Load cache sizes into R11_LP/R8_LP

diff --git a/ChangeLog b/ChangeLog
index 51b0bd5..079b1a9 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,11 @@
 2012-05-15  H.J. Lu  <hongjiu.lu@intel.com>
 
+       * sysdeps/x86_64/memcpy.S: Load __x86_64_data_cache_size_half
+       into R11_LP and load __x86_64_shared_cache_size_half into
+       R8_LP.
+
+2012-05-15  H.J. Lu  <hongjiu.lu@intel.com>
+
        * sysdeps/x86_64/multiarch/memcmp-sse4.S: Load cache size into
        R8_LP.
 

diff --git a/sysdeps/x86_64/memcpy.S b/sysdeps/x86_64/memcpy.S
index d74e532..9e693f2 100644 (file)
--- a/sysdeps/x86_64/memcpy.S
+++ b/sysdeps/x86_64/memcpy.S
@@ -254,7 +254,7 @@ L(32after):
 
 L(fasttry):                            /* first 1/2 L1 */
 #ifndef NOT_IN_libc                    /* only up to this algorithm outside of libc.so */
-       movq    __x86_64_data_cache_size_half(%rip), %r11
+       mov     __x86_64_data_cache_size_half(%rip), %R11_LP
        cmpq    %rdx, %r11              /* calculate the smaller of */
        cmovaq  %rdx, %r11              /* remaining bytes and 1/2 L1 */
 #endif
@@ -303,7 +303,7 @@ L(fastafter):
 /* Handle large blocks smaller than 1/2 L2. */
 
 L(pretry):                             /* first 1/2 L2 */
-       movq    __x86_64_shared_cache_size_half (%rip), %r8
+       mov     __x86_64_shared_cache_size_half (%rip), %R8_LP
        cmpq    %rdx, %r8               /* calculate the lesser of */
        cmovaq  %rdx, %r8               /* remaining bytes and 1/2 L2 */