This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
[PATCH 1/3][AArch64] Add more choices for the reciprocal square root approximation
- From: Evandro Menezes <e dot menezes at samsung dot com>
- To: GCC Patches <gcc-patches at gcc dot gnu dot org>, James Greenhalgh <james dot greenhalgh at arm dot com>, Wilco Dijkstra <Wilco dot Dijkstra at arm dot com>, Andrew Pinski <pinskia at gmail dot com>, "philipp dot tomsich at theobroma-systems dot com" <philipp dot tomsich at theobroma-systems dot com>, Benedikt Huber <benedikt dot huber at theobroma-systems dot com>
- Date: Wed, 27 Apr 2016 16:13:33 -0500
- Subject: [PATCH 1/3][AArch64] Add more choices for the reciprocal square root approximation
- Authentication-results: sourceware.org; auth=none
gcc/
* config/aarch64/aarch64-protos.h
(AARCH64_APPROX_MODE): New macro.
(AARCH64_APPROX_{NONE,SP,DP,DFORM,QFORM,SCALAR,VECTOR,ALL}):
Likewise.
(tune_params): New member "approx_rsqrt_modes".
* config/aarch64/aarch64-tuning-flags.def
(AARCH64_EXTRA_TUNE_APPROX_RSQRT): Remove macro.
* config/aarch64/aarch64.c
(generic_tunings): New member "approx_rsqrt_modes".
(cortexa35_tunings): Likewise.
(cortexa53_tunings): Likewise.
(cortexa57_tunings): Likewise.
(cortexa72_tunings): Likewise.
(exynosm1_tunings): Likewise.
(thunderx_tunings): Likewise.
(xgene1_tunings): Likewise.
(use_rsqrt_p): New argument for the mode and use new member from
"tune_params".
(aarch64_builtin_reciprocal): Devise mode from builtin.
(aarch64_optab_supported_p): New argument for the mode.
* doc/invoke.texi (-mlow-precision-recip-sqrt): Reword description.
--
Evandro Menezes
>From 2cb6c0f35bbdc3b4cc6f88c61a50f3fbb168ec99 Mon Sep 17 00:00:00 2001
From: Evandro Menezes <e.menezes@samsung.com>
Date: Thu, 3 Mar 2016 18:13:46 -0600
Subject: [PATCH 1/3] [AArch64] Add more choices for the reciprocal square root
approximation
Allow a target to prefer such operation depending on the operation mode.
2016-03-03 Evandro Menezes <e.menezes@samsung.com>
gcc/
* config/aarch64/aarch64-protos.h
(AARCH64_APPROX_MODE): New macro.
(AARCH64_APPROX_{NONE,SP,DP,DFORM,QFORM,SCALAR,VECTOR,ALL}): Likewise.
(tune_params): New member "approx_rsqrt_modes".
* config/aarch64/aarch64-tuning-flags.def
(AARCH64_EXTRA_TUNE_APPROX_RSQRT): Remove macro.
* config/aarch64/aarch64.c
(generic_tunings): New member "approx_rsqrt_modes".
(cortexa35_tunings): Likewise.
(cortexa53_tunings): Likewise.
(cortexa57_tunings): Likewise.
(cortexa72_tunings): Likewise.
(exynosm1_tunings): Likewise.
(thunderx_tunings): Likewise.
(xgene1_tunings): Likewise.
(use_rsqrt_p): New argument for the mode and use new member from
"tune_params".
(aarch64_builtin_reciprocal): Devise mode from builtin.
(aarch64_optab_supported_p): New argument for the mode.
* doc/invoke.texi (-mlow-precision-recip-sqrt): Reword description.
---
gcc/config/aarch64/aarch64-protos.h | 27 ++++++++++++++++++++
gcc/config/aarch64/aarch64-tuning-flags.def | 2 --
gcc/config/aarch64/aarch64.c | 39 ++++++++++++++++++-----------
gcc/doc/invoke.texi | 2 +-
4 files changed, 53 insertions(+), 17 deletions(-)
diff --git a/gcc/config/aarch64/aarch64-protos.h b/gcc/config/aarch64/aarch64-protos.h
index f22a31c..50f1d24 100644
--- a/gcc/config/aarch64/aarch64-protos.h
+++ b/gcc/config/aarch64/aarch64-protos.h
@@ -178,6 +178,32 @@ struct cpu_branch_cost
const int unpredictable; /* Unpredictable branch or optimizing for speed. */
};
+/* Control approximate alternatives to certain FP operators. */
+#define AARCH64_APPROX_MODE(MODE) \
+ ((MIN_MODE_FLOAT <= (MODE) && (MODE) <= MAX_MODE_FLOAT) \
+ ? (1 << ((MODE) - MIN_MODE_FLOAT)) \
+ : (MIN_MODE_VECTOR_FLOAT <= (MODE) && (MODE) <= MAX_MODE_VECTOR_FLOAT) \
+ ? (1 << ((MODE) - MIN_MODE_VECTOR_FLOAT \
+ + MAX_MODE_FLOAT - MIN_MODE_FLOAT + 1)) \
+ : (0))
+#define AARCH64_APPROX_NONE (0)
+#define AARCH64_APPROX_SP (AARCH64_APPROX_MODE (SFmode) \
+ | AARCH64_APPROX_MODE (V2SFmode) \
+ | AARCH64_APPROX_MODE (V4SFmode))
+#define AARCH64_APPROX_DP (AARCH64_APPROX_MODE (DFmode) \
+ | AARCH64_APPROX_MODE (V2DFmode))
+#define AARCH64_APPROX_DFORM (AARCH64_APPROX_MODE (SFmode) \
+ | AARCH64_APPROX_MODE (DFmode) \
+ | AARCH64_APPROX_MODE (V2SFmode))
+#define AARCH64_APPROX_QFORM (AARCH64_APPROX_MODE (V4SFmode) \
+ | AARCH64_APPROX_MODE (V2DFmode))
+#define AARCH64_APPROX_SCALAR (AARCH64_APPROX_MODE (SFmode) \
+ | AARCH64_APPROX_MODE (DFmode))
+#define AARCH64_APPROX_VECTOR (AARCH64_APPROX_MODE (V2SFmode) \
+ | AARCH64_APPROX_MODE (V4SFmode) \
+ | AARCH64_APPROX_MODE (V2DFmode))
+#define AARCH64_APPROX_ALL (-1)
+
struct tune_params
{
const struct cpu_cost_table *insn_extra_cost;
@@ -218,6 +244,7 @@ struct tune_params
} autoprefetcher_model;
unsigned int extra_tuning_flags;
+ unsigned int approx_rsqrt_modes;
};
#define AARCH64_FUSION_PAIR(x, name) \
diff --git a/gcc/config/aarch64/aarch64-tuning-flags.def b/gcc/config/aarch64/aarch64-tuning-flags.def
index 7e45a0c..048c2a3 100644
--- a/gcc/config/aarch64/aarch64-tuning-flags.def
+++ b/gcc/config/aarch64/aarch64-tuning-flags.def
@@ -29,5 +29,3 @@
AARCH64_TUNE_ to give an enum name. */
AARCH64_EXTRA_TUNING_OPTION ("rename_fma_regs", RENAME_FMA_REGS)
-AARCH64_EXTRA_TUNING_OPTION ("approx_rsqrt", APPROX_RSQRT)
-
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 9995494..68381bf 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -38,6 +38,7 @@
#include "recog.h"
#include "diagnostic.h"
#include "insn-attr.h"
+#include "insn-modes.h"
#include "alias.h"
#include "fold-const.h"
#include "stor-layout.h"
@@ -414,7 +415,8 @@ static const struct tune_params generic_tunings =
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ (AARCH64_APPROX_NONE) /* approx_rsqrt_modes. */
};
static const struct tune_params cortexa35_tunings =
@@ -439,7 +441,8 @@ static const struct tune_params cortexa35_tunings =
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ (AARCH64_APPROX_NONE) /* approx_rsqrt_modes. */
};
static const struct tune_params cortexa53_tunings =
@@ -464,7 +467,8 @@ static const struct tune_params cortexa53_tunings =
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ (AARCH64_APPROX_NONE) /* approx_rsqrt_modes. */
};
static const struct tune_params cortexa57_tunings =
@@ -489,7 +493,8 @@ static const struct tune_params cortexa57_tunings =
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_RENAME_FMA_REGS) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_RENAME_FMA_REGS), /* tune_flags. */
+ (AARCH64_APPROX_NONE) /* approx_rsqrt_modes. */
};
static const struct tune_params cortexa72_tunings =
@@ -514,7 +519,8 @@ static const struct tune_params cortexa72_tunings =
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ (AARCH64_APPROX_NONE) /* approx_rsqrt_modes. */
};
static const struct tune_params exynosm1_tunings =
@@ -538,7 +544,8 @@ static const struct tune_params exynosm1_tunings =
48, /* max_case_values. */
64, /* cache_line_size. */
tune_params::AUTOPREFETCHER_WEAK, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_APPROX_RSQRT) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ (AARCH64_APPROX_ALL) /* approx_rsqrt_modes. */
};
static const struct tune_params thunderx_tunings =
@@ -562,7 +569,8 @@ static const struct tune_params thunderx_tunings =
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_NONE) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ (AARCH64_APPROX_NONE) /* approx_rsqrt_modes. */
};
static const struct tune_params xgene1_tunings =
@@ -586,7 +594,8 @@ static const struct tune_params xgene1_tunings =
0, /* max_case_values. */
0, /* cache_line_size. */
tune_params::AUTOPREFETCHER_OFF, /* autoprefetcher_model. */
- (AARCH64_EXTRA_TUNE_APPROX_RSQRT) /* tune_flags. */
+ (AARCH64_EXTRA_TUNE_NONE), /* tune_flags. */
+ (AARCH64_APPROX_ALL) /* approx_rsqrt_modes. */
};
/* Support for fine-grained override of the tuning structures. */
@@ -7452,12 +7461,12 @@ aarch64_memory_move_cost (machine_mode mode ATTRIBUTE_UNUSED,
to optimize 1.0/sqrt. */
static bool
-use_rsqrt_p (void)
+use_rsqrt_p (machine_mode mode)
{
return (!flag_trapping_math
&& flag_unsafe_math_optimizations
- && ((aarch64_tune_params.extra_tuning_flags
- & AARCH64_EXTRA_TUNE_APPROX_RSQRT)
+ && ((aarch64_tune_params.approx_rsqrt_modes
+ & AARCH64_APPROX_MODE (mode))
|| flag_mrecip_low_precision_sqrt));
}
@@ -7467,7 +7476,9 @@ use_rsqrt_p (void)
static tree
aarch64_builtin_reciprocal (tree fndecl)
{
- if (!use_rsqrt_p ())
+ machine_mode mode = TYPE_MODE (TREE_TYPE (fndecl));
+
+ if (!use_rsqrt_p (mode))
return NULL_TREE;
return aarch64_builtin_rsqrt (DECL_FUNCTION_CODE (fndecl));
}
@@ -13889,13 +13900,13 @@ aarch64_promoted_type (const_tree t)
/* Implement the TARGET_OPTAB_SUPPORTED_P hook. */
static bool
-aarch64_optab_supported_p (int op, machine_mode, machine_mode,
+aarch64_optab_supported_p (int op, machine_mode mode1, machine_mode,
optimization_type opt_type)
{
switch (op)
{
case rsqrt_optab:
- return opt_type == OPTIMIZE_FOR_SPEED && use_rsqrt_p ();
+ return opt_type == OPTIMIZE_FOR_SPEED && use_rsqrt_p (mode1);
default:
return true;
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index f1ac257..4340b08 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -12939,7 +12939,7 @@ corresponding flag to the linker.
When calculating the reciprocal square root approximation,
uses one less step than otherwise, thus reducing latency and precision.
This is only relevant if @option{-ffast-math} enables the reciprocal square root
-approximation, which in turn depends on the target processor.
+approximation.
@item -march=@var{name}
@opindex march
--
2.6.3