From mboxrd@z Thu Jan 1 00:00:00 1970 Message-ID: <5350F27E.4020002@mitrol.it> Date: Fri, 18 Apr 2014 11:38:06 +0200 From: Paolo Minazzi MIME-Version: 1.0 References: <5347D5BB.1070107@mitrol.it> <5347D6E0.2030805@xenomai.org> <5347DCCC.3040801@mitrol.it> <5347DF09.9080905@xenomai.org> <5347E0E1.3020807@mitrol.it> <5347E3DA.6010106@xenomai.org> <5347E8AB.7020908@mitrol.it> <5347EB00.7060203@xenomai.org> <534FC6F3.1050305@mitrol.it> <534FD826.8030701@xenomai.org> <5350E6BE.9080104@mitrol.it> <5350E9C7.7010904@optusnet.com.au> In-Reply-To: <5350E9C7.7010904@optusnet.com.au> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Xenomai] arm imx6 and hardware FPU [SOLVED] List-Id: Discussions about the Xenomai project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: xenomai@xenomai.org Il 18/04/2014 11.00, Tom Evans ha scritto: >> I'm sorry ... all works correctly, also with hardware floating point. It >> was all my fault. >> Paolo > > Please post the solution in case someone else has the same problem. > > Did you forget CONFIG_VFP in the kernel configuration, or is there > something different for i.MX6? > > The Kernel has to be told about the FPU so it can swap out all the FPU > registers during a context swap. > > We have a product with an FPU we configure without kernel support, and > then only compile ONE program with hardware FP as the FPU context > switch time would slow the device down otherwise. > > Tom Evans > > The bug was is my test. All alarms was dummy. In my first email to mailing list I wrote the important points of my configuration. Thay were correct. There are no problem of reentrance of math function. All compiled with a linaro toolchain hf (hardware floating). Repeat, all was my buggy test.