From owner-freebsd-amd64@FreeBSD.ORG Thu Mar 15 11:55:47 2012 Return-Path: Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 284B2106564A for ; Thu, 15 Mar 2012 11:55:47 +0000 (UTC) (envelope-from maho.nakata@gmail.com) Received: from mail-gy0-f182.google.com (mail-gy0-f182.google.com [209.85.160.182]) by mx1.freebsd.org (Postfix) with ESMTP id CD8EE8FC14 for ; Thu, 15 Mar 2012 11:55:46 +0000 (UTC) Received: by ghrr20 with SMTP id r20so3559945ghr.13 for ; Thu, 15 Mar 2012 04:55:46 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=sender:date:message-id:to:cc:subject:from:in-reply-to:references :x-mailer:mime-version:content-type:content-transfer-encoding; bh=qIFi7p64GQUQVNdr11Ok52gmyE21hnqQTIeu28OnlME=; b=YwgbKOXWXewMw4yx68g6RMksRhqZZvYN6mnLEI2R3UudNU0j95XOarBiZXNzeF4hwk fyIGsH6x7HFKE53sLKyOcgt0uQHgGRQE9G+BkDhCn3ZNUP9nllR09kpJWejQ3wG/d+JI ztwfgqJGc7wsqPLurrGjkxDnCMWjq1B9FtZILGhKsqhbc1WJ5qBT3ETmP6XLjg4uuBGN T+tGZu69IuhzDJtj+Tuf/XwewsXOrY174Cg5FchTPICg0nB9cMx43UElVENlINIxVKBK SnAciENFHoUNM7KWHwPAXiQSJKjDtS7oEtj0WjIR0GSL6/CwHbJEOFJsBXgzTwaDUrDp 0pxA== Received: by 10.68.225.194 with SMTP id rm2mr4693355pbc.95.1331812546002; Thu, 15 Mar 2012 04:55:46 -0700 (PDT) Received: from localhost (rikad42.riken.jp. [134.160.214.42]) by mx.google.com with ESMTPS id p10sm1747441pbo.55.2012.03.15.04.55.43 (version=SSLv3 cipher=OTHER); Thu, 15 Mar 2012 04:55:44 -0700 (PDT) Sender: Maho NAKATA Date: Thu, 15 Mar 2012 20:55:37 +0900 (JST) Message-Id: <20120315.205537.1682271453232733525.chat95@mac.com> To: tomdean@speakeasy.org From: Maho NAKATA In-Reply-To: <4F4DDCE7.9000008@speakeasy.org> References: <4F4DA398.6070703@speakeasy.org> <20120229161408.G2514@besplex.bde.org> <4F4DDCE7.9000008@speakeasy.org> X-Mailer: Mew version 6.3 on Emacs 23.4 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: freebsd-amd64@freebsd.org Subject: Re: Gcc46 and 128 Bit Floating Point X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Mar 2012 11:55:47 -0000 Hi Thomas D. Dean Why not using double-double approach? double-double is poorman's quad math. Using NVIDIA C2050, we can obtain 16GFlops to 26GFlops performance for matrix-matrix multiplication. I have been developing a linear algebra library. http://mplapack.sourceforge.net/ . Thanks Nakata Maho From: "Thomas D. Dean" Subject: Re: Gcc46 and 128 Bit Floating Point Date: Wed, 29 Feb 2012 00:08:07 -0800 > On 02/28/12 22:03, Bruce Evans wrote: > >> >> But why would you want it? It is essentially unusable on sparc64, >> since it is several thousand times slower than 80-bit floating point >> on i386. At equal CPU clock speeds, it is only about 1000 times >> slower. >> Most of the factors of 10 are due to fundamental slowness of multi- >> word artithmetic in software and the soft-float implementations not >> being very good (I only tested with the old NetBSD/4.4BSD-derived one. >> This has been replaced by the Hauser one, which has good chances for >> being worse due to its greater generality and correctness, but the old >> one has a lot of slop to improve). A modern x86 is much faster than >> an old sparc64, giving about another factor of 10. 64-bit operations >> are only about this 10 times slower (or more like 3 times slower at >> equal CPU clock speeds) on an old sparc64 as on a not-so-modern core2 >> x86. The gnu libraries might be better. So you could hope for only >> a factor of 100 slowdown on scalar code. But modern x86's can also >> do vector code, and thus be up to 8 times faster for 32-bit floating >> point with AVX. Really good multi-word libraries might be able to >> exploit some vector operations, but I think multi-word operations are >> too seial in nature to get much parallelism with them. > > I have an application that takes 10 days to run on a 4.16GHz Core-i7 > 3930K. No output until it finishes. > > When I first started looking at this, I naively thought the 80-bit FPU > floats were scaled to 128-bits. Would be nice... > > The application uses libgmp, but, about 1/2 to 2/3 of the work will > fit in a 128-bit float. > > I wanted to get 128-bit floating point operations so I could do 2/3 > the work in an FPU. With 80-bits, I can only do 1/3 the work(+-). > > Mostly, this is just "can I do it faster...". Maybe some asm code to > work the inner loops in FPU registers. At some point, hand off to > libgmp. I now think the speed improvement would not be worth the > work. > > Tom Dean > _______________________________________________ > freebsd-amd64@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-amd64 > To unsubscribe, send any mail to > "freebsd-amd64-unsubscribe@freebsd.org" >