From owner-freebsd-hackers Sat Feb 7 21:09:05 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id VAA27521 for hackers-outgoing; Sat, 7 Feb 1998 21:09:05 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from damon.com (3QgBXPMfLUkBJnflDr7Bahy5VKQ14Xb2@damon.com [207.170.114.1]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id VAA27380 for ; Sat, 7 Feb 1998 21:07:36 -0800 (PST) (envelope-from dap@damon.com) Received: (from dap@localhost) by damon.com (8.8.7/8.8.7) id XAA10438 for hackers@FreeBSD.ORG; Sat, 7 Feb 1998 23:03:31 -0600 (CST) (envelope-from dap) From: Damon Permezel Message-Id: <199802080503.XAA10438@damon.com> Subject: MMX, pentium, etc To: hackers@FreeBSD.ORG Date: Sat, 7 Feb 1998 23:03:31 -0600 (CST) X-Mailer: ELM [version 2.4ME+ PL32 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG I have a Java app which uses some intensive FP, for which I have written native (aka: C) routines to accelerate. I am getting to the point where I am once again tapped out, so I want to explore hand coded MMX instructions in my (unrolled, hand optimized) inner loops. I have "ordered" the MMX dox from INTEL, and expect them any day now, so I need to start preparing for the next step: namely a gcc/gas which understands the MMX mmxnomnics. A .h file with nice asm macros already defined for the instructions would be nice also (although, I can type if pressed). I've seen discussions on MMX here, and on pgcc. I went to build the pgcc port once, and was informed that it was broken. I am running -current, cvsupped, cvsupping ports, and there is no Makefile in ports/lang/pgcc*. I suspect I might get a bit of a perf boost if I were to use pgcc. Help? To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe hackers" in the body of the message