From a23bd00f9d810c28d9e83ce1d7cf53968375937d Mon Sep 17 00:00:00 2001 From: "Paul E. Murphy" Date: Mon, 18 May 2020 11:16:06 -0500 Subject: powerpc64le: add optimized strlen for P9 This started as a trivial change to Anton's rawmemchr. I got carried away. This is a hybrid between P8's asympotically faster 64B checks with extremely efficient small string checks e.g <64B (and sometimes a little bit more depending on alignment). The second trick is to align to 64B by running a 48B checking loop 16B at a time until we naturally align to 64B (i.e checking 48/96/144 bytes/iteration based on the alignment after the first 5 comparisons). This allieviates the need to check page boundaries. Finally, explicly use the P7 strlen with the runtime loader when building P9. We need to be cautious about vector/vsx extensions here on P9 only builds. --- sysdeps/powerpc/powerpc64/multiarch/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'sysdeps/powerpc/powerpc64/multiarch/Makefile') diff --git a/sysdeps/powerpc/powerpc64/multiarch/Makefile b/sysdeps/powerpc/powerpc64/multiarch/Makefile index fc2268f6b5..19acb6c64a 100644 --- a/sysdeps/powerpc/powerpc64/multiarch/Makefile +++ b/sysdeps/powerpc/powerpc64/multiarch/Makefile @@ -33,7 +33,7 @@ sysdep_routines += memcpy-power8-cached memcpy-power7 memcpy-a2 memcpy-power6 \ ifneq (,$(filter %le,$(config-machine))) sysdep_routines += strcmp-power9 strncmp-power9 strcpy-power9 stpcpy-power9 \ - rawmemchr-power9 + rawmemchr-power9 strlen-power9 endif CFLAGS-strncase-power7.c += -mcpu=power7 -funroll-loops CFLAGS-strncase_l-power7.c += -mcpu=power7 -funroll-loops -- cgit 1.4.1