diff options
| author | Ayan Shafqat <ayan.x.shafqat@gmail.com> | 2025-03-17 09:28:27 +0100 |
|---|---|---|
| committer | Kyrylo Tkachov <ktkachov@nvidia.com> | 2025-03-17 09:29:56 +0100 |
| commit | f4f7216c56fe2f67c72db5b7c4afa220725f3ed1 (patch) | |
| tree | c0d3850128c232ce2f3a0b69cb23285f85db9eb8 /gcc | |
| parent | 8912313df87679e202f2897ec25c924a67ee8117 (diff) | |
| download | gcc-f4f7216c56fe2f67c72db5b7c4afa220725f3ed1.zip gcc-f4f7216c56fe2f67c72db5b7c4afa220725f3ed1.tar.gz gcc-f4f7216c56fe2f67c72db5b7c4afa220725f3ed1.tar.bz2 | |
Aarch64: Add FMA and FMAF intrinsic and corresponding tests
This patch introduces inline definitions for the __fma and __fmaf
functions in arm_acle.h for Aarch64 targets. These definitions rely on
__builtin_fma and __builtin_fmaf to ensure proper inlining and to meet
the ACLE requirements [1].
The patch has been tested locally using a crosstool-NG sysroot for
Aarch64, confirming that the generated code uses the expected fused
multiply-accumulate instructions (fmadd).
[1] https://arm-software.github.io/acle/main/acle.html#fused-multiply-accumulate-fma
gcc/ChangeLog:
* config/aarch64/arm_acle.h (__fma, __fmaf): New functions.
gcc/testsuite/ChangeLog:
* gcc.target/aarch64/acle/acle_fma.c: New test.
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/config/aarch64/arm_acle.h | 14 | ||||
| -rw-r--r-- | gcc/testsuite/gcc.target/aarch64/acle/acle_fma.c | 17 |
2 files changed, 31 insertions, 0 deletions
diff --git a/gcc/config/aarch64/arm_acle.h b/gcc/config/aarch64/arm_acle.h index 7976c11..d9e2401 100644 --- a/gcc/config/aarch64/arm_acle.h +++ b/gcc/config/aarch64/arm_acle.h @@ -129,6 +129,20 @@ __jcvt (double __a) #pragma GCC pop_options +__extension__ extern __inline double +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__fma (double __x, double __y, double __z) +{ + return __builtin_fma (__x, __y, __z); +} + +__extension__ extern __inline float +__attribute__ ((__always_inline__, __gnu_inline__, __artificial__)) +__fmaf (float __x, float __y, float __z) +{ + return __builtin_fmaf (__x, __y, __z); +} + #pragma GCC push_options #pragma GCC target ("+nothing+frintts") __extension__ extern __inline float diff --git a/gcc/testsuite/gcc.target/aarch64/acle/acle_fma.c b/gcc/testsuite/gcc.target/aarch64/acle/acle_fma.c new file mode 100644 index 0000000..9363a75 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/acle/acle_fma.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* { dg-options "-O2" } */ + +#include "arm_acle.h" + +double test_acle_fma (double x, double y, double z) +{ + return __fma (x, y, z); +} + +float test_acle_fmaf (float x, float y, float z) +{ + return __fmaf (x, y, z); +} + +/* { dg-final { scan-assembler-times "fmadd\td\[0-9\]" 1 } } */ +/* { dg-final { scan-assembler-times "fmadd\ts\[0-9\]" 1 } } */ |