!14 Small loop unrolling in O2.

From: @github-27907959 Reviewed-by: @li-yancheng, @eastb233 Signed-off-by: @eastb233
2022-12-07 01:57:29 +00:00 · 2022-12-07 01:57:29 +00:00 · eb34b0fb56
commit eb34b0fb56
parent c7f246f05b 5603bb17fc
3 changed files with 723 additions and 1 deletions
--- a/0005-Enable-small-loop-unrolling-for-O2.patch
+++ b/0005-Enable-small-loop-unrolling-for-O2.patch
@ -0,0 +1,481 @@
+From 6c977a4e458eab0dd7684b143baf72240b96fda8 Mon Sep 17 00:00:00 2001
+From: Hongyu Wang <hongyu.wang@intel.com>
+Date: Thu, 8 Sep 2022 16:52:02 +0800
+Subject: [PATCH 4/5] Enable small loop unrolling for O2
+
+Modern processors has multiple way instruction decoders
+For x86, icelake/zen3 has 5 uops, so for small loop with <= 4
+instructions (usually has 3 uops with a cmp/jmp pair that can be
+macro-fused), the decoder would have 2 uops bubble for each iteration
+and the pipeline could not be fully utilized.
+
+Therefore, this patch enables loop unrolling for small size loop at O2
+to fullfill the decoder as much as possible. It turns on rtl loop
+unrolling when targetm.loop_unroll_adjust exists and O2 plus speed only.
+In x86 backend the default behavior is to unroll small loops with less
+than 4 insns by 1 time.
+
+This improves 548.exchange2 by 9% on icelake and 7.4% on zen3 with
+0.9% 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.
+
+gcc/ChangeLog:
+
+	* common/config/i386/i386-common.cc (ix86_optimization_table):
+	Enable small loop unroll at O2 by default.
+	* config/i386/i386.cc (ix86_loop_unroll_adjust): Adjust unroll
+	factor if -munroll-only-small-loops enabled and -funroll-loops/
+	-funroll-all-loops are disabled.
+	* config/i386/i386.h (struct processor_costs): Add 2 field
+	small_unroll_ninsns and small_unroll_factor.
+	* config/i386/i386.opt: Add -munroll-only-small-loops.
+	* doc/invoke.texi: Document -munroll-only-small-loops.
+	* loop-init.cc (pass_rtl_unroll_loops::gate): Enable rtl
+	loop unrolling for -O2-speed and above if target hook
+	loop_unroll_adjust exists.
+	(pass_rtl_unroll_loops::execute): Set UAP_UNROLL flag
+	when target hook loop_unroll_adjust exists.
+	* config/i386/x86-tune-costs.h: Update all processor costs
+	with small_unroll_ninsns = 4 and small_unroll_factor = 2.
+
+gcc/testsuite/ChangeLog:
+
+	* gcc.dg/guality/loop-1.c: Add additional option
+	-mno-unroll-only-small-loops.
+	* gcc.target/i386/pr86270.c: Add -mno-unroll-only-small-loops.
+	* gcc.target/i386/pr93002.c: Likewise.
+---
+ gcc/common/config/i386/i386-common.cc   |  1 +
+ gcc/config/i386/i386.cc                 | 18 ++++++++
+ gcc/config/i386/i386.h                  |  5 +++
+ gcc/config/i386/i386.opt                |  4 ++
+ gcc/config/i386/x86-tune-costs.h        | 56 +++++++++++++++++++++++++
+ gcc/doc/invoke.texi                     | 11 ++++-
+ gcc/loop-init.cc                        | 10 +++--
+ 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 +-
+ 10 files changed, 105 insertions(+), 6 deletions(-)
+
+diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
+index 07fdd045f30..e1c1fb07d8a 100644
+--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
+@@ -1687,6 +1687,7 @@ 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_munroll_only_small_loops, NULL, 1 },
+     /* 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.cc b/gcc/config/i386/i386.cc
+index b16df5b183e..39b2468799c 100644
+--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
+@@ -23561,6 +23561,24 @@ 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 (!(flag_unroll_loops
+	|| flag_unroll_all_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 (!TARGET_ADJUST_UNROLL)
+      return nunroll;
+ 
+diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
+index a61c32b8957..421801111a7 100644
+--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
+@@ -219,6 +219,11 @@ struct processor_costs {
+   const char *const align_jump;		/* Jump alignment.  */
+   const char *const align_label;	/* Label alignment.  */
+   const char *const align_func;		/* Function alignment.  */
+
+  const unsigned small_unroll_ninsns;	/* Insn count limit for small loop
+					   to be unrolled.  */
+  const unsigned small_unroll_factor;   /* Unroll factor for small loop to
+					   be unrolled.  */
+ };
+ 
+ extern const struct processor_costs *ix86_cost;
+diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
+index a6b0e28f238..3d369647bf7 100644
+--- a/gcc/config/i386/i386.opt
+++ b/gcc/config/i386/i386.opt
+@@ -1214,3 +1214,7 @@ 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.
+diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h
+index 017ffa69958..b4303e4e971 100644
+--- a/gcc/config/i386/x86-tune-costs.h
+++ b/gcc/config/i386/x86-tune-costs.h
+@@ -135,6 +135,8 @@ struct processor_costs ix86_size_cost = {/* costs for tuning for size */
+   NULL,					/* Jump alignment.  */
+   NULL,					/* Label alignment.  */
+   NULL,					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* Processor costs (relative to an add) */
+@@ -244,6 +246,8 @@ struct processor_costs i386_cost = {	/* 386 specific costs */
+   "4",					/* Jump alignment.  */
+   NULL,					/* Label alignment.  */
+   "4",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs i486_memcpy[2] = {
+@@ -354,6 +358,8 @@ struct processor_costs i486_cost = {	/* 486 specific costs */
+   "16",					/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs pentium_memcpy[2] = {
+@@ -462,6 +468,8 @@ struct processor_costs pentium_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static const
+@@ -563,6 +571,8 @@ struct processor_costs lakemont_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* PentiumPro has optimized rep instructions for blocks aligned by 8 bytes
+@@ -679,6 +689,8 @@ struct processor_costs pentiumpro_cost = {
+   "16:11:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs geode_memcpy[2] = {
+@@ -786,6 +798,8 @@ struct processor_costs geode_cost = {
+   NULL,					/* Jump alignment.  */
+   NULL,					/* Label alignment.  */
+   NULL,					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs k6_memcpy[2] = {
+@@ -896,6 +910,8 @@ struct processor_costs k6_cost = {
+   "32:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "32",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* For some reason, Athlon deals better with REP prefix (relative to loops)
+@@ -1007,6 +1023,8 @@ struct processor_costs athlon_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* K8 has optimized REP instruction for medium sized blocks, but for very
+@@ -1127,6 +1145,8 @@ struct processor_costs k8_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* AMDFAM10 has optimized REP instruction for medium sized blocks, but for
+@@ -1255,6 +1275,8 @@ struct processor_costs amdfam10_cost = {
+   "32:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "32",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /*  BDVER has optimized REP instruction for medium sized blocks, but for
+@@ -1376,6 +1398,8 @@ const struct processor_costs bdver_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "11",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ 
+@@ -1529,6 +1553,8 @@ struct processor_costs znver1_cost = {
+   "16",					/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /*  ZNVER2 has optimized REP instruction for medium sized blocks, but for
+@@ -1686,6 +1712,8 @@ struct processor_costs znver2_cost = {
+   "16",					/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ struct processor_costs znver3_cost = {
+@@ -1818,6 +1846,8 @@ struct processor_costs znver3_cost = {
+   "16",					/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* skylake_cost should produce code tuned for Skylake familly of CPUs.  */
+@@ -1942,6 +1972,8 @@ struct processor_costs skylake_cost = {
+   "16:11:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* icelake_cost should produce code tuned for Icelake family of CPUs.
+@@ -2068,6 +2100,8 @@ struct processor_costs icelake_cost = {
+   "16:11:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* alderlake_cost should produce code tuned for alderlake family of CPUs.  */
+@@ -2188,6 +2222,8 @@ struct processor_costs alderlake_cost = {
+   "16:11:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+   /* BTVER1 has optimized REP instruction for medium sized blocks, but for
+@@ -2301,6 +2337,8 @@ const struct processor_costs btver1_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "11",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs btver2_memcpy[2] = {
+@@ -2411,6 +2449,8 @@ const struct processor_costs btver2_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "11",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs pentium4_memcpy[2] = {
+@@ -2520,6 +2560,8 @@ struct processor_costs pentium4_cost = {
+   NULL,					/* Jump alignment.  */
+   NULL,					/* Label alignment.  */
+   NULL,					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs nocona_memcpy[2] = {
+@@ -2632,6 +2674,8 @@ struct processor_costs nocona_cost = {
+   NULL,					/* Jump alignment.  */
+   NULL,					/* Label alignment.  */
+   NULL,					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs atom_memcpy[2] = {
+@@ -2742,6 +2786,8 @@ struct processor_costs atom_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs slm_memcpy[2] = {
+@@ -2852,6 +2898,8 @@ struct processor_costs slm_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs tremont_memcpy[2] = {
+@@ -2976,6 +3024,8 @@ struct processor_costs tremont_cost = {
+   "16:11:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ static stringop_algs intel_memcpy[2] = {
+@@ -3086,6 +3136,8 @@ struct processor_costs intel_cost = {
+   "16:8:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* Generic should produce code tuned for Core-i7 (and newer chips)
+@@ -3205,6 +3257,8 @@ struct processor_costs generic_cost = {
+   "16:11:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+ /* core_cost should produce code tuned for Core familly of CPUs.  */
+@@ -3331,5 +3385,7 @@ struct processor_costs core_cost = {
+   "16:11:8",				/* Jump alignment.  */
+   "0:0:8",				/* Label alignment.  */
+   "16",					/* Func alignment.  */
+  4,					/* Small unroll limit.  */
+  2,					/* Small unroll factor.  */
+ };
+ 
+diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
+index 9ac7f89ebb1..1961cafa2bb 100644
+--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
+@@ -1448,7 +1448,8 @@ See RS/6000 and PowerPC Options.
+ -mgeneral-regs-only  -mcall-ms2sysv-xlogues -mrelax-cmpxchg-loop @gol
+ -mindirect-branch=@var{choice}  -mfunction-return=@var{choice} @gol
+ -mindirect-branch-register -mharden-sls=@var{choice} @gol
+--mindirect-branch-cs-prefix -mneeded -mno-direct-extern-access}
+-mindirect-branch-cs-prefix -mneeded -mno-direct-extern-access @gol
+-munroll-only-small-loops}
+ 
+ @emph{x86 Windows Options}
+ @gccoptlist{-mconsole  -mcygwin  -mno-cygwin  -mdll @gol
+@@ -33157,6 +33158,14 @@ treat access to protected symbols as local symbols.  The default is
+ @option{-mno-direct-extern-access} and executable compiled with
+ @option{-mdirect-extern-access} may not be binary compatible if
+ protected symbols are used in shared libraries and executable.
+
+@item -munroll-only-small-loops
+@opindex munroll-only-small-loops
+@opindex mno-unroll-only-small-loops
+Controls conservative small loop unrolling. It is default enabled by
+O2, and unrolls loop with less than 4 insns by 1 time. Explicit
+-f[no-]unroll-[all-]loops would disable this flag to avoid any
+unintended unrolling behavior that user does not want.
+ @end table
+ 
+ @node x86 Windows Options
+diff --git a/gcc/loop-init.cc b/gcc/loop-init.cc
+index 1e4f6cfd7fb..84336865ef7 100644
+--- a/gcc/loop-init.cc
+++ b/gcc/loop-init.cc
+@@ -565,9 +565,12 @@ public:
+   {}
+ 
+   /* opt_pass methods: */
+-  virtual bool gate (function *)
+  virtual bool gate (function * fun)
+     {
+-      return (flag_unroll_loops || flag_unroll_all_loops || cfun->has_unroll);
+      return (flag_unroll_loops || flag_unroll_all_loops || cfun->has_unroll
+	      || (targetm.loop_unroll_adjust
+		  && optimize >= 2
+		  && optimize_function_for_speed_p (fun)));
+     }
+ 
+   virtual unsigned int execute (function *);
+@@ -583,7 +586,8 @@ pass_rtl_unroll_loops::execute (function *fun)
+       if (dump_file)
+ 	df_dump (dump_file);
+ 
+-      if (flag_unroll_loops)
+      if (flag_unroll_loops
+	  || targetm.loop_unroll_adjust)
+ 	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 1b1f6d32271..a32ea445a3f 100644
+--- a/gcc/testsuite/gcc.dg/guality/loop-1.c
+++ b/gcc/testsuite/gcc.dg/guality/loop-1.c
+@@ -1,5 +1,7 @@
+ /* { 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 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;
+-- 
+2.18.2
+
--- a/0006-i386-Only-enable-small-loop-unrolling-in-backend-PR-.patch
+++ 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 <hongyu.wang@intel.com>
+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
+
--- a/gcc-12.spec
+++ b/gcc-12.spec
@ -86,7 +86,7 @@
 Summary: Various compilers (C, C++, Objective-C, ...)
 Name: %{?scl_prefix}gcc%{gcc_ver}
 Version: 12.2.1
-Release: 11
+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 +138,8 @@ Patch0: 0001-change-gcc-version.patch
 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
@ -599,6 +601,8 @@ not stable, so plugins must be rebuilt any time GCC is updated.
 %patch1 -p1
 %patch2 -p1
 %patch3 -p1
+%patch4 -p1
+%patch5 -p1

 echo '%{vendor} %{version}-%{release}' > gcc/DEV-PHASE

@ -2659,6 +2663,12 @@ end
 %doc rpm.doc/changelogs/libcc1/ChangeLog*

 %changelog
+* Tue Nov 29 2022 Hongyu Wang <hongyu.wang@intel.com> 12.2.1-13
+- i386: Only enable small loop unrolling in backend [PR 107692]
+
+* Tue Nov 29 2022 Hongyu Wang <hongyu.wang@intel.com> 12.2.1-12
+- Enable small loop unrolling for O2
+
 * Fri Nov 18 2022 Chenxi Mao <chenxi.mao@suse.com> 12.2.1-11
 - Support --program-suffix configuration