From mboxrd@z Thu Jan 1 00:00:00 1970 X-Msuck: nntp://news.gmane.org/gmane.linux.lib.musl.general/7362 Path: news.gmane.org!not-for-mail From: John Mudd Newsgroups: gmane.linux.lib.musl.general Subject: Re: musl perf, 20% slower than native build? Date: Wed, 8 Apr 2015 16:16:05 -0400 Message-ID: References: <20150408160507.GB31681@port70.net> Reply-To: musl@lists.openwall.com NNTP-Posting-Host: plane.gmane.org Mime-Version: 1.0 Content-Type: multipart/alternative; boundary=001a1141f1049eba7b05133c34a2 X-Trace: ger.gmane.org 1428524204 23394 80.91.229.3 (8 Apr 2015 20:16:44 GMT) X-Complaints-To: usenet@ger.gmane.org NNTP-Posting-Date: Wed, 8 Apr 2015 20:16:44 +0000 (UTC) Cc: musl To: Alexander Monakov Original-X-From: musl-return-7375-gllmg-musl=m.gmane.org@lists.openwall.com Wed Apr 08 22:16:40 2015 Return-path: Envelope-to: gllmg-musl@m.gmane.org Original-Received: from mother.openwall.net ([195.42.179.200]) by plane.gmane.org with smtp (Exim 4.69) (envelope-from ) id 1YfwOt-0004fM-AB for gllmg-musl@m.gmane.org; Wed, 08 Apr 2015 22:16:39 +0200 Original-Received: (qmail 1831 invoked by uid 550); 8 Apr 2015 20:16:37 -0000 Mailing-List: contact musl-help@lists.openwall.com; run by ezmlm Precedence: bulk List-Post: List-Help: List-Unsubscribe: List-Subscribe: Original-Received: (qmail 1813 invoked from network); 8 Apr 2015 20:16:36 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type; bh=N34ztArRIctLeOk1SNIXd8V7mAx6tg0P0C7AWRE9oeE=; b=zP6MFAZ6x8a7PHGYj/9iDCTxV/vmMQJqaoXdOMKvQTZ4BCM4sAlYEDgLPHLTLYmAKX d0w+zYlB8OYLcb44XeNXpldc6W8UWA2nZraJhQFzMSSk6bnDX4UqEDspWxGKAGT2c/hk y+laR2Ibm58GCYYQ0VQOvUd6mya47lyIPwPF4n7HtCFEoUu3/geVUXhD2k16hl7dkLPY GomDiERxPikmh/OkZKBLzMee0tgCMbwASTV5rhm81OyFitIWSaEdJ2Jc9fLmno2AXEMk Od1sGmDmoebFdnSQCpzfkhs4L+17kJ50hf/Ohxb3a0ZyXXuChVBdj115lj8TTnQwU7Fs LICg== X-Received: by 10.107.166.11 with SMTP id p11mr41448359ioe.30.1428524185333; Wed, 08 Apr 2015 13:16:25 -0700 (PDT) In-Reply-To: Xref: news.gmane.org gmane.linux.lib.musl.general:7362 Archived-At: --001a1141f1049eba7b05133c34a2 Content-Type: text/plain; charset=KOI8-R I don't see any of those "a_*" names in the output of 'nm' or 'readelf -a' on musl-1.1.8/lib/libc.so. Here's my configure command: ./configure --prefix=$(pwd).install --syslibdir=/usr/rx30/musl/lib/ CFLAGS=-O3 CC=gcc Here's a sample of the make output: gcc -std=c99 -nostdinc -ffreestanding -fexcess-precision=standard -frounding-math -D_XOPEN_SOURCE=700 -I./arch/i386 -I./src/internal -I./include -pipe -fomit-frame-pointer -fno-unwind-tables -fno-asynchronous-unwind-tables -Wa,--noexecstack -march=i486 -mtune=generic -Werror=implicit-function-declaration -Werror=implicit-int -Werror=pointer-sign -Werror=pointer-arith -fno-stack-protector -O3 -c -o crt/crt1.o crt/i386/crt1.s cp crt/crt1.o lib/crt1.o gcc -std=c99 -nostdinc -ffreestanding -fexcess-precision=standard -frounding-math -D_XOPEN_SOURCE=700 -I./arch/i386 -I./src/internal -I./include -pipe -fomit-frame-pointer -fno-unwind-tables -fno-asynchronous-unwind-tables -Wa,--noexecstack -march=i486 -mtune=generic -Werror=implicit-function-declaration -Werror=implicit-int -Werror=pointer-sign -Werror=pointer-arith -fno-stack-protector -O3 -fPIC -c -o crt/Scrt1.o crt/i386/Scrt1.s cp crt/Scrt1.o lib/Scrt1.o gcc -std=c99 -nostdinc -ffreestanding -fexcess-precision=standard -frounding-math -D_XOPEN_SOURCE=700 -I./arch/i386 -I./src/internal -I./include -pipe -fomit-frame-pointer -fno-unwind-tables -fno-asynchronous-unwind-tables -Wa,--noexecstack -march=i486 -mtune=generic -Werror=implicit-function-declaration -Werror=implicit-int -Werror=pointer-sign -Werror=pointer-arith -fno-stack-protector -O3 -c -o crt/crti.o crt/i386/crti.s cp crt/crti.o lib/crti.o On Wed, Apr 8, 2015 at 3:33 PM, Alexander Monakov wrote: > That a_* functions appear in this profile implies they were not inlined, > which > is quite strange. Are you positive -O3 was used for your musl compile? > Can > you check the list of symbols in libc.so (e.g. using nm or `readelf -a`) to > double check? > > Thanks. > > Alexander > > --001a1141f1049eba7b05133c34a2 Content-Type: text/html; charset=KOI8-R Content-Transfer-Encoding: quoted-printable
I don't see any of those "a_*" names in= the output of 'nm' or 'readelf -a' on musl-1.1.8/lib/libc.= so.

Here's my configure command:
./configure --prefix=3D$(pwd).install --syslibdir=3D/usr/rx30/m= usl/lib/ CFLAGS=3D-O3 CC=3Dgcc

Here's a sample= of the make output:

gcc -std=3Dc99 -nostdinc -ffr= eestanding -fexcess-precision=3Dstandard -frounding-math -D_XOPEN_SOURCE=3D= 700 -I./arch/i386 -I./src/internal -I./include =9A-pipe -fomit-frame-pointe= r -fno-unwind-tables -fno-asynchronous-unwind-tables -Wa,--noexecstack -mar= ch=3Di486 -mtune=3Dgeneric -Werror=3Dimplicit-function-declaration -Werror= =3Dimplicit-int -Werror=3Dpointer-sign -Werror=3Dpointer-arith -fno-stack-p= rotector -O3 -c -o crt/crt1.o crt/i386/crt1.s
cp crt/crt1.o lib/c= rt1.o
gcc -std=3Dc99 -nostdinc -ffreestanding -fexcess-precision= =3Dstandard -frounding-math -D_XOPEN_SOURCE=3D700 -I./arch/i386 -I./src/int= ernal -I./include =9A-pipe -fomit-frame-pointer -fno-unwind-tables -fno-asy= nchronous-unwind-tables -Wa,--noexecstack -march=3Di486 -mtune=3Dgeneric -W= error=3Dimplicit-function-declaration -Werror=3Dimplicit-int -Werror=3Dpoin= ter-sign -Werror=3Dpointer-arith -fno-stack-protector -O3 -fPIC -c -o crt/S= crt1.o crt/i386/Scrt1.s
cp crt/Scrt1.o lib/Scrt1.o
gcc = -std=3Dc99 -nostdinc -ffreestanding -fexcess-precision=3Dstandard -froundin= g-math -D_XOPEN_SOURCE=3D700 -I./arch/i386 -I./src/internal -I./include =9A= -pipe -fomit-frame-pointer -fno-unwind-tables -fno-asynchronous-unwind-tabl= es -Wa,--noexecstack -march=3Di486 -mtune=3Dgeneric -Werror=3Dimplicit-func= tion-declaration -Werror=3Dimplicit-int -Werror=3Dpointer-sign -Werror=3Dpo= inter-arith -fno-stack-protector -O3 -c -o crt/crti.o crt/i386/crti.s
=
cp crt/crti.o lib/crti.o

On Wed, Apr 8, 2015 at 3:33 PM, Alexander Monakov <amon= akov@ispras.ru> wrote:
That= a_* functions appear in this profile implies they were not inlined, which<= br> is quite strange.=9A Are you positive -O3 was used for your musl compile?= =9A Can
you check the list of symbols in libc.so (e.g. using nm or `readelf -a`) to=
double check?

Thanks.

Alexander


--001a1141f1049eba7b05133c34a2--