This patch moves the scalar and single-vector Advanced SIMD types
from arm_neon.h into a private header, so that they can be defined
by arm_sve.h as well. This is needed for the upcoming SVE2.1
hybrid-VLA reductions, which return 128-bit Advanced SIMD vectors.
The approach follows Claudio's patch for FP8.
gcc/
* config.gcc (extra_headers): Add arm_private_neon_types.h.
* config/aarch64/arm_private_neon_types.h: New file, split out
from...
* config/aarch64/arm_neon.h: ...here.
* config/aarch64/arm_sve.h: Include arm_private_neon_types.h
---
gcc/config.gcc | 2 +-
gcc/config/aarch64/arm_neon.h | 49 +------------
gcc/config/aarch64/arm_private_neon_types.h | 79 +++++++++++++++++++++
gcc/config/aarch64/arm_sve.h | 5 +-
4 files changed, 84 insertions(+), 51 deletions(-)
create mode 100644 gcc/config/aarch64/arm_private_neon_types.h
diff --git a/gcc/config.gcc b/gcc/config.gcc
index 1b0637d7ff8..7e0108e2154 100644
--- a/gcc/config.gcc
+++ b/gcc/config.gcc
@@ -347,7 +347,7 @@ m32c*-*-*)
;;
aarch64*-*-*)
cpu_type=aarch64
- extra_headers="arm_fp16.h arm_neon.h arm_bf16.h arm_acle.h arm_sve.h
arm_sme.h arm_neon_sve_bridge.h arm_private_fp8.h"
+ extra_headers="arm_fp16.h arm_neon.h arm_bf16.h arm_acle.h arm_sve.h
arm_sme.h arm_neon_sve_bridge.h arm_private_fp8.h arm_private_neon_types.h"
c_target_objs="aarch64-c.o"
cxx_target_objs="aarch64-c.o"
d_target_objs="aarch64-d.o"
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index d3533f3ee6f..c727302ac75 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -30,58 +30,15 @@
#pragma GCC push_options
#pragma GCC target ("+nothing+simd")
+#include <stdint.h>
#include <arm_private_fp8.h>
-#pragma GCC aarch64 "arm_neon.h"
+#include <arm_private_neon_types.h>
-#include <stdint.h>
+#pragma GCC aarch64 "arm_neon.h"
#define __AARCH64_UINT64_C(__C) ((uint64_t) __C)
#define __AARCH64_INT64_C(__C) ((int64_t) __C)
-typedef __Int8x8_t int8x8_t;
-typedef __Int16x4_t int16x4_t;
-typedef __Int32x2_t int32x2_t;
-typedef __Int64x1_t int64x1_t;
-typedef __Float16x4_t float16x4_t;
-typedef __Float32x2_t float32x2_t;
-typedef __Poly8x8_t poly8x8_t;
-typedef __Poly16x4_t poly16x4_t;
-typedef __Uint8x8_t uint8x8_t;
-typedef __Uint16x4_t uint16x4_t;
-typedef __Uint32x2_t uint32x2_t;
-typedef __Float64x1_t float64x1_t;
-typedef __Uint64x1_t uint64x1_t;
-typedef __Int8x16_t int8x16_t;
-typedef __Int16x8_t int16x8_t;
-typedef __Int32x4_t int32x4_t;
-typedef __Int64x2_t int64x2_t;
-typedef __Float16x8_t float16x8_t;
-typedef __Float32x4_t float32x4_t;
-typedef __Float64x2_t float64x2_t;
-typedef __Poly8x16_t poly8x16_t;
-typedef __Poly16x8_t poly16x8_t;
-typedef __Poly64x2_t poly64x2_t;
-typedef __Poly64x1_t poly64x1_t;
-typedef __Uint8x16_t uint8x16_t;
-typedef __Uint16x8_t uint16x8_t;
-typedef __Uint32x4_t uint32x4_t;
-typedef __Uint64x2_t uint64x2_t;
-
-typedef __Poly8_t poly8_t;
-typedef __Poly16_t poly16_t;
-typedef __Poly64_t poly64_t;
-typedef __Poly128_t poly128_t;
-
-typedef __Mfloat8x8_t mfloat8x8_t;
-typedef __Mfloat8x16_t mfloat8x16_t;
-
-typedef __fp16 float16_t;
-typedef float float32_t;
-typedef double float64_t;
-
-typedef __Bfloat16x4_t bfloat16x4_t;
-typedef __Bfloat16x8_t bfloat16x8_t;
-
/* __aarch64_vdup_lane internal macros. */
#define __aarch64_vdup_lane_any(__size, __q, __a, __b) \
vdup##__q##_n_##__size (__aarch64_vget_lane_any (__a, __b))
diff --git a/gcc/config/aarch64/arm_private_neon_types.h
b/gcc/config/aarch64/arm_private_neon_types.h
new file mode 100644
index 00000000000..0f588f026b7
--- /dev/null
+++ b/gcc/config/aarch64/arm_private_neon_types.h
@@ -0,0 +1,79 @@
+/* AArch64 type definitions for arm_neon.h
+ Do not include this file directly. Use one of arm_neon.h, arm_sme.h,
+ or arm_sve.h instead.
+
+ Copyright (C) 2024 Free Software Foundation, Inc.
+
+ This file is part of GCC.
+
+ GCC is free software; you can redistribute it and/or modify it
+ under the terms of the GNU General Public License as published
+ by the Free Software Foundation; either version 3, or (at your
+ option) any later version.
+
+ GCC is distributed in the hope that it will be useful, but WITHOUT
+ ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public
+ License for more details.
+
+ Under Section 7 of GPL version 3, you are granted additional
+ permissions described in the GCC Runtime Library Exception, version
+ 3.1, as published by the Free Software Foundation.
+
+ You should have received a copy of the GNU General Public License and
+ a copy of the GCC Runtime Library Exception along with this program;
+ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+ <http://www.gnu.org/licenses/>. */
+
+#ifndef _GCC_ARM_PRIVATE_NEON_TYPES_H
+#define _GCC_ARM_PRIVATE_NEON_TYPES_H
+
+#if !defined(_AARCH64_NEON_H_) && !defined(_ARM_SVE_H_)
+#error "This file should not be used standalone. Please include one of
arm_neon.h arm_sve.h arm_sme.h instead."
+#endif
+
+typedef __Int8x8_t int8x8_t;
+typedef __Int16x4_t int16x4_t;
+typedef __Int32x2_t int32x2_t;
+typedef __Int64x1_t int64x1_t;
+typedef __Float16x4_t float16x4_t;
+typedef __Float32x2_t float32x2_t;
+typedef __Poly8x8_t poly8x8_t;
+typedef __Poly16x4_t poly16x4_t;
+typedef __Uint8x8_t uint8x8_t;
+typedef __Uint16x4_t uint16x4_t;
+typedef __Uint32x2_t uint32x2_t;
+typedef __Float64x1_t float64x1_t;
+typedef __Uint64x1_t uint64x1_t;
+typedef __Int8x16_t int8x16_t;
+typedef __Int16x8_t int16x8_t;
+typedef __Int32x4_t int32x4_t;
+typedef __Int64x2_t int64x2_t;
+typedef __Float16x8_t float16x8_t;
+typedef __Float32x4_t float32x4_t;
+typedef __Float64x2_t float64x2_t;
+typedef __Poly8x16_t poly8x16_t;
+typedef __Poly16x8_t poly16x8_t;
+typedef __Poly64x2_t poly64x2_t;
+typedef __Poly64x1_t poly64x1_t;
+typedef __Uint8x16_t uint8x16_t;
+typedef __Uint16x8_t uint16x8_t;
+typedef __Uint32x4_t uint32x4_t;
+typedef __Uint64x2_t uint64x2_t;
+
+typedef __Poly8_t poly8_t;
+typedef __Poly16_t poly16_t;
+typedef __Poly64_t poly64_t;
+typedef __Poly128_t poly128_t;
+
+typedef __Mfloat8x8_t mfloat8x8_t;
+typedef __Mfloat8x16_t mfloat8x16_t;
+
+typedef __fp16 float16_t;
+typedef float float32_t;
+typedef double float64_t;
+
+typedef __Bfloat16x4_t bfloat16x4_t;
+typedef __Bfloat16x8_t bfloat16x8_t;
+
+#endif
diff --git a/gcc/config/aarch64/arm_sve.h b/gcc/config/aarch64/arm_sve.h
index aa0bd9909f9..a887c0f2f45 100644
--- a/gcc/config/aarch64/arm_sve.h
+++ b/gcc/config/aarch64/arm_sve.h
@@ -27,12 +27,9 @@
#include <stdint.h>
#include <arm_private_fp8.h>
+#include <arm_private_neon_types.h>
#include <arm_bf16.h>
-typedef __fp16 float16_t;
-typedef float float32_t;
-typedef double float64_t;
-
/* NOTE: This implementation of arm_sve.h is intentionally short. It does
not define the SVE types and intrinsic functions directly in C and C++
code, but instead uses the following pragma to tell GCC to insert the
--
2.25.1
