[PATCH, PR 49089] Don't split AVX256 unaligned loads by default on bdver1 and generic

[Fang, Changpeng]

Hi,

The patch ( http://gcc.gnu.org/ml/gcc-patches/2011-02/txt00059.txt ) which 
introduces splitting avx256 unaligned loads. 
However, we found that it causes significant regressions for cpu2006 ( 
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=49089 ).

In this work, we introduce a tune option that sets splitting unaligned loads 
default only for such CPUs that such splitting
is beneficial.

The patch passed bootstrapping and regression tests on x86_64-unknown-linux-gnu 
system.

Is it OK to commit?

Thanks,

Changpeng 
From 415012803abf2cac95c067394504c55dd968f4f5 Mon Sep 17 00:00:00 2001
From: Changpeng Fang <chfang@huainan.(none)>
Date: Mon, 13 Jun 2011 13:13:32 -0700
Subject: [PATCH] pr49089: enable avx256 splitting unaligned load only when beneficial

	* config/i386/i386.h (ix86_tune_indices): Introduce
	  X86_TUNE_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL.
	  (TARGET_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL): New definition.

	* config/i386/i386.c (ix86_tune_features): Add entry for
	  X86_TUNE_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL.
	  (ix86_option_override_internal): Enable avx256 unaligned load splitting
	  only when TARGET_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL is set.
---
 gcc/config/i386/i386.c |    9 +++++++--
 gcc/config/i386/i386.h |    3 +++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 7b266b9..d5f358f 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -2088,7 +2088,11 @@ static unsigned int initial_ix86_tune_features[X86_TUNE_LAST] = {
   /* X86_SOFTARE_PREFETCHING_BENEFICIAL: Enable software prefetching
      at -O3.  For the moment, the prefetching seems badly tuned for Intel
      chips.  */
-  m_K6_GEODE | m_AMD_MULTIPLE
+  m_K6_GEODE | m_AMD_MULTIPLE,
+
+  /* X86_TUNE_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL: Enable splitting 256-bit
+     unaligned load.  It hurts the performance on Bulldozer.  */
+  m_COREI7
 };
 
 /* Feature tests against the various architecture variations.  */
@@ -4194,7 +4198,8 @@ ix86_option_override_internal (bool main_args_p)
 	  if (flag_expensive_optimizations
 	      && !(target_flags_explicit & MASK_VZEROUPPER))
 	    target_flags |= MASK_VZEROUPPER;
-	  if (!(target_flags_explicit & MASK_AVX256_SPLIT_UNALIGNED_LOAD))
+	  if (TARGET_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL
+	      && !(target_flags_explicit & MASK_AVX256_SPLIT_UNALIGNED_LOAD))
 	    target_flags |= MASK_AVX256_SPLIT_UNALIGNED_LOAD;
 	  if (!(target_flags_explicit & MASK_AVX256_SPLIT_UNALIGNED_STORE))
 	    target_flags |= MASK_AVX256_SPLIT_UNALIGNED_STORE;
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 8badcbb..b2a1bc8 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -312,6 +312,7 @@ enum ix86_tune_indices {
   X86_TUNE_OPT_AGU,
   X86_TUNE_VECTORIZE_DOUBLE,
   X86_TUNE_SOFTWARE_PREFETCHING_BENEFICIAL,
+  X86_TUNE_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL,
 
   X86_TUNE_LAST
 };
@@ -410,6 +411,8 @@ extern unsigned char ix86_tune_features[X86_TUNE_LAST];
 	ix86_tune_features[X86_TUNE_VECTORIZE_DOUBLE]
 #define TARGET_SOFTWARE_PREFETCHING_BENEFICIAL \
 	ix86_tune_features[X86_TUNE_SOFTWARE_PREFETCHING_BENEFICIAL]
+#define TARGET_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL \
+	ix86_tune_features[X86_TUNE_AVX256_SPLIT_UNALIGNED_LOAD_OPTIMAL]
 
 /* Feature tests against the various architecture variations.  */
 enum ix86_arch_indices {
-- 
1.7.0.4