Fix issues in x86 memcmp-ssse3.S

diff --git a/ChangeLog b/ChangeLog
index 84196ee37dcf4bcd2957df72e1d8e5fdd59315ce..bbf54aa2c3693fe372475e5ba9b05451b8329082 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,8 @@
+2010-03-18  H.J. Lu  <hongjiu.lu@intel.com>
+
+       * sysdeps/i386/i686/multiarch/memcmp-ssse3.S: Update %xmm3
+       when exit from loop.
+
 2010-03-09  David S. Miller  <davem@davemloft.net>
 
        * sysdeps/sparc/sparc64/dl-machine.h (elf_machine_rela): Handling

diff --git a/sysdeps/i386/i686/multiarch/memcmp-ssse3.S b/sysdeps/i386/i686/multiarch/memcmp-ssse3.S
index d2f852f7266a188631b480ec9824899d3372061a..2e0d15fe55de0a11d93b3cf39f839756785afb3d 100644 (file)
--- a/sysdeps/i386/i686/multiarch/memcmp-ssse3.S
+++ b/sysdeps/i386/i686/multiarch/memcmp-ssse3.S
@@ -269,6 +269,7 @@ L(shr_1_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_1_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_1_gobble_next)
@@ -352,6 +353,7 @@ L(shr_2_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_2_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_2_gobble_next)
@@ -434,6 +436,7 @@ L(shr_3_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_3_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_3_gobble_next)
@@ -516,6 +519,7 @@ L(shr_4_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_4_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_4_gobble_next)
@@ -598,6 +602,7 @@ L(shr_5_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_5_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_5_gobble_next)
@@ -680,6 +685,7 @@ L(shr_6_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_6_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_6_gobble_next)
@@ -762,6 +768,7 @@ L(shr_7_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_7_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_7_gobble_next)
@@ -844,6 +851,7 @@ L(shr_8_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_8_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_8_gobble_next)
@@ -926,6 +934,7 @@ L(shr_9_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_9_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_9_gobble_next)
@@ -1008,6 +1017,7 @@ L(shr_10_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_10_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_10_gobble_next)
@@ -1090,6 +1100,7 @@ L(shr_11_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_11_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_11_gobble_next)
@@ -1172,6 +1183,7 @@ L(shr_12_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_12_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_12_gobble_next)
@@ -1254,6 +1266,7 @@ L(shr_13_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_13_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_13_gobble_next)
@@ -1336,6 +1349,7 @@ L(shr_14_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_14_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_14_gobble_next)
@@ -1418,6 +1432,7 @@ L(shr_15_gobble_loop):
 
        lea     32(%edi), %edi
        jz      L(shr_15_gobble_loop)
+       pand    %xmm0, %xmm3
 
        cmp     $0, %ecx
        jge     L(shr_15_gobble_next)