Date: Thu, 15 Mar 2012 22:37:27 +1100 From: Andrew Reilly <areilly@bigpond.net.au> To: Peter Wemm <peter@wemm.org> Cc: freebsd-amd64@freebsd.org Subject: Re: Gcc46 and 128 Bit Floating Point Message-ID: <20120315113727.GB35074@johnny.reilly.home> In-Reply-To: <CAGE5yCoTN-qMMs3tLew8W7FgUFmT-kkXeuP7MGKKE3oM7eNC3Q@mail.gmail.com> References: <4F3EA37F.9010207@speakeasy.org> <CAGE5yCpvF0-b1iKAVGbya=fUNaYbGyrpj1PHSQxw4BvycNMLDg@mail.gmail.com> <4F3EC0B4.6050107@speakeasy.org> <4F4DA398.6070703@speakeasy.org> <20120229161408.G2514@besplex.bde.org> <4F4DDCE7.9000008@speakeasy.org> <20120229192417.U3167@besplex.bde.org> <CAGE5yCoTN-qMMs3tLew8W7FgUFmT-kkXeuP7MGKKE3oM7eNC3Q@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Feb 29, 2012 at 11:10:12PM -0800, Peter Wemm wrote:
> This is what he's getting at. If he could get access to 128 bit fp,
> he could move between 1/2 and 2/3 of the work into hardware operations
> and bypass a large chunk of GMP work which would be many many times
> slower than 128 bit hardware FP.
You make it sound as though "128 bit hardware FP" exists.
Bruce's point (I'm fairly certain) is that there's no such thing
(at least in the x86 world: could be different in IBM Power
series, not sure.) Have I missed a press release or tech doc?
AVX, just like SSE{2,3,4} only does 64-bit double: everything
else is software.
Cheers,
--
Andrew
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20120315113727.GB35074>