Skip to content

R
riscv-gcc-1
Commit 77a205be by James Greenhalgh Committed by James Greenhalgh
Options

[AArch64] Convert NEON frint implementations to use builtins. 

gcc/
	* config/aarch64/arm_neon.h (vrndq<a,m,n,p>_f<32, 64>): Rename to...
	(vrnd<a,m,n,p>q_f<32, 64>): ...This, implement using builtin.
	(vrnd<a,m,n,p>_f32): Implement using builtins.
	(vrnd<i,x><q>_f<32, 64>): New.

gcc/testsuite/
	* gcc.target/aarch64/vect-vrnd.c: New.

From-SVN: r198396
parent 0659ce6f
Showing with 267 additions and 165 deletions
gcc/ChangeLog
2013-04-29 James Greenhalgh <james.greenhalgh@arm.com>
* config/aarch64/arm_neon.h (vrndq<a,m,n,p>_f<32, 64>): Rename to...
(vrnd<a,m,n,p>q_f<32, 64>): ...This, implement using builtin.
(vrnd<a,m,n,p>_f32): Implement using builtins.
(vrnd<i,x><q>_f<32, 64>): New.
2013-04-29 James Greenhalgh <james.greenhalgh@arm.com>
* config/aarch64/aarch64-builtins.c
(aarch64_builtin_vectorized_function): Fold to standard pattern names.
* config/aarch64/aarch64-simd-builtins.def (frintn): New.
......
gcc/config/aarch64/arm_neon.h
......@@ -14941,171 +14941,6 @@ vrev64q_u32 (uint32x4_t a)
return result;
}
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrnd_f32 (float32x2_t a)
{
float32x2_t result;
__asm__ ("frintz %0.2s,%1.2s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrnda_f32 (float32x2_t a)
{
float32x2_t result;
__asm__ ("frinta %0.2s,%1.2s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndm_f32 (float32x2_t a)
{
float32x2_t result;
__asm__ ("frintm %0.2s,%1.2s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndn_f32 (float32x2_t a)
{
float32x2_t result;
__asm__ ("frintn %0.2s,%1.2s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndp_f32 (float32x2_t a)
{
float32x2_t result;
__asm__ ("frintp %0.2s,%1.2s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndq_f32 (float32x4_t a)
{
float32x4_t result;
__asm__ ("frintz %0.4s,%1.4s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndq_f64 (float64x2_t a)
{
float64x2_t result;
__asm__ ("frintz %0.2d,%1.2d"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndqa_f32 (float32x4_t a)
{
float32x4_t result;
__asm__ ("frinta %0.4s,%1.4s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndqa_f64 (float64x2_t a)
{
float64x2_t result;
__asm__ ("frinta %0.2d,%1.2d"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndqm_f32 (float32x4_t a)
{
float32x4_t result;
__asm__ ("frintm %0.4s,%1.4s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndqm_f64 (float64x2_t a)
{
float64x2_t result;
__asm__ ("frintm %0.2d,%1.2d"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndqn_f32 (float32x4_t a)
{
float32x4_t result;
__asm__ ("frintn %0.4s,%1.4s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndqn_f64 (float64x2_t a)
{
float64x2_t result;
__asm__ ("frintn %0.2d,%1.2d"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndqp_f32 (float32x4_t a)
{
float32x4_t result;
__asm__ ("frintp %0.4s,%1.4s"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndqp_f64 (float64x2_t a)
{
float64x2_t result;
__asm__ ("frintp %0.2d,%1.2d"
: "=w"(result)
: "w"(a)
: /* No clobbers */);
return result;
}
#define vrshrn_high_n_s16(a, b, c) \
__extension__ \
({ \
......@@ -23069,6 +22904,145 @@ vrecpxd_f64 (float64_t __a)
return __builtin_aarch64_frecpxdf (__a);
}
/* vrnd */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrnd_f32 (float32x2_t __a)
{
return __builtin_aarch64_btruncv2sf (__a);
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndq_f32 (float32x4_t __a)
{
return __builtin_aarch64_btruncv4sf (__a);
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndq_f64 (float64x2_t __a)
{
return __builtin_aarch64_btruncv2df (__a);
}
/* vrnda */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrnda_f32 (float32x2_t __a)
{
return __builtin_aarch64_roundv2sf (__a);
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndaq_f32 (float32x4_t __a)
{
return __builtin_aarch64_roundv4sf (__a);
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndaq_f64 (float64x2_t __a)
{
return __builtin_aarch64_roundv2df (__a);
}
/* vrndi */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndi_f32 (float32x2_t __a)
{
return __builtin_aarch64_nearbyintv2sf (__a);
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndiq_f32 (float32x4_t __a)
{
return __builtin_aarch64_nearbyintv4sf (__a);
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndiq_f64 (float64x2_t __a)
{
return __builtin_aarch64_nearbyintv2df (__a);
}
/* vrndm */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndm_f32 (float32x2_t __a)
{
return __builtin_aarch64_floorv2sf (__a);
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndmq_f32 (float32x4_t __a)
{
return __builtin_aarch64_floorv4sf (__a);
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndmq_f64 (float64x2_t __a)
{
return __builtin_aarch64_floorv2df (__a);
}
/* vrndn */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndn_f32 (float32x2_t __a)
{
return __builtin_aarch64_frintnv2sf (__a);
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndnq_f32 (float32x4_t __a)
{
return __builtin_aarch64_frintnv4sf (__a);
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndnq_f64 (float64x2_t __a)
{
return __builtin_aarch64_frintnv2df (__a);
}
/* vrndp */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndp_f32 (float32x2_t __a)
{
return __builtin_aarch64_ceilv2sf (__a);
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndpq_f32 (float32x4_t __a)
{
return __builtin_aarch64_ceilv4sf (__a);
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndpq_f64 (float64x2_t __a)
{
return __builtin_aarch64_ceilv2df (__a);
}
/* vrndx */
__extension__ static __inline float32x2_t __attribute__ ((__always_inline__))
vrndx_f32 (float32x2_t __a)
{
return __builtin_aarch64_rintv2sf (__a);
}
__extension__ static __inline float32x4_t __attribute__ ((__always_inline__))
vrndxq_f32 (float32x4_t __a)
{
return __builtin_aarch64_rintv4sf (__a);
}
__extension__ static __inline float64x2_t __attribute__ ((__always_inline__))
vrndxq_f64 (float64x2_t __a)
{
return __builtin_aarch64_rintv2df (__a);
}
/* vrshl */
__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
......
gcc/testsuite/ChangeLog
2013-04-29 James Greenhalgh <james.greenhalgh@arm.com>
* gcc.target/aarch64/vect-vrnd.c: New.
2013-04-29 Richard Biener <rguenther@suse.de>
PR tree-optimization/57081
......
gcc/testsuite/gcc.target/aarch64/vect-vrnd.c 0 → 100644
/* { dg-do run } */
/* { dg-options "-O3 --save-temps" } */
#include <arm_neon.h>
extern void abort (void);
extern float fabsf (float);
extern double fabs (double);
extern double trunc (double);
extern double round (double);
extern double nearbyint (double);
extern double floor (double);
extern double ceil (double);
extern double rint (double);
extern float truncf (float);
extern float roundf (float);
extern float nearbyintf (float);
extern float floorf (float);
extern float ceilf (float);
extern float rintf (float);
#define NUM_TESTS 8
#define DELTA 0.000001
float input_f32[] = {0.1f, -0.1f, 0.4f, 10.3f,
200.0f, -800.0f, -13.0f, -0.5f};
double input_f64[] = {0.1, -0.1, 0.4, 10.3,
200.0, -800.0, -13.0, -0.5};
#define TEST(SUFFIX, Q, WIDTH, LANES, C_FN, F) \
int \
test_vrnd##SUFFIX##_float##WIDTH##x##LANES##_t (void) \
{ \
int ret = 1; \
int i = 0; \
int nlanes = LANES; \
float##WIDTH##_t expected_out[NUM_TESTS]; \
float##WIDTH##_t actual_out[NUM_TESTS]; \
\
for (i = 0; i < NUM_TESTS; i++) \
{ \
expected_out[i] = C_FN##F (input_f##WIDTH[i]); \
/* Don't vectorize this. */ \
asm volatile ("" : : : "memory"); \
} \
\
/* Prevent the compiler from noticing these two loops do the same \
thing and optimizing away the comparison. */ \
asm volatile ("" : : : "memory"); \
\
for (i = 0; i < NUM_TESTS; i+=nlanes) \
{ \
float##WIDTH##x##LANES##_t out = \
vrnd##SUFFIX##Q##_f##WIDTH \
(vld1##Q##_f##WIDTH (input_f##WIDTH + i)); \
vst1##Q##_f##WIDTH (actual_out + i, out); \
} \
\
for (i = 0; i < NUM_TESTS; i++) \
ret &= fabs##F (expected_out[i] - actual_out[i]) < DELTA; \
\
return ret; \
} \
#define BUILD_VARIANTS(SUFFIX, C_FN) \
TEST (SUFFIX, , 32, 2, C_FN, f) \
TEST (SUFFIX, q, 32, 4, C_FN, f) \
TEST (SUFFIX, q, 64, 2, C_FN, ) \
BUILD_VARIANTS ( , trunc)
/* { dg-final { scan-assembler "frintz\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s" } } */
/* { dg-final { scan-assembler "frintz\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s" } } */
/* { dg-final { scan-assembler "frintz\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d" } } */
BUILD_VARIANTS (a, round)
/* { dg-final { scan-assembler "frinta\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s" } } */
/* { dg-final { scan-assembler "frinta\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s" } } */
/* { dg-final { scan-assembler "frinta\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d" } } */
BUILD_VARIANTS (i, nearbyint)
/* { dg-final { scan-assembler "frinti\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s" } } */
/* { dg-final { scan-assembler "frinti\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s" } } */
/* { dg-final { scan-assembler "frinti\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d" } } */
BUILD_VARIANTS (m, floor)
/* { dg-final { scan-assembler "frintm\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s" } } */
/* { dg-final { scan-assembler "frintm\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s" } } */
/* { dg-final { scan-assembler "frintm\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d" } } */
BUILD_VARIANTS (p, ceil)
/* { dg-final { scan-assembler "frintp\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s" } } */
/* { dg-final { scan-assembler "frintp\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s" } } */
/* { dg-final { scan-assembler "frintp\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d" } } */
BUILD_VARIANTS (x, rint)
/* { dg-final { scan-assembler "frintx\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s" } } */
/* { dg-final { scan-assembler "frintx\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s" } } */
/* { dg-final { scan-assembler "frintx\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d" } } */
#undef TEST
#define TEST(SUFFIX, Q, WIDTH, LANES, C_FN, F) \
{ \
if (!test_vrnd##SUFFIX##_float##WIDTH##x##LANES##_t ()) \
abort (); \
}
int
main (int argc, char **argv)
{
BUILD_VARIANTS ( , trunc)
BUILD_VARIANTS (a, round)
BUILD_VARIANTS (i, nearbyint)
BUILD_VARIANTS (m, floor)
BUILD_VARIANTS (p, ceil)
BUILD_VARIANTS (x, rint)
return 0;
}
/* { dg-final { cleanup-saved-temps } } */
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