[gcc r13-2246] s390: Add -munroll-only-small-loops.

[Robin Dapp <rdapp@gcc.gnu.org>]

https://gcc.gnu.org/g:af8955112f4d3294d9cc50a2a125718b202321f0

commit r13-2246-gaf8955112f4d3294d9cc50a2a125718b202321f0
Author: Robin Dapp <rdapp@linux.ibm.com>
Date:   Thu Mar 3 15:06:21 2022 +0100

    s390: Add -munroll-only-small-loops.
    
    Inspired by Power we also introduce -munroll-only-small-loops.  This
    implies activating -funroll-loops and -munroll-only-small-loops at -O2 and
    above.
    
    gcc/ChangeLog:
    
            * common/config/s390/s390-common.cc: Enable -funroll-loops and
            -munroll-only-small-loops for OPT_LEVELS_2_PLUS_SPEED_ONLY.
            * config/s390/s390.cc (s390_loop_unroll_adjust): Do not unroll
            loops larger than 12 instructions.
            (s390_override_options_after_change): Set unroll options.
            (s390_option_override_internal): Likewise.
            * config/s390/s390.opt: Document munroll-only-small-loops.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.target/s390/vector/vec-copysign.c: Do not unroll.
            * gcc.target/s390/zvector/autovec-double-quiet-uneq.c: Dito.
            * gcc.target/s390/zvector/autovec-double-signaling-ltgt.c: Dito.
            * gcc.target/s390/zvector/autovec-float-quiet-uneq.c: Dito.
            * gcc.target/s390/zvector/autovec-float-signaling-ltgt.c: Dito.

Diff:
---
 gcc/common/config/s390/s390-common.cc              |  5 ++++
 gcc/config/s390/s390.cc                            | 31 ++++++++++++++++++++++
 gcc/config/s390/s390.opt                           |  4 +++
 .../gcc.target/s390/vector/vec-copysign.c          |  2 +-
 .../s390/zvector/autovec-double-quiet-uneq.c       |  2 +-
 .../s390/zvector/autovec-double-signaling-ltgt.c   |  2 +-
 .../s390/zvector/autovec-float-quiet-uneq.c        |  2 +-
 .../s390/zvector/autovec-float-signaling-ltgt.c    |  2 +-
 8 files changed, 45 insertions(+), 5 deletions(-)

diff --git a/gcc/common/config/s390/s390-common.cc b/gcc/common/config/s390/s390-common.cc
index 72a5ef47eaa..be3e6f20142 100644
--- a/gcc/common/config/s390/s390-common.cc
+++ b/gcc/common/config/s390/s390-common.cc
@@ -64,6 +64,11 @@ static const struct default_options s390_option_optimization_table[] =
     /* Enable -fsched-pressure by default when optimizing.  */
     { 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 },
+
     /* ??? There are apparently still problems with -fcaller-saves.  */
     { OPT_LEVELS_ALL, OPT_fcaller_saves, NULL, 0 },
 
diff --git a/gcc/config/s390/s390.cc b/gcc/config/s390/s390.cc
index 5e06bf9350c..942ed267b87 100644
--- a/gcc/config/s390/s390.cc
+++ b/gcc/config/s390/s390.cc
@@ -15420,6 +15420,21 @@ s390_loop_unroll_adjust (unsigned nunroll, struct loop *loop)
   if (s390_tune < PROCESSOR_2097_Z10)
     return nunroll;
 
+  if (unroll_only_small_loops)
+    {
+      /* Only unroll loops smaller than or equal to 12 insns.  */
+      const unsigned int small_threshold = 12;
+
+      if (loop->ninsns > small_threshold)
+	return 0;
+
+      /* ???: Make this dependent on the type of registers in
+	 the loop.  Increase the limit for vector registers.  */
+      const unsigned int max_insns = optimize >= 3 ? 36 : 24;
+
+      nunroll = MIN (nunroll, max_insns / loop->ninsns);
+    }
+
   /* Count the number of memory references within the loop body.  */
   bbs = get_loop_body (loop);
   subrtx_iterator::array_type array;
@@ -15494,6 +15509,19 @@ static void
 s390_override_options_after_change (void)
 {
   s390_default_align (&global_options);
+
+  /* Explicit -funroll-loops turns -munroll-only-small-loops off.  */
+  if ((OPTION_SET_P (flag_unroll_loops) && flag_unroll_loops)
+       || (OPTION_SET_P (flag_unroll_all_loops)
+	   && flag_unroll_all_loops))
+    {
+      if (!OPTION_SET_P (unroll_only_small_loops))
+	unroll_only_small_loops = 0;
+      if (!OPTION_SET_P (flag_cunroll_grow_size))
+	flag_cunroll_grow_size = 1;
+    }
+  else if (!OPTION_SET_P (flag_cunroll_grow_size))
+    flag_cunroll_grow_size = flag_peel_loops || optimize >= 3;
 }
 
 static void
@@ -15703,6 +15731,9 @@ s390_option_override_internal (struct gcc_options *opts,
   /* Set the default alignment.  */
   s390_default_align (opts);
 
+  /* Set unroll options.  */
+  s390_override_options_after_change ();
+
   /* Call target specific restore function to do post-init work.  At the moment,
      this just sets opts->x_s390_cost_pointer.  */
   s390_function_specific_restore (opts, opts_set, NULL);
diff --git a/gcc/config/s390/s390.opt b/gcc/config/s390/s390.opt
index 9e8d3bfd404..c375b9c5f72 100644
--- a/gcc/config/s390/s390.opt
+++ b/gcc/config/s390/s390.opt
@@ -321,3 +321,7 @@ and the default behavior is to emit separate multiplication and addition
 instructions for long doubles in vector registers, because measurements show
 that this improves performance.  This option allows overriding it for testing
 purposes.
+
+munroll-only-small-loops
+Target Undocumented Var(unroll_only_small_loops) Init(0) Save
+; Use conservative small loop unrolling.
diff --git a/gcc/testsuite/gcc.target/s390/vector/vec-copysign.c b/gcc/testsuite/gcc.target/s390/vector/vec-copysign.c
index 64c6970c23e..b723ceb13be 100644
--- a/gcc/testsuite/gcc.target/s390/vector/vec-copysign.c
+++ b/gcc/testsuite/gcc.target/s390/vector/vec-copysign.c
@@ -1,5 +1,5 @@
 /* { dg-do compile { target { s390*-*-* } } } */
-/* { dg-options "-O2 -ftree-vectorize -mzarch" } */
+/* { dg-options "-O2 -ftree-vectorize -mzarch -fno-unroll-loops" } */
 /* { dg-final { scan-assembler-times "vgmg" 1 } } */
 /* { dg-final { scan-assembler-times "vgmf" 1 } } */
 /* { dg-final { scan-assembler-times "vsel" 2 } } */
diff --git a/gcc/testsuite/gcc.target/s390/zvector/autovec-double-quiet-uneq.c b/gcc/testsuite/gcc.target/s390/zvector/autovec-double-quiet-uneq.c
index 7c9b20fd2e0..8948be28ed5 100644
--- a/gcc/testsuite/gcc.target/s390/zvector/autovec-double-quiet-uneq.c
+++ b/gcc/testsuite/gcc.target/s390/zvector/autovec-double-quiet-uneq.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -march=z13 -mzvector -mzarch" } */
+/* { dg-options "-O3 -march=z13 -mzvector -mzarch -fno-unroll-loops" } */
 
 #include "autovec.h"
 
diff --git a/gcc/testsuite/gcc.target/s390/zvector/autovec-double-signaling-ltgt.c b/gcc/testsuite/gcc.target/s390/zvector/autovec-double-signaling-ltgt.c
index 9dfae8f2f7e..9417b0c4838 100644
--- a/gcc/testsuite/gcc.target/s390/zvector/autovec-double-signaling-ltgt.c
+++ b/gcc/testsuite/gcc.target/s390/zvector/autovec-double-signaling-ltgt.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -march=z14 -mzvector -mzarch" } */
+/* { dg-options "-O3 -march=z14 -mzvector -mzarch -fno-unroll-loops" } */
 
 #include "autovec.h"
 
diff --git a/gcc/testsuite/gcc.target/s390/zvector/autovec-float-quiet-uneq.c b/gcc/testsuite/gcc.target/s390/zvector/autovec-float-quiet-uneq.c
index 5ab9337880d..0a2aca0d5dd 100644
--- a/gcc/testsuite/gcc.target/s390/zvector/autovec-float-quiet-uneq.c
+++ b/gcc/testsuite/gcc.target/s390/zvector/autovec-float-quiet-uneq.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -march=z14 -mzvector -mzarch" } */
+/* { dg-options "-O3 -march=z14 -mzvector -mzarch -fno-unroll-loops" } */
 
 #include "autovec.h"
 
diff --git a/gcc/testsuite/gcc.target/s390/zvector/autovec-float-signaling-ltgt.c b/gcc/testsuite/gcc.target/s390/zvector/autovec-float-signaling-ltgt.c
index c34cf091608..15e61b70b0b 100644
--- a/gcc/testsuite/gcc.target/s390/zvector/autovec-float-signaling-ltgt.c
+++ b/gcc/testsuite/gcc.target/s390/zvector/autovec-float-signaling-ltgt.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O3 -march=z14 -mzvector -mzarch" } */
+/* { dg-options "-O3 -march=z14 -mzvector -mzarch -fno-unroll-loops" } */
 
 #include "autovec.h"