|
|
|
We keep with the idea behind this patch but adjust all of the changes
|
|
|
|
to match the existing impelementations in RHEL 7.3.
|
|
|
|
|
|
|
|
commit 0b5395f052ee09cd7e3d219af4e805c38058afb5
|
|
|
|
Author: H.J. Lu <hjl.tools@gmail.com>
|
|
|
|
Date: Thu Aug 13 03:38:47 2015 -0700
|
|
|
|
|
|
|
|
Update x86_64 multiarch functions for <cpu-features.h>
|
|
|
|
|
|
|
|
This patch updates x86_64 multiarch functions to use the newly defined
|
|
|
|
HAS_CPU_FEATURE, HAS_ARCH_FEATURE and LOAD_RTLD_GLOBAL_RO_RDX from
|
|
|
|
<cpu-features.h>.
|
|
|
|
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_asin.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/e_asin.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_asin.c
|
|
|
|
@@ -8,11 +8,15 @@ extern double __ieee754_acos_fma4 (doubl
|
|
|
|
extern double __ieee754_asin_fma4 (double);
|
|
|
|
|
|
|
|
libm_ifunc (__ieee754_acos,
|
|
|
|
- HAS_FMA4 ? __ieee754_acos_fma4 : __ieee754_acos_sse2);
|
|
|
|
+ HAS_ARCH_FEATURE (FMA4_Usable)
|
|
|
|
+ ? __ieee754_acos_fma4
|
|
|
|
+ : __ieee754_acos_sse2);
|
|
|
|
strong_alias (__ieee754_acos, __acos_finite)
|
|
|
|
|
|
|
|
libm_ifunc (__ieee754_asin,
|
|
|
|
- HAS_FMA4 ? __ieee754_asin_fma4 : __ieee754_asin_sse2);
|
|
|
|
+ HAS_ARCH_FEATURE (FMA4_Usable)
|
|
|
|
+ ? __ieee754_asin_fma4
|
|
|
|
+ : __ieee754_asin_sse2);
|
|
|
|
strong_alias (__ieee754_asin, __asin_finite)
|
|
|
|
|
|
|
|
# define __ieee754_acos __ieee754_acos_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_atan2.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/e_atan2.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_atan2.c
|
|
|
|
@@ -7,14 +7,15 @@ extern double __ieee754_atan2_avx (doubl
|
|
|
|
# ifdef HAVE_FMA4_SUPPORT
|
|
|
|
extern double __ieee754_atan2_fma4 (double, double);
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __ieee754_atan2_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
libm_ifunc (__ieee754_atan2,
|
|
|
|
- HAS_FMA4 ? __ieee754_atan2_fma4
|
|
|
|
- : (HAS_AVX ? __ieee754_atan2_avx : __ieee754_atan2_sse2));
|
|
|
|
+ HAS_ARCH_FEATURE (FMA4_Usable) ? __ieee754_atan2_fma4
|
|
|
|
+ : (HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
+ ? __ieee754_atan2_avx : __ieee754_atan2_sse2));
|
|
|
|
strong_alias (__ieee754_atan2, __atan2_finite)
|
|
|
|
|
|
|
|
# define __ieee754_atan2 __ieee754_atan2_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_exp.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/e_exp.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_exp.c
|
|
|
|
@@ -7,14 +7,15 @@ extern double __ieee754_exp_avx (double)
|
|
|
|
# ifdef HAVE_FMA4_SUPPORT
|
|
|
|
extern double __ieee754_exp_fma4 (double);
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __ieee754_exp_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
libm_ifunc (__ieee754_exp,
|
|
|
|
- HAS_FMA4 ? __ieee754_exp_fma4
|
|
|
|
- : (HAS_AVX ? __ieee754_exp_avx : __ieee754_exp_sse2));
|
|
|
|
+ HAS_ARCH_FEATURE (FMA4_Usable) ? __ieee754_exp_fma4
|
|
|
|
+ : (HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
+ ? __ieee754_exp_avx : __ieee754_exp_sse2));
|
|
|
|
strong_alias (__ieee754_exp, __exp_finite)
|
|
|
|
|
|
|
|
# define __ieee754_exp __ieee754_exp_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_log.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/e_log.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_log.c
|
|
|
|
@@ -7,14 +7,15 @@ extern double __ieee754_log_avx (double)
|
|
|
|
# ifdef HAVE_FMA4_SUPPORT
|
|
|
|
extern double __ieee754_log_fma4 (double);
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __ieee754_log_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
libm_ifunc (__ieee754_log,
|
|
|
|
- HAS_FMA4 ? __ieee754_log_fma4
|
|
|
|
- : (HAS_AVX ? __ieee754_log_avx : __ieee754_log_sse2));
|
|
|
|
+ HAS_ARCH_FEATURE (FMA4_Usable) ? __ieee754_log_fma4
|
|
|
|
+ : (HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
+ ? __ieee754_log_avx : __ieee754_log_sse2));
|
|
|
|
strong_alias (__ieee754_log, __log_finite)
|
|
|
|
|
|
|
|
# define __ieee754_log __ieee754_log_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_pow.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/e_pow.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/e_pow.c
|
|
|
|
@@ -5,7 +5,10 @@
|
|
|
|
extern double __ieee754_pow_sse2 (double, double);
|
|
|
|
extern double __ieee754_pow_fma4 (double, double);
|
|
|
|
|
|
|
|
-libm_ifunc (__ieee754_pow, HAS_FMA4 ? __ieee754_pow_fma4 : __ieee754_pow_sse2);
|
|
|
|
+libm_ifunc (__ieee754_pow,
|
|
|
|
+ HAS_ARCH_FEATURE (FMA4_Usable)
|
|
|
|
+ ? __ieee754_pow_fma4
|
|
|
|
+ : __ieee754_pow_sse2);
|
|
|
|
strong_alias (__ieee754_pow, __pow_finite)
|
|
|
|
|
|
|
|
# define __ieee754_pow __ieee754_pow_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_atan.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_atan.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_atan.c
|
|
|
|
@@ -7,13 +7,14 @@ extern double __atan_avx (double);
|
|
|
|
# ifdef HAVE_FMA4_SUPPORT
|
|
|
|
extern double __atan_fma4 (double);
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __atan_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
-libm_ifunc (atan, (HAS_FMA4 ? __atan_fma4 :
|
|
|
|
- HAS_AVX ? __atan_avx : __atan_sse2));
|
|
|
|
+libm_ifunc (atan, (HAS_ARCH_FEATURE (FMA4_Usable) ? __atan_fma4 :
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
+ ? __atan_avx : __atan_sse2));
|
|
|
|
|
|
|
|
# define atan __atan_sse2
|
|
|
|
#endif
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_ceil.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_ceil.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_ceil.S
|
|
|
|
@@ -22,10 +22,9 @@
|
|
|
|
|
|
|
|
ENTRY(__ceil)
|
|
|
|
.type __ceil, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
- movq %rax, %rdx
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
leaq __ceil_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __ceil_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_ceilf.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_ceilf.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_ceilf.S
|
|
|
|
@@ -22,10 +22,9 @@
|
|
|
|
|
|
|
|
ENTRY(__ceilf)
|
|
|
|
.type __ceilf, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
- movq %rax, %rdx
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
leaq __ceilf_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __ceilf_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_floor.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_floor.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_floor.S
|
|
|
|
@@ -22,10 +22,9 @@
|
|
|
|
|
|
|
|
ENTRY(__floor)
|
|
|
|
.type __floor, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
- movq %rax, %rdx
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
leaq __floor_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __floor_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_floorf.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_floorf.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_floorf.S
|
|
|
|
@@ -22,10 +22,10 @@
|
|
|
|
|
|
|
|
ENTRY(__floorf)
|
|
|
|
.type __floorf, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
movq %rax, %rdx
|
|
|
|
leaq __floorf_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __floorf_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_fma.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_fma.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_fma.c
|
|
|
|
@@ -42,14 +42,15 @@ __fma_fma4 (double x, double y, double z
|
|
|
|
return x;
|
|
|
|
}
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __fma_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
|
|
|
|
-libm_ifunc (__fma, HAS_FMA
|
|
|
|
- ? __fma_fma3 : (HAS_FMA4 ? __fma_fma4 : __fma_sse2));
|
|
|
|
+libm_ifunc (__fma, HAS_ARCH_FEATURE (FMA_Usable)
|
|
|
|
+ ? __fma_fma3 : (HAS_ARCH_FEATURE (FMA4_Usable)
|
|
|
|
+ ? __fma_fma4 : __fma_sse2));
|
|
|
|
weak_alias (__fma, fma)
|
|
|
|
|
|
|
|
# define __fma __fma_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_fmaf.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_fmaf.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_fmaf.c
|
|
|
|
@@ -41,14 +41,15 @@ __fmaf_fma4 (float x, float y, float z)
|
|
|
|
return x;
|
|
|
|
}
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __fmaf_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
|
|
|
|
-libm_ifunc (__fmaf, HAS_FMA
|
|
|
|
- ? __fmaf_fma3 : (HAS_FMA4 ? __fmaf_fma4 : __fmaf_sse2));
|
|
|
|
+libm_ifunc (__fmaf, HAS_ARCH_FEATURE (FMA_Usable)
|
|
|
|
+ ? __fmaf_fma3 : (HAS_ARCH_FEATURE (FMA4_Usable)
|
|
|
|
+ ? __fmaf_fma4 : __fmaf_sse2));
|
|
|
|
weak_alias (__fmaf, fmaf)
|
|
|
|
|
|
|
|
# define __fmaf __fmaf_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_nearbyint.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_nearbyint.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_nearbyint.S
|
|
|
|
@@ -22,10 +22,10 @@
|
|
|
|
|
|
|
|
ENTRY(__nearbyint)
|
|
|
|
.type __nearbyint, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
movq %rax, %rdx
|
|
|
|
leaq __nearbyint_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __nearbyint_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S
|
|
|
|
@@ -22,10 +22,9 @@
|
|
|
|
|
|
|
|
ENTRY(__nearbyintf)
|
|
|
|
.type __nearbyintf, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
- movq %rax, %rdx
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
leaq __nearbyintf_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __nearbyintf_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_rint.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_rint.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_rint.S
|
|
|
|
@@ -22,10 +22,9 @@
|
|
|
|
|
|
|
|
ENTRY(__rint)
|
|
|
|
.type __rint, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
- movq %rax, %rdx
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
leaq __rint_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __rint_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_rintf.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_rintf.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_rintf.S
|
|
|
|
@@ -22,10 +22,9 @@
|
|
|
|
|
|
|
|
ENTRY(__rintf)
|
|
|
|
.type __rintf, @gnu_indirect_function
|
|
|
|
- call __get_cpu_features@plt
|
|
|
|
- movq %rax, %rdx
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
leaq __rintf_sse41(%rip), %rax
|
|
|
|
- testl $bit_SSE4_1, CPUID_OFFSET+index_SSE4_1(%rdx)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jnz 2f
|
|
|
|
leaq __rintf_c(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_sin.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_sin.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_sin.c
|
|
|
|
@@ -11,18 +11,20 @@ extern double __sin_avx (double);
|
|
|
|
extern double __cos_fma4 (double);
|
|
|
|
extern double __sin_fma4 (double);
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __cos_fma4 ((void *) 0)
|
|
|
|
# define __sin_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
-libm_ifunc (__cos, (HAS_FMA4 ? __cos_fma4 :
|
|
|
|
- HAS_AVX ? __cos_avx : __cos_sse2));
|
|
|
|
+libm_ifunc (__cos, (HAS_ARCH_FEATURE (FMA4_Usable) ? __cos_fma4 :
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
+ ? __cos_avx : __cos_sse2));
|
|
|
|
weak_alias (__cos, cos)
|
|
|
|
|
|
|
|
-libm_ifunc (__sin, (HAS_FMA4 ? __sin_fma4 :
|
|
|
|
- HAS_AVX ? __sin_avx : __sin_sse2));
|
|
|
|
+libm_ifunc (__sin, (HAS_ARCH_FEATURE (FMA4_Usable) ? __sin_fma4 :
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
+ ? __sin_avx : __sin_sse2));
|
|
|
|
weak_alias (__sin, sin)
|
|
|
|
|
|
|
|
# define __cos __cos_sse2
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_tan.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/fpu/multiarch/s_tan.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/fpu/multiarch/s_tan.c
|
|
|
|
@@ -7,13 +7,14 @@ extern double __tan_avx (double);
|
|
|
|
# ifdef HAVE_FMA4_SUPPORT
|
|
|
|
extern double __tan_fma4 (double);
|
|
|
|
# else
|
|
|
|
-# undef HAS_FMA4
|
|
|
|
-# define HAS_FMA4 0
|
|
|
|
+# undef HAS_ARCH_FEATURE
|
|
|
|
+# define HAS_ARCH_FEATURE(feature) 0
|
|
|
|
# define __tan_fma4 ((void *) 0)
|
|
|
|
# endif
|
|
|
|
|
|
|
|
-libm_ifunc (tan, (HAS_FMA4 ? __tan_fma4 :
|
|
|
|
- HAS_AVX ? __tan_avx : __tan_sse2));
|
|
|
|
+libm_ifunc (tan, (HAS_ARCH_FEATURE (FMA4_Usable) ? __tan_fma4 :
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
+ ? __tan_avx : __tan_sse2));
|
|
|
|
|
|
|
|
# define tan __tan_sse2
|
|
|
|
#endif
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/ifunc-impl-list.c
|
|
|
|
@@ -39,25 +39,26 @@ __libc_ifunc_impl_list (const char *name
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/memcmp.S. */
|
|
|
|
IFUNC_IMPL (i, name, memcmp,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, memcmp, HAS_SSE4_1,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, memcmp, HAS_CPU_FEATURE (SSE4_1),
|
|
|
|
__memcmp_sse4_1)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, memcmp, HAS_SSSE3, __memcmp_ssse3)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, memcmp, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
+ __memcmp_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, memcmp, 1, __memcmp_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/memmove_chk.S. */
|
|
|
|
IFUNC_IMPL (i, name, __memmove_chk,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, __memmove_chk, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, __memmove_chk, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__memmove_chk_ssse3_back)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, __memmove_chk, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, __memmove_chk, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__memmove_chk_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, __memmove_chk, 1,
|
|
|
|
__memmove_chk_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/memmove.S. */
|
|
|
|
IFUNC_IMPL (i, name, memmove,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, memmove, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, memmove, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__memmove_ssse3_back)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, memmove, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, memmove, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__memmove_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, memmove, 1, __memmove_sse2))
|
|
|
|
|
|
|
|
@@ -74,13 +75,13 @@ __libc_ifunc_impl_list (const char *name
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/rawmemchr.S. */
|
|
|
|
IFUNC_IMPL (i, name, rawmemchr,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, rawmemchr, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, rawmemchr, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__rawmemchr_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, rawmemchr, 1, __rawmemchr_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/stpncpy.S. */
|
|
|
|
IFUNC_IMPL (i, name, stpncpy,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, stpncpy, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, stpncpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__stpncpy_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, stpncpy, 1,
|
|
|
|
__stpncpy_sse2_unaligned)
|
|
|
|
@@ -88,92 +89,105 @@ __libc_ifunc_impl_list (const char *name
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/stpcpy.S. */
|
|
|
|
IFUNC_IMPL (i, name, stpcpy,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, stpcpy, HAS_SSSE3, __stpcpy_ssse3)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, stpcpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
+ __stpcpy_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, stpcpy, 1, __stpcpy_sse2_unaligned)
|
|
|
|
IFUNC_IMPL_ADD (array, i, stpcpy, 1, __stpcpy_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strcasecmp_l.S. */
|
|
|
|
IFUNC_IMPL (i, name, strcasecmp,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcasecmp, HAS_AVX,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcasecmp,
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable),
|
|
|
|
__strcasecmp_avx)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcasecmp, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcasecmp,
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strcasecmp_sse42)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcasecmp, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcasecmp,
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__strcasecmp_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcasecmp, 1, __strcasecmp_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strcasecmp_l.S. */
|
|
|
|
IFUNC_IMPL (i, name, strcasecmp_l,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcasecmp_l, HAS_AVX,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcasecmp_l,
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable),
|
|
|
|
__strcasecmp_l_avx)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcasecmp_l, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcasecmp_l,
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strcasecmp_l_sse42)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcasecmp_l, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcasecmp_l,
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__strcasecmp_l_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcasecmp_l, 1,
|
|
|
|
__strcasecmp_l_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strcasestr.c. */
|
|
|
|
IFUNC_IMPL (i, name, strcasestr,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcasestr, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcasestr, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strcasestr_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcasestr, 1, __strcasestr_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strcat.S. */
|
|
|
|
IFUNC_IMPL (i, name, strcat,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcat, HAS_SSSE3, __strcat_ssse3)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcat, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
+ __strcat_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcat, 1, __strcat_sse2_unaligned)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcat, 1, __strcat_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strchr.S. */
|
|
|
|
IFUNC_IMPL (i, name, strchr,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strchr, HAS_SSE4_2, __strchr_sse42)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strchr, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
+ __strchr_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strchr, 1, __strchr_sse2_no_bsf)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strchr, 1, __strchr_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strcmp.S. */
|
|
|
|
IFUNC_IMPL (i, name, strcmp,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcmp, HAS_SSE4_2, __strcmp_sse42)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcmp, HAS_SSSE3, __strcmp_ssse3)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcmp, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
+ __strcmp_sse42)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcmp, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
+ __strcmp_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcmp, 1, __strcmp_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strcpy.S. */
|
|
|
|
IFUNC_IMPL (i, name, strcpy,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcpy, HAS_SSSE3, __strcpy_ssse3)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
+ __strcpy_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcpy, 1, __strcpy_sse2_unaligned)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcpy, 1, __strcpy_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strcspn.S. */
|
|
|
|
IFUNC_IMPL (i, name, strcspn,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strcspn, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strcspn, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strcspn_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strcspn, 1, __strcspn_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strncase_l.S. */
|
|
|
|
IFUNC_IMPL (i, name, strncasecmp,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncasecmp, HAS_AVX,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncasecmp, HAS_ARCH_FEATURE (AVX_Usable),
|
|
|
|
__strncasecmp_avx)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncasecmp, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncasecmp, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strncasecmp_sse42)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncasecmp, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncasecmp, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__strncasecmp_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strncasecmp, 1,
|
|
|
|
__strncasecmp_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strncase_l.S. */
|
|
|
|
IFUNC_IMPL (i, name, strncasecmp_l,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncasecmp_l, HAS_AVX,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncasecmp_l,
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable),
|
|
|
|
__strncasecmp_l_avx)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncasecmp_l, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncasecmp_l, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strncasecmp_l_sse42)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncasecmp_l, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncasecmp_l, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__strncasecmp_l_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strncasecmp_l, 1,
|
|
|
|
__strncasecmp_l_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strncat.S. */
|
|
|
|
IFUNC_IMPL (i, name, strncat,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncat, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncat, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__strncat_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strncat, 1,
|
|
|
|
__strncat_sse2_unaligned)
|
|
|
|
@@ -181,7 +195,7 @@ __libc_ifunc_impl_list (const char *name
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strncpy.S. */
|
|
|
|
IFUNC_IMPL (i, name, strncpy,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncpy, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__strncpy_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strncpy, 1,
|
|
|
|
__strncpy_sse2_unaligned)
|
|
|
|
@@ -194,79 +208,83 @@ __libc_ifunc_impl_list (const char *name
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strpbrk.S. */
|
|
|
|
IFUNC_IMPL (i, name, strpbrk,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strpbrk, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strpbrk, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strpbrk_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strpbrk, 1, __strpbrk_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strrchr.S. */
|
|
|
|
IFUNC_IMPL (i, name, strrchr,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strrchr, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strrchr, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strrchr_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strrchr, 1, __strrchr_sse2_no_bsf)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strrchr, 1, __strrchr_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strspn.S. */
|
|
|
|
IFUNC_IMPL (i, name, strspn,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strspn, HAS_SSE4_2, __strspn_sse42)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strspn, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
+ __strspn_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strspn, 1, __strspn_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strstr-c.c. */
|
|
|
|
IFUNC_IMPL (i, name, strstr,
|
|
|
|
IFUNC_IMPL_ADD (array, i, strstr, use_unaligned_strstr (),
|
|
|
|
__strstr_sse2_unaligned)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strstr, HAS_SSE4_2, __strstr_sse42)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strstr, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
+ __strstr_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strstr, 1, __strstr_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/wcscpy.S. */
|
|
|
|
IFUNC_IMPL (i, name, wcscpy,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, wcscpy, HAS_SSSE3, __wcscpy_ssse3)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, wcscpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
+ __wcscpy_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, wcscpy, 1, __wcscpy_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/wmemcmp.S. */
|
|
|
|
IFUNC_IMPL (i, name, wmemcmp,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, wmemcmp, HAS_SSE4_1,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, wmemcmp, HAS_CPU_FEATURE (SSE4_1),
|
|
|
|
__wmemcmp_sse4_1)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, wmemcmp, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, wmemcmp, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__wmemcmp_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, wmemcmp, 1, __wmemcmp_sse2))
|
|
|
|
|
|
|
|
#ifdef SHARED
|
|
|
|
/* Support sysdeps/x86_64/multiarch/memcpy_chk.S. */
|
|
|
|
IFUNC_IMPL (i, name, __memcpy_chk,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, __memcpy_chk, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, __memcpy_chk, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__memcpy_chk_ssse3_back)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, __memcpy_chk, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, __memcpy_chk, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__memcpy_chk_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, __memcpy_chk, 1,
|
|
|
|
__memcpy_chk_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/memcpy.S. */
|
|
|
|
IFUNC_IMPL (i, name, memcpy,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, memcpy, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, memcpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__memcpy_ssse3_back)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, memcpy, HAS_SSSE3, __memcpy_ssse3)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, memcpy, HAS_CPU_FEATURE (SSSE3), __memcpy_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, memcpy, 1, __memcpy_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/mempcpy_chk.S. */
|
|
|
|
IFUNC_IMPL (i, name, __mempcpy_chk,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, __mempcpy_chk, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, __mempcpy_chk, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__mempcpy_chk_ssse3_back)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, __mempcpy_chk, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, __mempcpy_chk, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__mempcpy_chk_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, __mempcpy_chk, 1,
|
|
|
|
__mempcpy_chk_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/mempcpy.S. */
|
|
|
|
IFUNC_IMPL (i, name, mempcpy,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, mempcpy, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, mempcpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__mempcpy_ssse3_back)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, mempcpy, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, mempcpy, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__mempcpy_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, mempcpy, 1, __mempcpy_sse2))
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strlen.S. */
|
|
|
|
IFUNC_IMPL (i, name, strlen,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strlen, HAS_SSE4_2, __strlen_sse42)
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strlen, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
+ __strlen_sse42)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strlen, 1, __strlen_sse2_pminub)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strlen, 1, __strlen_sse2_no_bsf)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strlen, 1, __strlen_sse2)
|
|
|
|
@@ -274,9 +292,9 @@ __libc_ifunc_impl_list (const char *name
|
|
|
|
|
|
|
|
/* Support sysdeps/x86_64/multiarch/strncmp.S. */
|
|
|
|
IFUNC_IMPL (i, name, strncmp,
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncmp, HAS_SSE4_2,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncmp, HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
__strncmp_sse42)
|
|
|
|
- IFUNC_IMPL_ADD (array, i, strncmp, HAS_SSSE3,
|
|
|
|
+ IFUNC_IMPL_ADD (array, i, strncmp, HAS_CPU_FEATURE (SSSE3),
|
|
|
|
__strncmp_ssse3)
|
|
|
|
IFUNC_IMPL_ADD (array, i, strncmp, 1, __strncmp_sse2))
|
|
|
|
#endif
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memcmp.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/memcmp.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memcmp.S
|
|
|
|
@@ -26,16 +26,13 @@
|
|
|
|
.text
|
|
|
|
ENTRY(memcmp)
|
|
|
|
.type memcmp, @gnu_indirect_function
|
|
|
|
- cmpl $0, KIND_OFFSET+__cpu_features(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-
|
|
|
|
-1: testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jnz 2f
|
|
|
|
leaq __memcmp_sse2(%rip), %rax
|
|
|
|
ret
|
|
|
|
|
|
|
|
-2: testl $bit_SSE4_1, __cpu_features+CPUID_OFFSET+index_SSE4_1(%rip)
|
|
|
|
+2: HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jz 3f
|
|
|
|
leaq __memcmp_sse4_1(%rip), %rax
|
|
|
|
ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memcpy.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/memcpy.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memcpy.S
|
|
|
|
@@ -29,14 +29,12 @@
|
|
|
|
.text
|
|
|
|
ENTRY(__new_memcpy)
|
|
|
|
.type __new_memcpy, @gnu_indirect_function
|
|
|
|
- cmpl $0, KIND_OFFSET+__cpu_features(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __memcpy_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __memcpy_sse2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jz 2f
|
|
|
|
leaq __memcpy_ssse3(%rip), %rax
|
|
|
|
- testl $bit_Fast_Copy_Backward, __cpu_features+FEATURE_OFFSET+index_Fast_Copy_Backward(%rip)
|
|
|
|
+ HAS_ARCH_FEATURE (Fast_Copy_Backward)
|
|
|
|
jz 2f
|
|
|
|
leaq __memcpy_ssse3_back(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memcpy_chk.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/memcpy_chk.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memcpy_chk.S
|
|
|
|
@@ -29,14 +29,12 @@
|
|
|
|
.text
|
|
|
|
ENTRY(__memcpy_chk)
|
|
|
|
.type __memcpy_chk, @gnu_indirect_function
|
|
|
|
- cmpl $0, KIND_OFFSET+__cpu_features(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __memcpy_chk_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __memcpy_chk_sse2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jz 2f
|
|
|
|
leaq __memcpy_chk_ssse3(%rip), %rax
|
|
|
|
- testl $bit_Fast_Copy_Backward, __cpu_features+FEATURE_OFFSET+index_Fast_Copy_Backward(%rip)
|
|
|
|
+ HAS_ARCH_FEATURE (Fast_Copy_Backward)
|
|
|
|
jz 2f
|
|
|
|
leaq __memcpy_chk_ssse3_back(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memmove.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/memmove.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memmove.c
|
|
|
|
@@ -47,8 +47,8 @@ extern __typeof (__redirect_memmove) __m
|
|
|
|
ifunc symbol properly. */
|
|
|
|
extern __typeof (__redirect_memmove) __libc_memmove;
|
|
|
|
libc_ifunc (__libc_memmove,
|
|
|
|
- HAS_SSSE3
|
|
|
|
- ? (HAS_FAST_COPY_BACKWARD
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
+ ? (HAS_ARCH_FEATURE (Fast_Copy_Backward)
|
|
|
|
? __memmove_ssse3_back : __memmove_ssse3)
|
|
|
|
: __memmove_sse2)
|
|
|
|
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memmove_chk.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/memmove_chk.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memmove_chk.c
|
|
|
|
@@ -29,7 +29,7 @@ extern __typeof (__memmove_chk) __memmov
|
|
|
|
#include "debug/memmove_chk.c"
|
|
|
|
|
|
|
|
libc_ifunc (__memmove_chk,
|
|
|
|
- HAS_SSSE3
|
|
|
|
- ? (HAS_FAST_COPY_BACKWARD
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
+ ? (HAS_ARCH_FEATURE (Fast_Copy_Backward)
|
|
|
|
? __memmove_chk_ssse3_back : __memmove_chk_ssse3)
|
|
|
|
: __memmove_chk_sse2);
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/mempcpy.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/mempcpy.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/mempcpy.S
|
|
|
|
@@ -27,14 +27,12 @@
|
|
|
|
#if defined SHARED && IS_IN (libc)
|
|
|
|
ENTRY(__mempcpy)
|
|
|
|
.type __mempcpy, @gnu_indirect_function
|
|
|
|
- cmpl $0, KIND_OFFSET+__cpu_features(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __mempcpy_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __mempcpy_sse2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jz 2f
|
|
|
|
leaq __mempcpy_ssse3(%rip), %rax
|
|
|
|
- testl $bit_Fast_Copy_Backward, __cpu_features+FEATURE_OFFSET+index_Fast_Copy_Backward(%rip)
|
|
|
|
+ HAS_ARCH_FEATURE (Fast_Copy_Backward)
|
|
|
|
jz 2f
|
|
|
|
leaq __mempcpy_ssse3_back(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/mempcpy_chk.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/mempcpy_chk.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/mempcpy_chk.S
|
|
|
|
@@ -29,14 +29,12 @@
|
|
|
|
.text
|
|
|
|
ENTRY(__mempcpy_chk)
|
|
|
|
.type __mempcpy_chk, @gnu_indirect_function
|
|
|
|
- cmpl $0, KIND_OFFSET+__cpu_features(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __mempcpy_chk_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __mempcpy_chk_sse2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jz 2f
|
|
|
|
leaq __mempcpy_chk_ssse3(%rip), %rax
|
|
|
|
- testl $bit_Fast_Copy_Backward, __cpu_features+FEATURE_OFFSET+index_Fast_Copy_Backward(%rip)
|
|
|
|
+ HAS_ARCH_FEATURE (Fast_Copy_Backward)
|
|
|
|
jz 2f
|
|
|
|
leaq __mempcpy_chk_ssse3_back(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memset.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/memset.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memset.S
|
|
|
|
@@ -24,11 +24,9 @@
|
|
|
|
#if IS_IN (libc)
|
|
|
|
ENTRY(memset)
|
|
|
|
.type memset, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __memset_x86_64(%rip), %rax
|
|
|
|
- testl $bit_Prefer_SSE_for_memop, __cpu_features+FEATURE_OFFSET+index_Prefer_SSE_for_memop(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __memset_x86_64(%rip), %rax
|
|
|
|
+ HAS_ARCH_FEATURE (Prefer_SSE_for_memop)
|
|
|
|
jz 2f
|
|
|
|
leaq __memset_sse2(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memset_chk.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/memset_chk.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/memset_chk.S
|
|
|
|
@@ -25,11 +25,9 @@
|
|
|
|
# ifdef SHARED
|
|
|
|
ENTRY(__memset_chk)
|
|
|
|
.type __memset_chk, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __memset_chk_x86_64(%rip), %rax
|
|
|
|
- testl $bit_Prefer_SSE_for_memop, __cpu_features+FEATURE_OFFSET+index_Prefer_SSE_for_memop(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __memset_chk_x86_64(%rip), %rax
|
|
|
|
+ HAS_ARCH_FEATURE (Prefer_SSE_for_memop)
|
|
|
|
jz 2f
|
|
|
|
leaq __memset_chk_sse2(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/sched_cpucount.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/sched_cpucount.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/sched_cpucount.c
|
|
|
|
@@ -33,4 +33,4 @@
|
|
|
|
#undef __sched_cpucount
|
|
|
|
|
|
|
|
libc_ifunc (__sched_cpucount,
|
|
|
|
- HAS_POPCOUNT ? popcount_cpucount : generic_cpucount);
|
|
|
|
+ HAS_CPU_FEATURE (POPCOUNT) ? popcount_cpucount : generic_cpucount);
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcat.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strcat.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcat.S
|
|
|
|
@@ -47,14 +47,12 @@
|
|
|
|
.text
|
|
|
|
ENTRY(STRCAT)
|
|
|
|
.type STRCAT, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq STRCAT_SSE2_UNALIGNED(%rip), %rax
|
|
|
|
- testl $bit_Fast_Unaligned_Load, __cpu_features+FEATURE_OFFSET+index_Fast_Unaligned_Load(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq STRCAT_SSE2_UNALIGNED(%rip), %rax
|
|
|
|
+ HAS_ARCH_FEATURE (Fast_Unaligned_Load)
|
|
|
|
jnz 2f
|
|
|
|
leaq STRCAT_SSE2(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jz 2f
|
|
|
|
leaq STRCAT_SSSE3(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strchr.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strchr.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strchr.S
|
|
|
|
@@ -25,15 +25,13 @@
|
|
|
|
.text
|
|
|
|
ENTRY(strchr)
|
|
|
|
.type strchr, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __strchr_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __strchr_sse2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jz 2f
|
|
|
|
leaq __strchr_sse42(%rip), %rax
|
|
|
|
ret
|
|
|
|
-2: testl $bit_Slow_BSF, __cpu_features+FEATURE_OFFSET+index_Slow_BSF(%rip)
|
|
|
|
+2: HAS_ARCH_FEATURE (Slow_BSF)
|
|
|
|
jz 3f
|
|
|
|
leaq __strchr_sse2_no_bsf(%rip), %rax
|
|
|
|
3: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcmp.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strcmp.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcmp.S
|
|
|
|
@@ -83,16 +83,12 @@
|
|
|
|
.text
|
|
|
|
ENTRY(STRCMP)
|
|
|
|
.type STRCMP, @gnu_indirect_function
|
|
|
|
- /* Manually inlined call to __get_cpu_features. */
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1:
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
leaq STRCMP_SSE42(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jnz 2f
|
|
|
|
leaq STRCMP_SSSE3(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jnz 2f
|
|
|
|
leaq STRCMP_SSE2(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
@@ -101,21 +97,17 @@ END(STRCMP)
|
|
|
|
# ifdef USE_AS_STRCASECMP_L
|
|
|
|
ENTRY(__strcasecmp)
|
|
|
|
.type __strcasecmp, @gnu_indirect_function
|
|
|
|
- /* Manually inlined call to __get_cpu_features. */
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1:
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
# ifdef HAVE_AVX_SUPPORT
|
|
|
|
leaq __strcasecmp_avx(%rip), %rax
|
|
|
|
- testl $bit_AVX_Usable, __cpu_features+FEATURE_OFFSET+index_AVX_Usable(%rip)
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
jnz 2f
|
|
|
|
# endif
|
|
|
|
leaq __strcasecmp_sse42(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jnz 2f
|
|
|
|
leaq __strcasecmp_ssse3(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jnz 2f
|
|
|
|
leaq __strcasecmp_sse2(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
@@ -125,21 +117,17 @@ weak_alias (__strcasecmp, strcasecmp)
|
|
|
|
# ifdef USE_AS_STRNCASECMP_L
|
|
|
|
ENTRY(__strncasecmp)
|
|
|
|
.type __strncasecmp, @gnu_indirect_function
|
|
|
|
- /* Manually inlined call to __get_cpu_features. */
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1:
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
# ifdef HAVE_AVX_SUPPORT
|
|
|
|
leaq __strncasecmp_avx(%rip), %rax
|
|
|
|
- testl $bit_AVX_Usable, __cpu_features+FEATURE_OFFSET+index_AVX_Usable(%rip)
|
|
|
|
+ HAS_ARCH_FEATURE (AVX_Usable)
|
|
|
|
jnz 2f
|
|
|
|
# endif
|
|
|
|
leaq __strncasecmp_sse42(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jnz 2f
|
|
|
|
leaq __strncasecmp_ssse3(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jnz 2f
|
|
|
|
leaq __strncasecmp_sse2(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcpy.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strcpy.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcpy.S
|
|
|
|
@@ -61,14 +61,12 @@
|
|
|
|
.text
|
|
|
|
ENTRY(STRCPY)
|
|
|
|
.type STRCPY, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq STRCPY_SSE2_UNALIGNED(%rip), %rax
|
|
|
|
- testl $bit_Fast_Unaligned_Load, __cpu_features+FEATURE_OFFSET+index_Fast_Unaligned_Load(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq STRCPY_SSE2_UNALIGNED(%rip), %rax
|
|
|
|
+ HAS_ARCH_FEATURE (Fast_Unaligned_Load)
|
|
|
|
jnz 2f
|
|
|
|
leaq STRCPY_SSE2(%rip), %rax
|
|
|
|
- testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jz 2f
|
|
|
|
leaq STRCPY_SSSE3(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcspn.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strcspn.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcspn.S
|
|
|
|
@@ -45,11 +45,9 @@
|
|
|
|
.text
|
|
|
|
ENTRY(STRCSPN)
|
|
|
|
.type STRCSPN, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq STRCSPN_SSE2(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq STRCSPN_SSE2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jz 2f
|
|
|
|
leaq STRCSPN_SSE42(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strspn.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strspn.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strspn.S
|
|
|
|
@@ -30,11 +30,9 @@
|
|
|
|
.text
|
|
|
|
ENTRY(strspn)
|
|
|
|
.type strspn, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __strspn_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __strspn_sse2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jz 2f
|
|
|
|
leaq __strspn_sse42(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/test-multiarch.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/test-multiarch.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/test-multiarch.c
|
|
|
|
@@ -75,12 +75,18 @@ do_test (int argc, char **argv)
|
|
|
|
int fails;
|
|
|
|
|
|
|
|
get_cpuinfo ();
|
|
|
|
- fails = check_proc ("avx", HAS_AVX, "HAS_AVX");
|
|
|
|
- fails += check_proc ("fma4", HAS_FMA4, "HAS_FMA4");
|
|
|
|
- fails += check_proc ("sse4_2", HAS_SSE4_2, "HAS_SSE4_2");
|
|
|
|
- fails += check_proc ("sse4_1", HAS_SSE4_1, "HAS_SSE4_1");
|
|
|
|
- fails += check_proc ("ssse3", HAS_SSSE3, "HAS_SSSE3");
|
|
|
|
- fails += check_proc ("popcnt", HAS_POPCOUNT, "HAS_POPCOUNT");
|
|
|
|
+ fails = check_proc ("avx", HAS_ARCH_FEATURE (AVX_Usable),
|
|
|
|
+ "HAS_ARCH_FEATURE (AVX_Usable)");
|
|
|
|
+ fails += check_proc ("fma4", HAS_ARCH_FEATURE (FMA4_Usable),
|
|
|
|
+ "HAS_ARCH_FEATURE (FMA4_Usable)");
|
|
|
|
+ fails += check_proc ("sse4_2", HAS_CPU_FEATURE (SSE4_2),
|
|
|
|
+ "HAS_CPU_FEATURE (SSE4_2)");
|
|
|
|
+ fails += check_proc ("sse4_1", HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
+ , "HAS_CPU_FEATURE (SSE4_1)");
|
|
|
|
+ fails += check_proc ("ssse3", HAS_CPU_FEATURE (SSSE3),
|
|
|
|
+ "HAS_CPU_FEATURE (SSSE3)");
|
|
|
|
+ fails += check_proc ("popcnt", HAS_CPU_FEATURE (POPCOUNT),
|
|
|
|
+ "HAS_CPU_FEATURE (POPCOUNT)");
|
|
|
|
|
|
|
|
printf ("%d differences between /proc/cpuinfo and glibc code.\n", fails);
|
|
|
|
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/wcscpy.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/wcscpy.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/wcscpy.S
|
|
|
|
@@ -27,11 +27,8 @@
|
|
|
|
.text
|
|
|
|
ENTRY(wcscpy)
|
|
|
|
.type wcscpy, @gnu_indirect_function
|
|
|
|
- cmpl $0, KIND_OFFSET+__cpu_features(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-
|
|
|
|
-1: testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jnz 2f
|
|
|
|
leaq __wcscpy_sse2(%rip), %rax
|
|
|
|
ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/wmemcmp.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/wmemcmp.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/wmemcmp.S
|
|
|
|
@@ -26,16 +26,13 @@
|
|
|
|
.text
|
|
|
|
ENTRY(wmemcmp)
|
|
|
|
.type wmemcmp, @gnu_indirect_function
|
|
|
|
- cmpl $0, KIND_OFFSET+__cpu_features(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-
|
|
|
|
-1: testl $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ HAS_CPU_FEATURE (SSSE3)
|
|
|
|
jnz 2f
|
|
|
|
leaq __wmemcmp_sse2(%rip), %rax
|
|
|
|
ret
|
|
|
|
|
|
|
|
-2: testl $bit_SSE4_1, __cpu_features+CPUID_OFFSET+index_SSE4_1(%rip)
|
|
|
|
+2: HAS_CPU_FEATURE (SSE4_1)
|
|
|
|
jz 3f
|
|
|
|
leaq __wmemcmp_sse4_1(%rip), %rax
|
|
|
|
ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/rawmemchr.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/rawmemchr.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/rawmemchr.S
|
|
|
|
@@ -27,12 +27,10 @@
|
|
|
|
.text
|
|
|
|
ENTRY(rawmemchr)
|
|
|
|
.type rawmemchr, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: testl $bit_Prefer_PMINUB_for_stringop, __cpu_features+FEATURE_OFFSET+index_Prefer_PMINUB_for_stringop(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ HAS_ARCH_FEATURE (Prefer_PMINUB_for_stringop)
|
|
|
|
jnz 2f
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jz 2f
|
|
|
|
leaq __rawmemchr_sse42(%rip), %rax
|
|
|
|
ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strlen.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strlen.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strlen.S
|
|
|
|
@@ -29,18 +29,16 @@
|
|
|
|
.text
|
|
|
|
ENTRY(strlen)
|
|
|
|
.type strlen, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __strlen_sse2_pminub(%rip), %rax
|
|
|
|
- testl $bit_Prefer_PMINUB_for_stringop, __cpu_features+FEATURE_OFFSET+index_Prefer_PMINUB_for_stringop(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __strlen_sse2_pminub(%rip), %rax
|
|
|
|
+ HAS_ARCH_FEATURE (Prefer_PMINUB_for_stringop)
|
|
|
|
jnz 2f
|
|
|
|
leaq __strlen_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jz 2f
|
|
|
|
leaq __strlen_sse42(%rip), %rax
|
|
|
|
ret
|
|
|
|
-2: testl $bit_Slow_BSF, __cpu_features+FEATURE_OFFSET+index_Slow_BSF(%rip)
|
|
|
|
+2: HAS_ARCH_FEATURE (Slow_BSF)
|
|
|
|
jz 3f
|
|
|
|
leaq __strlen_sse2_no_bsf(%rip), %rax
|
|
|
|
3: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strnlen.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strnlen.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strnlen.S
|
|
|
|
@@ -27,11 +27,9 @@
|
|
|
|
.text
|
|
|
|
ENTRY(__strnlen)
|
|
|
|
.type __strnlen, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __strnlen_sse2(%rip), %rax
|
|
|
|
- testl $bit_Slow_BSF, __cpu_features+FEATURE_OFFSET+index_Slow_BSF(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __strnlen_sse2(%rip), %rax
|
|
|
|
+ HAS_ARCH_FEATURE (Slow_BSF)
|
|
|
|
jz 2f
|
|
|
|
leaq __strnlen_sse2_no_bsf(%rip), %rax
|
|
|
|
2: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strrchr.S
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strrchr.S
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strrchr.S
|
|
|
|
@@ -28,15 +28,13 @@
|
|
|
|
.text
|
|
|
|
ENTRY(strrchr)
|
|
|
|
.type strrchr, @gnu_indirect_function
|
|
|
|
- cmpl $0, __cpu_features+KIND_OFFSET(%rip)
|
|
|
|
- jne 1f
|
|
|
|
- call __init_cpu_features
|
|
|
|
-1: leaq __strrchr_sse2(%rip), %rax
|
|
|
|
- testl $bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
|
|
|
|
+ LOAD_RTLD_GLOBAL_RO_RDX
|
|
|
|
+ leaq __strrchr_sse2(%rip), %rax
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2)
|
|
|
|
jz 2f
|
|
|
|
leaq __strrchr_sse42(%rip), %rax
|
|
|
|
ret
|
|
|
|
-2: testl $bit_Slow_BSF, __cpu_features+FEATURE_OFFSET+index_Slow_BSF(%rip)
|
|
|
|
+2: HAS_ARCH_FEATURE (Slow_BSF)
|
|
|
|
jz 3f
|
|
|
|
leaq __strrchr_sse2_no_bsf(%rip), %rax
|
|
|
|
3: ret
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcasestr-c.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strcasestr-c.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strcasestr-c.c
|
|
|
|
@@ -12,8 +12,8 @@ extern __typeof (__strcasestr_sse2) __st
|
|
|
|
|
|
|
|
#if 1
|
|
|
|
libc_ifunc (__strcasestr,
|
|
|
|
- HAS_SSE4_2 && !use_unaligned_strstr () ? __strcasestr_sse42 :
|
|
|
|
- __strcasestr_sse2);
|
|
|
|
+ HAS_CPU_FEATURE (SSE4_2) && !use_unaligned_strstr ()
|
|
|
|
+ ? __strcasestr_sse42 : __strcasestr_sse2);
|
|
|
|
#else
|
|
|
|
libc_ifunc (__strcasestr,
|
|
|
|
0 ? __strcasestr_sse42 : __strcasestr_sse2);
|
|
|
|
Index: glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strstr-c.c
|
|
|
|
===================================================================
|
|
|
|
--- glibc-2.17-c758a686.orig/sysdeps/x86_64/multiarch/strstr-c.c
|
|
|
|
+++ glibc-2.17-c758a686/sysdeps/x86_64/multiarch/strstr-c.c
|
|
|
|
@@ -42,7 +42,7 @@ extern __typeof (__redirect_strstr) __st
|
|
|
|
/* Avoid DWARF definition DIE on ifunc symbol so that GDB can handle
|
|
|
|
ifunc symbol properly. */
|
|
|
|
extern __typeof (__redirect_strstr) __libc_strstr;
|
|
|
|
-libc_ifunc (__libc_strstr, HAS_SSE4_2 ? (use_unaligned_strstr () ?
|
|
|
|
+libc_ifunc (__libc_strstr, HAS_CPU_FEATURE (SSE4_2) ? (use_unaligned_strstr () ?
|
|
|
|
__strstr_sse2_unaligned :
|
|
|
|
__strstr_sse42) : __strstr_sse2)
|
|
|
|
|