From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from sanddollar.geekisp.com ([216.168.135.167]) by linuxtogo.org with smtp (Exim 4.72) (envelope-from ) id 1Tqpyd-0005rX-C2 for openembedded-core@lists.openembedded.org; Thu, 03 Jan 2013 19:57:18 +0100 Received: (qmail 7651 invoked by uid 1003); 3 Jan 2013 14:42:39 -0000 Received: from unknown (HELO ?192.168.1.105?) (philip@opensdr.com@96.240.164.36) by mail.geekisp.com with (DHE-RSA-AES256-SHA encrypted) SMTP; 3 Jan 2013 14:42:39 -0000 Message-ID: <50E5D101.9030701@balister.org> Date: Thu, 03 Jan 2013 13:42:09 -0500 From: Philip Balister User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/17.0 Thunderbird/17.0 MIME-Version: 1.0 To: openembedded-core X-Enigmail-Version: 1.4.6 Subject: Enabling NEON instructions for fftw X-BeenThere: openembedded-core@lists.openembedded.org X-Mailman-Version: 2.1.11 Precedence: list List-Id: Patches and discussions about the oe-core layer List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 03 Jan 2013 18:57:18 -0000 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit So, recent versions of fftw have NEON support for the single precision build. In the poast, I just passed --enable-neon to configure or the armv7a case. Now, this is not entirely correct, since some armv7a's lack a NEON coprocessor. Does anyone have a suggestion for how to handle this better? Personally, I think if you want to run fftwf without NEON, you should have your head examined, but I would like to avoid generating packages that SIGILL on people. Philip