Commit bbeb5beb by Uros Bizjak

i386.md (round<mode>2): New expander.

	* config/i386/i386.md (round<mode>2): New expander.
	* config/i386/i386.c (enum ix86_builtins): Add
	IX86_BUILTIN_ROUND{PS,PD}_AZ{,256}.
	(struct builtin_description): Add __builtin_ia32_round{ps,pd}_az{,256}
	descriptions.
	(ix86_builtin_vectorized_function): Handle BUILT_IN_ROUND{,F} builtins.

testsuite/ChangeLog:

	* gcc.target/i386/sse_4_1-round-vec.c: New test.
	* gcc.target/i386/sse_4_1-roundf-vec.c: New test.
	* gcc.target/i386/avx-round-vec.c: New test.
	* gcc.target/i386/avx-roundf-vec.c: New test.

From-SVN: r178123
parent 44782c0c
......@@ -23661,10 +23661,12 @@ enum ix86_builtins
IX86_BUILTIN_CEILPD,
IX86_BUILTIN_TRUNCPD,
IX86_BUILTIN_RINTPD,
IX86_BUILTIN_ROUNDPD_AZ,
IX86_BUILTIN_FLOORPS,
IX86_BUILTIN_CEILPS,
IX86_BUILTIN_TRUNCPS,
IX86_BUILTIN_RINTPS,
IX86_BUILTIN_ROUNDPS_AZ,
IX86_BUILTIN_PTESTZ,
IX86_BUILTIN_PTESTC,
......@@ -23837,10 +23839,12 @@ enum ix86_builtins
IX86_BUILTIN_CEILPD256,
IX86_BUILTIN_TRUNCPD256,
IX86_BUILTIN_RINTPD256,
IX86_BUILTIN_ROUNDPD_AZ256,
IX86_BUILTIN_FLOORPS256,
IX86_BUILTIN_CEILPS256,
IX86_BUILTIN_TRUNCPS256,
IX86_BUILTIN_RINTPS256,
IX86_BUILTIN_ROUNDPS_AZ256,
IX86_BUILTIN_UNPCKHPD256,
IX86_BUILTIN_UNPCKLPD256,
......@@ -25063,11 +25067,15 @@ static const struct builtin_description bdesc_args[] =
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_truncpd", IX86_BUILTIN_TRUNCPD, (enum rtx_code) ROUND_TRUNC, (int) V2DF_FTYPE_V2DF_ROUND },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundpd, "__builtin_ia32_rintpd", IX86_BUILTIN_RINTPD, (enum rtx_code) ROUND_MXCSR, (int) V2DF_FTYPE_V2DF_ROUND },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_roundv2df2, "__builtin_ia32_roundpd_az", IX86_BUILTIN_ROUNDPD_AZ, UNKNOWN, (int) V2DF_FTYPE_V2DF },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundps, "__builtin_ia32_floorps", IX86_BUILTIN_FLOORPS, (enum rtx_code) ROUND_FLOOR, (int) V4SF_FTYPE_V4SF_ROUND },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundps, "__builtin_ia32_ceilps", IX86_BUILTIN_CEILPS, (enum rtx_code) ROUND_CEIL, (int) V4SF_FTYPE_V4SF_ROUND },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundps, "__builtin_ia32_truncps", IX86_BUILTIN_TRUNCPS, (enum rtx_code) ROUND_TRUNC, (int) V4SF_FTYPE_V4SF_ROUND },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_roundps, "__builtin_ia32_rintps", IX86_BUILTIN_RINTPS, (enum rtx_code) ROUND_MXCSR, (int) V4SF_FTYPE_V4SF_ROUND },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_roundv4sf2, "__builtin_ia32_roundps_az", IX86_BUILTIN_ROUNDPS_AZ, UNKNOWN, (int) V4SF_FTYPE_V4SF },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_ptest, "__builtin_ia32_ptestz128", IX86_BUILTIN_PTESTZ, EQ, (int) INT_FTYPE_V2DI_V2DI_PTEST },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_ptest, "__builtin_ia32_ptestc128", IX86_BUILTIN_PTESTC, LTU, (int) INT_FTYPE_V2DI_V2DI_PTEST },
{ OPTION_MASK_ISA_ROUND, CODE_FOR_sse4_1_ptest, "__builtin_ia32_ptestnzc128", IX86_BUILTIN_PTESTNZC, GTU, (int) INT_FTYPE_V2DI_V2DI_PTEST },
......@@ -25185,11 +25193,15 @@ static const struct builtin_description bdesc_args[] =
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_roundpd256, "__builtin_ia32_truncpd256", IX86_BUILTIN_TRUNCPD256, (enum rtx_code) ROUND_TRUNC, (int) V4DF_FTYPE_V4DF_ROUND },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_roundpd256, "__builtin_ia32_rintpd256", IX86_BUILTIN_RINTPD256, (enum rtx_code) ROUND_MXCSR, (int) V4DF_FTYPE_V4DF_ROUND },
{ OPTION_MASK_ISA_AVX, CODE_FOR_roundv4df2, "__builtin_ia32_roundpd_az256", IX86_BUILTIN_ROUNDPD_AZ256, UNKNOWN, (int) V4DF_FTYPE_V4DF },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_roundps256, "__builtin_ia32_floorps256", IX86_BUILTIN_FLOORPS256, (enum rtx_code) ROUND_FLOOR, (int) V8SF_FTYPE_V8SF_ROUND },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_roundps256, "__builtin_ia32_ceilps256", IX86_BUILTIN_CEILPS256, (enum rtx_code) ROUND_CEIL, (int) V8SF_FTYPE_V8SF_ROUND },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_roundps256, "__builtin_ia32_truncps256", IX86_BUILTIN_TRUNCPS256, (enum rtx_code) ROUND_TRUNC, (int) V8SF_FTYPE_V8SF_ROUND },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_roundps256, "__builtin_ia32_rintps256", IX86_BUILTIN_RINTPS256, (enum rtx_code) ROUND_MXCSR, (int) V8SF_FTYPE_V8SF_ROUND },
{ OPTION_MASK_ISA_AVX, CODE_FOR_roundv8sf2, "__builtin_ia32_roundps_az256", IX86_BUILTIN_ROUNDPS_AZ256, UNKNOWN, (int) V8SF_FTYPE_V8SF },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_unpckhpd256, "__builtin_ia32_unpckhpd256", IX86_BUILTIN_UNPCKHPD256, UNKNOWN, (int) V4DF_FTYPE_V4DF_V4DF },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_unpcklpd256, "__builtin_ia32_unpcklpd256", IX86_BUILTIN_UNPCKLPD256, UNKNOWN, (int) V4DF_FTYPE_V4DF_V4DF },
{ OPTION_MASK_ISA_AVX, CODE_FOR_avx_unpckhps256, "__builtin_ia32_unpckhps256", IX86_BUILTIN_UNPCKHPS256, UNKNOWN, (int) V8SF_FTYPE_V8SF_V8SF },
......@@ -28146,6 +28158,34 @@ ix86_builtin_vectorized_function (tree fndecl, tree type_out,
}
break;
case BUILT_IN_ROUND:
/* The round insn does not trap on denormals. */
if (flag_trapping_math || !TARGET_ROUND)
break;
if (out_mode == DFmode && in_mode == DFmode)
{
if (out_n == 2 && in_n == 2)
return ix86_builtins[IX86_BUILTIN_ROUNDPD_AZ];
else if (out_n == 4 && in_n == 4)
return ix86_builtins[IX86_BUILTIN_ROUNDPD_AZ256];
}
break;
case BUILT_IN_ROUNDF:
/* The round insn does not trap on denormals. */
if (flag_trapping_math || !TARGET_ROUND)
break;
if (out_mode == SFmode && in_mode == SFmode)
{
if (out_n == 4 && in_n == 4)
return ix86_builtins[IX86_BUILTIN_ROUNDPS_AZ];
else if (out_n == 8 && in_n == 8)
return ix86_builtins[IX86_BUILTIN_ROUNDPS_AZ256];
}
break;
case BUILT_IN_FMA:
if (out_mode == DFmode && in_mode == DFmode)
{
......@@ -9646,6 +9646,40 @@
(set_attr "prefix" "orig,vex")
(set_attr "mode" "<MODE>")])
(define_expand "round<mode>2"
[(set (match_dup 4)
(plus:VF
(match_operand:VF 1 "nonimmediate_operand" "")
(match_dup 3)))
(set (match_operand:VF 0 "register_operand" "")
(unspec:VF
[(match_dup 4) (match_dup 5)]
UNSPEC_ROUND))]
"TARGET_ROUND && !flag_trapping_math"
{
enum machine_mode scalar_mode;
const struct real_format *fmt;
REAL_VALUE_TYPE pred_half, half_minus_pred_half;
rtx half, vec_half;
scalar_mode = GET_MODE_INNER (<MODE>mode);
/* load nextafter (0.5, 0.0) */
fmt = REAL_MODE_FORMAT (scalar_mode);
real_2expN (&half_minus_pred_half, -(fmt->p) - 1, scalar_mode);
REAL_ARITHMETIC (pred_half, MINUS_EXPR, dconsthalf, half_minus_pred_half);
half = const_double_from_real_value (pred_half, scalar_mode);
vec_half = ix86_build_const_vector (<MODE>mode, true, half);
vec_half = force_reg (<MODE>mode, vec_half);
operands[3] = gen_reg_rtx (<MODE>mode);
emit_insn (gen_copysign<mode>3 (operands[3], vec_half, operands[1]));
operands[4] = gen_reg_rtx (<MODE>mode);
operands[5] = GEN_INT (ROUND_TRUNC);
})
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
;; Intel SSE4.2 string/text processing instructions
......
2011-08-26 Uros Bizjak <ubizjak@gmail.com>
* gcc.target/i386/sse_4_1-round-vec.c: New test.
* gcc.target/i386/sse_4_1-roundf-vec.c: New test.
* gcc.target/i386/avx-round-vec.c: New test.
* gcc.target/i386/avx-roundf-vec.c: New test.
2011-08-26 Jakub Jelinek <jakub@redhat.com>
* gcc.target/i386/cmpxchg16b-1.c: Match also space after the
......@@ -12,10 +19,10 @@
2011-08-26 Jiangning Liu <jiangning.liu@arm.com>
* gcc.target/arm/thumb2-cond-cmp-1.c: New.
* gcc.target/arm/thumb2-cond-cmp-2.c: Likewise.
* gcc.target/arm/thumb2-cond-cmp-3.c: Likewise.
* gcc.target/arm/thumb2-cond-cmp-4.c: Likewise.
* gcc.target/arm/thumb2-cond-cmp-1.c: New.
* gcc.target/arm/thumb2-cond-cmp-2.c: Likewise.
* gcc.target/arm/thumb2-cond-cmp-3.c: Likewise.
* gcc.target/arm/thumb2-cond-cmp-4.c: Likewise.
2011-08-26 Andrew Stubbs <ams@codesourcery.com>
......
/* { dg-do run } */
/* { dg-options "-O2 -ffast-math -ftree-vectorize -mavx" } */
/* { dg-require-effective-target avx } */
/* { dg-skip-if "no M_PI" { vxworks_kernel } } */
#include "avx-check.h"
#include <math.h>
extern double floor (double);
#define NUM 64
static void
__attribute__((__target__("fpmath=sse")))
init_src (double *src)
{
int i, sign = 1;
double f = rand ();
for (i = 0; i < NUM; i++)
{
src[i] = (i + 1) * f * M_PI * sign;
if (i < (NUM / 2))
{
if ((i % 6) == 0)
f = f * src[i];
}
else if (i == (NUM / 2))
f = rand ();
else if ((i % 6) == 0)
f = 1 / (f * (i + 1) * src[i] * M_PI * sign);
sign = -sign;
}
}
static void
__attribute__((__target__("fpmath=387")))
avx_test (void)
{
double a[NUM];
double r[NUM];
int i;
init_src (a);
for (i = 0; i < NUM; i++)
r[i] = round (a[i]);
/* check results: */
for (i = 0; i < NUM; i++)
if (r[i] != round (a[i]))
abort();
}
/* { dg-do run } */
/* { dg-options "-O2 -ffast-math -ftree-vectorize -mavx" } */
/* { dg-require-effective-target avx } */
/* { dg-skip-if "no M_PI" { vxworks_kernel } } */
#include "avx-check.h"
#include <math.h>
extern float roundf (float);
#define NUM 64
static void
__attribute__((__target__("fpmath=sse")))
init_src (float *src)
{
int i, sign = 1;
float f = rand ();
for (i = 0; i < NUM; i++)
{
src[i] = (i + 1) * f * M_PI * sign;
if (i < (NUM / 2))
{
if ((i % 6) == 0)
f = f * src[i];
}
else if (i == (NUM / 2))
f = rand ();
else if ((i % 6) == 0)
f = 1 / (f * (i + 1) * src[i] * M_PI * sign);
sign = -sign;
}
}
static void
__attribute__((__target__("fpmath=387")))
avx_test (void)
{
float a[NUM];
float r[NUM];
int i;
init_src (a);
for (i = 0; i < NUM; i++)
r[i] = roundf (a[i]);
/* check results: */
for (i = 0; i < NUM; i++)
if (r[i] != roundf (a[i]))
abort();
}
/* { dg-do run } */
/* { dg-options "-O2 -ffast-math -ftree-vectorize -msse4.1" } */
/* { dg-require-effective-target sse4 } */
/* { dg-skip-if "no M_PI" { vxworks_kernel } } */
#include "sse4_1-check.h"
#include <math.h>
extern double round (double);
#define NUM 64
static void
__attribute__((__target__("fpmath=sse")))
init_src (double *src)
{
int i, sign = 1;
double f = rand ();
for (i = 0; i < NUM; i++)
{
src[i] = (i + 1) * f * M_PI * sign;
if (i < (NUM / 2))
{
if ((i % 6) == 0)
f = f * src[i];
}
else if (i == (NUM / 2))
f = rand ();
else if ((i % 6) == 0)
f = 1 / (f * (i + 1) * src[i] * M_PI * sign);
sign = -sign;
}
}
static void
__attribute__((__target__("fpmath=387")))
sse4_1_test (void)
{
double a[NUM];
double r[NUM];
int i;
init_src (a);
for (i = 0; i < NUM; i++)
r[i] = round (a[i]);
/* check results: */
for (i = 0; i < NUM; i++)
if (r[i] != round (a[i]))
abort();
}
/* { dg-do run } */
/* { dg-options "-O2 -ffast-math -ftree-vectorize -msse4.1" } */
/* { dg-require-effective-target sse4 } */
/* { dg-skip-if "no M_PI" { vxworks_kernel } } */
#include "sse4_1-check.h"
#include <math.h>
extern float roundf (float);
#define NUM 64
static void
__attribute__((__target__("fpmath=sse")))
init_src (float *src)
{
int i, sign = 1;
float f = rand ();
for (i = 0; i < NUM; i++)
{
src[i] = (i + 1) * f * M_PI * sign;
if (i < (NUM / 2))
{
if ((i % 6) == 0)
f = f * src[i];
}
else if (i == (NUM / 2))
f = rand ();
else if ((i % 6) == 0)
f = 1 / (f * (i + 1) * src[i] * M_PI * sign);
sign = -sign;
}
}
static void
__attribute__((__target__("fpmath=387")))
sse4_1_test (void)
{
float a[NUM];
float r[NUM];
int i;
init_src (a);
for (i = 0; i < NUM; i++)
r[i] = roundf (a[i]);
/* check results: */
for (i = 0; i < NUM; i++)
if (r[i] != roundf (a[i]))
abort();
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment