From: gautier_niouzes@hotmail.com
Subject: Re: Poor performance with GNAT-GPL-2017
Date: Wed, 21 Jun 2017 07:29:33 -0700 (PDT)
Date: 2017-06-21T07:29:33-07:00 [thread overview]
Message-ID: <77c1c1c6-f750-44cf-a95a-6a6843b950e1@googlegroups.com> (raw)
In-Reply-To: <d0fc88d6-cffb-40d8-af33-dc8c838d5e10@googlegroups.com>
On a number-crunching program, I also get an average of +5% improvement with GPL 2017 too. It depends a lot on the kind of program, tasking or not, compiler options, part of FPU calculation, the machine itself, etc. So no general conclusion.
The compiler options I use are:
when "Optimize" =>
for Default_Switches ("ada") use ("-gnat12", "-gnatwu", "-O2", "-gnatpn",
"-funroll-loops", "-fpeel-loops", "-funswitch-loops",
"-ftracer", "-fweb", "-frename-registers",
"-fpredictive-commoning", "-fgcse-after-reload", "-ftree-vectorize", "-fipa-cp-clone",
"-ffunction-sections",
"-mfpmath=sse", "-msse4.2",
"-g");
Cheers
Gautier
_____________________________________________________________
A free online game in Ada: http://pasta.phyrama.com/game.html
next prev parent reply other threads:[~2017-06-21 14:29 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-06-10 11:23 Poor performance with GNAT-GPL-2017 Charly
2017-06-10 12:43 ` Jacob Sparre Andersen
2017-06-11 20:48 ` Robert Eachus
2017-06-12 19:00 ` Charly
2017-06-13 4:14 ` Robert Eachus
2017-06-13 13:57 ` Lucretia
2017-06-13 17:41 ` Robert Eachus
2017-06-12 12:21 ` Emile
2017-06-12 18:22 ` Charly
2017-06-12 15:28 ` Mark Lorenzen
2017-06-13 19:46 ` alkhimey
2017-06-15 15:19 ` Charly
2017-06-15 16:31 ` Charly
2017-06-15 18:00 ` Anh Vo
2017-06-15 19:21 ` Charly
2017-06-15 19:24 ` Anh Vo
2017-06-16 21:33 ` stephane.carrez
2017-06-21 14:29 ` gautier_niouzes [this message]
2017-06-20 22:39 ` Anatoly Chernyshev
2017-06-19 10:26 ` briot.emmanuel
2017-06-19 12:25 ` Simon Wright
replies disabled
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox