diff options
| author | Ayan Shafqat <ayan.x.shafqat@gmail.com> | 2025-05-01 06:17:30 -0700 |
|---|---|---|
| committer | Kyrylo Tkachov <ktkachov@nvidia.com> | 2025-05-01 15:44:28 +0200 |
| commit | 05df554536a8d33f4c438cfc7b006b3b2083246a (patch) | |
| tree | 9516f4d5607fe338a68352d1a0ed92d6aecf1a12 /gcc | |
| parent | 5c917a585d765b0878afd9435e3b3eece9f820f9 (diff) | |
| download | gcc-05df554536a8d33f4c438cfc7b006b3b2083246a.zip gcc-05df554536a8d33f4c438cfc7b006b3b2083246a.tar.gz gcc-05df554536a8d33f4c438cfc7b006b3b2083246a.tar.bz2 | |
Aarch64: Add __sqrt and __sqrtf intrinsics and corresponding tests
This patch introduces two new inline functions, __sqrt and __sqrtf, in
arm_acle.h for Aarch64 targets. These functions wrap the new builtins
__builtin_aarch64_sqrtdf and __builtin_aarch64_sqrtsf, respectively,
providing direct access to hardware instructions without relying on the
standard math library or optimization levels.
This patch also introduces acle_sqrt.c in the AArch64 testsuite,
verifying that the new __sqrt and __sqrtf intrinsics emit the expected
fsqrt instructions for double and float arguments.
Coverage for new intrinsics ensures that __sqrt and __sqrtf are
correctly expanded to hardware instructions and do not fall back to
library calls, regardless of optimization levels.
gcc/ChangeLog:
* config/aarch64/arm_acle.h (__sqrt, __sqrtf): New function.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/acle/acle_sqrt.c: New test.
Signed-off-by: Ayan Shafqat <ayan.x.shafqat@gmail.com>
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/config/aarch64/arm_acle.h | 14 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.target/aarch64/acle/acle_sqrt.c | 19 |
2 files changed, 33 insertions, 0 deletions
diff --git a/gcc/config/aarch64/arm_acle.h b/gcc/config/aarch64/arm_acle.h index d9e2401..507b6e7 100644 --- a/gcc/config/aarch64/arm_acle.h +++ b/gcc/config/aarch64/arm_acle.h @@ -118,6 +118,20 @@ __revl (unsigned long __value) return __rev (__value); } +__extension__ extern __inline double +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__sqrt (double __x) +{ + return __builtin_aarch64_sqrtdf (__x); +} + +__extension__ extern __inline float +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__sqrtf (float __x) +{ + return __builtin_aarch64_sqrtsf (__x); +} + #pragma GCC push_options #pragma GCC target ("+nothing+jscvt") __extension__ extern __inline int32_t diff --git a/gcc/testsuite/gcc.target/aarch64/acle/acle_sqrt.c b/gcc/testsuite/gcc.target/aarch64/acle/acle_sqrt.c new file mode 100644 index 0000000..482351f --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/acle/acle_sqrt.c @@ -0,0 +1,19 @@ +/* { dg-do compile } */ +/* { dg-options "-O2" } */ + +#include "arm_acle.h" + +double +test_acle_sqrt (double x) +{ + return __sqrt (x); +} + +float +test_acle_sqrtf (float x) +{ + return __sqrtf (x); +} + +/* { dg-final { scan-assembler-times "fsqrt\td\[0-9\]" 1 } } */ +/* { dg-final { scan-assembler-times "fsqrt\ts\[0-9\]" 1 } } */ |