[aarch64/64821]: Simplify __builtin_aarch64_sqrt* into internal function .SQRT.

This is a simple patch which simplifies the __builtin_aarch64_sqrt* builtins
into the internal function SQRT which allows for constant folding and other
optimizations at the gimple level. It was originally suggested we do to
__builtin_sqrt just for __builtin_aarch64_sqrtdf when -fno-math-errno
but since r6-4969-g686ee9719a4 we have the internal function SQRT which does
the same so it makes we don't need to check -fno-math-errno either now.

Applied as approved after bootstrapped and tested on aarch64-linux-gnu with no regressions.

	PR target/64821

gcc/ChangeLog:

	* config/aarch64/aarch64-builtins.cc
	(aarch64_general_gimple_fold_builtin): Handle
	__builtin_aarch64_sqrt* and simplify into SQRT internal
	function.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/vsqrt-1.c: New test.
	* gcc.target/aarch64/vsqrt-2.c: New test.

3 files changed, 52 insertions, 0 deletions

diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index b7f338d..5217dbd 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -2820,6 +2820,13 @@ aarch64_general_gimple_fold_builtin (unsigned int fcode, gcall *stmt,
 	gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
 	break;
 
+      /* Lower sqrt builtins to gimple/internal function sqrt. */
+      BUILTIN_VHSDF_DF (UNOP, sqrt, 2, FP)
+	new_stmt = gimple_build_call_internal (IFN_SQRT,
+					       1, args[0]);
+	gimple_call_set_lhs (new_stmt, gimple_call_lhs (stmt));
+	break;
+
      /*lower store and load neon builtins to gimple.  */
      BUILTIN_VALL_F16 (LOAD1, ld1, 0, LOAD)
      BUILTIN_VDQ_I (LOAD1_U, ld1, 0, LOAD)
diff --git a/gcc/testsuite/gcc.target/aarch64/vsqrt-1.c b/gcc/testsuite/gcc.target/aarch64/vsqrt-1.c
new file mode 100644
index 0000000..e614c7d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vsqrt-1.c
@@ -0,0 +1,17 @@
+/* PR target/64821 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+/* Check that we constant fold sqrt(4.0) into 2.0. */
+/* { dg-final { scan-tree-dump-not " \\\.SQRT" "optimized" } } */
+/* { dg-final { scan-tree-dump " 2\\\.0e\\\+0" "optimized" } } */
+/* { dg-final { scan-assembler-not "fsqrt" } } */
+/* We should produce a fmov to d0 with 2.0 but currently don't, see PR 103959. */
+/* { dg-final { scan-assembler-times "\n\tfmov\td0, 2.0e.0" 1 { xfail *-*-* } } } */
+
+#include <arm_neon.h>
+
+float64x1_t f64(void)
+{
+   float64x1_t a = (float64x1_t){4.0};
+   return vsqrt_f64 (a);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/vsqrt-2.c b/gcc/testsuite/gcc.target/aarch64/vsqrt-2.c
new file mode 100644
index 0000000..4dea4da
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vsqrt-2.c
@@ -0,0 +1,28 @@
+/* PR target/64821 */
+/* { dg-do compile } */
+/* { dg-options "-fdump-tree-optimized" } */
+#include <arm_neon.h>
+
+/* Check that we lower __builtin_aarch64_sqrt* into the internal function SQRT. */
+/* { dg-final { scan-tree-dump-times " __builtin_aarch64_sqrt" 0 "optimized" } } */
+/* { dg-final { scan-tree-dump-times " \\\.SQRT " 4 "optimized" } } */
+
+float64x1_t f64(float64x1_t a)
+{
+      return vsqrt_f64 (a);
+}
+
+float64x2_t f64q(float64x2_t a)
+{
+      return vsqrtq_f64 (a);
+}
+
+float32x2_t f32(float32x2_t a)
+{
+      return vsqrt_f32 (a);
+}
+
+float32x4_t f32q(float32x4_t a)
+{
+      return vsqrtq_f32 (a);
+}