[AARCH64] Fix support for vectorization over sqrt (), sqrtf ().

gcc/
	* config/aarch64/aarch64-builtins.c
	(aarch64_builtin_vectorized_function): Handle sqrt, sqrtf.

gcc/testsuite/
	* gcc.target/aarch64/vsqrt.c (test_square_root_v2sf): Use
	endian-safe float pool loading.
	(test_square_root_v4sf): Likewise.
	(test_square_root_v2df): Likewise.
	* lib/target-supports.exp
	(check_effective_target_vect_call_sqrtf): Add AArch64.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@195017 138bc75d-0d04-0410-961f-82ee72b054a4

5 files changed, 28 insertions, 4 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index a4c8481ff55..478b4edbdf6 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2013-01-08  James Greenhalgh  <james.greenhalgh@arm.com>
+
+	* config/aarch64/aarch64-builtins.c
+	(aarch64_builtin_vectorized_function): Handle sqrt, sqrtf.
+
 2013-01-08  Martin Jambor  <mjambor@suse.cz>
 
 	PR debug/55579
diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c
index a683afd0bb6..f54e9f4a68d 100644
--- a/gcc/config/aarch64/aarch64-builtins.c
+++ b/gcc/config/aarch64/aarch64-builtins.c
@@ -1271,6 +1271,9 @@ aarch64_builtin_vectorized_function (tree fndecl, tree type_out, tree type_in)
 	case BUILT_IN_NEARBYINT:
 	case BUILT_IN_NEARBYINTF:
 	  return AARCH64_FIND_FRINT_VARIANT (frinti);
+	case BUILT_IN_SQRT:
+	case BUILT_IN_SQRTF:
+	  return AARCH64_FIND_FRINT_VARIANT (sqrt);
 #undef AARCH64_CHECK_BUILTIN_MODE
 #define AARCH64_CHECK_BUILTIN_MODE(C, N) \
   (out_mode == N##Imode && out_n == C \
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 5d6acaf6194..a2ef1e84122 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2013-01-08  James Greenhalgh  <james.greenhalgh@arm.com>
+
+	* gcc.target/aarch64/vsqrt.c (test_square_root_v2sf): Use
+	endian-safe float pool loading.
+	(test_square_root_v4sf): Likewise.
+	(test_square_root_v2df): Likewise.
+	* lib/target-supports.exp
+	(check_effective_target_vect_call_sqrtf): Add AArch64.
+
 2013-01-08  Martin Jambor  <mjambor@suse.cz>
 
 	PR debug/55579
diff --git a/gcc/testsuite/gcc.target/aarch64/vsqrt.c b/gcc/testsuite/gcc.target/aarch64/vsqrt.c
index b59535a9b5f..5b777b236da 100644
--- a/gcc/testsuite/gcc.target/aarch64/vsqrt.c
+++ b/gcc/testsuite/gcc.target/aarch64/vsqrt.c
@@ -11,9 +11,11 @@ extern void abort (void);
 void
 test_square_root_v2sf ()
 {
-  float32x2_t val = {4.0f, 9.0f};
+  const float32_t pool[] = {4.0f, 9.0f};
+  float32x2_t val;
   float32x2_t res;
 
+  val = vld1_f32 (pool);
   res = vsqrt_f32 (val);
 
   if (vget_lane_f32 (res, 0) != 2.0f)
@@ -25,9 +27,11 @@ test_square_root_v2sf ()
 void
 test_square_root_v4sf ()
 {
-  float32x4_t val = {4.0f, 9.0f, 16.0f, 25.0f};
+  const float32_t pool[] = {4.0f, 9.0f, 16.0f, 25.0f};
+  float32x4_t val;
   float32x4_t res;
 
+  val = vld1q_f32 (pool);
   res = vsqrtq_f32 (val);
 
   if (vgetq_lane_f32 (res, 0) != 2.0f)
@@ -43,9 +47,11 @@ test_square_root_v4sf ()
 void
 test_square_root_v2df ()
 {
-  float64x2_t val = {4.0, 9.0};
+  const float64_t pool[] = {4.0, 9.0};
+  float64x2_t val;
   float64x2_t res;
 
+  val = vld1q_f64 (pool);
   res = vsqrtq_f64 (val);
 
   if (vgetq_lane_f64 (res, 0) != 2.0)
diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp
index a3828cbbec6..a6d766e279f 100644
--- a/gcc/testsuite/lib/target-supports.exp
+++ b/gcc/testsuite/lib/target-supports.exp
@@ -3952,7 +3952,8 @@ proc check_effective_target_vect_call_sqrtf { } {
 	verbose "check_effective_target_vect_call_sqrtf: using cached result" 2
     } else {
 	set et_vect_call_sqrtf_saved 0
-	if { [istarget i?86-*-*]
+	if { [istarget aarch64*-*-*]
+	     || [istarget i?86-*-*]
 	     || [istarget x86_64-*-*]
 	     || ([istarget powerpc*-*-*] && [check_vsx_hw_available]) } {
 	    set et_vect_call_sqrtf_saved 1