From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ozlabs.org (bilbo.ozlabs.org [203.11.71.1]) (using TLSv1.2 with cipher ADH-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 41Zg3B2ggPzDqyZ for ; Tue, 24 Jul 2018 23:59:50 +1000 (AEST) In-Reply-To: <1528336675-10879-2-git-send-email-wei.guo.simon@gmail.com> To: wei.guo.simon@gmail.com, linuxppc-dev@lists.ozlabs.org From: Michael Ellerman Cc: "Naveen N. Rao" , Simon Guo , Cyril Bur Subject: Re: [v8, 1/5] powerpc/64: Align bytes before fall back to .Lshort in powerpc64 memcmp() Message-Id: <41Zg395wSgz9s4Z@ozlabs.org> Date: Tue, 24 Jul 2018 23:59:49 +1000 (AEST) List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Thu, 2018-06-07 at 01:57:51 UTC, wei.guo.simon@gmail.com wrote: > From: Simon Guo > > Currently memcmp() 64bytes version in powerpc will fall back to .Lshort > (compare per byte mode) if either src or dst address is not 8 bytes aligned. > It can be opmitized in 2 situations: > > 1) if both addresses are with the same offset with 8 bytes boundary: > memcmp() can compare the unaligned bytes within 8 bytes boundary firstly > and then compare the rest 8-bytes-aligned content with .Llong mode. > > 2) If src/dst addrs are not with the same offset of 8 bytes boundary: > memcmp() can align src addr with 8 bytes, increment dst addr accordingly, > then load src with aligned mode and load dst with unaligned mode. > > This patch optmizes memcmp() behavior in the above 2 situations. > > Tested with both little/big endian. Performance result below is based on > little endian. > > Following is the test result with src/dst having the same offset case: > (a similar result was observed when src/dst having different offset): > (1) 256 bytes > Test with the existing tools/testing/selftests/powerpc/stringloops/memcmp: > - without patch > 29.773018302 seconds time elapsed ( +- 0.09% ) > - with patch > 16.485568173 seconds time elapsed ( +- 0.02% ) > -> There is ~+80% percent improvement > > (2) 32 bytes > To observe performance impact on < 32 bytes, modify > tools/testing/selftests/powerpc/stringloops/memcmp.c with following: > ------- > #include > #include "utils.h" > > -#define SIZE 256 > +#define SIZE 32 > #define ITERATIONS 10000 > > int test_memcmp(const void *s1, const void *s2, size_t n); > -------- > > - Without patch > 0.244746482 seconds time elapsed ( +- 0.36%) > - with patch > 0.215069477 seconds time elapsed ( +- 0.51%) > -> There is ～+13% improvement > > (3) 0~8 bytes > To observe <8 bytes performance impact, modify > tools/testing/selftests/powerpc/stringloops/memcmp.c with following: > ------- > #include > #include "utils.h" > > -#define SIZE 256 > -#define ITERATIONS 10000 > +#define SIZE 8 > +#define ITERATIONS 1000000 > > int test_memcmp(const void *s1, const void *s2, size_t n); > ------- > - Without patch > 1.845642503 seconds time elapsed ( +- 0.12% ) > - With patch > 1.849767135 seconds time elapsed ( +- 0.26% ) > -> They are nearly the same. (-0.2%) > > Signed-off-by: Simon Guo Series applied to powerpc next, thanks. https://git.kernel.org/powerpc/c/2d9ee327adce5f6becea2dd51d282a cheers