Previously, turning -funroll-loops on at -O2, which also turn on
GIMPLE cunroll fully. While cunroll unrolls some complex loops.
This patch turn on -frtl-unroll-loops at -O2 only, and continue to
use previous tuned rs6000 heurisitics for small loops. While this
patch does not turn on GIMPLE cunroll any more. We may tune
cunroll in near future at -O2.
In this patch, it become simpler to check/set -fweb, -frename-register
and -munroll-only-small-loops. Together with -frtl-unroll-loops, -fweb
is useful, then turn -fweb on; and -frename-registers is no need to
be checked, because it is affected by -frtl-unroll-loops.
Bootstrap and regtest pass on powerpc64le, is this ok for trunk?
And backport to GCC10 together with the patch "Seperate -funroll-loops
for GIMPLE unroller and RTL unroller"
Jiufu
gcc/ChangeLog
2020-05-25 Jiufu Guo <guoji...@cn.ibm.com>
PR target/95018
* common/config/rs6000/rs6000-common.c
(rs6000_option_optimization_table)
[OPT_LEVELS_2_PLUS_SPEED_ONLY]: Replace -funroll-loops
with -frtl-unroll-loops. Remove -munroll-only-small-loops
and add -fweb.
[OPT_LEVELS_ALL]: Remove turn off -frename-registers.
* config/rs6000/rs6000.c (rs6000_option_override_internal):
-funroll-loops overrides -munroll-only-small-loops and
-frtl-unroll-loops.
---
gcc/common/config/rs6000/rs6000-common.c | 11 +++--------
gcc/config/rs6000/rs6000.c | 21 ++++++++++-----------
2 files changed, 13 insertions(+), 19 deletions(-)
diff --git a/gcc/common/config/rs6000/rs6000-common.c
b/gcc/common/config/rs6000/rs6000-common.c
index ee37b9dc90b..c7388edb867 100644
--- a/gcc/common/config/rs6000/rs6000-common.c
+++ b/gcc/common/config/rs6000/rs6000-common.c
@@ -34,14 +34,9 @@ static const struct default_options
rs6000_option_optimization_table[] =
{ OPT_LEVELS_ALL, OPT_fsplit_wide_types_early, NULL, 1 },
/* Enable -fsched-pressure for first pass instruction scheduling. */
{ OPT_LEVELS_1_PLUS, OPT_fsched_pressure, NULL, 1 },
- /* Enable -munroll-only-small-loops with -funroll-loops to unroll small
- loops at -O2 and above by default. */
- { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_funroll_loops, NULL, 1 },
- { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_munroll_only_small_loops, NULL, 1 },
-
- /* -frename-registers leads to non-optimal codegen and performance
- on rs6000, turn it off by default. */
- { OPT_LEVELS_ALL, OPT_frename_registers, NULL, 0 },
+ /* Enable -frtl-unroll-loops and -fweb at -O2 and above by default. */
+ { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_frtl_unroll_loops, NULL, 1 },
+ { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_fweb, NULL, 1 },
/* Double growth factor to counter reduced min jump length. */
{ OPT_LEVELS_ALL, OPT__param_max_grow_copy_bb_insns_, NULL, 16 },
diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c
index 8435bc15d72..96620651a59 100644
--- a/gcc/config/rs6000/rs6000.c
+++ b/gcc/config/rs6000/rs6000.c
@@ -4557,17 +4557,16 @@ rs6000_option_override_internal (bool global_init_p)
param_sched_pressure_algorithm,
SCHED_PRESSURE_MODEL);
- /* Explicit -funroll-loops turns -munroll-only-small-loops off, and
- turns -frename-registers on. */
- if ((global_options_set.x_flag_unroll_loops && flag_unroll_loops)
- || (global_options_set.x_flag_unroll_all_loops
- && flag_unroll_all_loops))
- {
- if (!global_options_set.x_unroll_only_small_loops)
- unroll_only_small_loops = 0;
- if (!global_options_set.x_flag_rename_registers)
- flag_rename_registers = 1;
- }
+ /* if -f[no-]unroll-loops is specified explicitly, turn [off/]on
+ -frtl-unroll-loops. */
+ if (global_options_set.x_flag_unroll_loops
+ && !global_options_set.x_flag_rtl_unroll_loops)
+ flag_rtl_unroll_loops = flag_unroll_loops;
+
+ /* If flag_unroll_loops is effect, not _only_ small loops, but
+ large loops are unrolled if possible. */
+ if (!global_options_set.x_unroll_only_small_loops)
+ unroll_only_small_loops = flag_unroll_loops ? 0 : 1;
/* If using typedef char *va_list, signal that
__builtin_va_start (&ap, 0) can be optimized to
--
2.17.1
