From: Paul Davis Subject: Re: ham radio OSS duplex realtime mmap program. Date: Fri, 26 Sep 2003 12:14:26 -0400 Sender: alsa-devel-admin@lists.sourceforge.net Message-ID: <200309261614.h8QGEQ3X011667@oud> References: <3F746479.5040805@libero.it> Return-path: In-reply-to: Your message of "Fri, 26 Sep 2003 18:08:25 +0200." <3F746479.5040805@libero.it> Errors-To: alsa-devel-admin@lists.sourceforge.net List-Help: List-Post: List-Subscribe: , List-Unsubscribe: , List-Archive: To: Abramo Bagnara Cc: Jaroslav Kysela , James Courtier-Dutton , =?ISO-8859-1?Q?=22Dr=2E_med=2E_G=FCnther_Montag=22?= , alsa-devel@lists.sourceforge.net, hfterm-hackers@lists.sourceforge.net List-Id: alsa-devel@alsa-project.org >Paul Davis ha scritto: >>>By the way, does JACK still rely on the float samples internally? Then it >>>is not a good solution for the soft-modem application (driver) where >>>everything should be highly optimized. >> >> >> it does. on most modern CPUs, the FPU is as fast or faster than the >> integer unit for arithmetic. the optimized float<->int/short > >According to my measurement your belief is definitely false for add/sub, >sometimes true for mul and very likely true for div. my belief is based on measurements done by tomshardware, arstechnica and others. that doesn't mean it can't be wrong. ------------------------------------------------------- This sf.net email is sponsored by:ThinkGeek Welcome to geek heaven. http://thinkgeek.com/sf