Skip to content

R
riscv-gcc-1
Commit 9d04c986 by Tamar Christina Committed by Tamar Christina
Options

AArch64: Update Armv8.4-a's FP16 FML intrinsics 

This patch updates the Armv8.4-a FP16 FML intrinsics's suffixes from u32 to f16
to be more consistent with the naming convention for intrinsics.

The specifications for these intrinsics have not been published yet so we do
not need to maintain the old names.

The patch was created with the following script:

grep -lIE "(vfml[as].+)_u32" -r gcc/ | grep -iEv ".+Changelog.*" \
  | xargs sed -i -E -e "s/(vfml[as].+)_u32/\1_f16/g"

gcc/ChangeLog:

	* config/aarch64/arm_neon.h (vfmlal_low_u32, vfmlsl_low_u32,
	vfmlalq_low_u32, vfmlslq_low_u32, vfmlal_high_u32, vfmlsl_high_u32,
	vfmlalq_high_u32, vfmlslq_high_u32, vfmlal_lane_low_u32,
	vfmlsl_lane_low_u32, vfmlal_laneq_low_u32, vfmlsl_laneq_low_u32,
	vfmlalq_lane_low_u32, vfmlslq_lane_low_u32, vfmlalq_laneq_low_u32,
	vfmlslq_laneq_low_u32, vfmlal_lane_high_u32, vfmlsl_lane_high_u32,
	vfmlal_laneq_high_u32, vfmlsl_laneq_high_u32, vfmlalq_lane_high_u32,
	vfmlslq_lane_high_u32, vfmlalq_laneq_high_u32, vfmlslq_laneq_high_u32):
	Rename ...
	(vfmlal_low_f16, vfmlsl_low_f16, vfmlalq_low_f16, vfmlslq_low_f16,
	vfmlal_high_f16, vfmlsl_high_f16, vfmlalq_high_f16, vfmlslq_high_f16,
	vfmlal_lane_low_f16, vfmlsl_lane_low_f16, vfmlal_laneq_low_f16,
	vfmlsl_laneq_low_f16, vfmlalq_lane_low_f16, vfmlslq_lane_low_f16,
	vfmlalq_laneq_low_f16, vfmlslq_laneq_low_f16, vfmlal_lane_high_f16,
	vfmlsl_lane_high_f16, vfmlal_laneq_high_f16, vfmlsl_laneq_high_f16,
	vfmlalq_lane_high_f16, vfmlslq_lane_high_f16, vfmlalq_laneq_high_f16,
	vfmlslq_laneq_high_f16): ... To this.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/fp16_fmul_high.h (test_vfmlal_high_u32,
	test_vfmlalq_high_u32, test_vfmlsl_high_u32, test_vfmlslq_high_u32):
	Rename ...
	(test_vfmlal_high_f16, test_vfmlalq_high_f16, test_vfmlsl_high_f16,
	test_vfmlslq_high_f16): ... To this.
	* gcc.target/aarch64/fp16_fmul_lane_high.h (test_vfmlal_lane_high_u32,
	tets_vfmlsl_lane_high_u32, test_vfmlal_laneq_high_u32,
	test_vfmlsl_laneq_high_u32, test_vfmlalq_lane_high_u32,
	test_vfmlslq_lane_high_u32, test_vfmlalq_laneq_high_u32,
	test_vfmlslq_laneq_high_u32): Rename ...
	(test_vfmlal_lane_high_f16, tets_vfmlsl_lane_high_f16,
	test_vfmlal_laneq_high_f16, test_vfmlsl_laneq_high_f16,
	test_vfmlalq_lane_high_f16, test_vfmlslq_lane_high_f16,
	test_vfmlalq_laneq_high_f16, test_vfmlslq_laneq_high_f16): ... To this.
	* gcc.target/aarch64/fp16_fmul_lane_low.h (test_vfmlal_lane_low_u32,
	test_vfmlsl_lane_low_u32, test_vfmlal_laneq_low_u32,
	test_vfmlsl_laneq_low_u32, test_vfmlalq_lane_low_u32,
	test_vfmlslq_lane_low_u32, test_vfmlalq_laneq_low_u32,
	test_vfmlslq_laneq_low_u32): Rename ...
	(test_vfmlal_lane_low_f16, test_vfmlsl_lane_low_f16,
	test_vfmlal_laneq_low_f16, test_vfmlsl_laneq_low_f16,
	test_vfmlalq_lane_low_f16, test_vfmlslq_lane_low_f16,
	test_vfmlalq_laneq_low_f16, test_vfmlslq_laneq_low_f16): ... To this.
	* gcc.target/aarch64/fp16_fmul_low.h (test_vfmlal_low_u32,
	test_vfmlalq_low_u32, test_vfmlsl_low_u32, test_vfmlslq_low_u32):
	Rename ...
	(test_vfmlal_low_f16, test_vfmlalq_low_f16, test_vfmlsl_low_f16,
	test_vfmlslq_low_f16): ... To This.
	* lib/target-supports.exp
	(check_effective_target_arm_fp16fml_neon_ok_nocache): Update test.

From-SVN: r269191
parent 6388eda0
Showing with 127 additions and 73 deletions
gcc/ChangeLog
2019-02-25 Tamar Christina <tamar.christina@arm.com>
* config/aarch64/arm_neon.h (vfmlal_low_u32, vfmlsl_low_u32,
vfmlalq_low_u32, vfmlslq_low_u32, vfmlal_high_u32, vfmlsl_high_u32,
vfmlalq_high_u32, vfmlslq_high_u32, vfmlal_lane_low_u32,
vfmlsl_lane_low_u32, vfmlal_laneq_low_u32, vfmlsl_laneq_low_u32,
vfmlalq_lane_low_u32, vfmlslq_lane_low_u32, vfmlalq_laneq_low_u32,
vfmlslq_laneq_low_u32, vfmlal_lane_high_u32, vfmlsl_lane_high_u32,
vfmlal_laneq_high_u32, vfmlsl_laneq_high_u32, vfmlalq_lane_high_u32,
vfmlslq_lane_high_u32, vfmlalq_laneq_high_u32, vfmlslq_laneq_high_u32):
Rename ...
(vfmlal_low_f16, vfmlsl_low_f16, vfmlalq_low_f16, vfmlslq_low_f16,
vfmlal_high_f16, vfmlsl_high_f16, vfmlalq_high_f16, vfmlslq_high_f16,
vfmlal_lane_low_f16, vfmlsl_lane_low_f16, vfmlal_laneq_low_f16,
vfmlsl_laneq_low_f16, vfmlalq_lane_low_f16, vfmlslq_lane_low_f16,
vfmlalq_laneq_low_f16, vfmlslq_laneq_low_f16, vfmlal_lane_high_f16,
vfmlsl_lane_high_f16, vfmlal_laneq_high_f16, vfmlsl_laneq_high_f16,
vfmlalq_lane_high_f16, vfmlslq_lane_high_f16, vfmlalq_laneq_high_f16,
vfmlslq_laneq_high_f16): ... To this.
2019-02-25 Alexander Monakov <amonakov@ispras.ru>
PR rtl-optimization/86096
......
gcc/config/aarch64/arm_neon.h
......@@ -33777,63 +33777,63 @@ vcmlaq_rot270_laneq_f32 (float32x4_t __r, float32x4_t __a, float32x4_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlal_low_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
vfmlal_low_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
{
return __builtin_aarch64_fmlal_lowv2sf (__r, __a, __b);
}
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlsl_low_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
vfmlsl_low_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
{
return __builtin_aarch64_fmlsl_lowv2sf (__r, __a, __b);
}
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlalq_low_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
vfmlalq_low_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
{
return __builtin_aarch64_fmlalq_lowv4sf (__r, __a, __b);
}
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlslq_low_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
vfmlslq_low_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
{
return __builtin_aarch64_fmlslq_lowv4sf (__r, __a, __b);
}
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlal_high_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
vfmlal_high_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
{
return __builtin_aarch64_fmlal_highv2sf (__r, __a, __b);
}
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlsl_high_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
vfmlsl_high_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b)
{
return __builtin_aarch64_fmlsl_highv2sf (__r, __a, __b);
}
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlalq_high_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
vfmlalq_high_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
{
return __builtin_aarch64_fmlalq_highv4sf (__r, __a, __b);
}
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlslq_high_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
vfmlslq_high_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b)
{
return __builtin_aarch64_fmlslq_highv4sf (__r, __a, __b);
}
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlal_lane_low_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
vfmlal_lane_low_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlal_lane_lowv2sf (__r, __a, __b, __lane);
......@@ -33841,7 +33841,7 @@ vfmlal_lane_low_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlsl_lane_low_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
vfmlsl_lane_low_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlsl_lane_lowv2sf (__r, __a, __b, __lane);
......@@ -33849,7 +33849,7 @@ vfmlsl_lane_low_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlal_laneq_low_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
vfmlal_laneq_low_f16 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlal_laneq_lowv2sf (__r, __a, __b, __lane);
......@@ -33857,7 +33857,7 @@ vfmlal_laneq_low_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlsl_laneq_low_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
vfmlsl_laneq_low_f16 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlsl_laneq_lowv2sf (__r, __a, __b, __lane);
......@@ -33865,7 +33865,7 @@ vfmlsl_laneq_low_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlalq_lane_low_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
vfmlalq_lane_low_f16 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlalq_lane_lowv4sf (__r, __a, __b, __lane);
......@@ -33873,7 +33873,7 @@ vfmlalq_lane_low_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlslq_lane_low_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
vfmlslq_lane_low_f16 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlslq_lane_lowv4sf (__r, __a, __b, __lane);
......@@ -33881,7 +33881,7 @@ vfmlslq_lane_low_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlalq_laneq_low_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
vfmlalq_laneq_low_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlalq_laneq_lowv4sf (__r, __a, __b, __lane);
......@@ -33889,7 +33889,7 @@ vfmlalq_laneq_low_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlslq_laneq_low_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
vfmlslq_laneq_low_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlslq_laneq_lowv4sf (__r, __a, __b, __lane);
......@@ -33897,7 +33897,7 @@ vfmlslq_laneq_low_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlal_lane_high_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
vfmlal_lane_high_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlal_lane_highv2sf (__r, __a, __b, __lane);
......@@ -33905,7 +33905,7 @@ vfmlal_lane_high_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlsl_lane_high_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
vfmlsl_lane_high_f16 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlsl_lane_highv2sf (__r, __a, __b, __lane);
......@@ -33913,7 +33913,7 @@ vfmlsl_lane_high_u32 (float32x2_t __r, float16x4_t __a, float16x4_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlal_laneq_high_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
vfmlal_laneq_high_f16 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlal_laneq_highv2sf (__r, __a, __b, __lane);
......@@ -33921,7 +33921,7 @@ vfmlal_laneq_high_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
__extension__ extern __inline float32x2_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlsl_laneq_high_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
vfmlsl_laneq_high_f16 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlsl_laneq_highv2sf (__r, __a, __b, __lane);
......@@ -33929,7 +33929,7 @@ vfmlsl_laneq_high_u32 (float32x2_t __r, float16x4_t __a, float16x8_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlalq_lane_high_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
vfmlalq_lane_high_f16 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlalq_lane_highv4sf (__r, __a, __b, __lane);
......@@ -33937,7 +33937,7 @@ vfmlalq_lane_high_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlslq_lane_high_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
vfmlslq_lane_high_f16 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
const int __lane)
{
return __builtin_aarch64_fmlslq_lane_highv4sf (__r, __a, __b, __lane);
......@@ -33945,7 +33945,7 @@ vfmlslq_lane_high_u32 (float32x4_t __r, float16x8_t __a, float16x4_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlalq_laneq_high_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
vfmlalq_laneq_high_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlalq_laneq_highv4sf (__r, __a, __b, __lane);
......@@ -33953,7 +33953,7 @@ vfmlalq_laneq_high_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
__extension__ extern __inline float32x4_t
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
vfmlslq_laneq_high_u32 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
vfmlslq_laneq_high_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
const int __lane)
{
return __builtin_aarch64_fmlslq_laneq_highv4sf (__r, __a, __b, __lane);
gcc/testsuite/ChangeLog
2019-02-25 Tamar Christina <tamar.christina@arm.com>
* gcc.target/aarch64/fp16_fmul_high.h (test_vfmlal_high_u32,
test_vfmlalq_high_u32, test_vfmlsl_high_u32, test_vfmlslq_high_u32):
Rename ...
(test_vfmlal_high_f16, test_vfmlalq_high_f16, test_vfmlsl_high_f16,
test_vfmlslq_high_f16): ... To this.
* gcc.target/aarch64/fp16_fmul_lane_high.h (test_vfmlal_lane_high_u32,
tets_vfmlsl_lane_high_u32, test_vfmlal_laneq_high_u32,
test_vfmlsl_laneq_high_u32, test_vfmlalq_lane_high_u32,
test_vfmlslq_lane_high_u32, test_vfmlalq_laneq_high_u32,
test_vfmlslq_laneq_high_u32): Rename ...
(test_vfmlal_lane_high_f16, tets_vfmlsl_lane_high_f16,
test_vfmlal_laneq_high_f16, test_vfmlsl_laneq_high_f16,
test_vfmlalq_lane_high_f16, test_vfmlslq_lane_high_f16,
test_vfmlalq_laneq_high_f16, test_vfmlslq_laneq_high_f16): ... To this.
* gcc.target/aarch64/fp16_fmul_lane_low.h (test_vfmlal_lane_low_u32,
test_vfmlsl_lane_low_u32, test_vfmlal_laneq_low_u32,
test_vfmlsl_laneq_low_u32, test_vfmlalq_lane_low_u32,
test_vfmlslq_lane_low_u32, test_vfmlalq_laneq_low_u32,
test_vfmlslq_laneq_low_u32): Rename ...
(test_vfmlal_lane_low_f16, test_vfmlsl_lane_low_f16,
test_vfmlal_laneq_low_f16, test_vfmlsl_laneq_low_f16,
test_vfmlalq_lane_low_f16, test_vfmlslq_lane_low_f16,
test_vfmlalq_laneq_low_f16, test_vfmlslq_laneq_low_f16): ... To this.
* gcc.target/aarch64/fp16_fmul_low.h (test_vfmlal_low_u32,
test_vfmlalq_low_u32, test_vfmlsl_low_u32, test_vfmlslq_low_u32):
Rename ...
(test_vfmlal_low_f16, test_vfmlalq_low_f16, test_vfmlsl_low_f16,
test_vfmlslq_low_f16): ... To This.
* lib/target-supports.exp
(check_effective_target_arm_fp16fml_neon_ok_nocache): Update test.
2019-02-25 Dominique d'Humieres <dominiq@gcc.gnu.org>
PR fortran/89282
......
gcc/testsuite/gcc.target/aarch64/fp16_fmul_high.h
#include "arm_neon.h"
float32x2_t
test_vfmlal_high_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
test_vfmlal_high_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlal_high_u32 (r, a, b);
return vfmlal_high_f16 (r, a, b);
}
float32x4_t
test_vfmlalq_high_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlalq_high_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlalq_high_u32 (r, a, b);
return vfmlalq_high_f16 (r, a, b);
}
float32x2_t
test_vfmlsl_high_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
test_vfmlsl_high_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlsl_high_u32 (r, a, b);
return vfmlsl_high_f16 (r, a, b);
}
float32x4_t
test_vfmlslq_high_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlslq_high_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlslq_high_u32 (r, a, b);
return vfmlslq_high_f16 (r, a, b);
}
gcc/testsuite/gcc.target/aarch64/fp16_fmul_lane_high.h
#include "arm_neon.h"
float32x2_t
test_vfmlal_lane_high_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
test_vfmlal_lane_high_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlal_lane_high_u32 (r, a, b, 0);
return vfmlal_lane_high_f16 (r, a, b, 0);
}
float32x2_t
tets_vfmlsl_lane_high_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
tets_vfmlsl_lane_high_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlsl_lane_high_u32 (r, a, b, 0);
return vfmlsl_lane_high_f16 (r, a, b, 0);
}
float32x2_t
test_vfmlal_laneq_high_u32 (float32x2_t r, float16x4_t a, float16x8_t b)
test_vfmlal_laneq_high_f16 (float32x2_t r, float16x4_t a, float16x8_t b)
{
return vfmlal_laneq_high_u32 (r, a, b, 6);
return vfmlal_laneq_high_f16 (r, a, b, 6);
}
float32x2_t
test_vfmlsl_laneq_high_u32 (float32x2_t r, float16x4_t a, float16x8_t b)
test_vfmlsl_laneq_high_f16 (float32x2_t r, float16x4_t a, float16x8_t b)
{
return vfmlsl_laneq_high_u32 (r, a, b, 6);
return vfmlsl_laneq_high_f16 (r, a, b, 6);
}
float32x4_t
test_vfmlalq_lane_high_u32 (float32x4_t r, float16x8_t a, float16x4_t b)
test_vfmlalq_lane_high_f16 (float32x4_t r, float16x8_t a, float16x4_t b)
{
return vfmlalq_lane_high_u32 (r, a, b, 1);
return vfmlalq_lane_high_f16 (r, a, b, 1);
}
float32x4_t
test_vfmlslq_lane_high_u32 (float32x4_t r, float16x8_t a, float16x4_t b)
test_vfmlslq_lane_high_f16 (float32x4_t r, float16x8_t a, float16x4_t b)
{
return vfmlslq_lane_high_u32 (r, a, b, 1);
return vfmlslq_lane_high_f16 (r, a, b, 1);
}
float32x4_t
test_vfmlalq_laneq_high_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlalq_laneq_high_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlalq_laneq_high_u32 (r, a, b, 7);
return vfmlalq_laneq_high_f16 (r, a, b, 7);
}
float32x4_t
test_vfmlslq_laneq_high_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlslq_laneq_high_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlslq_laneq_high_u32 (r, a, b, 7);
return vfmlslq_laneq_high_f16 (r, a, b, 7);
}
gcc/testsuite/gcc.target/aarch64/fp16_fmul_lane_low.h
#include "arm_neon.h"
float32x2_t
test_vfmlal_lane_low_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
test_vfmlal_lane_low_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlal_lane_low_u32 (r, a, b, 0);
return vfmlal_lane_low_f16 (r, a, b, 0);
}
float32x2_t
test_vfmlsl_lane_low_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
test_vfmlsl_lane_low_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlsl_lane_low_u32 (r, a, b, 0);
return vfmlsl_lane_low_f16 (r, a, b, 0);
}
float32x2_t
test_vfmlal_laneq_low_u32 (float32x2_t r, float16x4_t a, float16x8_t b)
test_vfmlal_laneq_low_f16 (float32x2_t r, float16x4_t a, float16x8_t b)
{
return vfmlal_laneq_low_u32 (r, a, b, 6);
return vfmlal_laneq_low_f16 (r, a, b, 6);
}
float32x2_t
test_vfmlsl_laneq_low_u32 (float32x2_t r, float16x4_t a, float16x8_t b)
test_vfmlsl_laneq_low_f16 (float32x2_t r, float16x4_t a, float16x8_t b)
{
return vfmlsl_laneq_low_u32 (r, a, b, 6);
return vfmlsl_laneq_low_f16 (r, a, b, 6);
}
float32x4_t
test_vfmlalq_lane_low_u32 (float32x4_t r, float16x8_t a, float16x4_t b)
test_vfmlalq_lane_low_f16 (float32x4_t r, float16x8_t a, float16x4_t b)
{
return vfmlalq_lane_low_u32 (r, a, b, 1);
return vfmlalq_lane_low_f16 (r, a, b, 1);
}
float32x4_t
test_vfmlslq_lane_low_u32 (float32x4_t r, float16x8_t a, float16x4_t b)
test_vfmlslq_lane_low_f16 (float32x4_t r, float16x8_t a, float16x4_t b)
{
return vfmlslq_lane_low_u32 (r, a, b, 1);
return vfmlslq_lane_low_f16 (r, a, b, 1);
}
float32x4_t
test_vfmlalq_laneq_low_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlalq_laneq_low_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlalq_laneq_low_u32 (r, a, b, 7);
return vfmlalq_laneq_low_f16 (r, a, b, 7);
}
float32x4_t
test_vfmlslq_laneq_low_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlslq_laneq_low_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlslq_laneq_low_u32 (r, a, b, 7);
return vfmlslq_laneq_low_f16 (r, a, b, 7);
}
gcc/testsuite/gcc.target/aarch64/fp16_fmul_low.h
#include "arm_neon.h"
float32x2_t
test_vfmlal_low_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
test_vfmlal_low_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlal_low_u32 (r, a, b);
return vfmlal_low_f16 (r, a, b);
}
float32x4_t
test_vfmlalq_low_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlalq_low_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlalq_low_u32 (r, a, b);
return vfmlalq_low_f16 (r, a, b);
}
float32x2_t
test_vfmlsl_low_u32 (float32x2_t r, float16x4_t a, float16x4_t b)
test_vfmlsl_low_f16 (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlsl_low_u32 (r, a, b);
return vfmlsl_low_f16 (r, a, b);
}
float32x4_t
test_vfmlslq_low_u32 (float32x4_t r, float16x8_t a, float16x8_t b)
test_vfmlslq_low_f16 (float32x4_t r, float16x8_t a, float16x8_t b)
{
return vfmlslq_low_u32 (r, a, b);
return vfmlslq_low_f16 (r, a, b);
}
gcc/testsuite/lib/target-supports.exp
......@@ -4567,7 +4567,7 @@ proc check_effective_target_arm_fp16fml_neon_ok_nocache { } {
float32x2_t
foo (float32x2_t r, float16x4_t a, float16x4_t b)
{
return vfmlal_high_u32 (r, a, b);
return vfmlal_high_f16 (r, a, b);
}
} "$flags -march=armv8.2-a+fp16fml"] } {
set et_arm_fp16fml_neon_flags "$flags -march=armv8.2-a+fp16fml"
......
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