[gcc r9-8946] AArch64: Implement poly-type vadd intrinsics

[Kyrylo Tkachov]

https://gcc.gnu.org/g:48e274be62b924379541ae0321b82862f572b973

commit r9-8946-g48e274be62b924379541ae0321b82862f572b973
Author: Kyrylo Tkachov <kyrylo.tkachov@arm.com>
Date:   Tue Sep 22 11:58:36 2020 +0100

    AArch64: Implement poly-type vadd intrinsics
    
    This implements the vadd[p]_p* intrinsics.
    In terms of functionality they are aliases of veor operations on the relevant unsigned types.
    
    Bootstrapped and tested on aarch64-none-linux-gnu.
    
    gcc/
            PR target/71233
            * config/aarch64/arm_neon.h (vadd_p8, vadd_p16, vadd_p64, vaddq_p8,
            vaddq_p16, vaddq_p64, vaddq_p128): Define.
    
    gcc/testsuite/
            PR target/71233
            * gcc.target/aarch64/simd/vadd_poly_1.c: New test.
    
    (cherry picked from commit fa9ad35dae03dcb20c4ccb50ba1b351a8ab77970)

Diff:
---
 gcc/config/aarch64/arm_neon.h                      | 49 +++++++++++++++++++++
 .../gcc.target/aarch64/simd/vadd_poly_1.c          | 50 ++++++++++++++++++++++
 2 files changed, 99 insertions(+)

diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 9ecc00c46b9..c2374d9c868 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -34469,6 +34469,55 @@ vfmlslq_laneq_high_f16 (float32x4_t __r, float16x8_t __a, float16x8_t __b,
 
 #pragma GCC pop_options
 
+__extension__ extern __inline poly8x8_t
+__attribute ((__always_inline__, __gnu_inline__, __artificial__))
+vadd_p8 (poly8x8_t __a, poly8x8_t __b)
+{
+  return __a ^ __b;
+}
+
+__extension__ extern __inline poly16x4_t
+__attribute ((__always_inline__, __gnu_inline__, __artificial__))
+vadd_p16 (poly16x4_t __a, poly16x4_t __b)
+{
+  return __a ^ __b;
+}
+
+__extension__ extern __inline poly64x1_t
+__attribute ((__always_inline__, __gnu_inline__, __artificial__))
+vadd_p64 (poly64x1_t __a, poly64x1_t __b)
+{
+  return __a ^ __b;
+}
+
+__extension__ extern __inline poly8x16_t
+__attribute ((__always_inline__, __gnu_inline__, __artificial__))
+vaddq_p8 (poly8x16_t __a, poly8x16_t __b)
+{
+  return __a ^ __b;
+}
+
+__extension__ extern __inline poly16x8_t
+__attribute ((__always_inline__, __gnu_inline__, __artificial__))
+vaddq_p16 (poly16x8_t __a, poly16x8_t __b)
+{
+  return __a ^__b;
+}
+
+__extension__ extern __inline poly64x2_t
+__attribute ((__always_inline__, __gnu_inline__, __artificial__))
+vaddq_p64 (poly64x2_t __a, poly64x2_t __b)
+{
+  return __a ^ __b;
+}
+
+__extension__ extern __inline poly128_t
+__attribute ((__always_inline__, __gnu_inline__, __artificial__))
+vaddq_p128 (poly128_t __a, poly128_t __b)
+{
+  return __a ^ __b;
+}
+
 #undef __aarch64_vget_lane_any
 
 #undef __aarch64_vdup_lane_any
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/vadd_poly_1.c b/gcc/testsuite/gcc.target/aarch64/simd/vadd_poly_1.c
new file mode 100644
index 00000000000..a5cdf290b0d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/vadd_poly_1.c
@@ -0,0 +1,50 @@
+/* { dg-do compile } */
+/* { dg-options "-O" } */
+
+#include <arm_neon.h>
+
+poly8x8_t
+foo (poly8x8_t a, poly8x8_t b)
+{
+  return vadd_p8 (a, b);
+}
+
+poly16x4_t
+foo16 (poly16x4_t a, poly16x4_t b)
+{
+  return vadd_p16 (a, b);
+}
+
+poly64x1_t
+foo64 (poly64x1_t a, poly64x1_t b)
+{
+  return vadd_p64 (a, b);
+}
+
+poly8x16_t
+fooq (poly8x16_t a, poly8x16_t b)
+{
+  return vaddq_p8 (a, b);
+}
+
+poly16x8_t
+fooq16 (poly16x8_t a, poly16x8_t b)
+{
+  return vaddq_p16 (a, b);
+}
+
+poly64x2_t
+fooq64 (poly64x2_t a, poly64x2_t b)
+{
+  return vaddq_p64 (a, b);
+}
+
+poly128_t
+fooq128 (poly128_t a, poly128_t b)
+{
+  return vaddq_p128 (a, b);
+}
+
+/* { dg-final { scan-assembler-times "eor\\tv\[0-9\]+\.8b, v\[0-9\]+\.8b, v\[0-9\]+\.8b" 3 } } */
+/* { dg-final { scan-assembler-times "eor\\tv\[0-9\]+\.16b, v\[0-9\]+\.16b, v\[0-9\]+\.16b" 3 } } */
+/* { dg-final { scan-assembler-times "eor\\tx\[0-9\]+, x\[0-9\]+, x\[0-9\]+" 2 } } */