From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <Paul.Zimmermann@inria.fr>
Received: from mail2-relais-roc.national.inria.fr
 (mail2-relais-roc.national.inria.fr [192.134.164.83])
 by sourceware.org (Postfix) with ESMTPS id 4E18F3858D32
 for <libc-alpha@sourceware.org>; Mon, 22 Aug 2022 12:28:58 +0000 (GMT)
DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 4E18F3858D32
Received-SPF: SoftFail (mail2-relais-roc.national.inria.fr:
 domain of Paul.Zimmermann@inria.fr is inclined to not
 designate 152.81.10.51 as permitted sender)
 identity=mailfrom; client-ip=152.81.10.51;
 receiver=mail2-relais-roc.national.inria.fr;
 envelope-from="Paul.Zimmermann@inria.fr";
 x-sender="Paul.Zimmermann@inria.fr"; x-conformance=spf_only;
 x-record-type="v=spf1"; x-record-text="v=spf1
 ip4:192.134.164.0/24 mx ~all"
Received-SPF: None (mail2-relais-roc.national.inria.fr: no sender
 authenticity information available from domain of
 postmaster@tomate) identity=helo; client-ip=152.81.10.51;
 receiver=mail2-relais-roc.national.inria.fr;
 envelope-from="Paul.Zimmermann@inria.fr";
 x-sender="postmaster@tomate"; x-conformance=spf_only
X-IronPort-AV: E=Sophos;i="5.93,254,1654552800"; d="scan'208";a="49499172"
Received: from tomate.loria.fr (HELO tomate) ([152.81.10.51])
 by mail2-relais-roc.national.inria.fr with
 ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 22 Aug 2022 14:28:57 +0200
Date: Mon, 22 Aug 2022 14:28:57 +0200
Message-Id: <mw8rngpily.fsf@tomate.loria.fr>
From: Paul Zimmermann <Paul.Zimmermann@inria.fr>
To: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
Cc: michael.hudson@canonical.com, joseph@codesourcery.com,
 libc-alpha@sourceware.org
In-Reply-To: <AM5PR0801MB1668EC9F8A41F189B0C0B191836A9@AM5PR0801MB1668.eurprd08.prod.outlook.com>
 (message from Wilco Dijkstra via Libc-alpha on Wed, 17 Aug 2022
 11:53:43 +0000)
Subject: Re: [PATCH] Ensure calculations happen with desired rounding mode in
 y1lf128
References: <AM5PR0801MB16686F7E4FC42758D0C6930E83679@AM5PR0801MB1668.eurprd08.prod.outlook.com>
 <alpine.DEB.2.22.394.2208152055090.311521@digraph.polyomino.org.uk>
 <CAJ8wqtdtuvTO6Er7O+L_-E0PqPzVpCv+1rtQJWJsd+KTHzN8Xw@mail.gmail.com>
 <AM5PR0801MB1668EC9F8A41F189B0C0B191836A9@AM5PR0801MB1668.eurprd08.prod.outlook.com>
X-Spam-Status: No, score=-3.0 required=5.0 tests=BAYES_00, DKIM_SIGNED,
 DKIM_VALID, DKIM_VALID_AU, DKIM_VALID_EF, KAM_NUMSUBJECT, SPF_HELO_NONE,
 SPF_PASS, TXREP,
 T_SCC_BODY_TEXT_LINE autolearn=no autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
 server2.sourceware.org
X-BeenThere: libc-alpha@sourceware.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Libc-alpha mailing list <libc-alpha.sourceware.org>
List-Unsubscribe: <https://sourceware.org/mailman/options/libc-alpha>,
 <mailto:libc-alpha-request@sourceware.org?subject=unsubscribe>
List-Archive: <https://sourceware.org/pipermail/libc-alpha/>
List-Post: <mailto:libc-alpha@sourceware.org>
List-Help: <mailto:libc-alpha-request@sourceware.org?subject=help>
List-Subscribe: <https://sourceware.org/mailman/listinfo/libc-alpha>,
 <mailto:libc-alpha-request@sourceware.org?subject=subscribe>
X-List-Received-Date: Mon, 22 Aug 2022 12:28:59 -0000

> Rewriting this function would not be trivial, but the math functions that are already
> rewritten (like exp, pow, log) prove you can get fast and accurate results without
> ever needing rounding mode changes.

indeed, you can even get correct rounding (for all rounding modes) faster than
the current glibc implementations. See https://hal.inria.fr/hal-03721525
for example, or the current LLVM libc implementations (cf bottom table of
https://core-math.gitlabpages.inria.fr/).

Paul Zimmermann