From mboxrd@z Thu Jan 1 00:00:00 1970 From: Albert ARIBAUD Date: Sat, 01 Oct 2011 08:48:06 +0200 Subject: [U-Boot] [RFC PATCH] arm: provide a CONFIG flag for disabling relocation In-Reply-To: <4E856DF7.6010703@gmail.com> References: <20110920180959.8008F1208F1E@gemini.denx.de> <4E78E5DE.60300@aribaud.net> <4E79C1B5.7040101@aribaud.net> <4E79C887.6010906@gmail.com> <4E79D27D.30409@aribaud.net> <4E79D91C.8070008@gmail.com> <4E856DF7.6010703@gmail.com> Message-ID: <4E86B7A6.5080204@aribaud.net> List-Id: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: u-boot@lists.denx.de Le 30/09/2011 09:21, Simon Schwarz a ?crit : > On 09/29/2011 06:14 PM, Andreas Bie?mann wrote: > [SNIP] >> Simon, who has just finished his bachelor thesis did this test for me >> (thanks to this way ...). >> It seems using more register for ldmia/stmia does _not_ improve the copy >> time that much. Simon measured 10.8 ms for r9-r10 and 10.65 ms for >> r3-r10 (unfortunately >> I do not know which system he tested, but I guess devkit8000). >> >> best regards >> >> Andreas Bie?mann >> >> > Yes, devkit8000. > > Regards > Simon Thanks to both of you. I'd somehow expected there not to be a great increase as the true limit is bus width. So let us stick with two registers and avoid register pushes/pops. Amicalement, -- Albert.