From mboxrd@z Thu Jan 1 00:00:00 1970 From: catalin.marinas@arm.com (Catalin Marinas) Date: Thu, 19 Dec 2013 16:14:25 +0000 Subject: [PATCH 4/6] arm64: lib: Implement optimized memcmp routine In-Reply-To: References: <1386743082-5231-1-git-send-email-zhichang.yuan@linaro.org> <1386743082-5231-5-git-send-email-zhichang.yuan@linaro.org> <20131216165647.GH20193@mudshark.cambridge.arm.com> Message-ID: <20131219161424.GB29174@localhost> To: linux-arm-kernel@lists.infradead.org List-Id: linux-arm-kernel.lists.infradead.org On Thu, Dec 19, 2013 at 08:18:59AM +0000, Deepak Saxena wrote: > On 16 December 2013 08:56, Will Deacon wrote: > > On Wed, Dec 11, 2013 at 06:24:40AM +0000, zhichang.yuan at linaro.org wrote: > >> From: "zhichang.yuan" > >> > >> This patch, based on Linaro's Cortex Strings library, adds > >> an assembly optimized memcmp() function. > > > > [...] > > > >> +#ifndef __ARM64EB__ > >> + rev diff, diff > >> + rev data1, data1 > >> + rev data2, data2 > >> +#endif > > > > Given that I can't see you defining __ARM64EB__, I'd take a guess at you > > never having tested this code on a big-endian machine. > > We'll test it, but I believe __ARM64BE__ is a compiler constant that > is automagically present when building big endian, similar to > __ARMBE__ It's __AARCH64EB__ (that's how we spot people not testing on big-endian ;)). -- Catalin