* config/i386/x86-tune.def: Enable X86_TUNE_SSE_TYPELESS_STORES

	for generic, enable X86_TUNE_SSE_LOAD0_BY_PXOR for Bulldozer,
	Bobcat and generic.

	* gcc.target/i386/avx256-unaligned-store-3.c: Update template for
	tuning change.
	* gcc.target/i386/avx256-unaligned-store-1.c: Likewise.
	* gcc.target/i386/pr49168-1.c: Likewise.
	* gcc.target/i386/pr49002-2.c: Likewise.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@203387 138bc75d-0d04-0410-961f-82ee72b054a4

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index e91562f..0e3efc3 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2013-10-10  Jan Hubicka  <jh@suse.cz>
+
+       * config/i386/x86-tune.def: Enable X86_TUNE_SSE_TYPELESS_STORES
+       for generic, enable X86_TUNE_SSE_LOAD0_BY_PXOR for Bulldozer,
+       Bobcat and generic.
+
 2013-10-10  Jakub Jelinek  <jakub@redhat.com>
 
        PR middle-end/58670

diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 6b0a593..34484a2 100644 (file)
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -221,16 +221,14 @@ DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL, "sse_packed_single_insn_optim
    upper part undefined.  */
 DEF_TUNE (X86_TUNE_SSE_SPLIT_REGS, "sse_split_regs", m_ATHLON_K8)
 
-/* X86_TUNE_SSE_TYPELESS_STORES: Always movaps/movups for 128bit stores. 
-   FIXME: Shall we enable it for generic?  */
+/* X86_TUNE_SSE_TYPELESS_STORES: Always movaps/movups for 128bit stores.   */
 DEF_TUNE (X86_TUNE_SSE_TYPELESS_STORES, "sse_typeless_stores",
-         m_AMD_MULTIPLE | m_CORE_ALL)
+         m_AMD_MULTIPLE | m_CORE_ALL | m_GENERIC)
 
 /* X86_TUNE_SSE_LOAD0_BY_PXOR: Always use pxor to load0 as opposed to
-   xorps/xorpd and other variants.
-   FIXME: Shall we enable it buldozers and for generic?  */
+   xorps/xorpd and other variants.  */
 DEF_TUNE (X86_TUNE_SSE_LOAD0_BY_PXOR, "sse_load0_by_pxor",
-         m_PPRO | m_P4_NOCONA | m_CORE_ALL)
+         m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BDVER | m_BTVER | m_GENERIC)
 
 /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by
    full sized loads.  */

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 5e4882a..92b24ea 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,11 @@
+2013-10-10  Jan Hubicka  <jh@suse.cz>
+
+       * gcc.target/i386/avx256-unaligned-store-3.c: Update template for
+       tuning change.
+       * gcc.target/i386/avx256-unaligned-store-1.c: Likewise.
+       * gcc.target/i386/pr49168-1.c: Likewise.
+       * gcc.target/i386/pr49002-2.c: Likewise.
+
 2013-10-10  Jakub Jelinek  <jakub@redhat.com>
 
        PR middle-end/58670

diff --git a/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-2.c b/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-2.c
index 977662b..48e2efa 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-2.c
+++ b/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-2.c
@@ -24,5 +24,5 @@ avx_test (void)
 }
 
 /* { dg-final { scan-assembler-not "avx_storedqu256" } } */
-/* { dg-final { scan-assembler "vmovdqu.*\\*movv16qi_internal/3" } } */
+/* { dg-final { scan-assembler "vmovups.*\\*movv16qi_internal/3" } } */
 /* { dg-final { scan-assembler "vextract.128" } } */

diff --git a/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-3.c b/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-3.c
index e6744a8..6175d52 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-3.c
+++ b/gcc/testsuite/gcc.target/i386/avx256-unaligned-store-3.c
@@ -18,5 +18,5 @@ avx_test (void)
 }
 
 /* { dg-final { scan-assembler-not "avx_storeupd256" } } */
-/* { dg-final { scan-assembler "vmovupd.*\\*movv2df_internal/3" } } */
+/* { dg-final { scan-assembler "vmovups.*\\*movv2df_internal/3" } } */
 /* { dg-final { scan-assembler "vextractf128" } } */

diff --git a/gcc/testsuite/gcc.target/i386/pr49002-2.c b/gcc/testsuite/gcc.target/i386/pr49002-2.c
index b0e1009..9f21a2d 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr49002-2.c
+++ b/gcc/testsuite/gcc.target/i386/pr49002-2.c
@@ -11,4 +11,5 @@ void foo(const __m128d from, __m256d *to)
 
 /* Ensure we store ymm, not xmm.  */
 /* { dg-final { scan-assembler-not "vmovapd\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */
-/* { dg-final { scan-assembler "vmovapd\[\t \]*%ymm\[0-9\]\+,\[^,\]*" } } */
+/* { dg-final { scan-assembler-not "vmovaps\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */
+/* { dg-final { scan-assembler "vmovaps\[\t \]*%ymm\[0-9\]\+,\[^,\]*" } } */

diff --git a/gcc/testsuite/gcc.target/i386/pr49168-1.c b/gcc/testsuite/gcc.target/i386/pr49168-1.c
index 9676dc8..4ca5e34 100644 (file)
--- a/gcc/testsuite/gcc.target/i386/pr49168-1.c
+++ b/gcc/testsuite/gcc.target/i386/pr49168-1.c
@@ -2,7 +2,8 @@
 /* { dg-do compile } */
 /* { dg-options "-O2 -msse2 -mtune=generic" } */
 /* { dg-final { scan-assembler-not "movdqa\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */
-/* { dg-final { scan-assembler "movdqu\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */
+/* { dg-final { scan-assembler-not "movaps\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */
+/* { dg-final { scan-assembler "movups\[\t \]*%xmm\[0-9\]\+,\[^,\]*" } } */
 
 void
 flt128_va (void *mem, __float128 d)