From patchwork Thu Jan 26 10:04:26 2017
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Jan Hubicka <hubicka@ucw.cz>
X-Patchwork-Id: 720035
Return-Path: 
 <gcc-patches-return-447168-incoming=patchwork.ozlabs.org@gcc.gnu.org>
X-Original-To: incoming@patchwork.ozlabs.org
Delivered-To: patchwork-incoming@bilbo.ozlabs.org
Received: from sourceware.org (server1.sourceware.org [209.132.180.131])
	(using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256
	bits)) (No client certificate requested)
	by ozlabs.org (Postfix) with ESMTPS id 3v8HZw1RTDz9ryT
	for <incoming@patchwork.ozlabs.org>;
	Thu, 26 Jan 2017 21:04:40 +1100 (AEDT)
Authentication-Results: ozlabs.org; dkim=pass (1024-bit key;
	unprotected) header.d=gcc.gnu.org header.i=@gcc.gnu.org
	header.b="aD8dnlF+"; dkim-atps=neutral
DomainKey-Signature: a=rsa-sha1; c=nofws; d=gcc.gnu.org; h=list-id
	:list-unsubscribe:list-archive:list-post:list-help:sender:date
	:from:to:cc:subject:message-id:references:mime-version
	:content-type:in-reply-to; q=dns; s=default; b=OWIgP0mBsRCjc5dn5
	nOXxN0UPi8p+y7ATnQvppelDWBtuY9BMLCad/hKE2Pa/BByc0Ed8Ol6vTF0WpvtL
	9Xte30o6dVtePwc+WnCwFWAVdzRtzrhRQ9XrMnkycs1oFtGdUoP2/5GWDqQ4M4ID
	NgeCriIWc7T4wABapL8smKgcUw=
DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=gcc.gnu.org; h=list-id
	:list-unsubscribe:list-archive:list-post:list-help:sender:date
	:from:to:cc:subject:message-id:references:mime-version
	:content-type:in-reply-to; s=default; bh=EAGipERHjTbPLjZMhiYBn4e
	3nv8=; b=aD8dnlF+nSZR0VAbus6axyeaU+lD0g2GB5cEKY4cBC8JOv1eCwXNh+0
	6ERGChmuEBnEl7LjxnBNSvIxirHYarvvCM/j3RBGOKFa9+RspUPaaRUIX+7ptfLt
	mk/T+VzUm8vY6IPZgya/+A7veJd/hIAl+CJdpasaYVScV4Qx1Dus=
Received: (qmail 118891 invoked by alias); 26 Jan 2017 10:04:31 -0000
Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm
Precedence: bulk
List-Id: <gcc-patches.gcc.gnu.org>
List-Unsubscribe: 
 <mailto:gcc-patches-unsubscribe-incoming=patchwork.ozlabs.org@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
Delivered-To: mailing list gcc-patches@gcc.gnu.org
Received: (qmail 118878 invoked by uid 89); 26 Jan 2017 10:04:30 -0000
Authentication-Results: sourceware.org; auth=none
X-Virus-Found: No
X-Spam-SWARE-Status: No, score=-3.8 required=5.0 tests=AWL, BAYES_00,
	KAM_LAZY_DOMAIN_SECURITY,
	RP_MATCHES_RCVD autolearn=ham version=3.3.2 spammy=path_length,
	H*i:CAFiYyc12K, H*f:sk:xk_XLp2, H*MI:sk:xk_XLp2
X-HELO: nikam.ms.mff.cuni.cz
Received: from nikam.ms.mff.cuni.cz (HELO nikam.ms.mff.cuni.cz)
	(195.113.20.16) by sourceware.org
	(qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP;
	Thu, 26 Jan 2017 10:04:28 +0000
Received: by nikam.ms.mff.cuni.cz (Postfix, from userid 16202)	id
	30399547E17; Thu, 26 Jan 2017 11:04:26 +0100 (CET)
Date: Thu, 26 Jan 2017 11:04:26 +0100
From: Jan Hubicka <hubicka@ucw.cz>
To: Richard Biener <richard.guenther@gmail.com>
Cc: Jan Hubicka <hubicka@ucw.cz>, GCC Patches <gcc-patches@gcc.gnu.org>,
	Jeff Law <law@redhat.com>
Subject: Re: Enable jump threading on maths meeting hot paths
Message-ID: <20170126100425.GA60443@kam.mff.cuni.cz>
References: <20170125181107.GB14317@kam.mff.cuni.cz>
	<CAFiYyc12K=xk_XLp2bQf5VE47WpcybN6DF_zSvWT22ecw03FZw@mail.gmail.com>
MIME-Version: 1.0
Content-Disposition: inline
In-Reply-To: 
 <CAFiYyc12K=xk_XLp2bQf5VE47WpcybN6DF_zSvWT22ecw03FZw@mail.gmail.com>
User-Agent: Mutt/1.5.23 (2014-03-12)

> > +      if (!contains_hot_bb && speed_p)
> > +       contains_hot_bb |= optimize_bb_for_speed_p (bb);
> > +
> 
> Hmm, but you are also counting the destination of the threading here
> which we will
> not duplicate.  Shouldn't this be under the if (j < path_length - 1)
> conditional so we
> look for hot BBs we are actually duplicating only (similar restrictions apply to
> path[0]?).

Aha, you are right.  I am re-testing updated patch (it also solves the PR)

Honza

Index: tree-ssa-threadbackward.c
===================================================================
--- tree-ssa-threadbackward.c	(revision 244732)
+++ tree-ssa-threadbackward.c	(working copy)
@@ -159,6 +159,7 @@ profitable_jump_thread_path (vec<basic_b
   bool threaded_through_latch = false;
   bool multiway_branch_in_path = false;
   bool threaded_multiway_branch = false;
+  bool contains_hot_bb = false;
 
   /* Count the number of instructions on the path: as these instructions
      will have to be duplicated, we will not record the path if there
@@ -168,6 +169,9 @@ profitable_jump_thread_path (vec<basic_b
     {
       basic_block bb = (*path)[j];
 
+      if (!contains_hot_bb && speed_p && j < path_length - 1)
+	contains_hot_bb |= optimize_bb_for_speed_p (bb);
+
       /* Remember, blocks in the path are stored in opposite order
 	 in the PATH array.  The last entry in the array represents
 	 the block with an outgoing edge that we will redirect to the
@@ -311,7 +315,11 @@ profitable_jump_thread_path (vec<basic_b
       return NULL;
     }
 
-  if (speed_p && optimize_edge_for_speed_p (taken_edge))
+  /* Threading is profitable if the path duplicated is hot but also
+     in a case we separate cold path from hot path and permit optimization
+     of the hot path later.  Be on the agressive side here. In some testcases,
+     as in PR 78407 this leads to noticeable improvements.  */
+  if (speed_p && (optimize_edge_for_speed_p (taken_edge) || contains_hot_bb))
     {
       if (n_insns >= PARAM_VALUE (PARAM_MAX_FSM_THREAD_PATH_INSNS))
 	{