[PATCH] i386: Enable small loop unrolling for O2

Hongyu Wang hongyu.wang@intel.com
Wed Oct 26 05:52:48 GMT 2022


Hi,

Inspired by rs6000 and s390 port changes, this patch
enables loop unrolling for small size loop at O2 by default.
The default behavior is to unroll loop with unknown trip-count and
less than 4 insns by 1 time.

This improves 548.exchange2 by 3.5% on icelake and 6% on zen3 with
1.2% codesize increment. For other benchmarks the variants are minor
and overall codesize increased by 0.2%.

The kernel image size increased by 0.06%, and no impact on eembc.

Bootstrapped & regrtested on x86_64-pc-linux-gnu.

Ok for trunk?

gcc/ChangeLog:

	* common/config/i386/i386-common.cc (ix86_optimization_table):
	Enable loop unroll and small loop unroll at O2 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.
	* config/i386/i386.opt: Add -munroll-only-small-loops,
	-param=x86-small-unroll-ninsns= for loop insn limit,
	-param=x86-small-unroll-factor= for unroll factor.
	* doc/invoke.texi: Document -munroll-only-small-loops,
	x86-small-unroll-ninsns and x86-small-unroll-factor.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr86270.c: Add -mno-unroll-only-small-loops.
	* gcc.target/i386/pr93002.c: Likewise.
---
 gcc/common/config/i386/i386-common.cc   |  6 ++++
 gcc/config/i386/i386-options.cc         | 40 ++++++++++++++++++++++---
 gcc/config/i386/i386.cc                 | 13 ++++++++
 gcc/config/i386/i386.opt                | 13 ++++++++
 gcc/doc/invoke.texi                     | 14 +++++++++
 gcc/testsuite/gcc.target/i386/pr86270.c |  2 +-
 gcc/testsuite/gcc.target/i386/pr93002.c |  2 +-
 7 files changed, 84 insertions(+), 6 deletions(-)

diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
index d6a68dc9b1d..0e580b39d14 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -1686,6 +1686,12 @@ 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 },
+    { 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 acb2291e70f..6ea347c32e1 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -1819,8 +1819,43 @@ 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;
+      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;
+      /* Disables loop unrolling if -mno-unroll-only-small-loops is
+	 explicitly set and -funroll-loops is not enabled.  */
+      if (OPTION_SET_P (ix86_unroll_only_small_loops)
+	  && !ix86_unroll_only_small_loops
+	  && !(OPTION_SET_P (flag_unroll_loops)
+	       || OPTION_SET_P (flag_unroll_all_loops)))
+	flag_unroll_loops = flag_unroll_all_loops = 0;
+    }
+
 }
 
 /* Clear stack slot assignments remembered from previous functions.
@@ -2332,7 +2367,7 @@ 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
@@ -2363,9 +2398,6 @@ 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 480db35f6cd..75829a5d0f4 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -23820,6 +23820,19 @@ ix86_loop_unroll_adjust (unsigned nunroll, class loop *loop)
   unsigned i;
   unsigned mem_count = 0;
 
+  /* Unroll small size loop when unroll factor is not explicitly
+     specified.  */
+  if (ix86_unroll_only_small_loops && !loop->unroll)
+    {
+      int small_unroll = 0;
+      if (loop->ninsns <= (unsigned) ix86_small_unroll_ninsns)
+	small_unroll = MIN ((unsigned) ix86_small_unroll_factor,
+			    nunroll);
+      else
+	small_unroll = 1;
+      return small_unroll;
+    }
+
   if (!TARGET_ADJUST_UNROLL)
      return nunroll;
 
diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
index 0dbaacb57ed..a724c73c0c4 100644
--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
@@ -1214,3 +1214,16 @@ Do not use GOT to access external symbols.
 -param=x86-stlf-window-ninsns=
 Target Joined UInteger Var(x86_stlf_window_ninsns) Init(64) Param
 Instructions number above which STFL stall penalty can be compensated.
+
+munroll-only-small-loops
+Target Var(ix86_unroll_only_small_loops) Init(0) Save
+Enable conservative small loop unrolling.
+
+-param=x86-small-unroll-ninsns=
+Target Joined UInteger Var(ix86_small_unroll_ninsns) Init(4) Param
+Insturctions number limit for loop to be unrolled under
+-munroll-only-small-loops.
+
+-param=x86-small-unroll-factor=
+Target Joined UInteger Var(ix86_small_unroll_factor) Init(2) Param
+Unroll factor for -munroll-only-small-loops.
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index cd4d3c1d72c..b6fa79eccc3 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -15779,6 +15779,14 @@ The following choices of @var{name} are available on i386 and x86_64 targets:
 @item x86-stlf-window-ninsns
 Instructions number above which STFL stall penalty can be compensated.
 
+@item x86-small-unroll-ninsns
+If -munroll-only-small-loops is enabled, only unroll loops with instruction
+count less than this parameter. The default value is 4.
+
+@item x86-small-unroll-factor
+If -munroll-only-small-loops is enabled, reset the unroll factor with this
+value. The default value is 2 which means the loop will be unrolled once.
+
 @end table
 
 @end table
@@ -25186,6 +25194,12 @@ environments where no dynamic link is performed, like firmwares, OS
 kernels, executables linked with @option{-static} or @option{-static-pie}.
 @option{-mdirect-extern-access} is not compatible with @option{-fPIC} or
 @option{-fpic}.
+
+@item -munroll-only-small-loops
+@itemx -mno-unroll-only-small-loops
+@opindex munroll-only-small-loops
+Controls conservative small loop unrolling. It is default enbaled by
+O2, and unrolls loop with less than 4 insns by 1 time.
 @end table
 
 @node M32C Options
diff --git a/gcc/testsuite/gcc.target/i386/pr86270.c b/gcc/testsuite/gcc.target/i386/pr86270.c
index 81841ef5bd7..cbc9fbb0450 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" } */
+/* { dg-options "-O2 -mno-unroll-only-small-loops" } */
 
 int *a;
 long len;
diff --git a/gcc/testsuite/gcc.target/i386/pr93002.c b/gcc/testsuite/gcc.target/i386/pr93002.c
index 0248fcc00a5..f75a847f75d 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" } */
+/* { dg-options "-O2 -mno-unroll-only-small-loops" } */
 /* { dg-final { scan-assembler-not "cmp\[^\n\r]*-1" } } */
 
 volatile int sink;
-- 
2.18.1



More information about the Gcc-patches mailing list