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>.

	* sysdeps/x86_64/fpu/multiarch/e_asin.c: Replace HAS_XXX with
	HAS_CPU_FEATURE/HAS_ARCH_FEATURE (XXX).
	* sysdeps/x86_64/fpu/multiarch/e_atan2.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/e_exp.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/e_log.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/e_pow.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_atan.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_fma.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_fmaf.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_sin.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_tan.c: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_ceil.S: Use
	LOAD_RTLD_GLOBAL_RO_RDX and HAS_CPU_FEATURE (SSE4_1).
	* sysdeps/x86_64/fpu/multiarch/s_ceilf.S: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_floor.S: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_floorf.S: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_nearbyint.S : Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_rintf.S: Likewise.
	* sysdeps/x86_64/fpu/multiarch/s_rintf.S : Likewise.
	* sysdeps/x86_64/multiarch/ifunc-impl-list.c: Likewise.
	* sysdeps/x86_64/multiarch/sched_cpucount.c: Likewise.
	* sysdeps/x86_64/multiarch/strstr.c: Likewise.
	* sysdeps/x86_64/multiarch/memmove.c: Likewise.
	* sysdeps/x86_64/multiarch/memmove_chk.c: Likewise.
	* sysdeps/x86_64/multiarch/test-multiarch.c: Likewise.
	* sysdeps/x86_64/multiarch/memcmp.S: Remove __init_cpu_features
	call.  Add LOAD_RTLD_GLOBAL_RO_RDX.  Replace HAS_XXX with
	HAS_CPU_FEATURE/HAS_ARCH_FEATURE (XXX).
	* sysdeps/x86_64/multiarch/memcpy.S: Likewise.
	* sysdeps/x86_64/multiarch/memcpy_chk.S: Likewise.
	* sysdeps/x86_64/multiarch/mempcpy.S: Likewise.
	* sysdeps/x86_64/multiarch/mempcpy_chk.S: Likewise.
	* sysdeps/x86_64/multiarch/memset.S: Likewise.
	* sysdeps/x86_64/multiarch/memset_chk.S: Likewise.
	* sysdeps/x86_64/multiarch/strcat.S: Likewise.
	* sysdeps/x86_64/multiarch/strchr.S: Likewise.
	* sysdeps/x86_64/multiarch/strcmp.S: Likewise.
	* sysdeps/x86_64/multiarch/strcpy.S: Likewise.
	* sysdeps/x86_64/multiarch/strcspn.S: Likewise.
	* sysdeps/x86_64/multiarch/strspn.S: Likewise.
	* sysdeps/x86_64/multiarch/wcscpy.S: Likewise.
	* sysdeps/x86_64/multiarch/wmemcmp.S: Likewise.

39 files changed, 246 insertions, 233 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/e_asin.c b/sysdeps/x86_64/fpu/multiarch/e_asin.c
index e742a9c..5a9091b 100644
--- a/sysdeps/x86_64/fpu/multiarch/e_asin.c
+++ b/sysdeps/x86_64/fpu/multiarch/e_asin.c
@@ -8,11 +8,15 @@ extern double __ieee754_acos_fma4 (double);
 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
diff --git a/sysdeps/x86_64/fpu/multiarch/e_atan2.c b/sysdeps/x86_64/fpu/multiarch/e_atan2.c
index 6867c6e..a865ed6 100644
--- a/sysdeps/x86_64/fpu/multiarch/e_atan2.c
+++ b/sysdeps/x86_64/fpu/multiarch/e_atan2.c
@@ -7,14 +7,15 @@ extern double __ieee754_atan2_avx (double, double);
 # 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
diff --git a/sysdeps/x86_64/fpu/multiarch/e_exp.c b/sysdeps/x86_64/fpu/multiarch/e_exp.c
index d244954..9c124ca 100644
--- a/sysdeps/x86_64/fpu/multiarch/e_exp.c
+++ b/sysdeps/x86_64/fpu/multiarch/e_exp.c
@@ -8,14 +8,15 @@ 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
diff --git a/sysdeps/x86_64/fpu/multiarch/e_log.c b/sysdeps/x86_64/fpu/multiarch/e_log.c
index 05f3668..bf932c6 100644
--- a/sysdeps/x86_64/fpu/multiarch/e_log.c
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/e_pow.c b/sysdeps/x86_64/fpu/multiarch/e_pow.c
index 433cce0..6d422d6 100644
--- a/sysdeps/x86_64/fpu/multiarch/e_pow.c
+++ b/sysdeps/x86_64/fpu/multiarch/e_pow.c
@@ -6,7 +6,10 @@
 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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_atan.c b/sysdeps/x86_64/fpu/multiarch/s_atan.c
index ae16d7c..57b5c65 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_atan.c
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_ceil.S b/sysdeps/x86_64/fpu/multiarch/s_ceil.S
index 00ecede..c1b9026 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_ceil.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_ceilf.S b/sysdeps/x86_64/fpu/multiarch/s_ceilf.S
index c8ed705..7809e03 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_ceilf.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_floor.S b/sysdeps/x86_64/fpu/multiarch/s_floor.S
index 952ffaa..fa3f98e 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_floor.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_floorf.S b/sysdeps/x86_64/fpu/multiarch/s_floorf.S
index c8231e8..f60f662 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_floorf.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_fma.c b/sysdeps/x86_64/fpu/multiarch/s_fma.c
index 0963a0b..78e7732 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_fma.c
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_fmaf.c b/sysdeps/x86_64/fpu/multiarch/s_fmaf.c
index 6046961..bebd3ee 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_fmaf.c
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_nearbyint.S b/sysdeps/x86_64/fpu/multiarch/s_nearbyint.S
index b5d32b5..109395c 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_nearbyint.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S b/sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S
index cd7e177..b870c0c 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_nearbyintf.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_rint.S b/sysdeps/x86_64/fpu/multiarch/s_rint.S
index f52cef6..b238d49 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_rint.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_rintf.S b/sysdeps/x86_64/fpu/multiarch/s_rintf.S
index e2608d4..8869196 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_rintf.S
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_sin.c b/sysdeps/x86_64/fpu/multiarch/s_sin.c
index a0c2521..3bc7330 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_sin.c
+++ b/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
diff --git a/sysdeps/x86_64/fpu/multiarch/s_tan.c b/sysdeps/x86_64/fpu/multiarch/s_tan.c
index 904308f..d99d9db 100644
--- a/sysdeps/x86_64/fpu/multiarch/s_tan.c
+++ b/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
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index b64e4f1..f5a576c 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -39,48 +39,57 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 
   /* 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_AVX,
+	      IFUNC_IMPL_ADD (array, i, __memmove_chk,
+			      HAS_ARCH_FEATURE (AVX_Usable),
 			      __memmove_chk_avx_unaligned)
-	      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_AVX,
+	      IFUNC_IMPL_ADD (array, i, memmove,
+			      HAS_ARCH_FEATURE (AVX_Usable),
 			      __memmove_avx_unaligned)
-	      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))
 
 #ifdef HAVE_AVX2_SUPPORT
   /* Support sysdeps/x86_64/multiarch/memset_chk.S.  */
   IFUNC_IMPL (i, name, __memset_chk,
-	      IFUNC_IMPL_ADD (array, i, __memset_chk, 1, __memset_chk_sse2)
-	      IFUNC_IMPL_ADD (array, i, __memset_chk, HAS_AVX2,
+	      IFUNC_IMPL_ADD (array, i, __memset_chk, 1,
+			      __memset_chk_sse2)
+	      IFUNC_IMPL_ADD (array, i, __memset_chk,
+			      HAS_ARCH_FEATURE (AVX2_Usable),
 			      __memset_chk_avx2))
 
   /* Support sysdeps/x86_64/multiarch/memset.S.  */
   IFUNC_IMPL (i, name, memset,
 	      IFUNC_IMPL_ADD (array, i, memset, 1, __memset_sse2)
-	      IFUNC_IMPL_ADD (array, i, memset, HAS_AVX2, __memset_avx2))
+	      IFUNC_IMPL_ADD (array, i, memset,
+			      HAS_ARCH_FEATURE (AVX2_Usable),
+			      __memset_avx2))
 #endif
 
   /* 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)
@@ -88,27 +97,34 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 
   /* 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))
@@ -119,7 +135,8 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 
   /* 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))
 
@@ -130,48 +147,57 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 
   /* 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_unaligned)
 	      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)
@@ -179,7 +205,7 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 
   /* 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)
@@ -187,14 +213,15 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 
   /* 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/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.  */
@@ -204,65 +231,75 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 
   /* 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_AVX,
+	      IFUNC_IMPL_ADD (array, i, __memcpy_chk,
+			      HAS_ARCH_FEATURE (AVX_Usable),
 			      __memcpy_chk_avx_unaligned)
-	      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_AVX,
+	      IFUNC_IMPL_ADD (array, i, memcpy,
+			      HAS_ARCH_FEATURE (AVX_Usable),
 			      __memcpy_avx_unaligned)
-	      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_unaligned)
 	      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_AVX,
+	      IFUNC_IMPL_ADD (array, i, __mempcpy_chk,
+			      HAS_ARCH_FEATURE (AVX_Usable),
 			      __mempcpy_chk_avx_unaligned)
-	      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_AVX,
+	      IFUNC_IMPL_ADD (array, i, mempcpy,
+			      HAS_ARCH_FEATURE (AVX_Usable),
 			      __mempcpy_avx_unaligned)
-	      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/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
diff --git a/sysdeps/x86_64/multiarch/memcmp.S b/sysdeps/x86_64/multiarch/memcmp.S
index f8b4636..871a081 100644
--- a/sysdeps/x86_64/multiarch/memcmp.S
+++ b/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
diff --git a/sysdeps/x86_64/multiarch/memcpy.S b/sysdeps/x86_64/multiarch/memcpy.S
index 4e18cd3..7e119d3 100644
--- a/sysdeps/x86_64/multiarch/memcpy.S
+++ b/sysdeps/x86_64/multiarch/memcpy.S
@@ -29,19 +29,17 @@
 	.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_avx_unaligned(%rip), %rax
-	testl	$bit_AVX_Fast_Unaligned_Load, __cpu_features+FEATURE_OFFSET+index_AVX_Fast_Unaligned_Load(%rip)
+	LOAD_RTLD_GLOBAL_RO_RDX
+	leaq	__memcpy_avx_unaligned(%rip), %rax
+	HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
 	jz 1f
 	ret
 1:	leaq	__memcpy_sse2(%rip), %rax
-	testl	$bit_Slow_BSF, __cpu_features+FEATURE_OFFSET+index_Slow_BSF(%rip)
+	HAS_ARCH_FEATURE (Slow_BSF)
 	jnz	2f
 	leaq	__memcpy_sse2_unaligned(%rip), %rax
 	ret
-2:	testl   $bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
+2:	HAS_CPU_FEATURE (SSSE3)
 	jz 3f
 	leaq    __memcpy_ssse3(%rip), %rax
 3:	ret
diff --git a/sysdeps/x86_64/multiarch/memcpy_chk.S b/sysdeps/x86_64/multiarch/memcpy_chk.S
index 1e756ea..81f83dd 100644
--- a/sysdeps/x86_64/multiarch/memcpy_chk.S
+++ b/sysdeps/x86_64/multiarch/memcpy_chk.S
@@ -29,17 +29,15 @@
 	.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
-	testl   $bit_AVX_Fast_Unaligned_Load, __cpu_features+FEATURE_OFFSET+index_AVX_Fast_Unaligned_Load(%rip)
+	HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
 	jz  2f
 	leaq    __memcpy_chk_avx_unaligned(%rip), %rax
 2:	ret
diff --git a/sysdeps/x86_64/multiarch/memmove.c b/sysdeps/x86_64/multiarch/memmove.c
index dd153a3..bbddbc1 100644
--- a/sysdeps/x86_64/multiarch/memmove.c
+++ b/sysdeps/x86_64/multiarch/memmove.c
@@ -49,10 +49,10 @@ extern __typeof (__redirect_memmove) __memmove_avx_unaligned attribute_hidden;
    ifunc symbol properly.  */
 extern __typeof (__redirect_memmove) __libc_memmove;
 libc_ifunc (__libc_memmove,
-	    HAS_AVX_FAST_UNALIGNED_LOAD
+	    HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
 	    ? __memmove_avx_unaligned
-	    : (HAS_SSSE3
-	       ? (HAS_FAST_COPY_BACKWARD
+	    : (HAS_CPU_FEATURE (SSSE3)
+	       ? (HAS_ARCH_FEATURE (Fast_Copy_Backward)
 	          ? __memmove_ssse3_back : __memmove_ssse3)
 	       : __memmove_sse2));
 
diff --git a/sysdeps/x86_64/multiarch/memmove_chk.c b/sysdeps/x86_64/multiarch/memmove_chk.c
index 8b12d00..5f70e3a 100644
--- a/sysdeps/x86_64/multiarch/memmove_chk.c
+++ b/sysdeps/x86_64/multiarch/memmove_chk.c
@@ -30,8 +30,8 @@ extern __typeof (__memmove_chk) __memmove_chk_avx_unaligned attribute_hidden;
 #include "debug/memmove_chk.c"
 
 libc_ifunc (__memmove_chk,
-	    HAS_AVX_FAST_UNALIGNED_LOAD ? __memmove_chk_avx_unaligned :
-	    (HAS_SSSE3
-	    ? (HAS_FAST_COPY_BACKWARD
+	    HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load) ? __memmove_chk_avx_unaligned :
+	    (HAS_CPU_FEATURE (SSSE3)
+	    ? (HAS_ARCH_FEATURE (Fast_Copy_Backward)
 	       ? __memmove_chk_ssse3_back : __memmove_chk_ssse3)
 	    : __memmove_chk_sse2));
diff --git a/sysdeps/x86_64/multiarch/mempcpy.S b/sysdeps/x86_64/multiarch/mempcpy.S
index 2eaacdf..ad36840 100644
--- a/sysdeps/x86_64/multiarch/mempcpy.S
+++ b/sysdeps/x86_64/multiarch/mempcpy.S
@@ -27,17 +27,15 @@
 #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
-	testl	$bit_AVX_Fast_Unaligned_Load, __cpu_features+FEATURE_OFFSET+index_AVX_Fast_Unaligned_Load(%rip)
+	HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
 	jz	2f
 	leaq	__mempcpy_avx_unaligned(%rip), %rax
 2:	ret
diff --git a/sysdeps/x86_64/multiarch/mempcpy_chk.S b/sysdeps/x86_64/multiarch/mempcpy_chk.S
index 17b8470..0a46b56 100644
--- a/sysdeps/x86_64/multiarch/mempcpy_chk.S
+++ b/sysdeps/x86_64/multiarch/mempcpy_chk.S
@@ -29,17 +29,15 @@
 	.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
-	testl	$bit_AVX_Fast_Unaligned_Load, __cpu_features+FEATURE_OFFSET+index_AVX_Fast_Unaligned_Load(%rip)
+	HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
 	jz	2f
 	leaq	__mempcpy_chk_avx_unaligned(%rip), %rax
 2:	ret
diff --git a/sysdeps/x86_64/multiarch/memset.S b/sysdeps/x86_64/multiarch/memset.S
index c5f1fb3..16fefa7 100644
--- a/sysdeps/x86_64/multiarch/memset.S
+++ b/sysdeps/x86_64/multiarch/memset.S
@@ -26,11 +26,9 @@
 # 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_sse2(%rip), %rax
-	testl	$bit_AVX2_Usable, __cpu_features+FEATURE_OFFSET+index_AVX2_Usable(%rip)
+	LOAD_RTLD_GLOBAL_RO_RDX
+	leaq	__memset_sse2(%rip), %rax
+	HAS_ARCH_FEATURE (AVX2_Usable)
 	jz	2f
 	leaq	__memset_avx2(%rip), %rax
 2:	ret
diff --git a/sysdeps/x86_64/multiarch/memset_chk.S b/sysdeps/x86_64/multiarch/memset_chk.S
index 64fed31..ef8c64f 100644
--- a/sysdeps/x86_64/multiarch/memset_chk.S
+++ b/sysdeps/x86_64/multiarch/memset_chk.S
@@ -25,11 +25,9 @@
 # if defined SHARED && defined HAVE_AVX2_SUPPORT
 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_sse2(%rip), %rax
-	testl	$bit_AVX2_Usable, __cpu_features+FEATURE_OFFSET+index_AVX2_Usable(%rip)
+	LOAD_RTLD_GLOBAL_RO_RDX
+	leaq	__memset_chk_sse2(%rip), %rax
+	HAS_ARCH_FEATURE (AVX2_Usable)
 	jz	2f
 	leaq	__memset_chk_avx2(%rip), %rax
 2:	ret
diff --git a/sysdeps/x86_64/multiarch/sched_cpucount.c b/sysdeps/x86_64/multiarch/sched_cpucount.c
index 72ad7b0..e9391a2 100644
--- a/sysdeps/x86_64/multiarch/sched_cpucount.c
+++ b/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);
diff --git a/sysdeps/x86_64/multiarch/strcat.S b/sysdeps/x86_64/multiarch/strcat.S
index 44993fa..25d926c 100644
--- a/sysdeps/x86_64/multiarch/strcat.S
+++ b/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
diff --git a/sysdeps/x86_64/multiarch/strchr.S b/sysdeps/x86_64/multiarch/strchr.S
index af55fac..0c5fdd9 100644
--- a/sysdeps/x86_64/multiarch/strchr.S
+++ b/sysdeps/x86_64/multiarch/strchr.S
@@ -25,11 +25,9 @@
 	.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
-2:	testl	$bit_Slow_BSF, __cpu_features+FEATURE_OFFSET+index_Slow_BSF(%rip)
+	LOAD_RTLD_GLOBAL_RO_RDX
+	leaq	__strchr_sse2(%rip), %rax
+2:	HAS_ARCH_FEATURE (Slow_BSF)
 	jz	3f
 	leaq    __strchr_sse2_no_bsf(%rip), %rax
 3:	ret
diff --git a/sysdeps/x86_64/multiarch/strcmp.S b/sysdeps/x86_64/multiarch/strcmp.S
index f50f26c..c180ce6 100644
--- a/sysdeps/x86_64/multiarch/strcmp.S
+++ b/sysdeps/x86_64/multiarch/strcmp.S
@@ -84,24 +84,20 @@
 	.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
 #ifdef USE_AS_STRCMP
 	leaq	__strcmp_sse2_unaligned(%rip), %rax
-	testl   $bit_Fast_Unaligned_Load, __cpu_features+FEATURE_OFFSET+index_Fast_Unaligned_Load(%rip)
+	HAS_ARCH_FEATURE (Fast_Unaligned_Load)
 	jnz     3f
 #else
-	testl	$bit_Slow_SSE4_2, __cpu_features+FEATURE_OFFSET+index_Slow_SSE4_2(%rip)
+	HAS_ARCH_FEATURE (Slow_SSE4_2)
 	jnz	2f
 	leaq	STRCMP_SSE42(%rip), %rax
-	testl	$bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
+	HAS_CPU_FEATURE (SSE4_2)
 	jnz	3f
 #endif
 2:	leaq	STRCMP_SSSE3(%rip), %rax
-	testl	$bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
+	HAS_CPU_FEATURE (SSSE3)
 	jnz	3f
 	leaq	STRCMP_SSE2(%rip), %rax
 3:	ret
@@ -110,23 +106,19 @@ 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	3f
 #  endif
-	testl	$bit_Slow_SSE4_2, __cpu_features+FEATURE_OFFSET+index_Slow_SSE4_2(%rip)
+	HAS_ARCH_FEATURE (Slow_SSE4_2)
 	jnz	2f
 	leaq	__strcasecmp_sse42(%rip), %rax
-	testl	$bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
+	HAS_CPU_FEATURE (SSE4_2)
 	jnz	3f
 2:	leaq	__strcasecmp_ssse3(%rip), %rax
-	testl	$bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
+	HAS_CPU_FEATURE (SSSE3)
 	jnz	3f
 	leaq	__strcasecmp_sse2(%rip), %rax
 3:	ret
@@ -136,23 +128,19 @@ 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	3f
 #  endif
-	testl	$bit_Slow_SSE4_2, __cpu_features+FEATURE_OFFSET+index_Slow_SSE4_2(%rip)
+	HAS_ARCH_FEATURE (Slow_SSE4_2)
 	jnz	2f
 	leaq	__strncasecmp_sse42(%rip), %rax
-	testl	$bit_SSE4_2, __cpu_features+CPUID_OFFSET+index_SSE4_2(%rip)
+	HAS_CPU_FEATURE (SSE4_2)
 	jnz	3f
 2:	leaq	__strncasecmp_ssse3(%rip), %rax
-	testl	$bit_SSSE3, __cpu_features+CPUID_OFFSET+index_SSSE3(%rip)
+	HAS_CPU_FEATURE (SSSE3)
 	jnz	3f
 	leaq	__strncasecmp_sse2(%rip), %rax
 3:	ret
diff --git a/sysdeps/x86_64/multiarch/strcpy.S b/sysdeps/x86_64/multiarch/strcpy.S
index 9464ee8..3aae8ee 100644
--- a/sysdeps/x86_64/multiarch/strcpy.S
+++ b/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
diff --git a/sysdeps/x86_64/multiarch/strcspn.S b/sysdeps/x86_64/multiarch/strcspn.S
index 00e4617..9c3af5b 100644
--- a/sysdeps/x86_64/multiarch/strcspn.S
+++ b/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
diff --git a/sysdeps/x86_64/multiarch/strspn.S b/sysdeps/x86_64/multiarch/strspn.S
index aea8e4c..684f730 100644
--- a/sysdeps/x86_64/multiarch/strspn.S
+++ b/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
diff --git a/sysdeps/x86_64/multiarch/strstr.c b/sysdeps/x86_64/multiarch/strstr.c
index 507994b..b8827f0 100644
--- a/sysdeps/x86_64/multiarch/strstr.c
+++ b/sysdeps/x86_64/multiarch/strstr.c
@@ -41,7 +41,10 @@ extern __typeof (__redirect_strstr) __strstr_sse2 attribute_hidden;
 /* 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_FAST_UNALIGNED_LOAD ? __strstr_sse2_unaligned : __strstr_sse2)
+libc_ifunc (__libc_strstr,
+	    HAS_ARCH_FEATURE (Fast_Unaligned_Load)
+	    ? __strstr_sse2_unaligned
+	    : __strstr_sse2)
 
 #undef strstr
 strong_alias (__libc_strstr, strstr)
diff --git a/sysdeps/x86_64/multiarch/test-multiarch.c b/sysdeps/x86_64/multiarch/test-multiarch.c
index 949d26e..e893894 100644
--- a/sysdeps/x86_64/multiarch/test-multiarch.c
+++ b/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);
 
diff --git a/sysdeps/x86_64/multiarch/wcscpy.S b/sysdeps/x86_64/multiarch/wcscpy.S
index ff2f5a7..c47c51c 100644
--- a/sysdeps/x86_64/multiarch/wcscpy.S
+++ b/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
diff --git a/sysdeps/x86_64/multiarch/wmemcmp.S b/sysdeps/x86_64/multiarch/wmemcmp.S
index 109e245..62215f4 100644
--- a/sysdeps/x86_64/multiarch/wmemcmp.S
+++ b/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