00 +0800 +Subject: [PATCH 5/5] i386: Only enable small loop unrolling in backend [PR + 107692] + +Followed by the discussion in pr107692, -munroll-only-small-loops +Does not turns on/off -funroll-loops, and current check in +pass_rtl_unroll_loops::gate would cause -fno-unroll-loops do not take +effect. Revert the change about targetm.loop_unroll_adjust and apply +the backend option change to strictly follow the rule that +-funroll-loops takes full control of loop unrolling, and +munroll-only-small-loops just change its behavior to unroll small size +loops. + +gcc/ChangeLog: + + PR target/107692 + * common/config/i386/i386-common.cc (ix86_optimization_table): + Enable loop unroll O2, disable -fweb and -frename-registers + by default. + * config/i386/i386-options.cc + (ix86_override_options_after_change): + Disable small loop unroll when funroll-loops enabled, reset + cunroll_grow_size when it is not explicitly enabled. + (ix86_option_override_internal): Call + ix86_override_options_after_change instead of calling + ix86_recompute_optlev_based_flags and ix86_default_align + separately. + * config/i386/i386.cc (ix86_loop_unroll_adjust): Adjust unroll + factor if -munroll-only-small-loops enabled. + * loop-init.cc (pass_rtl_unroll_loops::gate): Do not enable + loop unrolling for -O2-speed. + (pass_rtl_unroll_loops::execute): Rmove + targetm.loop_unroll_adjust check. + +gcc/testsuite/ChangeLog: + + PR target/107692 + * gcc.dg/guality/loop-1.c: Remove additional option for ia32. + * gcc.target/i386/pr86270.c: Add -fno-unroll-loops. + * gcc.target/i386/pr93002.c: Likewise. +--- + gcc/common/config/i386/i386-common.cc | 8 ++++++ + gcc/config/i386/i386-options.cc | 34 ++++++++++++++++++++++--- + gcc/config/i386/i386.cc | 18 ++++--------- + gcc/loop-init.cc | 11 +++----- + gcc/testsuite/gcc.dg/guality/loop-1.c | 2 -- + gcc/testsuite/gcc.target/i386/pr86270.c | 2 +- + gcc/testsuite/gcc.target/i386/pr93002.c | 2 +- + 7 files changed, 49 insertions(+), 28 deletions(-) + +diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc +index e1c1fb07d8a..5e777849f91 100644 +--- a/gcc/common/config/i386/i386-common.cc ++++ b/gcc/common/config/i386/i386-common.cc +@@ -1687,7 +1687,15 @@ static const struct default_options ix86_option_optimization_table[] = + /* The STC algorithm produces the smallest code at -Os, for x86. */ + { OPT_LEVELS_2_PLUS, OPT_freorder_blocks_algorithm_, NULL, + REORDER_BLOCKS_ALGORITHM_STC }, ++ ++ /* Turn on -funroll-loops with -munroll-only-small-loops to enable small ++ loop unrolling at -O2. */ ++ { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_funroll_loops, NULL, 1 }, + { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_munroll_only_small_loops, NULL, 1 }, ++ /* Turns off -frename-registers and -fweb which are enabled by ++ funroll-loops. */ ++ { OPT_LEVELS_ALL, OPT_frename_registers, NULL, 0 }, ++ { OPT_LEVELS_ALL, OPT_fweb, NULL, 0 }, + /* Turn off -fschedule-insns by default. It tends to make the + problem with not enough registers even worse. */ + { OPT_LEVELS_ALL, OPT_fschedule_insns, NULL, 0 }, +diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc +index 32cc58a764b..b853ff55825 100644 +--- a/gcc/config/i386/i386-options.cc ++++ b/gcc/config/i386/i386-options.cc +@@ -1816,8 +1816,37 @@ ix86_recompute_optlev_based_flags (struct gcc_options *opts, + void + ix86_override_options_after_change (void) + { ++ /* Default align_* from the processor table. */ + ix86_default_align (&global_options); ++ + ix86_recompute_optlev_based_flags (&global_options, &global_options_set); ++ ++ /* Disable unrolling small loops when there's explicit ++ -f{,no}unroll-loop. */ ++ if ((OPTION_SET_P (flag_unroll_loops)) ++ || (OPTION_SET_P (flag_unroll_all_loops) ++ && flag_unroll_all_loops)) ++ { ++ if (!OPTION_SET_P (ix86_unroll_only_small_loops)) ++ ix86_unroll_only_small_loops = 0; ++ /* Re-enable -frename-registers and -fweb if funroll-loops ++ enabled. */ ++ if (!OPTION_SET_P (flag_web)) ++ flag_web = flag_unroll_loops; ++ if (!OPTION_SET_P (flag_rename_registers)) ++ flag_rename_registers = flag_unroll_loops; ++ /* -fcunroll-grow-size default follws -f[no]-unroll-loops. */ ++ if (!OPTION_SET_P (flag_cunroll_grow_size)) ++ flag_cunroll_grow_size = flag_unroll_loops ++ || flag_peel_loops ++ || optimize >= 3; ++ } ++ else ++ { ++ if (!OPTION_SET_P (flag_cunroll_grow_size)) ++ flag_cunroll_grow_size = flag_peel_loops || optimize >= 3; ++ } ++ + } + + /* Clear stack slot assignments remembered from previous functions. +@@ -2329,7 +2358,7 @@ ix86_option_override_internal (bool main_args_p, + + set_ix86_tune_features (opts, ix86_tune, opts->x_ix86_dump_tunes); + +- ix86_recompute_optlev_based_flags (opts, opts_set); ++ ix86_override_options_after_change (); + + ix86_tune_cost = processor_cost_table[ix86_tune]; + /* TODO: ix86_cost should be chosen at instruction or function granuality +@@ -2360,9 +2389,6 @@ ix86_option_override_internal (bool main_args_p, + || TARGET_64BIT_P (opts->x_ix86_isa_flags)) + opts->x_ix86_regparm = REGPARM_MAX; + +- /* Default align_* from the processor table. */ +- ix86_default_align (opts); +- + /* Provide default for -mbranch-cost= value. */ + SET_OPTION_IF_UNSET (opts, opts_set, ix86_branch_cost, + ix86_tune_cost->branch_cost); +diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc +index 39b2468799c..000415c0e2e 100644 +--- a/gcc/config/i386/i386.cc ++++ b/gcc/config/i386/i386.cc +@@ -23563,20 +23563,12 @@ ix86_loop_unroll_adjust (unsigned nunroll, class loop *loop) + + /* Unroll small size loop when unroll factor is not explicitly + specified. */ +- if (!(flag_unroll_loops +- || flag_unroll_all_loops +- || loop->unroll)) ++ if (ix86_unroll_only_small_loops && !loop->unroll) + { +- nunroll = 1; +- +- /* Any explicit -f{no-}unroll-{all-}loops turns off +- -munroll-only-small-loops. */ +- if (ix86_unroll_only_small_loops +- && !OPTION_SET_P (flag_unroll_loops) +- && loop->ninsns <= ix86_cost->small_unroll_ninsns) +- nunroll = ix86_cost->small_unroll_factor; +- +- return nunroll; ++ if (loop->ninsns <= ix86_cost->small_unroll_ninsns) ++ return MIN (nunroll, ix86_cost->small_unroll_factor); ++ else ++ return 1; + } + + if (!TARGET_ADJUST_UNROLL) +diff --git a/gcc/loop-init.cc b/gcc/loop-init.cc +index 84336865ef7..ed1b2f6ebab 100644 +--- a/gcc/loop-init.cc ++++ b/gcc/loop-init.cc +@@ -565,12 +565,10 @@ public: + {} + + /* opt_pass methods: */ +- virtual bool gate (function * fun) ++ virtual bool gate (function *) + { +- return (flag_unroll_loops || flag_unroll_all_loops || cfun->has_unroll +- || (targetm.loop_unroll_adjust +- && optimize >= 2 +- && optimize_function_for_speed_p (fun))); ++ return (flag_unroll_loops || flag_unroll_all_loops ++ || cfun->has_unroll); + } + + virtual unsigned int execute (function *); +@@ -586,8 +584,7 @@ pass_rtl_unroll_loops::execute (function *fun) + if (dump_file) + df_dump (dump_file); + +- if (flag_unroll_loops +- || targetm.loop_unroll_adjust) ++ if (flag_unroll_loops) + flags |= UAP_UNROLL; + if (flag_unroll_all_loops) + flags |= UAP_UNROLL_ALL; +diff --git a/gcc/testsuite/gcc.dg/guality/loop-1.c b/gcc/testsuite/gcc.dg/guality/loop-1.c +index a32ea445a3f..1b1f6d32271 100644 +--- a/gcc/testsuite/gcc.dg/guality/loop-1.c ++++ b/gcc/testsuite/gcc.dg/guality/loop-1.c +@@ -1,7 +1,5 @@ + /* { dg-do run } */ + /* { dg-options "-fno-tree-scev-cprop -fno-tree-vectorize -g" } */ +-/* { dg-additional-options "-mno-unroll-only-small-loops" { target ia32 } } */ +- + + #include "../nop.h" + +diff --git a/gcc/testsuite/gcc.target/i386/pr86270.c b/gcc/testsuite/gcc.target/i386/pr86270.c +index cbc9fbb0450..98b012caf23 100644 +--- a/gcc/testsuite/gcc.target/i386/pr86270.c ++++ b/gcc/testsuite/gcc.target/i386/pr86270.c +@@ -1,5 +1,5 @@ + /* { dg-do compile } */ +-/* { dg-options "-O2 -mno-unroll-only-small-loops" } */ ++/* { dg-options "-O2 -fno-unroll-loops" } */ + + int *a; + long len; +diff --git a/gcc/testsuite/gcc.target/i386/pr93002.c b/gcc/testsuite/gcc.target/i386/pr93002.c +index f75a847f75d..7e2d869e17b 100644 +--- a/gcc/testsuite/gcc.target/i386/pr93002.c ++++ b/gcc/testsuite/gcc.target/i386/pr93002.c +@@ -1,6 +1,6 @@ + /* PR target/93002 */ + /* { dg-do compile } */ +-/* { dg-options "-O2 -mno-unroll-only-small-loops" } */ ++/* { dg-options "-O2 -fno-unroll-loops" } */ + /* { dg-final { scan-assembler-not "cmp\[^\n\r]*-1" } } */ + + volatile int sink; +-- +2.18.2 + diff --git a/gcc-12.spec b/gcc-12.spec index f6722b0..c00befb 100644 --- a/gcc-12.spec +++ b/gcc-12.spec @@ -85,7 +85,7 @@ Summary: Various compilers (C, C++, Objective-C, ...) Name: %{?scl_prefix}gcc%{gcc_ver} Version: 12.2.1 -Release: 12 +Release: 13 # libgcc, libgfortran, libgomp, libstdc++ and crtstuff have # GCC Runtime Exception. License: GPLv3+ and GPLv3+ with exceptions and GPLv2+ with exceptions and LGPLv2+ and BSD @@ -138,6 +138,7 @@ Patch1: 0002-i386-Add-syscall-to-enable-AMX-for-latest-kernels.patch Patch2: 0003-Remove-AVX512_VP2INTERSECT-from-PTA_SAPPHIRERAPIDS.patch Patch3: 0004-Add-attribute-hot-judgement-for-INLINE_HINT_known_ho.patch Patch4: 0005-Enable-small-loop-unrolling-for-O2.patch +Patch5: 0006-i386-Only-enable-small-loop-unrolling-in-backend-PR-.patch # On ARM EABI systems, we do want -gnueabi to be part of the @@ -600,6 +601,7 @@ not stable, so plugins must be rebuilt any time GCC is updated. %patch2 -p1 %patch3 -p1 %patch4 -p1 +%patch5 -p1 echo 'openEuler %{version}-%{release}' > gcc/DEV-PHASE @@ -2660,6 +2662,9 @@ end %doc rpm.doc/changelogs/libcc1/ChangeLog* %changelog +* Tue Nov 29 2022 Hongyu Wang 12.2.1-13 +- i386: Only enable small loop unrolling in backend [PR 107692] + * Tue Nov 29 2022 Hongyu Wang 12.2.1-12 - Enable small loop unrolling for O2