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. --- gcc/config/aarch64/arm_acle.h | 14 ++++++++++++++ .../gcc.target/aarch64/acle/acle_fma.c | 19 +++++++++++++++++++ 2 files changed, 33 insertions(+) create mode 100644 gcc/testsuite/gcc.target/aarch64/acle/acle_fma.c diff --git a/gcc/config/aarch64/arm_acle.h b/gcc/config/aarch64/arm_acle.h index 7976c117daf..d9e2401ea9f 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 00000000000..d7986caba31 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/acle/acle_fma.c @@ -0,0 +1,19 @@ +/* { 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 } } */ -- 2.43.0
