aarch64: disable LDP via tuning structure for -mcpu=ampere1

AmpereOne (-mcpu=ampere1) breaks LDP instructions into two uops.
Given the chance that this causes instructions to slip into the next
decoding cycle and the additional overheads when handling
cacheline-crossing LDP instructions, we disable the generation of LDP
isntructions through the tuning structure from instruction combining
(such as in peephole2).

Given the code-density benefits in builtins and prologue/epilogue
expansion, we allow LDPs there.

This commit:
 * adds a new tuning option AARCH64_EXTRA_TUNE_NO_LDP_COMBINE
 * allows -moverride=tune=... to override this

These changes are benchmark-driven, yielding the following changes
(with a net-overall improvement):
   503.bwaves_r.      -0.88%
   507.cactuBSSN_r     0.35%
   508.namd_r          3.09%
   510.parest_r       -2.99%
   511.povray_r        5.54%
   519.lbm_r          15.83%
   521.wrf_r           0.56%
   526.blender_r       2.47%
   527.cam4_r          0.70%
   538.imagick_r       0.00%
   544.nab_r          -0.33%
   549.fotonik3d_r.   -0.42%
   554.roms_r          0.00%
   -------------------------
   = total             1.79%

Signed-off-by: Philipp Tomsich <philipp.tomsich@vrull.eu>
Co-Authored-By: Di Zhao <di.zhao@amperecomputing.com>

gcc/ChangeLog:

	* config/aarch64/aarch64-tuning-flags.def (AARCH64_EXTRA_TUNING_OPTION):
	Add AARCH64_EXTRA_TUNE_NO_LDP_COMBINE.
	* config/aarch64/aarch64.cc (aarch64_operands_ok_for_ldpstp):
	Check for the above tuning option when processing loads.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/ampere1-no_ldp_combine.c: New test.

3 files changed, 30 insertions, 2 deletions

diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
index 712895a..52112ba 100644
--- a/gcc/config/aarch64/aarch64-tuning-flags.def
+++ b/gcc/config/aarch64/aarch64-tuning-flags.def
@@ -44,6 +44,9 @@ AARCH64_EXTRA_TUNING_OPTION ("cheap_shift_extend", CHEAP_SHIFT_EXTEND)
 /* Disallow load/store pair instructions on Q-registers.  */
 AARCH64_EXTRA_TUNING_OPTION ("no_ldp_stp_qregs", NO_LDP_STP_QREGS)
 
+/* Disallow load-pair instructions to be formed in combine/peephole.  */
+AARCH64_EXTRA_TUNING_OPTION ("no_ldp_combine", NO_LDP_COMBINE)
+
 AARCH64_EXTRA_TUNING_OPTION ("rename_load_regs", RENAME_LOAD_REGS)
 
 AARCH64_EXTRA_TUNING_OPTION ("cse_sve_vl_constants", CSE_SVE_VL_CONSTANTS)
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index f4ef22c..0f04ab9 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -1933,7 +1933,7 @@ static const struct tune_params ampere1_tunings =
   2,	/* min_div_recip_mul_df.  */
   0,	/* max_case_values.  */
   tune_params::AUTOPREFETCHER_WEAK,	/* autoprefetcher_model.  */
-  (AARCH64_EXTRA_TUNE_NONE),		/* tune_flags.  */
+  (AARCH64_EXTRA_TUNE_NO_LDP_COMBINE),	/* tune_flags.  */
   &ampere1_prefetch_tune
 };
 
@@ -1971,7 +1971,7 @@ static const struct tune_params ampere1a_tunings =
   2,	/* min_div_recip_mul_df.  */
   0,	/* max_case_values.  */
   tune_params::AUTOPREFETCHER_WEAK,	/* autoprefetcher_model.  */
-  (AARCH64_EXTRA_TUNE_NONE),		/* tune_flags.  */
+  (AARCH64_EXTRA_TUNE_NO_LDP_COMBINE),	/* tune_flags.  */
   &ampere1_prefetch_tune
 };
 
@@ -26053,6 +26053,20 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
   enum reg_class rclass_1, rclass_2;
   rtx mem_1, mem_2, reg_1, reg_2;
 
+  /* Allow the tuning structure to disable LDP instruction formation
+     from combining instructions (e.g., in peephole2).
+     TODO: Implement fine-grained tuning control for LDP and STP:
+	   1. control policies for load and store separately;
+	   2. support the following policies:
+	      - default (use what is in the tuning structure)
+	      - always
+	      - never
+	      - aligned (only if the compiler can prove that the
+		load will be aligned to 2 * element_size)  */
+  if (load && (aarch64_tune_params.extra_tuning_flags
+	       & AARCH64_EXTRA_TUNE_NO_LDP_COMBINE))
+    return false;
+
   if (load)
     {
       mem_1 = operands[1];
diff --git a/gcc/testsuite/gcc.target/aarch64/ampere1-no_ldp_combine.c b/gcc/testsuite/gcc.target/aarch64/ampere1-no_ldp_combine.c
new file mode 100644
index 0000000..bc871f4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/ampere1-no_ldp_combine.c
@@ -0,0 +1,11 @@
+/* { dg-options "-O3 -mtune=ampere1" } */
+
+long
+foo (long a[])
+{
+  return a[0] + a[1];
+}
+
+/* We should see two ldrs instead of one ldp. */
+/* { dg-final { scan-assembler {\tldr\t} } } */
+/* { dg-final { scan-assembler-not {\tldp\t} } } */