From 96d6fd6c4060d739abb1822e7ad633af749532b2 Mon Sep 17 00:00:00 2001 From: Adhemerval Zanella Date: Tue, 23 Dec 2014 05:59:44 -0600 Subject: powerpc: Optimized st{r,p}cpy for POWER8/PPC64 This patch adds an optimized POWER8 strcpy using unaligned accesses. For strings up to 16 bytes the implementation first calculate the string size, like strlen, and issues a memcpy. For larger strings, source is first aligned to 16 bytes and then tested over a loop that reads 16 bytes am combine the cmpb results for speedup. Special case is added for page cross reads. It shows 30%-60% improvement over the optimized POWER7 one that uses only aligned accesses. --- sysdeps/powerpc/powerpc64/multiarch/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'sysdeps/powerpc/powerpc64/multiarch/Makefile') diff --git a/sysdeps/powerpc/powerpc64/multiarch/Makefile b/sysdeps/powerpc/powerpc64/multiarch/Makefile index 39e441b9a0..f170551b44 100644 --- a/sysdeps/powerpc/powerpc64/multiarch/Makefile +++ b/sysdeps/powerpc/powerpc64/multiarch/Makefile @@ -13,7 +13,8 @@ sysdep_routines += memcpy-power7 memcpy-a2 memcpy-power6 memcpy-cell \ wcschr-power6 wcschr-ppc64 wcsrchr-power7 wcsrchr-power6 \ wcsrchr-ppc64 wcscpy-power7 wcscpy-power6 wcscpy-ppc64 \ wordcopy-power7 wordcopy-power6 wordcopy-ppc64 \ - strcpy-power7 strcpy-ppc64 stpcpy-power7 stpcpy-ppc64 \ + strcpy-power8 strcpy-power7 strcpy-ppc64 stpcpy-power8 \ + stpcpy-power7 stpcpy-ppc64 \ strrchr-power7 strrchr-ppc64 strncat-power7 strncat-ppc64 \ strncpy-power7 strncpy-ppc64 \ stpncpy-power7 stpncpy-ppc64 strcmp-power7 strcmp-ppc64 \ -- cgit 1.4.1