[PATCH][GCC][ARM] Dot Product NEON intrinsics [Patch (3/8)]

[Tamar Christina <tamar dot christina at arm dot com>]

Hi All,

This patch adds the NEON intrinsics for Dot product.

Dot product is available from ARMv8.2-a and onwards.

Regtested on arm-none-eabi, armeb-none-eabi,
aarch64-none-elf and aarch64_be-none-elf with no issues found.

Ok for trunk?

gcc/
2017-11-06  Tamar Christina  <tamar.christina@arm.com>

	* config/aarch64/arm_neon.h (vdot_u32, vdotq_u32)
	(vdot_s32, vdotq_s32): New.
	(vdot_lane_u32, vdotq_lane_u32): New.
	(vdot_lane_s32, vdotq_lane_s32): New.


gcc/testsuite/
2017-11-06  Tamar Christina  <tamar.christina@arm.com>

	* gcc.target/arm/simd/vdot-compile.c: New.
	* gcc.target/arm/simd/vect-dot-qi.h: New.
	* gcc.target/arm/simd/vect-dot-s8.c: New.
	* gcc.target/arm/simd/vect-dot-u8.c: New

-- 

diff --git a/gcc/config/arm/arm_neon.h b/gcc/config/arm/arm_neon.h
index 0d436e83d0f01f0c86f8d6a25f84466c841c7e11..419080417901f343737741e334cbff818bb1e70a 100644
--- a/gcc/config/arm/arm_neon.h
+++ b/gcc/config/arm/arm_neon.h
@@ -18034,6 +18034,72 @@ vzipq_f16 (float16x8_t __a, float16x8_t __b)
 
 #endif
 
+/* Adv.SIMD Dot Product intrinsics.  */
+
+#pragma GCC push_options
+#if __ARM_ARCH >= 8
+#pragma GCC target ("arch=armv8.2-a+dotprod")
+
+__extension__ extern __inline uint32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdot_u32 (uint32x2_t __r, uint8x8_t __a, uint8x8_t __b)
+{
+  return __builtin_neon_udotv8qi_uuuu (__r, __a, __b);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdotq_u32 (uint32x4_t __r, uint8x16_t __a, uint8x16_t __b)
+{
+  return __builtin_neon_udotv16qi_uuuu (__r, __a, __b);
+}
+
+__extension__ extern __inline int32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdot_s32 (int32x2_t __r, int8x8_t __a, int8x8_t __b)
+{
+  return __builtin_neon_sdotv8qi (__r, __a, __b);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdotq_s32 (int32x4_t __r, int8x16_t __a, int8x16_t __b)
+{
+  return __builtin_neon_sdotv16qi (__r, __a, __b);
+}
+
+__extension__ extern __inline uint32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdot_lane_u32 (uint32x2_t __r, uint8x8_t __a, uint8x8_t __b, const int __index)
+{
+  return __builtin_neon_udot_lanev8qi_uuuus (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline uint32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdotq_lane_u32 (uint32x4_t __r, uint8x16_t __a, uint8x8_t __b,
+		const int __index)
+{
+  return __builtin_neon_udot_lanev16qi_uuuus (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x2_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdot_lane_s32 (int32x2_t __r, int8x8_t __a, int8x8_t __b, const int __index)
+{
+  return __builtin_neon_sdot_lanev8qi (__r, __a, __b, __index);
+}
+
+__extension__ extern __inline int32x4_t
+__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
+vdotq_lane_s32 (int32x4_t __r, int8x16_t __a, int8x8_t __b, const int __index)
+{
+  return __builtin_neon_sdot_lanev16qi (__r, __a, __b, __index);
+}
+
+#pragma GCC pop_options
+#endif
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/gcc/testsuite/gcc.target/arm/simd/vdot-compile.c b/gcc/testsuite/gcc.target/arm/simd/vdot-compile.c
new file mode 100644
index 0000000000000000000000000000000000000000..a422384b0a0140d4afb4ff4a04223dd20f8d9960
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vdot-compile.c
@@ -0,0 +1,55 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3" } */
+/* { dg-require-effective-target arm_v8_2a_dotprod_neon_ok } */
+/* { dg-add-options arm_v8_2a_dotprod_neon }  */
+
+#include <arm_neon.h>
+
+/* Unsigned Dot Product instructions.  */
+
+uint32x2_t ufoo (uint32x2_t r, uint8x8_t x, uint8x8_t y)
+{
+  return vdot_u32 (r, x, y);
+}
+
+uint32x4_t ufooq (uint32x4_t r, uint8x16_t x, uint8x16_t y)
+{
+  return vdotq_u32 (r, x, y);
+}
+
+uint32x2_t ufoo_lane (uint32x2_t r, uint8x8_t x, uint8x8_t y)
+{
+  return vdot_lane_u32 (r, x, y, 0);
+}
+
+uint32x4_t ufooq_lane (uint32x4_t r, uint8x16_t x, uint8x8_t y)
+{
+  return vdotq_lane_u32 (r, x, y, 0);
+}
+
+/* Signed Dot Product instructions.  */
+
+int32x2_t sfoo (int32x2_t r, int8x8_t x, int8x8_t y)
+{
+  return vdot_s32 (r, x, y);
+}
+
+int32x4_t sfooq (int32x4_t r, int8x16_t x, int8x16_t y)
+{
+  return vdotq_s32 (r, x, y);
+}
+
+int32x2_t sfoo_lane (int32x2_t r, int8x8_t x, int8x8_t y)
+{
+  return vdot_lane_s32 (r, x, y, 0);
+}
+
+int32x4_t sfooq_lane (int32x4_t r, int8x16_t x, int8x8_t y)
+{
+  return vdotq_lane_s32 (r, x, y, 0);
+}
+
+/* { dg-final { scan-assembler-times {v[us]dot\.[us]8\td[0-9]+, d[0-9]+, d[0-9]+} 4 } } */
+/* { dg-final { scan-assembler-times {v[us]dot\.[us]8\tq[0-9]+, q[0-9]+, q[0-9]+} 2 } } */
+/* { dg-final { scan-assembler-times {v[us]dot\.[us]8\td[0-9]+, d[0-9]+, d[0-9]+\[#?[0-9]\]} 2 } } */
+/* { dg-final { scan-assembler-times {v[us]dot\.[us]8\tq[0-9]+, q[0-9]+, d[0-9]+\[#?[0-9]\]} 2 } } */
diff --git a/gcc/testsuite/gcc.target/arm/simd/vect-dot-qi.h b/gcc/testsuite/gcc.target/arm/simd/vect-dot-qi.h
new file mode 100644
index 0000000000000000000000000000000000000000..90b00aff95cfef96d1963be17673dc191cc71169
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vect-dot-qi.h
@@ -0,0 +1,15 @@
+TYPE char X[N] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
+TYPE char Y[N] __attribute__ ((__aligned__(__BIGGEST_ALIGNMENT__)));
+
+__attribute__ ((noinline)) int
+foo1(int len) {
+  int i;
+  TYPE int result = 0;
+  TYPE short prod;
+
+  for (i=0; i<len; i++) {
+    prod = X[i] * Y[i];
+    result += prod;
+  }
+  return result;
+}
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/arm/simd/vect-dot-s8.c b/gcc/testsuite/gcc.target/arm/simd/vect-dot-s8.c
new file mode 100644
index 0000000000000000000000000000000000000000..6593404a682f76c8adce6b34de8ec4a2d0d97feb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vect-dot-s8.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3" } */
+/* { dg-require-effective-target arm_v8_2a_dotprod_neon_ok } */
+/* { dg-add-options arm_v8_2a_dotprod_neon }  */
+
+#define N 64
+#define TYPE signed
+
+#include "vect-dot-qi.h"
+
+/* { dg-final { scan-assembler-times {vsdot\.s8\tq[0-9]+, q[0-9]+, q[0-9]+} 4 } } */
\ No newline at end of file
diff --git a/gcc/testsuite/gcc.target/arm/simd/vect-dot-u8.c b/gcc/testsuite/gcc.target/arm/simd/vect-dot-u8.c
new file mode 100644
index 0000000000000000000000000000000000000000..c4d191ee827268f267c23427aa51101efbaeff38
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arm/simd/vect-dot-u8.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3" } */
+/* { dg-require-effective-target arm_v8_2a_dotprod_neon_ok } */
+/* { dg-add-options arm_v8_2a_dotprod_neon }  */
+
+#define N 64
+#define TYPE unsigned
+
+#include "vect-dot-qi.h"
+
+/* { dg-final { scan-assembler-times {vudot\.u8\tq[0-9]+, q[0-9]+, q[0-9]+} 4 } } */
\ No newline at end of file