Align functions to 16-byte boundary.

Some of the new multi-arch string functions for x86-64 were
not aligned to 16 byte boundarie,s possibly creating unnecessary
cache line misses and delays.

diff --git a/ChangeLog b/ChangeLog
index 53fcf2a1f8574cced262048ddc0b7cd487c322dd..8b02c0cba52fa357906315437499122f35cc4410 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,11 @@
+2009-07-03  Ulrich Drepper  <drepper@redhat.com>
+
+       * sysdeps/x86_64/multiarch/strcmp.S: Make sure functions are all
+       aligned to 16 byte boundaries.
+       * sysdeps/x86_64/multiarch/strcpy.S: Likewise.
+       * sysdeps/x86_64/multiarch/strlen.S: Likewise.
+       * sysdeps/x86_64/multiarch/rawmemchr.S: Likewise.
+
 2009-07-02  H.J. Lu  <hongjiu.lu@intel.com>
 
        * config.h.in (HAVE_SSE4_SUPPORT): New macro.

diff --git a/sysdeps/x86_64/multiarch/rawmemchr.S b/sysdeps/x86_64/multiarch/rawmemchr.S
index 93ca631633438542b05dc6963d4909ec5aebda33..d4f265f430035cf0e55e3c4f75001d2a276886fe 100644 (file)
--- a/sysdeps/x86_64/multiarch/rawmemchr.S
+++ b/sysdeps/x86_64/multiarch/rawmemchr.S
@@ -77,6 +77,7 @@ __rawmemchr_sse42:
 # undef ENTRY
 # define ENTRY(name) \
        .type __rawmemchr_sse2, @function; \
+       .align 16; \
        __rawmemchr_sse2: cfi_startproc; \
        CALL_MCOUNT
 # undef END

diff --git a/sysdeps/x86_64/multiarch/strcmp.S b/sysdeps/x86_64/multiarch/strcmp.S
index 2f4bf17d956df9441a8b976c46eb044d09dc3f74..37985036aa16fb98683f2e41879bfdc3a79790c9 100644 (file)
--- a/sysdeps/x86_64/multiarch/strcmp.S
+++ b/sysdeps/x86_64/multiarch/strcmp.S
@@ -1659,6 +1659,7 @@ LABEL(unaligned_table):
 # undef ENTRY
 # define ENTRY(name) \
        .type STRCMP_SSE2, @function; \
+       .align 16; \
        STRCMP_SSE2: cfi_startproc; \
        CALL_MCOUNT
 # undef END

diff --git a/sysdeps/x86_64/multiarch/strcpy.S b/sysdeps/x86_64/multiarch/strcpy.S
index 9920b0ec74b7c25660573fc548183409553e2eb5..25cd01307dfdbcb78b3447bfb3b45285ab0d982e 100644 (file)
--- a/sysdeps/x86_64/multiarch/strcpy.S
+++ b/sysdeps/x86_64/multiarch/strcpy.S
@@ -1896,6 +1896,7 @@ LABEL(unaligned_table):
 # undef ENTRY
 # define ENTRY(name) \
        .type STRCPY_SSE2, @function; \
+       .align 16; \
        STRCPY_SSE2: cfi_startproc; \
        CALL_MCOUNT
 # undef END

diff --git a/sysdeps/x86_64/multiarch/strlen.S b/sysdeps/x86_64/multiarch/strlen.S
index 79e6a977ecf082f1c8157f3accaff60f000f4a01..82b03ccc28ceb9173b2b0d0fb632960dae9bff36 100644 (file)
--- a/sysdeps/x86_64/multiarch/strlen.S
+++ b/sysdeps/x86_64/multiarch/strlen.S
@@ -77,6 +77,7 @@ __strlen_sse42:
 # undef ENTRY
 # define ENTRY(name) \
        .type __strlen_sse2, @function; \
+       .align 16; \
        __strlen_sse2: cfi_startproc; \
        CALL_MCOUNT
 # undef END