about summary refs log tree commit diff
path: root/sysdeps/x86_64
diff options
context:
space:
mode:
authorOndřej Bílka <neleai@seznam.cz>2014-03-18 11:01:38 +0100
committerOndřej Bílka <neleai@seznam.cz>2015-05-12 20:18:51 +0200
commit0f4840be2528b3e3f2ecea009ab08e753701e9be (patch)
treefc4eafdf024c8eccba2724f48153a6ccc7166121 /sysdeps/x86_64
parent7327b333e56926d7d79bb9e01b839d3618bf750f (diff)
downloadglibc-0f4840be2528b3e3f2ecea009ab08e753701e9be.tar.gz
glibc-0f4840be2528b3e3f2ecea009ab08e753701e9be.tar.xz
glibc-0f4840be2528b3e3f2ecea009ab08e753701e9be.zip
Use strspn/strcspn/strpbrk ifunc in internal calls.
To make a strtok faster and improve performance in general we need to do one
additional change.

A comment:

/* It doesn't make sense to send libc-internal strcspn calls through a PLT.
   The speedup we get from using SSE4.2 instruction is likely eaten away
   by the indirect call in the PLT.  */

Does not make sense at all because nobody bothered to check it. Gap
between these implementations is quite big, when haystack is empty a
sse2 is around 40 cycles slower because it needs to populate a lookup
table and difference only increases with size. That is much bigger than
plt slowdown which is few cycles.

Even benchtest show a gap which also may be reverse by branch
misprediction but my internal benchmark shown.

 simple_strspn stupid_strspn __strspn_sse42  __strspn_sse2
Length    0, alignment  0, acc len  6:  18.6562 35.2344 17.0469 61.6719
Length    6, alignment  0, acc len  6:  59.5469 72.5781 16.4219 73.625

This patch also handles strpbrk which is implemented by including a
x86_64/multiarch/strcspn.S file.

	* sysdeps/x86_64/multiarch/strspn.S: Remove plt indirection.
	* sysdeps/x86_64/multiarch/strcspn.S: Likewise.
Diffstat (limited to 'sysdeps/x86_64')
-rw-r--r--sysdeps/x86_64/multiarch/strcspn.S7
-rw-r--r--sysdeps/x86_64/multiarch/strspn.S6
2 files changed, 0 insertions, 13 deletions
diff --git a/sysdeps/x86_64/multiarch/strcspn.S b/sysdeps/x86_64/multiarch/strcspn.S
index 00e46173ae..95e882c443 100644
--- a/sysdeps/x86_64/multiarch/strcspn.S
+++ b/sysdeps/x86_64/multiarch/strcspn.S
@@ -65,14 +65,7 @@ END(STRCSPN)
 # undef END
 # define END(name) \
 	cfi_endproc; .size STRCSPN_SSE2, .-STRCSPN_SSE2
-# undef libc_hidden_builtin_def
-/* It doesn't make sense to send libc-internal strcspn calls through a PLT.
-   The speedup we get from using SSE4.2 instruction is likely eaten away
-   by the indirect call in the PLT.  */
-# define libc_hidden_builtin_def(name) \
-	.globl __GI_STRCSPN; __GI_STRCSPN = STRCSPN_SSE2
 #endif
-
 #endif /* HAVE_SSE4_SUPPORT */
 
 #ifdef USE_AS_STRPBRK
diff --git a/sysdeps/x86_64/multiarch/strspn.S b/sysdeps/x86_64/multiarch/strspn.S
index aea8e4c945..b734c1729a 100644
--- a/sysdeps/x86_64/multiarch/strspn.S
+++ b/sysdeps/x86_64/multiarch/strspn.S
@@ -50,12 +50,6 @@ END(strspn)
 # undef END
 # define END(name) \
 	cfi_endproc; .size __strspn_sse2, .-__strspn_sse2
-# undef libc_hidden_builtin_def
-/* It doesn't make sense to send libc-internal strspn calls through a PLT.
-   The speedup we get from using SSE4.2 instruction is likely eaten away
-   by the indirect call in the PLT.  */
-# define libc_hidden_builtin_def(name) \
-	.globl __GI_strspn; __GI_strspn = __strspn_sse2
 #endif
 
 #endif /* HAVE_SSE4_SUPPORT */