From 9f489a5731f12b8e6b49994e8f61acb5d26f508e Mon Sep 17 00:00:00 2001 From: Richard Biener Date: Fri, 2 Jul 2021 13:48:07 +0200 Subject: [PATCH] add -fmove-loop-stores option to control GIMPLE loop store-motion This adds the -fmove-loop-stores option, mainly as a way to disable the store-motion part of GIMPLE invariant motion (-ftree-loop-im) which is enabled by default. It might be sensible to turn off -fmove-loop-stores at -O1 since it can result in compile-time as well as memory usage issues but this patch tries to preserve existing behavior besides introducing the new option with the exception of -Og where I've disabled it. Controlling store-motion has been made easy by earlier refactoring for the invariant motion only use after loop interchange. 2021-07-02 Richard Biener * doc/invoke.texi (fmove-loop-stores): Document. * common.opt (fmove-loop-stores): New option. * opts.c (default_options_table): Enable -fmove-loop-stores at -O1 but not -Og. * tree-ssa-loop-im.c (pass_lim::execute): Pass flag_move_loop_stores instead of true to loop_invariant_motion_in_fun. --- gcc/common.opt | 4 ++++ gcc/doc/invoke.texi | 14 ++++++++++++-- gcc/opts.c | 1 + gcc/tree-ssa-loop-im.c | 2 +- 4 files changed, 18 insertions(+), 3 deletions(-) diff --git a/gcc/common.opt b/gcc/common.opt index 5b03bbc66620..d9da1131edaa 100644 --- a/gcc/common.opt +++ b/gcc/common.opt @@ -2084,6 +2084,10 @@ fmove-loop-invariants Common Var(flag_move_loop_invariants) Optimization Move loop invariant computations out of loops. +fmove-loop-stores +Common Var(flag_move_loop_stores) Optimization +Move stores out of loops. + fdce Common Var(flag_dce) Init(1) Optimization Use the RTL dead code elimination pass. diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index f470fc6be58e..e67d47af676d 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -528,7 +528,7 @@ Objective-C and Objective-C++ Dialects}. -floop-parallelize-all -flra-remat -flto -flto-compression-level @gol -flto-partition=@var{alg} -fmerge-all-constants @gol -fmerge-constants -fmodulo-sched -fmodulo-sched-allow-regmoves @gol --fmove-loop-invariants -fno-branch-count-reg @gol +-fmove-loop-invariants -fmove-loop-stores -fno-branch-count-reg @gol -fno-defer-pop -fno-fp-int-builtin-inexact -fno-function-cse @gol -fno-guess-branch-probability -fno-inline -fno-math-errno -fno-peephole @gol -fno-peephole2 -fno-printf-return-value -fno-sched-interblock @gol @@ -10260,6 +10260,7 @@ compilation time. -fipa-reference-addressable @gol -fmerge-constants @gol -fmove-loop-invariants @gol +-fmove-loop-stores@gol -fomit-frame-pointer @gol -freorder-blocks @gol -fshrink-wrap @gol @@ -10403,7 +10404,7 @@ optimization flags except for those that may interfere with debugging: @gccoptlist{-fbranch-count-reg -fdelayed-branch @gol -fdse -fif-conversion -fif-conversion2 @gol -finline-functions-called-once @gol --fmove-loop-invariants -fssa-phiopt @gol +-fmove-loop-invariants -fmove-loop-stores -fssa-phiopt @gol -ftree-bit-ccp -ftree-dse -ftree-pta -ftree-sra} @end table @@ -13011,6 +13012,15 @@ Enabled by @option{-O3}, @option{-fprofile-use}, and @option{-fauto-profile}. Enables the loop invariant motion pass in the RTL loop optimizer. Enabled at level @option{-O1} and higher, except for @option{-Og}. +@item -fmove-loop-stores +@opindex fmove-loop-stores +Enables the loop store motion pass in the GIMPLE loop optimizer. This +moves invariant stores to after the end of the loop in exchange for +carrying the stored value in a register across the iteration. +Note for this option to have an effect @option{-ftree-loop-im} has to +be enabled as well. Enabled at level @option{-O1} and higher, except +for @option{-Og}. + @item -fsplit-loops @opindex fsplit-loops Split a loop into two if it contains a condition that's always true diff --git a/gcc/opts.c b/gcc/opts.c index f159bb35130b..25282f71a3b7 100644 --- a/gcc/opts.c +++ b/gcc/opts.c @@ -575,6 +575,7 @@ static const struct default_options default_options_table[] = { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_fif_conversion2, NULL, 1 }, { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_finline_functions_called_once, NULL, 1 }, { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_fmove_loop_invariants, NULL, 1 }, + { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_fmove_loop_stores, NULL, 1 }, { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_fssa_phiopt, NULL, 1 }, { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_fipa_modref, NULL, 1 }, { OPT_LEVELS_1_PLUS_NOT_DEBUG, OPT_ftree_bit_ccp, NULL, 1 }, diff --git a/gcc/tree-ssa-loop-im.c b/gcc/tree-ssa-loop-im.c index e7a3050ba9da..9ac390b9a4b4 100644 --- a/gcc/tree-ssa-loop-im.c +++ b/gcc/tree-ssa-loop-im.c @@ -3258,7 +3258,7 @@ pass_lim::execute (function *fun) if (number_of_loops (fun) <= 1) return 0; - unsigned int todo = loop_invariant_motion_in_fun (fun, true); + unsigned int todo = loop_invariant_motion_in_fun (fun, flag_move_loop_stores); if (!in_loop_pipeline) loop_optimizer_finalize (); -- 2.47.2