re PR tree-optimization/43432 (Missed vectorization: "complicated access pattern" for increasing and decreasing data indexing)

	PR tree-optimization/43432
	* tree-vect-data-refs.c (vect_analyze_data_ref_access):
	Accept backwards consecutive accesses.
	(vect_create_data_ref_ptr): If step is negative generate
	decreasing IVs.
	* tree-vect-stmts.c (vectorizable_store): Reject negative steps.
	(perm_mask_for_reverse, reverse_vec_elements): New functions.
	(vectorizable_load): Handle loads with negative steps when easily
	possible.

testsuite/
	PR tree-optimization/43432
	* lib/target-supports.exp (check_effective_target_vect_perm_byte,
	check_effective_target_vect_perm_short): New predicates.
	(check_effective_target_vect_perm): Include x86_64.
	* gcc.dg/vect/pr43432.c: New test.
	* gcc.dg/vect/vect-114.c: Adjust.
	* gcc.dg/vect/vect-15.c: Ditto.
	* gcc.dg/vect/slp-perm-8.c: Use new predicate.
	* gcc.dg/vect/slp-perm-9.c: Ditto.

From-SVN: r164367

7 files changed, 77 insertions, 6 deletions

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 43ea053..55f05f4 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,15 @@
+2010-09-17  Michael Matz  <matz@suse.de>
+
+	PR tree-optimization/43432
+	* lib/target-supports.exp (check_effective_target_vect_perm_byte,
+	check_effective_target_vect_perm_short): New predicates.
+	(check_effective_target_vect_perm): Include x86_64.
+	* gcc.dg/vect/pr43432.c: New test.
+	* gcc.dg/vect/vect-114.c: Adjust.
+	* gcc.dg/vect/vect-15.c: Ditto.
+	* gcc.dg/vect/slp-perm-8.c: Use new predicate.
+	* gcc.dg/vect/slp-perm-9.c: Ditto.
+
 2010-09-17  Nicola Pero  <nicola.pero@meta-innovation.com>
 
 	PR testsuite/45692	
diff --git a/gcc/testsuite/gcc.dg/vect/pr43432.c b/gcc/testsuite/gcc.dg/vect/pr43432.c
new file mode 100644
index 0000000..3070318
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr43432.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target vect_float } */
+/* { dg-options "-O3 -ffast-math -fdump-tree-vect-details" } */
+
+
+void vector_fmul_reverse_c(float *dst, const float *src0, const float *src1,
+int len){
+    int i;
+    src1 += len-1;
+    for(i=0; i<len; i++)
+        dst[i] = src0[i] * src1[-i];
+}
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target { vect_perm } } } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/slp-perm-8.c b/gcc/testsuite/gcc.dg/vect/slp-perm-8.c
index 28c3529..deec308 100644
--- a/gcc/testsuite/gcc.dg/vect/slp-perm-8.c
+++ b/gcc/testsuite/gcc.dg/vect/slp-perm-8.c
@@ -53,7 +53,7 @@ int main (int argc, const char* argv[])
   return 0;
 }
 
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target vect_perm } } } */
-/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target vect_perm } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 2 "vect" { target vect_perm_byte } } } */
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1 "vect" { target vect_perm_byte } } } */
 /* { dg-final { cleanup-tree-dump "vect" } } */
 
diff --git a/gcc/testsuite/gcc.dg/vect/slp-perm-9.c b/gcc/testsuite/gcc.dg/vect/slp-perm-9.c
index 5c5176e..f438729 100644
--- a/gcc/testsuite/gcc.dg/vect/slp-perm-9.c
+++ b/gcc/testsuite/gcc.dg/vect/slp-perm-9.c
@@ -54,7 +54,7 @@ int main (int argc, const char* argv[])
 }
 
 /* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect"  } } */
-/* { dg-final { scan-tree-dump-times "permutation requires at least three vectors" 1 "vect" { target vect_perm } } } */
+/* { dg-final { scan-tree-dump-times "permutation requires at least three vectors" 1 "vect" { target vect_perm_short } } } */
 /* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 0 "vect"  } } */
 /* { dg-final { cleanup-tree-dump "vect" } } */
 
diff --git a/gcc/testsuite/gcc.dg/vect/vect-114.c b/gcc/testsuite/gcc.dg/vect/vect-114.c
index 035c9a8..f9132ac 100644
--- a/gcc/testsuite/gcc.dg/vect/vect-114.c
+++ b/gcc/testsuite/gcc.dg/vect/vect-114.c
@@ -34,6 +34,7 @@ int main (void)
   return main1 ();
 }
 
-/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" } } */
+/* { dg-final { scan-tree-dump-times "vectorized 0 loops" 1 "vect" { target { ! vect_perm } } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_perm } } } */
 /* { dg-final { cleanup-tree-dump "vect" } } */
 
diff --git a/gcc/testsuite/gcc.dg/vect/vect-15.c b/gcc/testsuite/gcc.dg/vect/vect-15.c
index b2ae9c8..87853c1 100644
--- a/gcc/testsuite/gcc.dg/vect/vect-15.c
+++ b/gcc/testsuite/gcc.dg/vect/vect-15.c
@@ -35,5 +35,5 @@ int main (void)
   return main1 ();
 }
 
-/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { xfail *-*-* } } } */
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" { target vect_perm } } } */
 /* { dg-final { cleanup-tree-dump "vect" } } */
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index 864f14e..c03b9f6 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -2425,7 +2425,8 @@ proc check_effective_target_vect_perm { } {
     } else {
         set et_vect_perm_saved 0
         if { [istarget powerpc*-*-*]
-             || [istarget spu-*-*] } {
+             || [istarget spu-*-*]
+	     || [istarget x86_64-*-*] } {
             set et_vect_perm_saved 1
         }
     }
@@ -2433,6 +2434,48 @@ proc check_effective_target_vect_perm { } {
     return $et_vect_perm_saved
 }
 
+# Return 1 if the target plus current options supports vector permutation
+# on byte-sized elements, 0 otherwise.
+#
+# This won't change for different subtargets so cache the result.
+
+proc check_effective_target_vect_perm_byte { } {
+    global et_vect_perm_byte
+
+    if [info exists et_vect_perm_byte_saved] {
+        verbose "check_effective_target_vect_perm_byte: using cached result" 2
+    } else {
+        set et_vect_perm_byte_saved 0
+        if { [istarget powerpc*-*-*]
+             || [istarget spu-*-*] } {
+            set et_vect_perm_byte_saved 1
+        }
+    }
+    verbose "check_effective_target_vect_perm_byte: returning $et_vect_perm_byte_saved" 2
+    return $et_vect_perm_byte_saved
+}
+
+# Return 1 if the target plus current options supports vector permutation
+# on short-sized elements, 0 otherwise.
+#
+# This won't change for different subtargets so cache the result.
+
+proc check_effective_target_vect_perm_short { } {
+    global et_vect_perm_short
+
+    if [info exists et_vect_perm_short_saved] {
+        verbose "check_effective_target_vect_perm_short: using cached result" 2
+    } else {
+        set et_vect_perm_short_saved 0
+        if { [istarget powerpc*-*-*]
+             || [istarget spu-*-*] } {
+            set et_vect_perm_short_saved 1
+        }
+    }
+    verbose "check_effective_target_vect_perm_short: returning $et_vect_perm_short_saved" 2
+    return $et_vect_perm_short_saved
+}
+
 # Return 1 if the target plus current options supports a vector
 # widening summation of *short* args into *int* result, 0 otherwise.
 #