aarch64: Add support for AdvSIMD faminmax

Message ID 20240801091410.2466996-1-saurabh.jha@arm.com
State New
Headers
Series aarch64: Add support for AdvSIMD faminmax |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 fail Patch failed to apply
linaro-tcwg-bot/tcwg_gcc_build--master-arm fail Patch failed to apply

Commit Message

Saurabh@sourceware.org, Jha@sourceware.org Aug. 1, 2024, 9:14 a.m. UTC
  The AArch64 FEAT_FAMINMAX extension is optional from Armv9.2-a and
mandatory from Armv9.5-a. It introduces instructions for computing the
floating point absolute maximum and minimum of the two vectors element-wise.

This patch does three things:
1. Introduces AdvSIMD faminmax intrinsics.
2. Adds code generation support for famax and famin in terms of the
   existing operators.
3. Move report_missing_extension and reported_missing_extension_p to
   make it more usable.

The intrinsics of this extension are implemented as the following
builtin functions:
* vamax_f16
* vamaxq_f16
* vamax_f32
* vamaxq_f32
* vamaxq_f64
* vamin_f16
* vaminq_f16
* vamin_f32
* vaminq_f32
* vaminq_f64

For code generation, famax/famin is equivalent to first taking fabs of
the operands and then taking fmax/fmin of the results of fabs.
	famax/famin (a, b) = fmax/fmin (fabs (a), fabs (b))
This is correct because NaN/Inf handling of famax/famin and fmax/fmin
are same. We cannot use fmaxnm/fminnm here as Nan/Inf are handled
differently in them.

We moved the definition of `report_missing_extension` from
gcc/config/aarch64/aarch64-sve-builtins.cc to
gcc/config/aarch64/aarch64-builtins.cc and its declaration to
gcc/config/aarch64/aarch64-builtins.h. We also moved the declaration
of `reported_missing_extension_p` from
gcc/config/aarch64/aarch64-sve-builtins.cc
to gcc/config/aarch64/aarch64-builtins.cc, closer to the definition of
`report_missing_extension`. In the exsiting code structure, this leads
to `report_missing_extension` being usable from both normal builtins
and sve builtins.

gcc/ChangeLog:

	* config/aarch64/aarch64-builtins.cc
	(enum aarch64_builtins): New enum values for faminmax builtins.
	(aarch64_init_faminmax_builtins): New function to declare new builtins.
	(handle_arm_neon_h): Modify to call aarch64_init_faminmax_builtins.
	(aarch64_general_check_builtin_call): Modify to check whether +faminmax flag is being used and printing error message if not being used.
	(aarch64_expand_builtin_faminmax): New function to emit instructions of this extension.
	(aarch64_general_expand_builtin): Modify to call aarch64_expand_builtin_faminmax.
	(report_missing_extension): Move from config/aarch64/aarch64-sve-builtins.cc.
	* config/aarch64/aarch64-builtins.h
	(report_missing_extension): Declaration for this function so
that it can be used wherever this header is included.
	(reported_missing_extension_p): Move from
config/aarch64/aarch64-sve-builtins.cc
        * config/aarch64/aarch64-option-extensions.def
	(AARCH64_OPT_EXTENSION): Introduce new flag for this extension.
        * config/aarch64/aarch64-simd.md
	(aarch64_<faminmax><mode>): Introduce instruction pattern for this extension.
	* config/aarch64/aarch64-sve-builtins.cc
	(reported_missing_extension_p): Move to config/aarch64/aarch64-builtins.cc
	(report_missing_extension): Move to
config/aarch64/aarch64-builtins.cc.
        * config/aarch64/aarch64.h
	(TARGET_FAMINMAX): Introduce new flag for this extension.
        * config/aarch64/iterators.md: Introduce new iterators for this extension.
        * config/arm/types.md: Introduce neon_fp_aminmax<q> attributes.
        * doc/invoke.texi: Document extension in AArch64 Options.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/simd/faminmax-builtins-no-flag.c: New test.
	* gcc.target/aarch64/simd/faminmax-builtins.c: New test.
	* gcc.target/aarch64/simd/faminmax-codegen-no-flag.c: New test.
	* gcc.target/aarch64/simd/faminmax-codegen.c: New test.

---
Hi,

Regression tested for aarch64-none-linux-gnu and found no regressions.

This patch is a revised version of an earlier patch
https://gcc.gnu.org/pipermail/gcc-patches/2024-July/657914.html but has
more scope than that. That's why I didn't add "v2" in the subject line.

Ok for master? I don't have commit access so can someone please commit
on my behalf?

Regards,
Saurabh
---
 gcc/config/aarch64/aarch64-builtins.cc        | 173 +++++++++++++++++-
 gcc/config/aarch64/aarch64-builtins.h         |   5 +-
 .../aarch64/aarch64-option-extensions.def     |   2 +
 gcc/config/aarch64/aarch64-simd.md            |  12 ++
 gcc/config/aarch64/aarch64-sve-builtins.cc    |  22 ---
 gcc/config/aarch64/aarch64.h                  |   4 +
 gcc/config/aarch64/iterators.md               |   8 +
 gcc/config/arm/types.md                       |   6 +
 gcc/doc/invoke.texi                           |   2 +
 .../aarch64/simd/faminmax-builtins-no-flag.c  |  10 +
 .../aarch64/simd/faminmax-builtins.c          |  75 ++++++++
 .../aarch64/simd/faminmax-codegen-no-flag.c   |  54 ++++++
 .../aarch64/simd/faminmax-codegen.c           | 104 +++++++++++
 13 files changed, 445 insertions(+), 32 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen-no-flag.c
 create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen.c
  

Comments

Kyrylo Tkachov Aug. 2, 2024, 8:10 a.m. UTC | #1
Hi Saurabh,

> On 1 Aug 2024, at 11:14, Saurabh Jha wrote:
> 
> External email: Use caution opening links or attachments
> 
> 
> The AArch64 FEAT_FAMINMAX extension is optional from Armv9.2-a and
> mandatory from Armv9.5-a. It introduces instructions for computing the
> floating point absolute maximum and minimum of the two vectors element-wise.
> 
> This patch does three things:
> 1. Introduces AdvSIMD faminmax intrinsics.
> 2. Adds code generation support for famax and famin in terms of the
>   existing operators.
> 3. Move report_missing_extension and reported_missing_extension_p to
>   make it more usable.
> 
> The intrinsics of this extension are implemented as the following
> builtin functions:
> * vamax_f16
> * vamaxq_f16
> * vamax_f32
> * vamaxq_f32
> * vamaxq_f64
> * vamin_f16
> * vaminq_f16
> * vamin_f32
> * vaminq_f32
> * vaminq_f64
> 
> For code generation, famax/famin is equivalent to first taking fabs of
> the operands and then taking fmax/fmin of the results of fabs.
>        famax/famin (a, b) = fmax/fmin (fabs (a), fabs (b))
> This is correct because NaN/Inf handling of famax/famin and fmax/fmin
> are same. We cannot use fmaxnm/fminnm here as Nan/Inf are handled
> differently in them.
> 

Thank you for the explanation.


> We moved the definition of `report_missing_extension` from
> gcc/config/aarch64/aarch64-sve-builtins.cc to
> gcc/config/aarch64/aarch64-builtins.cc and its declaration to
> gcc/config/aarch64/aarch64-builtins.h. We also moved the declaration
> of `reported_missing_extension_p` from
> gcc/config/aarch64/aarch64-sve-builtins.cc
> to gcc/config/aarch64/aarch64-builtins.cc, closer to the definition of
> `report_missing_extension`. In the exsiting code structure, this leads
> to `report_missing_extension` being usable from both normal builtins
> and sve builtins.

Thanks, this looks much better.


> 
> gcc/ChangeLog:
> 
>        * config/aarch64/aarch64-builtins.cc
>        (enum aarch64_builtins): New enum values for faminmax builtins.
>        (aarch64_init_faminmax_builtins): New function to declare new builtins.
>        (handle_arm_neon_h): Modify to call aarch64_init_faminmax_builtins.
>        (aarch64_general_check_builtin_call): Modify to check whether +faminmax flag is being used and printing error message if not being used.
>        (aarch64_expand_builtin_faminmax): New function to emit instructions of this extension.
>        (aarch64_general_expand_builtin): Modify to call aarch64_expand_builtin_faminmax.
>        (report_missing_extension): Move from config/aarch64/aarch64-sve-builtins.cc.
>        * config/aarch64/aarch64-builtins.h
>        (report_missing_extension): Declaration for this function so
> that it can be used wherever this header is included.
>        (reported_missing_extension_p): Move from
> config/aarch64/aarch64-sve-builtins.cc
>        * config/aarch64/aarch64-option-extensions.def
>        (AARCH64_OPT_EXTENSION): Introduce new flag for this extension.
>        * config/aarch64/aarch64-simd.md
>        (aarch64_<faminmax><mode>): Introduce instruction pattern for this extension.
>        * config/aarch64/aarch64-sve-builtins.cc
>        (reported_missing_extension_p): Move to config/aarch64/aarch64-builtins.cc
>        (report_missing_extension): Move to
> config/aarch64/aarch64-builtins.cc.
>        * config/aarch64/aarch64.h
>        (TARGET_FAMINMAX): Introduce new flag for this extension.
>        * config/aarch64/iterators.md: Introduce new iterators for this extension.
>        * config/arm/types.md: Introduce neon_fp_aminmax<q> attributes.
>        * doc/invoke.texi: Document extension in AArch64 Options.
> 
> gcc/testsuite/ChangeLog:
> 
>        * gcc.target/aarch64/simd/faminmax-builtins-no-flag.c: New test.
>        * gcc.target/aarch64/simd/faminmax-builtins.c: New test.
>        * gcc.target/aarch64/simd/faminmax-codegen-no-flag.c: New test.
>        * gcc.target/aarch64/simd/faminmax-codegen.c: New test.

The aarch64 backend parts look good, but I think the tests could be improved. Sorry for missing it out in the first review.


> 
> ---
> Hi,
> 
> Regression tested for aarch64-none-linux-gnu and found no regressions.
> 
> This patch is a revised version of an earlier patch
> https://gcc.gnu.org/pipermail/gcc-patches/2024-July/657914.html but has
> more scope than that. That's why I didn't add "v2" in the subject line.
> 
> Ok for master? I don't have commit access so can someone please commit
> on my behalf?
> 
> Regards,
> Saurabh
> ---
> gcc/config/aarch64/aarch64-builtins.cc        | 173 +++++++++++++++++-
> gcc/config/aarch64/aarch64-builtins.h         |   5 +-
> .../aarch64/aarch64-option-extensions.def     |   2 +
> gcc/config/aarch64/aarch64-simd.md            |  12 ++
> gcc/config/aarch64/aarch64-sve-builtins.cc    |  22 ---
> gcc/config/aarch64/aarch64.h                  |   4 +
> gcc/config/aarch64/iterators.md               |   8 +
> gcc/config/arm/types.md                       |   6 +
> gcc/doc/invoke.texi                           |   2 +
> .../aarch64/simd/faminmax-builtins-no-flag.c  |  10 +
> .../aarch64/simd/faminmax-builtins.c          |  75 ++++++++
> .../aarch64/simd/faminmax-codegen-no-flag.c   |  54 ++++++
> .../aarch64/simd/faminmax-codegen.c           | 104 +++++++++++
> 13 files changed, 445 insertions(+), 32 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c
> create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c
> create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen-no-flag.c
> create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen.c
> 


diff --git a/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c
new file mode 100644
index 00000000000..63ed1508c23
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c
@@ -0,0 +1,10 @@
+/* { dg-do assemble} */
+/* { dg-additional-options "-march=armv9-a" } */
+
+#include "arm_neon.h"
+
+void
+test (float32x4_t a, float32x4_t b)
+{
+  vamaxq_f32 (a, b); /* { dg-error {ACLE function 'vamaxq_f32' requires ISA extension 'faminmax'} } */
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c
new file mode 100644
index 00000000000..f2b5bafb81c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c
@@ -0,0 +1,75 @@
+/* { dg-do assemble} */
+/* { dg-additional-options "-march=armv9-a+faminmax" } */
+
+#include "arm_neon.h"
+
+float16x4_t
+test_vamax_f16 (float16x4_t a, float16x4_t b)
+{
+  return vamax_f16 (a, b);
+}
+
+float16x8_t
+test_vamaxq_f16 (float16x8_t a, float16x8_t b)
+{
+  return vamaxq_f16 (a, b);
+}
+
+float32x2_t
+test_vamax_f32 (float32x2_t a, float32x2_t b)
+{
+  return vamax_f32 (a, b);
+}
+
+float32x4_t
+test_vamaxq_f32 (float32x4_t a, float32x4_t b)
+{
+  return vamaxq_f32 (a, b);
+}
+
+float64x2_t
+test_vamaxq_f64 (float64x2_t a, float64x2_t b)
+{
+  return vamaxq_f64 (a, b);
+}
+
+float16x4_t
+test_vamin_f16 (float16x4_t a, float16x4_t b)
+{
+  return vamin_f16 (a, b);
+}
+
+float16x8_t
+test_vaminq_f16 (float16x8_t a, float16x8_t b)
+{
+  return vaminq_f16 (a, b);
+}
+
+float32x2_t
+test_vamin_f32 (float32x2_t a, float32x2_t b)
+{
+  return vamin_f32 (a, b);
+}
+
+float32x4_t
+test_vaminq_f32 (float32x4_t a, float32x4_t b)
+{
+  return vaminq_f32 (a, b);
+}
+
+float64x2_t
+test_vaminq_f64 (float64x2_t a, float64x2_t b)
+{
+  return vaminq_f64 (a, b);
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 1 } } */

We should use the check-function-bodies infrastructure to match the exact assembly for each of the test functions. You can grep around the gcc.target/aarch64 directory for examples of how to use that.

It would also be good to have some tests for generating these instructions from straight C code using __builtin_fmax/fmin and __builtin_fabs to make sure we’re not missing out on general codegen improvements from this work.

Thanks,
Kyrill
  

Patch

diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index 30669f8aa18..cd590186f22 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -829,6 +829,17 @@  enum aarch64_builtins
   AARCH64_RBIT,
   AARCH64_RBITL,
   AARCH64_RBITLL,
+  /* FAMINMAX builtins.  */
+  AARCH64_FAMINMAX_BUILTIN_FAMAX4H,
+  AARCH64_FAMINMAX_BUILTIN_FAMAX8H,
+  AARCH64_FAMINMAX_BUILTIN_FAMAX2S,
+  AARCH64_FAMINMAX_BUILTIN_FAMAX4S,
+  AARCH64_FAMINMAX_BUILTIN_FAMAX2D,
+  AARCH64_FAMINMAX_BUILTIN_FAMIN4H,
+  AARCH64_FAMINMAX_BUILTIN_FAMIN8H,
+  AARCH64_FAMINMAX_BUILTIN_FAMIN2S,
+  AARCH64_FAMINMAX_BUILTIN_FAMIN4S,
+  AARCH64_FAMINMAX_BUILTIN_FAMIN2D,
   /* System register builtins.  */
   AARCH64_RSR,
   AARCH64_RSRP,
@@ -1547,6 +1558,66 @@  aarch64_init_simd_builtin_functions (bool called_from_pragma)
     }
 }
 
+/* Initialize the absolute maximum/minimum (FAMINMAX) builtins.  */
+
+typedef struct
+{
+  const char *name;
+  unsigned int code;
+  tree eltype;
+  machine_mode mode;
+} faminmax_builtins_data;
+
+static void
+aarch64_init_faminmax_builtins ()
+{
+  faminmax_builtins_data data[] = {
+    /* Absolute maximum.  */
+    {"vamax_f16", AARCH64_FAMINMAX_BUILTIN_FAMAX4H,
+     aarch64_simd_types[Float16x4_t].eltype,
+     aarch64_simd_types[Float16x4_t].mode},
+    {"vamaxq_f16", AARCH64_FAMINMAX_BUILTIN_FAMAX8H,
+     aarch64_simd_types[Float16x8_t].eltype,
+     aarch64_simd_types[Float16x8_t].mode},
+    {"vamax_f32", AARCH64_FAMINMAX_BUILTIN_FAMAX2S,
+     aarch64_simd_types[Float32x2_t].eltype,
+     aarch64_simd_types[Float32x2_t].mode},
+    {"vamaxq_f32", AARCH64_FAMINMAX_BUILTIN_FAMAX4S,
+     aarch64_simd_types[Float32x4_t].eltype,
+     aarch64_simd_types[Float32x4_t].mode},
+    {"vamaxq_f64", AARCH64_FAMINMAX_BUILTIN_FAMAX2D,
+     aarch64_simd_types[Float64x2_t].eltype,
+     aarch64_simd_types[Float64x2_t].mode},
+    /* Absolute minimum.  */
+    {"vamin_f16", AARCH64_FAMINMAX_BUILTIN_FAMIN4H,
+     aarch64_simd_types[Float16x4_t].eltype,
+     aarch64_simd_types[Float16x4_t].mode},
+    {"vaminq_f16", AARCH64_FAMINMAX_BUILTIN_FAMIN8H,
+     aarch64_simd_types[Float16x8_t].eltype,
+     aarch64_simd_types[Float16x8_t].mode},
+    {"vamin_f32", AARCH64_FAMINMAX_BUILTIN_FAMIN2S,
+     aarch64_simd_types[Float32x2_t].eltype,
+     aarch64_simd_types[Float32x2_t].mode},
+    {"vaminq_f32", AARCH64_FAMINMAX_BUILTIN_FAMIN4S,
+     aarch64_simd_types[Float32x4_t].eltype,
+     aarch64_simd_types[Float32x4_t].mode},
+    {"vaminq_f64", AARCH64_FAMINMAX_BUILTIN_FAMIN2D,
+     aarch64_simd_types[Float64x2_t].eltype,
+     aarch64_simd_types[Float64x2_t].mode},
+  };
+
+  for (size_t i = 0; i < ARRAY_SIZE (data); ++i)
+    {
+      tree type
+	= build_vector_type (data[i].eltype, GET_MODE_NUNITS (data[i].mode));
+      tree fntype = build_function_type_list (type, type, type, NULL_TREE);
+      unsigned int code = data[i].code;
+      const char *name = data[i].name;
+      aarch64_builtin_decls[code]
+	= aarch64_general_simulate_builtin (name, fntype, code);
+    }
+}
+
 /* Register the tuple type that contains NUM_VECTORS of the AdvSIMD type
    indexed by TYPE_INDEX.  */
 static void
@@ -1640,6 +1711,7 @@  handle_arm_neon_h (void)
 
   aarch64_init_simd_builtin_functions (true);
   aarch64_init_simd_intrinsics ();
+  aarch64_init_faminmax_builtins ();
 }
 
 static void
@@ -2197,15 +2269,35 @@  aarch64_general_check_builtin_call (location_t location, vec<location_t>,
     case AARCH64_WSR64:
     case AARCH64_WSRF:
     case AARCH64_WSRF64:
-      tree addr = STRIP_NOPS (args[0]);
-      if (TREE_CODE (TREE_TYPE (addr)) != POINTER_TYPE
-	  || TREE_CODE (addr) != ADDR_EXPR
-	  || TREE_CODE (TREE_OPERAND (addr, 0)) != STRING_CST)
-	{
-	  error_at (location, "first argument to %qD must be a string literal",
-		    fndecl);
-	  return false;
-	}
+      {
+	tree addr = STRIP_NOPS (args[0]);
+	if (TREE_CODE (TREE_TYPE (addr)) != POINTER_TYPE
+	    || TREE_CODE (addr) != ADDR_EXPR
+	    || TREE_CODE (TREE_OPERAND (addr, 0)) != STRING_CST)
+	  {
+	    error_at (location,
+		      "first argument to %qD must be a string literal",
+		      fndecl);
+	    return false;
+	  }
+      }
+    case AARCH64_FAMINMAX_BUILTIN_FAMAX4H:
+    case AARCH64_FAMINMAX_BUILTIN_FAMAX8H:
+    case AARCH64_FAMINMAX_BUILTIN_FAMAX2S:
+    case AARCH64_FAMINMAX_BUILTIN_FAMAX4S:
+    case AARCH64_FAMINMAX_BUILTIN_FAMAX2D:
+    case AARCH64_FAMINMAX_BUILTIN_FAMIN4H:
+    case AARCH64_FAMINMAX_BUILTIN_FAMIN8H:
+    case AARCH64_FAMINMAX_BUILTIN_FAMIN2S:
+    case AARCH64_FAMINMAX_BUILTIN_FAMIN4S:
+    case AARCH64_FAMINMAX_BUILTIN_FAMIN2D:
+      {
+	if (!TARGET_FAMINMAX)
+	  {
+	    report_missing_extension (location, fndecl, "faminmax");
+	    return false;
+	  }
+      }
     }
   /* Default behavior.  */
   return true;
@@ -3071,6 +3163,44 @@  aarch64_expand_builtin_data_intrinsic (unsigned int fcode, tree exp, rtx target)
   return ops[0].value;
 }
 
+static rtx
+aarch64_expand_builtin_faminmax (unsigned int fcode, tree exp, rtx target)
+{
+  machine_mode mode = TYPE_MODE (TREE_TYPE (exp));
+  rtx op0 = force_reg (mode, expand_normal (CALL_EXPR_ARG (exp, 0)));
+  rtx op1 = force_reg (mode, expand_normal (CALL_EXPR_ARG (exp, 1)));
+
+  enum insn_code icode;
+  if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMAX4H)
+    icode = CODE_FOR_aarch64_famaxv4hf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMAX8H)
+    icode = CODE_FOR_aarch64_famaxv8hf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMAX2S)
+    icode = CODE_FOR_aarch64_famaxv2sf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMAX4S)
+    icode = CODE_FOR_aarch64_famaxv4sf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMAX2D)
+    icode = CODE_FOR_aarch64_famaxv2df;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMIN4H)
+    icode = CODE_FOR_aarch64_faminv4hf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMIN8H)
+    icode = CODE_FOR_aarch64_faminv8hf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMIN2S)
+    icode = CODE_FOR_aarch64_faminv2sf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMIN4S)
+    icode = CODE_FOR_aarch64_faminv4sf;
+  else if (fcode == AARCH64_FAMINMAX_BUILTIN_FAMIN2D)
+    icode = CODE_FOR_aarch64_faminv2df;
+  else
+    gcc_unreachable ();
+
+  rtx pat = GEN_FCN (icode) (target, op0, op1);
+
+  emit_insn (pat);
+
+  return target;
+}
+
 /* Expand an expression EXP as fpsr or fpcr setter (depending on
    UNSPEC) using MODE.  */
 static void
@@ -3250,6 +3380,9 @@  aarch64_general_expand_builtin (unsigned int fcode, tree exp, rtx target,
   if (fcode >= AARCH64_REV16
       && fcode <= AARCH64_RBITLL)
     return aarch64_expand_builtin_data_intrinsic (fcode, exp, target);
+  if (fcode >= AARCH64_FAMINMAX_BUILTIN_FAMAX4H
+      && fcode <= AARCH64_FAMINMAX_BUILTIN_FAMIN2D)
+    return aarch64_expand_builtin_faminmax (fcode, exp, target);
 
   gcc_unreachable ();
 }
@@ -3794,6 +3927,28 @@  aarch64_atomic_assign_expand_fenv (tree *hold, tree *clear, tree *update)
 			    reload_fenv, restore_fnenv), update_call);
 }
 
+/* True if we've already complained about attempts to use functions
+   when the required extension is disabled.  */
+static bool reported_missing_extension_p;
+
+/* Report an error against LOCATION that the user has tried to use
+   function FNDECL when extension EXTENSION is disabled.  */
+void
+report_missing_extension (location_t location, tree fndecl,
+			  const char *extension)
+{
+  /* Avoid reporting a slew of messages for a single oversight.  */
+  if (reported_missing_extension_p)
+    return;
+
+  error_at (location, "ACLE function %qD requires ISA extension %qs",
+	    fndecl, extension);
+  inform (location, "you can enable %qs using the command-line"
+	  " option %<-march%>, or by using the %<target%>"
+	  " attribute or pragma", extension);
+  reported_missing_extension_p = true;
+}
+
 /* Resolve overloaded MEMTAG build-in functions.  */
 #define AARCH64_BUILTIN_SUBCODE(F) \
   (DECL_MD_FUNCTION_CODE (F) >> AARCH64_BUILTIN_SHIFT)
diff --git a/gcc/config/aarch64/aarch64-builtins.h b/gcc/config/aarch64/aarch64-builtins.h
index e326fe66676..93e31a30ec6 100644
--- a/gcc/config/aarch64/aarch64-builtins.h
+++ b/gcc/config/aarch64/aarch64-builtins.h
@@ -96,4 +96,7 @@  struct GTY(()) aarch64_simd_type_info
 
 extern aarch64_simd_type_info aarch64_simd_types[];
 
-#endif
\ No newline at end of file
+void report_missing_extension (location_t location, tree fndecl,
+			       const char *extension);
+
+#endif
diff --git a/gcc/config/aarch64/aarch64-option-extensions.def b/gcc/config/aarch64/aarch64-option-extensions.def
index 42ec0eec31e..e95bd70893a 100644
--- a/gcc/config/aarch64/aarch64-option-extensions.def
+++ b/gcc/config/aarch64/aarch64-option-extensions.def
@@ -232,6 +232,8 @@  AARCH64_OPT_EXTENSION("the", THE, (), (), (), "the")
 
 AARCH64_OPT_EXTENSION("gcs", GCS, (), (), (), "gcs")
 
+AARCH64_OPT_EXTENSION("faminmax", FAMINMAX, (SIMD), (), (), "faminmax")
+
 #undef AARCH64_OPT_FMV_EXTENSION
 #undef AARCH64_OPT_EXTENSION
 #undef AARCH64_FMV_FEATURE
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index bbeee221f37..6fab2f5a976 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -9881,3 +9881,15 @@ 
   "shl\\t%d0, %d1, #16"
   [(set_attr "type" "neon_shift_imm")]
 )
+
+;; faminmax
+(define_insn "aarch64_<faminmax><mode>"
+  [(set (match_operand:VHSDF 0 "register_operand" "=w")
+	(unspec:VHSDF
+	  [(abs:VHSDF (match_operand:VHSDF 1 "register_operand" "w"))
+	   (abs:VHSDF (match_operand:VHSDF 2 "register_operand" "w"))]
+	  FMAXMIN_ONLY_UNS))]
+  "TARGET_FAMINMAX"
+  "<faminmax>\t%0.<Vtype>, %1.<Vtype>, %2.<Vtype>"
+  [(set_attr "type" "neon_fp_aminmax<q>")]
+)
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.cc b/gcc/config/aarch64/aarch64-sve-builtins.cc
index f3983a123e3..58c780b9464 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins.cc
@@ -947,10 +947,6 @@  static hash_table<registered_function_hasher> *function_table;
    are IDENTIFIER_NODEs.  */
 static GTY(()) hash_map<tree, registered_function *> *overload_names[2];
 
-/* True if we've already complained about attempts to use functions
-   when the required extension is disabled.  */
-static bool reported_missing_extension_p;
-
 /* True if we've already complained about attempts to use functions
    which require registers that are missing.  */
 static bool reported_missing_registers_p;
@@ -1076,24 +1072,6 @@  lookup_fndecl (tree fndecl)
   return &(*registered_functions)[subcode]->instance;
 }
 
-/* Report an error against LOCATION that the user has tried to use
-   function FNDECL when extension EXTENSION is disabled.  */
-static void
-report_missing_extension (location_t location, tree fndecl,
-			  const char *extension)
-{
-  /* Avoid reporting a slew of messages for a single oversight.  */
-  if (reported_missing_extension_p)
-    return;
-
-  error_at (location, "ACLE function %qD requires ISA extension %qs",
-	    fndecl, extension);
-  inform (location, "you can enable %qs using the command-line"
-	  " option %<-march%>, or by using the %<target%>"
-	  " attribute or pragma", extension);
-  reported_missing_extension_p = true;
-}
-
 /* Check whether the registers required by SVE function fndecl are available.
    Report an error against LOCATION and return false if not.  */
 static bool
diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h
index 8056c337957..c6773f64745 100644
--- a/gcc/config/aarch64/aarch64.h
+++ b/gcc/config/aarch64/aarch64.h
@@ -456,6 +456,10 @@  constexpr auto AARCH64_FL_DEFAULT_ISA_MODE ATTRIBUTE_UNUSED
     enabled through +gcs.  */
 #define TARGET_GCS AARCH64_HAVE_ISA (GCS)
 
+/*  Floating Point Absolute Maximum/Minimum extension instructions are
+    enabled through +faminmax.  */
+#define TARGET_FAMINMAX AARCH64_HAVE_ISA (FAMINMAX)
+
 /* Prefer different predicate registers for the output of a predicated
    operation over re-using an existing input predicate.  */
 #define TARGET_SVE_PRED_CLOBBER (TARGET_SVE \
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index 95fe8f070f4..8e144c8ee4e 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -4457,3 +4457,11 @@ 
    (UNSPECV_SET_FPCR "fpcr")])
 
 (define_int_attr bits_etype [(8 "b") (16 "h") (32 "s") (64 "d")])
+
+;; Iterators and attributes for faminmax
+
+(define_int_iterator FMAXMIN_ONLY_UNS [UNSPEC_FMAX UNSPEC_FMIN])
+(define_int_attr faminmax
+  [(UNSPEC_FMAX "famax") (UNSPEC_FMIN "famin")])
+
+
diff --git a/gcc/config/arm/types.md b/gcc/config/arm/types.md
index 9527bdb9e87..d8de9dbc9d1 100644
--- a/gcc/config/arm/types.md
+++ b/gcc/config/arm/types.md
@@ -492,6 +492,8 @@ 
 ; neon_fp_reduc_minmax_s_q
 ; neon_fp_reduc_minmax_d
 ; neon_fp_reduc_minmax_d_q
+; neon_fp_aminmax
+; neon_fp_aminmax_q
 ; neon_fp_cvt_narrow_s_q
 ; neon_fp_cvt_narrow_d_q
 ; neon_fp_cvt_widen_h
@@ -1044,6 +1046,8 @@ 
   neon_fp_reduc_minmax_d,\
   neon_fp_reduc_minmax_d_q,\
 \
+  neon_fp_aminmax,\
+  neon_fp_aminmax_q,\
   neon_fp_cvt_narrow_s_q,\
   neon_fp_cvt_narrow_d_q,\
   neon_fp_cvt_widen_h,\
@@ -1264,6 +1268,8 @@ 
           neon_fp_reduc_add_d_q, neon_fp_reduc_minmax_s,
           neon_fp_reduc_minmax_s_q, neon_fp_reduc_minmax_d,\
           neon_fp_reduc_minmax_d_q,\
+	  neon_fp_aminmax, neon_fp_aminmax_q,\
+          neon_fp_aminmax, neon_fp_aminmax_q,\
           neon_fp_cvt_narrow_s_q, neon_fp_cvt_narrow_d_q,\
           neon_fp_cvt_widen_h, neon_fp_cvt_widen_s, neon_fp_to_int_s,\
           neon_fp_to_int_s_q, neon_int_to_fp_s, neon_int_to_fp_s_q,\
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 4850c7379bf..d48516f4f60 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -21777,6 +21777,8 @@  Enable support for Armv9.4-a Guarded Control Stack extension.
 Enable support for Armv8.9-a/9.4-a translation hardening extension.
 @item rcpc3
 Enable the RCpc3 (Release Consistency) extension.
+@item faminmax
+Enable the Floating Point Absolute Maximum/Minimum extension.
 
 @end table
 
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c
new file mode 100644
index 00000000000..63ed1508c23
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins-no-flag.c
@@ -0,0 +1,10 @@ 
+/* { dg-do assemble} */
+/* { dg-additional-options "-march=armv9-a" } */
+
+#include "arm_neon.h"
+
+void
+test (float32x4_t a, float32x4_t b)
+{
+  vamaxq_f32 (a, b); /* { dg-error {ACLE function 'vamaxq_f32' requires ISA extension 'faminmax'} } */
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c
new file mode 100644
index 00000000000..f2b5bafb81c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-builtins.c
@@ -0,0 +1,75 @@ 
+/* { dg-do assemble} */
+/* { dg-additional-options "-march=armv9-a+faminmax" } */
+
+#include "arm_neon.h"
+
+float16x4_t
+test_vamax_f16 (float16x4_t a, float16x4_t b)
+{
+  return vamax_f16 (a, b);
+}
+
+float16x8_t
+test_vamaxq_f16 (float16x8_t a, float16x8_t b)
+{
+  return vamaxq_f16 (a, b);
+}
+
+float32x2_t
+test_vamax_f32 (float32x2_t a, float32x2_t b)
+{
+  return vamax_f32 (a, b);
+}
+
+float32x4_t
+test_vamaxq_f32 (float32x4_t a, float32x4_t b)
+{
+  return vamaxq_f32 (a, b);
+}
+
+float64x2_t
+test_vamaxq_f64 (float64x2_t a, float64x2_t b)
+{
+  return vamaxq_f64 (a, b);
+}
+
+float16x4_t
+test_vamin_f16 (float16x4_t a, float16x4_t b)
+{
+  return vamin_f16 (a, b);
+}
+
+float16x8_t
+test_vaminq_f16 (float16x8_t a, float16x8_t b)
+{
+  return vaminq_f16 (a, b);
+}
+
+float32x2_t
+test_vamin_f32 (float32x2_t a, float32x2_t b)
+{
+  return vamin_f32 (a, b);
+}
+
+float32x4_t
+test_vaminq_f32 (float32x4_t a, float32x4_t b)
+{
+  return vaminq_f32 (a, b);
+}
+
+float64x2_t
+test_vaminq_f64 (float64x2_t a, float64x2_t b)
+{
+  return vaminq_f64 (a, b);
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 1 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen-no-flag.c b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen-no-flag.c
new file mode 100644
index 00000000000..545a9468fdc
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen-no-flag.c
@@ -0,0 +1,54 @@ 
+/* { dg-do assemble} */
+/* { dg-additional-options "-O -march=armv9-a" } */
+
+#include "arm_neon.h"
+
+float16x4_t
+test_vamax_f16 (float16x4_t a, float16x4_t b)
+{
+  return vmax_f16 (vabs_f16 (a), vabs_f16 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 0 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.4h, v[0-9]+.4h} 2 } } */
+
+float16x8_t
+test_vamaxq_f16 (float16x8_t a, float16x8_t b)
+{
+  return vmaxq_f16 (vabsq_f16 (a), vabsq_f16 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 0 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.8h, v[0-9]+.8h} 2 } } */
+
+float32x2_t
+test_vamax_f32 (float32x2_t a, float32x2_t b)
+{
+  return vmax_f32 (vabs_f32 (a), vabs_f32 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 0 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.2s, v[0-9]+.2s} 2 } } */
+
+float32x4_t
+test_vamaxq_f32 (float32x4_t a, float32x4_t b)
+{
+  return vmaxq_f32 (vabsq_f32 (a), vabsq_f32 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 0 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.4s, v[0-9]+.4s} 2 } } */
+
+float64x2_t
+test_vamaxq_f64 (float64x2_t a, float64x2_t b)
+{
+  return vmaxq_f64 (vabsq_f64 (a), vabsq_f64 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 0 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 1 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.2d, v[0-9]+.2d} 2 } } */
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen.c b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen.c
new file mode 100644
index 00000000000..e4e079a6f9e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/faminmax-codegen.c
@@ -0,0 +1,104 @@ 
+/* { dg-do assemble} */
+/* { dg-additional-options "-O -march=armv9-a+faminmax" } */
+
+#include "arm_neon.h"
+
+float16x4_t
+test_vamax_f16 (float16x4_t a, float16x4_t b)
+{
+  return vmax_f16 (vabs_f16 (a), vabs_f16 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.4h, v[0-9]+.4h} 0 } } */
+
+float16x8_t
+test_vamaxq_f16 (float16x8_t a, float16x8_t b)
+{
+  return vmaxq_f16 (vabsq_f16 (a), vabsq_f16 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.8h, v[0-9]+.8h} 0 } } */
+
+float32x2_t
+test_vamax_f32 (float32x2_t a, float32x2_t b)
+{
+  return vmax_f32 (vabs_f32 (a), vabs_f32 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.2s, v[0-9]+.2s} 0 } } */
+
+float32x4_t
+test_vamaxq_f32 (float32x4_t a, float32x4_t b)
+{
+  return vmaxq_f32 (vabsq_f32 (a), vabsq_f32 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.4s, v[0-9]+.4s} 0 } } */
+
+float64x2_t
+test_vamaxq_f64 (float64x2_t a, float64x2_t b)
+{
+  return vmaxq_f64 (vabsq_f64 (a), vabsq_f64 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamax\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmax\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.2d, v[0-9]+.2d} 0 } } */
+
+float16x4_t
+test_vamin_f16 (float16x4_t a, float16x4_t b)
+{
+  return vmin_f16 (vabs_f16 (a), vabs_f16 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmin\tv[0-9]+.4h, v[0-9]+.4h, v[0-9]+.4h} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.4h, v[0-9]+.4h} 0 } } */
+
+float16x8_t
+test_vaminq_f16 (float16x8_t a, float16x8_t b)
+{
+  return vminq_f16 (vabsq_f16 (a), vabsq_f16 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmin\tv[0-9]+.8h, v[0-9]+.8h, v[0-9]+.8h} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.8h, v[0-9]+.8h} 0 } } */
+
+float32x2_t
+test_vamin_f32 (float32x2_t a, float32x2_t b)
+{
+  return vmin_f32 (vabs_f32 (a), vabs_f32 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmin\tv[0-9]+.2s, v[0-9]+.2s, v[0-9]+.2s} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.2s, v[0-9]+.2s} 0 } } */
+
+float32x4_t
+test_vaminq_f32 (float32x4_t a, float32x4_t b)
+{
+  return vminq_f32 (vabsq_f32 (a), vabsq_f32 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmin\tv[0-9]+.4s, v[0-9]+.4s, v[0-9]+.4s} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.4s, v[0-9]+.4s} 0 } } */
+
+float64x2_t
+test_vaminq_f64 (float64x2_t a, float64x2_t b)
+{
+  return vminq_f64 (vabsq_f64 (a), vabsq_f64 (b));
+}
+
+/* { dg-final { scan-assembler-times {\tfamin\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 1 } } */
+/* { dg-final { scan-assembler-times {\tfmin\tv[0-9]+.2d, v[0-9]+.2d, v[0-9]+.2d} 0 } } */
+/* { dg-final { scan-assembler-times {\tfabs\tv[0-9]+.2d, v[0-9]+.2d} 0 } } */