about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/Makefile
diff options
context:
space:
mode:
authorNoah Goldstein <goldstein.w.n@gmail.com>2022-11-08 17:38:40 -0800
committerNoah Goldstein <goldstein.w.n@gmail.com>2022-11-08 19:22:33 -0800
commit64b8b6516b3cba19dba4c8f4f9b97daa0556fd98 (patch)
tree93e9e1c8bd54c3a10eb9c00db604bd74696adb10 /sysdeps/x86_64/multiarch/Makefile
parent642933158e7cf072d873231b1a9bb03291f2b989 (diff)
downloadglibc-64b8b6516b3cba19dba4c8f4f9b97daa0556fd98.tar.gz
glibc-64b8b6516b3cba19dba4c8f4f9b97daa0556fd98.tar.xz
glibc-64b8b6516b3cba19dba4c8f4f9b97daa0556fd98.zip
x86: Add evex optimized functions for the wchar_t strcpy family
Implemented:
    wcscat-evex  (+ 905 bytes)
    wcscpy-evex  (+ 674 bytes)
    wcpcpy-evex  (+ 709 bytes)
    wcsncpy-evex (+1358 bytes)
    wcpncpy-evex (+1467 bytes)
    wcsncat-evex (+1213 bytes)

Performance Changes:
    Times are from N = 10 runs of the benchmark suite and are reported
    as geometric mean of all ratios of New Implementation / Best Old
    Implementation. Best Old Implementation was determined with the
    highest ISA implementation.

    wcscat-evex     -> 0.991
    wcscpy-evex     -> 0.587
    wcpcpy-evex     -> 0.695
    wcsncpy-evex    -> 0.719
    wcpncpy-evex    -> 0.694
    wcsncat-evex    -> 0.979

Code Size Changes:
    This change  increase the size of libc.so by ~6.3kb bytes. For
    reference the patch optimizing the normal strcpy family functions
    decreases libc.so by ~5.7kb.

Full check passes on x86-64 and build succeeds for all ISA levels w/
and w/o multiarch.
Diffstat (limited to 'sysdeps/x86_64/multiarch/Makefile')
-rw-r--r--sysdeps/x86_64/multiarch/Makefile14
1 files changed, 13 insertions, 1 deletions
diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
index 066bfa48d9..d6e01940c3 100644
--- a/sysdeps/x86_64/multiarch/Makefile
+++ b/sysdeps/x86_64/multiarch/Makefile
@@ -131,6 +131,12 @@ endif
 
 ifeq ($(subdir),wcsmbs)
 sysdep_routines += \
+  wcpcpy-evex \
+  wcpcpy-generic \
+  wcpncpy-evex \
+  wcpncpy-generic \
+  wcscat-evex \
+  wcscat-generic \
   wcschr-avx2 \
   wcschr-avx2-rtm \
   wcschr-evex \
@@ -140,6 +146,8 @@ sysdep_routines += \
   wcscmp-avx2-rtm \
   wcscmp-evex \
   wcscmp-sse2 \
+  wcscpy-evex \
+  wcscpy-generic \
   wcscpy-ssse3 \
   wcslen-avx2 \
   wcslen-avx2-rtm \
@@ -147,9 +155,13 @@ sysdep_routines += \
   wcslen-evex512 \
   wcslen-sse2 \
   wcslen-sse4_1 \
+  wcsncat-evex \
+  wcsncat-generic \
   wcsncmp-avx2 \
   wcsncmp-avx2-rtm \
   wcsncmp-evex \
+  wcsncpy-evex \
+  wcsncpy-generic \
   wcsnlen-avx2 \
   wcsnlen-avx2-rtm \
   wcsnlen-evex \
@@ -163,8 +175,8 @@ sysdep_routines += \
   wmemchr-avx2 \
   wmemchr-avx2-rtm \
   wmemchr-evex \
-  wmemchr-evex512 \
   wmemchr-evex-rtm \
+  wmemchr-evex512 \
   wmemchr-sse2 \
   wmemcmp-avx2-movbe \
   wmemcmp-avx2-movbe-rtm \