Date: Tue, 12 Apr 2016 12:25:10 -0600 From: Ian Lepore <ian@freebsd.org> To: =?ISO-8859-1?Q?Otac=EDlio?= <otacilio.neto@bsd.com.br>, "freebsd-arm@freebsd.org" <freebsd-arm@freebsd.org> Subject: Re: Float point in beaglebone Message-ID: <1460485510.52955.16.camel@freebsd.org> In-Reply-To: <570D2E3D.2010801@bsd.com.br> References: <570D2E3D.2010801@bsd.com.br>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 2016-04-12 at 14:19 -0300, Otacílio wrote: > Dears > > Now, how is made the float point calculations in beaglebone using > freebsd, by software or by hardware? > Hardware. Armv6/v7 systems on freebsd 11 have always used floating point hardware, but they pass arguments in the integer registers, which costs a small bit of performance. The upcoming change will switch to passing arguments in floating point registers, but for most apps the performance improvement will be small. -- Ian
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1460485510.52955.16.camel>