From 8e463d55c89233a623aad2412fb3055021fdd066 Mon Sep 17 00:00:00 2001
From: Evandro Menezes <e.menezes@samsung.com>
Date: Mon, 4 Apr 2016 11:23:29 -0500
Subject: [PATCH] [AArch64] Emit square root using the Newton series
2016-04-04 Evandro Menezes <e.menezes@samsung.com>
Wilco Dijkstra <wilco.dijkstra@arm.com>
gcc/
* config/aarch64/aarch64-protos.h
(aarch64_emit_approx_rsqrt): Replace with new function
"aarch64_emit_approx_sqrt".
(AARCH64_APPROX_MODE): New macro.
(AARCH64_APPROX_{NONE,SP,DP,DFORM,QFORM,SCALAR,VECTOR,ALL}: Likewise.
(tune_params): New member "approx_sqrt_modes".
* 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.
(aarch64_emit_approx_rsqrt): Replace with new function
"aarch64_emit_approx_sqrt".
(aarch64_override_options_after_change_1): Handle new option.
* config/aarch64/aarch64-simd.md
(rsqrt<mode>2): Use new function instead.
(sqrt<mode>2): New expansion and insn definitions.
* config/aarch64/aarch64.md: Likewise.
* config/aarch64/aarch64.opt
(mlow-precision-sqrt): Add new option description.
* doc/invoke.texi (mlow-precision-sqrt): Likewise.
---
gcc/config/aarch64/aarch64-protos.h | 29 ++++++++-
gcc/config/aarch64/aarch64-simd.md | 13 +++-
gcc/config/aarch64/aarch64.c | 115 +++++++++++++++++++++++++-----------
gcc/config/aarch64/aarch64.md | 11 +++-
gcc/config/aarch64/aarch64.opt | 9 ++-
gcc/doc/invoke.texi | 10 ++++
6 files changed, 147 insertions(+), 40 deletions(-)
@@ -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_sqrt_modes;
};
#define AARCH64_FUSION_PAIR(x, name) \
@@ -361,7 +388,7 @@ void aarch64_register_pragmas (void);
void aarch64_relayout_simd_types (void);
void aarch64_reset_previous_fndecl (void);
void aarch64_save_restore_target_globals (tree);
-void aarch64_emit_approx_rsqrt (rtx, rtx);
+bool aarch64_emit_approx_sqrt (rtx, rtx, bool);
/* Initialize builtins for SIMD intrinsics. */
void init_aarch64_simd_builtins (void);
@@ -405,7 +405,7 @@
UNSPEC_RSQRT))]
"TARGET_SIMD"
{
- aarch64_emit_approx_rsqrt (operands[0], operands[1]);
+ aarch64_emit_approx_sqrt (operands[0], operands[1], true);
DONE;
})
@@ -4307,7 +4307,16 @@
;; sqrt
-(define_insn "sqrt<mode>2"
+(define_expand "sqrt<mode>2"
+ [(set (match_operand:VDQF 0 "register_operand")
+ (sqrt:VDQF (match_operand:VDQF 1 "register_operand")))]
+ "TARGET_SIMD"
+{
+ if (aarch64_emit_approx_sqrt (operands[0], operands[1], false))
+ DONE;
+})
+
+(define_insn "*sqrt<mode>2"
[(set (match_operand:VDQF 0 "register_operand" "=w")
(sqrt:VDQF (match_operand:VDQF 1 "register_operand" "w")))]
"TARGET_SIMD"
@@ -38,6 +38,7 @@
#include "recog.h"
#include "diagnostic.h"
#include "insn-attr.h"
+#include "insn-flags.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_sqrt_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_sqrt_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_sqrt_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_sqrt_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_sqrt_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_APPROX_RSQRT), /* tune_flags. */
+ (AARCH64_APPROX_ALL) /* approx_sqrt_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_sqrt_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_APPROX_RSQRT), /* tune_flags. */
+ (AARCH64_APPROX_NONE) /* approx_sqrt_modes. */
};
/* Support for fine-grained override of the tuning structures. */
@@ -7510,46 +7519,78 @@ get_rsqrts_type (machine_mode mode)
}
}
-/* Emit instruction sequence to compute the reciprocal square root using the
- Newton-Raphson series. Iterate over the series twice for SF
- and thrice for DF. */
+/* Emit instruction sequence to compute either the approximate square root
+ or its approximate reciprocal. */
-void
-aarch64_emit_approx_rsqrt (rtx dst, rtx src)
+bool
+aarch64_emit_approx_sqrt (rtx dst, rtx src, bool recp)
{
- machine_mode mode = GET_MODE (src);
- gcc_assert (
- mode == SFmode || mode == V2SFmode || mode == V4SFmode
- || mode == DFmode || mode == V2DFmode);
-
- rtx xsrc = gen_reg_rtx (mode);
- emit_move_insn (xsrc, src);
- rtx x0 = gen_reg_rtx (mode);
+ machine_mode mode = GET_MODE (dst);
+ machine_mode mmsk = mode_for_vector (int_mode_for_mode (GET_MODE_INNER (mode)),
+ GET_MODE_NUNITS (mode));
+
+ if (!flag_finite_math_only
+ || flag_trapping_math
+ || !flag_unsafe_math_optimizations
+ || optimize_function_for_size_p (cfun)
+ || !((recp && (flag_mrecip_low_precision_sqrt
+ || (aarch64_tune_params.extra_tuning_flags
+ & AARCH64_EXTRA_TUNE_APPROX_RSQRT)))
+ || (!recp && (flag_mlow_precision_sqrt
+ || (aarch64_tune_params.approx_sqrt_modes
+ & AARCH64_APPROX_MODE (mode))))))
+ return false;
- emit_insn ((*get_rsqrte_type (mode)) (x0, xsrc));
+ rtx xmsk = gen_reg_rtx (mmsk);
+ if (!recp)
+ /* When calculating the approximate square root, compare the argument with
+ 0.0 and create a mask. */
+ emit_insn (gen_rtx_SET (xmsk, gen_rtx_NEG (mmsk, gen_rtx_EQ (mmsk, src,
+ CONST0_RTX (mode)))));
- bool double_mode = (mode == DFmode || mode == V2DFmode);
+ /* Estimate the approximate reciprocal square root. */
+ rtx xdst = gen_reg_rtx (mode);
+ emit_insn ((*get_rsqrte_type (mode)) (xdst, src));
- int iterations = double_mode ? 3 : 2;
+ /* Iterate over the series twice for SF and thrice for DF. */
+ int iterations = (GET_MODE_INNER (mode) == DFmode) ? 3 : 2;
- /* Optionally iterate over the series one less time than otherwise. */
- if (flag_mrecip_low_precision_sqrt)
+ /* Optionally iterate over the series once less for faster performance
+ while sacrificing the accuracy. */
+ if ((recp && flag_mrecip_low_precision_sqrt)
+ || (!recp && flag_mlow_precision_sqrt))
iterations--;
- for (int i = 0; i < iterations; ++i)
+ /* Iterate over the series to calculate the approximate reciprocal square root. */
+ rtx x1 = gen_reg_rtx (mode);
+ while (iterations--)
{
- rtx x1 = gen_reg_rtx (mode);
rtx x2 = gen_reg_rtx (mode);
- rtx x3 = gen_reg_rtx (mode);
- emit_set_insn (x2, gen_rtx_MULT (mode, x0, x0));
+ emit_set_insn (x2, gen_rtx_MULT (mode, xdst, xdst));
+
+ emit_insn ((*get_rsqrts_type (mode)) (x1, src, x2));
- emit_insn ((*get_rsqrts_type (mode)) (x3, xsrc, x2));
+ if (iterations > 0)
+ emit_set_insn (xdst, gen_rtx_MULT (mode, xdst, x1));
+ }
+
+ if (!recp)
+ {
+ /* Qualify the approximate reciprocal square root when the argument is
+ 0.0 by squashing the intermediary result to 0.0. */
+ rtx xtmp = gen_reg_rtx (mmsk);
+ emit_set_insn (xtmp, gen_rtx_AND (mmsk, gen_rtx_NOT (mmsk, xmsk),
+ gen_rtx_SUBREG (mmsk, xdst, 0)));
+ emit_move_insn (xdst, gen_rtx_SUBREG (mode, xtmp, 0));
- emit_set_insn (x1, gen_rtx_MULT (mode, x0, x3));
- x0 = x1;
+ /* Calculate the approximate square root. */
+ emit_set_insn (xdst, gen_rtx_MULT (mode, xdst, src));
}
- emit_move_insn (dst, x0);
+ /* Return the approximation. */
+ emit_set_insn (dst, gen_rtx_MULT (mode, xdst, x1));
+
+ return true;
}
/* Return the number of instructions that can be issued per cycle. */
@@ -8156,6 +8197,12 @@ aarch64_override_options_after_change_1 (struct gcc_options *opts)
&& (aarch64_cmodel == AARCH64_CMODEL_TINY
|| aarch64_cmodel == AARCH64_CMODEL_TINY_PIC))
aarch64_nopcrelative_literal_loads = false;
+
+ /* When enabling the lower precision Newton series for the square root, also
+ enable it for the reciprocal square root, since the later is an
+ intermediary step for the latter. */
+ if (flag_mlow_precision_sqrt)
+ flag_mrecip_low_precision_sqrt = true;
}
/* 'Unpack' up the internal tuning structs and update the options
@@ -4665,7 +4665,16 @@
[(set_attr "type" "ffarith<s>")]
)
-(define_insn "sqrt<mode>2"
+(define_expand "sqrt<mode>2"
+ [(set (match_operand:GPF 0 "register_operand")
+ (sqrt:GPF (match_operand:GPF 1 "register_operand")))]
+ "TARGET_SIMD"
+{
+ if (aarch64_emit_approx_sqrt (operands[0], operands[1], false))
+ DONE;
+})
+
+(define_insn "*sqrt<mode>2"
[(set (match_operand:GPF 0 "register_operand" "=w")
(sqrt:GPF (match_operand:GPF 1 "register_operand" "w")))]
"TARGET_FLOAT"
@@ -151,5 +151,10 @@ PC relative literal loads.
mlow-precision-recip-sqrt
Common Var(flag_mrecip_low_precision_sqrt) Optimization
-When calculating the reciprocal square root approximation,
-uses one less step than otherwise, thus reducing latency and precision.
+When calculating the approximate reciprocal square root,
+use one less step than otherwise, thus reducing latency and precision.
+
+mlow-precision-sqrt
+Common Var(flag_mlow_precision_sqrt) Optimization
+When calculating the approximate square root,
+use one less step than otherwise, thus reducing latency and precision.
@@ -573,6 +573,7 @@ Objective-C and Objective-C++ Dialects}.
-mfix-cortex-a53-835769 -mno-fix-cortex-a53-835769 @gol
-mfix-cortex-a53-843419 -mno-fix-cortex-a53-843419 @gol
-mlow-precision-recip-sqrt -mno-low-precision-recip-sqrt@gol
+-mlow-precision-sqrt -mno-low-precision-sqrt@gol
-march=@var{name} -mcpu=@var{name} -mtune=@var{name}}
@emph{Adapteva Epiphany Options}
@@ -12921,6 +12922,15 @@ 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.
+@item -mlow-precision-sqrt
+@item -mno-low-precision-sqrt
+@opindex -mlow-precision-sqrt
+@opindex -mno-low-precision-sqrt
+When calculating the square root approximation,
+uses one less step than otherwise, thus reducing latency and precision.
+This is only relevant if @option{-ffast-math} enables the square root
+approximation, which in turn depends on the target processor.
+
@item -march=@var{name}
@opindex march
Specify the name of the target architecture and, optionally, one or
--
1.9.1