[Patch 01/02] Introduce prefetch-minimum stride option

This patch adds a new option to control the minimum stride, for a memory
reference, after which the loop prefetch pass may issue software prefetch
hints for. There are two motivations:

* Make the pass less aggressive, only issuing prefetch hints for bigger strides
that are more likely to benefit from prefetching. I've noticed a case in cpu2017
where we were issuing thousands of hints, for example.

* For processors that have a hardware prefetcher, like Falkor, it allows the
loop prefetch pass to defer prefetching of smaller (less than the threshold)
strides to the hardware prefetcher instead. This prevents conflicts between
the software prefetcher and the hardware prefetcher.

I've noticed considerable reduction in the number of prefetch hints and
slightly positive performance numbers. This aligns GCC and LLVM in terms of
prefetch behavior for Falkor.

The default settings should guarantee no changes for existing targets. Those
are free to tweak the settings as necessary.

gcc/ChangeLog:

2018-05-23  Luis Machado  <luis.machado@linaro.org>

	* config/aarch64/aarch64-protos.h (cpu_prefetch_tune)
	<minimum_stride>: New const int field.
	* config/aarch64/aarch64.c (generic_prefetch_tune): Update to include
	minimum_stride field defaulting to -1.
	(exynosm1_prefetch_tune): Likewise.
	(thunderxt88_prefetch_tune): Likewise.
	(thunderx_prefetch_tune): Likewise.
	(thunderx2t99_prefetch_tune): Likewise.
	(qdf24xx_prefetch_tune) <minimum_stride>: Set to 2048.
	<default_opt_level>: Set to 3.
	(aarch64_override_options_internal): Update to set
	PARAM_PREFETCH_MINIMUM_STRIDE.
	* doc/invoke.texi (prefetch-minimum-stride): Document new option.
	* params.def (PARAM_PREFETCH_MINIMUM_STRIDE): New.
	* params.h (PARAM_PREFETCH_MINIMUM_STRIDE): Define.
	* tree-ssa-loop-prefetch.c (should_issue_prefetch_p): Return false if
	stride is constant and is below the minimum stride threshold.

From-SVN: r260617

7 files changed, 78 insertions, 1 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 12895be..403ee0e 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,23 @@
+2018-05-23  Luis Machado  <luis.machado@linaro.org>
+
+	* config/aarch64/aarch64-protos.h (cpu_prefetch_tune)
+	<minimum_stride>: New const int field.
+	* config/aarch64/aarch64.c (generic_prefetch_tune): Update to include
+	minimum_stride field defaulting to -1.
+	(exynosm1_prefetch_tune): Likewise.
+	(thunderxt88_prefetch_tune): Likewise.
+	(thunderx_prefetch_tune): Likewise.
+	(thunderx2t99_prefetch_tune): Likewise.
+	(qdf24xx_prefetch_tune) <minimum_stride>: Set to 2048.
+	<default_opt_level>: Set to 3.
+	(aarch64_override_options_internal): Update to set
+	PARAM_PREFETCH_MINIMUM_STRIDE.
+	* doc/invoke.texi (prefetch-minimum-stride): Document new option.
+	* params.def (PARAM_PREFETCH_MINIMUM_STRIDE): New.
+	* params.h (PARAM_PREFETCH_MINIMUM_STRIDE): Define.
+	* tree-ssa-loop-prefetch.c (should_issue_prefetch_p): Return false if
+	stride is constant and is below the minimum stride threshold.
+
 2018-05-23  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
 	* config/arm/arm-cpus.in (mode26): Delete.
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index 4ab6811..7e9fe3a 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -230,6 +230,9 @@ struct cpu_prefetch_tune
   const int l1_cache_size;
   const int l1_cache_line_size;
   const int l2_cache_size;
+  /* The minimum constant stride beyond which we should use prefetch
+     hints for.  */
+  const int minimum_stride;
   const int default_opt_level;
 };
 
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 7745192..561c407 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -550,6 +550,7 @@ static const cpu_prefetch_tune generic_prefetch_tune =
   -1,			/* l1_cache_size  */
   -1,			/* l1_cache_line_size  */
   -1,			/* l2_cache_size  */
+  -1,			/* minimum_stride */
   -1			/* default_opt_level  */
 };
 
@@ -559,6 +560,7 @@ static const cpu_prefetch_tune exynosm1_prefetch_tune =
   -1,			/* l1_cache_size  */
   64,			/* l1_cache_line_size  */
   -1,			/* l2_cache_size  */
+  -1,			/* minimum_stride */
   -1			/* default_opt_level  */
 };
 
@@ -568,7 +570,8 @@ static const cpu_prefetch_tune qdf24xx_prefetch_tune =
   32,			/* l1_cache_size  */
   64,			/* l1_cache_line_size  */
   512,			/* l2_cache_size  */
-  -1			/* default_opt_level  */
+  2048,			/* minimum_stride */
+  3			/* default_opt_level  */
 };
 
 static const cpu_prefetch_tune thunderxt88_prefetch_tune =
@@ -577,6 +580,7 @@ static const cpu_prefetch_tune thunderxt88_prefetch_tune =
   32,			/* l1_cache_size  */
   128,			/* l1_cache_line_size  */
   16*1024,		/* l2_cache_size  */
+  -1,			/* minimum_stride */
   3			/* default_opt_level  */
 };
 
@@ -586,6 +590,7 @@ static const cpu_prefetch_tune thunderx_prefetch_tune =
   32,			/* l1_cache_size  */
   128,			/* l1_cache_line_size  */
   -1,			/* l2_cache_size  */
+  -1,			/* minimum_stride */
   -1			/* default_opt_level  */
 };
 
@@ -595,6 +600,7 @@ static const cpu_prefetch_tune thunderx2t99_prefetch_tune =
   32,			/* l1_cache_size  */
   64,			/* l1_cache_line_size  */
   256,			/* l2_cache_size  */
+  -1,			/* minimum_stride */
   -1			/* default_opt_level  */
 };
 
@@ -10629,6 +10635,11 @@ aarch64_override_options_internal (struct gcc_options *opts)
 			   aarch64_tune_params.prefetch->l2_cache_size,
 			   opts->x_param_values,
 			   global_options_set.x_param_values);
+  if (aarch64_tune_params.prefetch->minimum_stride >= 0)
+    maybe_set_param_value (PARAM_PREFETCH_MINIMUM_STRIDE,
+			   aarch64_tune_params.prefetch->minimum_stride,
+			   opts->x_param_values,
+			   global_options_set.x_param_values);
 
   /* Use the alternative scheduling-pressure algorithm by default.  */
   maybe_set_param_value (PARAM_SCHED_PRESSURE_ALGORITHM, SCHED_PRESSURE_MODEL,
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 30d2a31..d1e50a0 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -10734,6 +10734,21 @@ The size of L1 cache, in kilobytes.
 @item l2-cache-size
 The size of L2 cache, in kilobytes.
 
+@item prefetch-minimum-stride
+Minimum constant stride, in bytes, to start using prefetch hints for.  If
+the stride is less than this threshold, prefetch hints will not be issued.
+
+This setting is useful for processors that have hardware prefetchers, in
+which case there may be conflicts between the hardware prefetchers and
+the software prefetchers.  If the hardware prefetchers have a maximum
+stride they can handle, it should be used here to improve the use of
+software prefetchers.
+
+A value of -1, the default, means we don't have a threshold and therefore
+prefetch hints can be issued for any constant stride.
+
+This setting is only useful for strides that are known and constant.
+
 @item loop-interchange-max-num-stmts
 The maximum number of stmts in a loop to be interchanged.
 
diff --git a/gcc/params.def b/gcc/params.def
index 5c4e2c9..6b208bf 100644
--- a/gcc/params.def
+++ b/gcc/params.def
@@ -795,6 +795,15 @@ DEFPARAM (PARAM_L2_CACHE_SIZE,
 	  "The size of L2 cache.",
 	  512, 0, 0)
 
+/* The minimum constant stride beyond which we should use prefetch hints
+   for.  */
+
+DEFPARAM (PARAM_PREFETCH_MINIMUM_STRIDE,
+	  "prefetch-minimum-stride",
+	  "The minimum constant stride beyond which we should use prefetch "
+	  "hints for.",
+	  -1, 0, 0)
+
 /* Maximum number of statements in loop nest for loop interchange.  */
 
 DEFPARAM (PARAM_LOOP_INTERCHANGE_MAX_NUM_STMTS,
diff --git a/gcc/params.h b/gcc/params.h
index 98249d2..96012db 100644
--- a/gcc/params.h
+++ b/gcc/params.h
@@ -196,6 +196,8 @@ extern void init_param_values (int *params);
   PARAM_VALUE (PARAM_L1_CACHE_LINE_SIZE)
 #define L2_CACHE_SIZE \
   PARAM_VALUE (PARAM_L2_CACHE_SIZE)
+#define PREFETCH_MINIMUM_STRIDE \
+  PARAM_VALUE (PARAM_PREFETCH_MINIMUM_STRIDE)
 #define USE_CANONICAL_TYPES \
   PARAM_VALUE (PARAM_USE_CANONICAL_TYPES)
 #define IRA_MAX_LOOPS_NUM \
diff --git a/gcc/tree-ssa-loop-prefetch.c b/gcc/tree-ssa-loop-prefetch.c
index 2f10db1..ac89bf7 100644
--- a/gcc/tree-ssa-loop-prefetch.c
+++ b/gcc/tree-ssa-loop-prefetch.c
@@ -992,6 +992,23 @@ prune_by_reuse (struct mem_ref_group *groups)
 static bool
 should_issue_prefetch_p (struct mem_ref *ref)
 {
+  /* Some processors may have a hardware prefetcher that may conflict with
+     prefetch hints for a range of strides.  Make sure we don't issue
+     prefetches for such cases if the stride is within this particular
+     range.  */
+  if (cst_and_fits_in_hwi (ref->group->step)
+      && abs_hwi (int_cst_value (ref->group->step))
+	  < (HOST_WIDE_INT) PREFETCH_MINIMUM_STRIDE)
+    {
+      if (dump_file && (dump_flags & TDF_DETAILS))
+	fprintf (dump_file,
+		 "Step for reference %u:%u (%ld) is less than the mininum "
+		 "required stride of %d\n",
+		 ref->group->uid, ref->uid, int_cst_value (ref->group->step),
+		 PREFETCH_MINIMUM_STRIDE);
+      return false;
+    }
+
   /* For now do not issue prefetches for only first few of the
      iterations.  */
   if (ref->prefetch_before != PREFETCH_ALL)