diff options
| author | Paul E. Murphy <murphyp@linux.vnet.ibm.com> | 2020-06-03 13:57:20 -0500 |
|---|---|---|
| committer | Paul E. Murphy <murphyp@linux.vnet.ibm.com> | 2020-06-05 15:29:44 -0500 |
| commit | 6ef422750985f7e60a8d480f07ecda59e0311fdf (patch) | |
| tree | 92ba3cc4db0728914cb322df7520e43c20286637 /sysdeps/powerpc/fpu | |
| parent | e52434a2e4d1105272daaef87678da950fbec73f (diff) | |
| download | glibc-6ef422750985f7e60a8d480f07ecda59e0311fdf.tar glibc-6ef422750985f7e60a8d480f07ecda59e0311fdf.tar.gz glibc-6ef422750985f7e60a8d480f07ecda59e0311fdf.tar.bz2 glibc-6ef422750985f7e60a8d480f07ecda59e0311fdf.zip | |
powerpc64le: use common fmaf128 implementation
This defines the macro such that it should behave best on all
supported powerpc targets. Likewise, this allows us to remove the
ppc64le specific s_fmaf128.c.
I have verified powerpc64le multiarch and powerpc64le power9
no-multiarch builds continue to generate optimize fmaf128.
Diffstat (limited to 'sysdeps/powerpc/fpu')
| -rw-r--r-- | sysdeps/powerpc/fpu/math-use-builtins.h | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/sysdeps/powerpc/fpu/math-use-builtins.h b/sysdeps/powerpc/fpu/math-use-builtins.h index 957216a191..72e28ec9cc 100644 --- a/sysdeps/powerpc/fpu/math-use-builtins.h +++ b/sysdeps/powerpc/fpu/math-use-builtins.h @@ -66,6 +66,12 @@ #define USE_FMA_BUILTIN 1 #define USE_FMAF_BUILTIN 1 #define USE_FMAL_BUILTIN 0 -#define USE_FMAF128_BUILTIN 0 + +/* This is not available for P8 or BE targets. */ +#ifdef __FP_FAST_FMAF128 +# define USE_FMAF128_BUILTIN 1 +#else +# define USE_FMAF128_BUILTIN 0 +#endif #endif |