From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-patches-return-508067-listarch-gcc-patches=gcc.gnu.org@gcc.gnu.org>
Received: (qmail 42650 invoked by alias); 30 Aug 2019 20:05:24 -0000
Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-patches.gcc.gnu.org>
List-Archive: <http://gcc.gnu.org/ml/gcc-patches/>
List-Post: <mailto:gcc-patches@gcc.gnu.org>
List-Help: <mailto:gcc-patches-help@gcc.gnu.org>
Sender: gcc-patches-owner@gcc.gnu.org
Received: (qmail 42636 invoked by uid 89); 30 Aug 2019 20:05:24 -0000
Authentication-Results: sourceware.org; auth=none
X-Spam-SWARE-Status: No, score=-3.9 required=5.0 tests=AWL,BAYES_00,SPF_HELO_PASS autolearn=ham version=3.3.1 spammy=H*f:sk:hpCkHob, H*i:sk:hpCkHob, H*f:sk:CAKqmYP, H*i:WpT
X-HELO: mx1.redhat.com
Received: from mx1.redhat.com (HELO mx1.redhat.com) (209.132.183.28) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP; Fri, 30 Aug 2019 20:05:23 +0000
Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22])	(using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits))	(No client certificate requested)	by mx1.redhat.com (Postfix) with ESMTPS id 3DF6BA36EE3;	Fri, 30 Aug 2019 20:05:22 +0000 (UTC)
Received: from localhost (unknown [10.33.36.20])	by smtp.corp.redhat.com (Postfix) with ESMTP id DD5C21001938;	Fri, 30 Aug 2019 20:05:21 +0000 (UTC)
Date: Fri, 30 Aug 2019 23:33:00 -0000
From: Jonathan Wakely <jwakely@redhat.com>
To: Antony Polukhin <antoshkka@gmail.com>
Cc: libstdc++ <libstdc++@gcc.gnu.org>,	gcc-patches List <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH] Optimize to_chars
Message-ID: <20190830200521.GT9487@redhat.com>
References: <CAKqmYPZh+KXP3J_5X3xmz=-D0h013_w201Z=E5e56sfvCtAr1A@mail.gmail.com> <20190830160126.GO9487@redhat.com> <CAKqmYPavSGRyNYc-Oxijkw4p+WpT+hpCkHobXdpTTxSsV5dsgw@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <CAKqmYPavSGRyNYc-Oxijkw4p+WpT+hpCkHobXdpTTxSsV5dsgw@mail.gmail.com>
X-Clacks-Overhead: GNU Terry Pratchett
User-Agent: Mutt/1.12.0 (2019-05-25)
X-SW-Source: 2019-08/txt/msg02112.txt.bz2

On 30/08/19 22:46 +0300, Antony Polukhin wrote:
>пт, 30 авг. 2019 г. в 19:01, Jonathan Wakely <jwakely@redhat.com>:
><...>
>> Have you tried comparing the improved code to libc++'s implementation?
>> I believe they use precomputed arrays of digits, but they use larger
>> arrays that allow 4 bytes to be written at once, which is considerably
>> faster (and those precomputed arrays libe in libc++.so not in the
>> header). Would we be better off keeping the precomputed arrays and
>> expanding them to do 4-byte writes?
>
>This would not do good for bases 2, 8 and 16. For power of two bases
>there is no costly `mod` or `div` instructions, only bit operations.
>By increasing the digits table size the cache misses become more
>likely.

OK, thanks. I'll try benchmarking your improved code against the
libc++ version next week.