diff options
Diffstat (limited to 'sysdeps/x86')
| -rw-r--r-- | sysdeps/x86/cpu-features.c | 14 | ||||
| -rw-r--r-- | sysdeps/x86/cpu-features.h | 6 |
2 files changed, 20 insertions, 0 deletions
diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c index 9ce4b495a5..11b9af2231 100644 --- a/sysdeps/x86/cpu-features.c +++ b/sysdeps/x86/cpu-features.c @@ -205,6 +205,20 @@ init_cpu_features (struct cpu_features *cpu_features) if (CPU_FEATURES_ARCH_P (cpu_features, AVX2_Usable)) cpu_features->feature[index_arch_AVX_Fast_Unaligned_Load] |= bit_arch_AVX_Fast_Unaligned_Load; + + /* To avoid SSE transition penalty, use _dl_runtime_resolve_slow. + If XGETBV suports ECX == 1, use _dl_runtime_resolve_opt. */ + cpu_features->feature[index_arch_Use_dl_runtime_resolve_slow] + |= bit_arch_Use_dl_runtime_resolve_slow; + if (cpu_features->max_cpuid >= 0xd) + { + unsigned int eax; + + __cpuid_count (0xd, 1, eax, ebx, ecx, edx); + if ((eax & (1 << 2)) != 0) + cpu_features->feature[index_arch_Use_dl_runtime_resolve_opt] + |= bit_arch_Use_dl_runtime_resolve_opt; + } } /* This spells out "AuthenticAMD". */ else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65) diff --git a/sysdeps/x86/cpu-features.h b/sysdeps/x86/cpu-features.h index e8910360de..bba33e6b0b 100644 --- a/sysdeps/x86/cpu-features.h +++ b/sysdeps/x86/cpu-features.h @@ -37,6 +37,8 @@ #define bit_arch_Prefer_No_VZEROUPPER (1 << 17) #define bit_arch_Fast_Unaligned_Copy (1 << 18) #define bit_arch_Prefer_ERMS (1 << 19) +#define bit_arch_Use_dl_runtime_resolve_opt (1 << 20) +#define bit_arch_Use_dl_runtime_resolve_slow (1 << 21) /* CPUID Feature flags. */ @@ -107,6 +109,8 @@ # define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1*FEATURE_SIZE # define index_arch_Fast_Unaligned_Copy FEATURE_INDEX_1*FEATURE_SIZE # define index_arch_Prefer_ERMS FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Use_dl_runtime_resolve_opt FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Use_dl_runtime_resolve_slow FEATURE_INDEX_1*FEATURE_SIZE # if defined (_LIBC) && !IS_IN (nonlib) @@ -277,6 +281,8 @@ extern const struct cpu_features *__get_cpu_features (void) # define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1 # define index_arch_Fast_Unaligned_Copy FEATURE_INDEX_1 # define index_arch_Prefer_ERMS FEATURE_INDEX_1 +# define index_arch_Use_dl_runtime_resolve_opt FEATURE_INDEX_1 +# define index_arch_Use_dl_runtime_resolve_slow FEATURE_INDEX_1 #endif /* !__ASSEMBLER__ */ |