package/gcc/5.5.0/831-ARM-PR-target-70473-Reduce-size-of-Cortex-A8-automat.patch

From 89bd94250827f887b38211ac048b4006229dc9c0 Mon Sep 17 00:00:00 2001
From: ktkachov <ktkachov@138bc75d-0d04-0410-961f-82ee72b054a4>
Date: Fri, 26 Aug 2016 10:23:20 +0000
Subject: [PATCH] [ARM] PR target/70473: Reduce size of Cortex-A8 automaton

	PR target/70473
	* config/arm/cortex-a8-neon.md (cortex_a8_vfp_muld): Reduce
	reservation duration to 15 cycles.
	(cortex_a8_vfp_macs): Likewise.
	(cortex_a8_vfp_macd): Likewise.
	(cortex_a8_vfp_divs): Likewise.
	(cortex_a8_vfp_divd): Likewise.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@239772 138bc75d-0d04-0410-961f-82ee72b054a4

[Backport from gcc upstream commit 79f5d5e3cd5a668d5ecb2b6b0cce80ef5706ac53.]
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
---
 gcc/config/arm/cortex-a8-neon.md | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/gcc/config/arm/cortex-a8-neon.md b/gcc/config/arm/cortex-a8-neon.md
index 04fa01e..4e6d05d 100644
--- a/gcc/config/arm/cortex-a8-neon.md
+++ b/gcc/config/arm/cortex-a8-neon.md
@@ -357,30 +357,34 @@
        (eq_attr "type" "fmuls"))
   "cortex_a8_vfp,cortex_a8_vfplite*11")
 
+;; Don't model a reservation for more than 15 cycles as this explodes the
+;; state space of the automaton for little gain.  It is unlikely that the
+;; scheduler will find enough instructions to hide the full latency of the
+;; instructions.
 (define_insn_reservation "cortex_a8_vfp_muld" 17
   (and (eq_attr "tune" "cortexa8")
        (eq_attr "type" "fmuld"))
-  "cortex_a8_vfp,cortex_a8_vfplite*16")
+  "cortex_a8_vfp,cortex_a8_vfplite*15")
 
 (define_insn_reservation "cortex_a8_vfp_macs" 21
   (and (eq_attr "tune" "cortexa8")
        (eq_attr "type" "fmacs,ffmas"))
-  "cortex_a8_vfp,cortex_a8_vfplite*20")
+  "cortex_a8_vfp,cortex_a8_vfplite*15")
 
 (define_insn_reservation "cortex_a8_vfp_macd" 26
   (and (eq_attr "tune" "cortexa8")
        (eq_attr "type" "fmacd,ffmad"))
-  "cortex_a8_vfp,cortex_a8_vfplite*25")
+  "cortex_a8_vfp,cortex_a8_vfplite*15")
 
 (define_insn_reservation "cortex_a8_vfp_divs" 37
   (and (eq_attr "tune" "cortexa8")
        (eq_attr "type" "fdivs, fsqrts"))
-  "cortex_a8_vfp,cortex_a8_vfplite*36")
+  "cortex_a8_vfp,cortex_a8_vfplite*15")
 
 (define_insn_reservation "cortex_a8_vfp_divd" 65
   (and (eq_attr "tune" "cortexa8")
        (eq_attr "type" "fdivd, fsqrtd"))
-  "cortex_a8_vfp,cortex_a8_vfplite*64")
+  "cortex_a8_vfp,cortex_a8_vfplite*15")
 
 ;; Comparisons can actually take 7 cycles sometimes instead of four,
 ;; but given all the other instructions lumped into type=ffarith that
-- 
2.7.4