diff mbox series

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

Message ID 1641814452-23872-1-git-send-email-apinski@marvell.com
State New
Headers show
Series None | expand

Commit Message

Pop, Sebastian via Gcc-patches Jan. 10, 2022, 11:34 a.m. UTC
From: Andrew Pinski <apinski@marvell.com>

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.

OK? Bootstrapped and tested on aarch64-linux-gnu with no regressions.

	PR target/64821

gcc/ChangeLog:

	* config/aarch64/aarch64-builtins.c
	(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.
---
 gcc/config/aarch64/aarch64-builtins.c      |  7 ++++++
 gcc/testsuite/gcc.target/aarch64/vsqrt-1.c | 17 +++++++++++++
 gcc/testsuite/gcc.target/aarch64/vsqrt-2.c | 28 ++++++++++++++++++++++
 3 files changed, 52 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/vsqrt-1.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/vsqrt-2.c

Comments

Richard Sandiford Jan. 10, 2022, 12:15 p.m. UTC | #1
apinski--- via Gcc-patches <gcc-patches@gcc.gnu.org> writes:
> From: Andrew Pinski <apinski@marvell.com>
>
> 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.
>
> OK? Bootstrapped and tested on aarch64-linux-gnu with no regressions.
>
> 	PR target/64821
>
> gcc/ChangeLog:
>
> 	* config/aarch64/aarch64-builtins.c
> 	(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.
> ---
>  gcc/config/aarch64/aarch64-builtins.c      |  7 ++++++
>  gcc/testsuite/gcc.target/aarch64/vsqrt-1.c | 17 +++++++++++++
>  gcc/testsuite/gcc.target/aarch64/vsqrt-2.c | 28 ++++++++++++++++++++++
>  3 files changed, 52 insertions(+)
>  create mode 100644 gcc/testsuite/gcc.target/aarch64/vsqrt-1.c
>  create mode 100644 gcc/testsuite/gcc.target/aarch64/vsqrt-2.c
>
> diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c
> index 58bcbd9875f..1bf487477eb 100644
> --- a/gcc/config/aarch64/aarch64-builtins.c
> +++ b/gcc/config/aarch64/aarch64-builtins.c
> @@ -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]);

Sorry for the nit-pick, but: IMO it looks odd to split this over two lines.

> +	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 00000000000..3207c8774ca
> --- /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-times ".SQRT" 0 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "2.0" 1 "optimized" } } */

I think these would be better as scan-tree-dump-not and scan-tree-dump
respectively.  The number of 2.0s isn't important and 2.0 has the risk
of matching someone's directory name.  Probably worth backslash-quoting
the "."s too.

OK with those changes, thanks.

Richard

> +/* { dg-final { scan-assembler-times "fsqrt" 0 } } */
> +/* 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 00000000000..7465b79f3a7
> --- /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" 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);
> +}
diff mbox series

Patch

diff --git a/gcc/config/aarch64/aarch64-builtins.c b/gcc/config/aarch64/aarch64-builtins.c
index 58bcbd9875f..1bf487477eb 100644
--- a/gcc/config/aarch64/aarch64-builtins.c
+++ b/gcc/config/aarch64/aarch64-builtins.c
@@ -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 00000000000..3207c8774ca
--- /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-times ".SQRT" 0 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "2.0" 1 "optimized" } } */
+/* { dg-final { scan-assembler-times "fsqrt" 0 } } */
+/* 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 00000000000..7465b79f3a7
--- /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" 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);
+}