vect-dot-qi.h: New.

2017-10-26  Tamar Christina  <tamar.christina@arm.com>

	* gcc.target/aarch64/advsimd-intrinsics/vect-dot-qi.h: New.
	* gcc.target/aarch64/advsimd-intrinsics/vdot-compile.c: New.
	* gcc.target/aarch64/advsimd-intrinsics/vect-dot-s8.c: New.
	* gcc.target/aarch64/advsimd-intrinsics/vect-dot-u8.c: New.

From-SVN: r254097

gcc/testsuite/ChangeLog

+2017-10-26  Tamar Christina  <tamar.christina@arm.com>
+
+	* gcc.target/aarch64/advsimd-intrinsics/vect-dot-qi.h: New.
+	* gcc.target/aarch64/advsimd-intrinsics/vdot-compile.c: New.
+	* gcc.target/aarch64/advsimd-intrinsics/vect-dot-s8.c: New.
+	* gcc.target/aarch64/advsimd-intrinsics/vect-dot-u8.c: New.
+
 2017-10-25  David Malcolm  <dmalcolm@redhat.com>
 
 	PR c/7356

gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vdot-compile.c

+/* { dg-do compile { target { aarch64*-*-* } } } */
+/* { dg-additional-options "-O3 -march=armv8.2-a+dotprod" } */
+
+#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);
+}
+
+uint32x2_t ufoo_laneq (uint32x2_t r, uint8x8_t x, uint8x16_t y)
+{
+  return vdot_laneq_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);
+}
+
+uint32x4_t ufooq_laneq (uint32x4_t r, uint8x16_t x, uint8x16_t y)
+{
+  return vdotq_laneq_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);
+}
+
+int32x2_t sfoo_laneq (int32x2_t r, int8x8_t x, int8x16_t y)
+{
+  return vdot_laneq_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);
+}
+
+int32x4_t sfooq_laneq (int32x4_t r, int8x16_t x, int8x16_t y)
+{
+  return vdotq_laneq_s32 (r, x, y, 0);
+}
+
+/* { dg-final { scan-assembler-times {[us]dot\tv[0-9]+\.2s, v[0-9]+\.8b, v[0-9]+\.8b} 2 } } */
+/* { dg-final { scan-assembler-times {[us]dot\tv[0-9]+\.2s, v[0-9]+\.8b, v[0-9]+\.4b\[[0-9]+\]}  4 } } */
+/* { dg-final { scan-assembler-times {[us]dot\tv[0-9]+\.4s, v[0-9]+\.16b, v[0-9]+\.16b}  2 } } */
+/* { dg-final { scan-assembler-times {[us]dot\tv[0-9]+\.4s, v[0-9]+\.16b, v[0-9]+\.4b\[[0-9]+\]}  4 } } */

gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vect-dot-qi.h

+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

gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vect-dot-s8.c

+/* { dg-do compile { target { aarch64*-*-* } } } */
+/* { dg-additional-options "-O3 -march=armv8.2-a+dotprod" } */
+
+#define N 64
+#define TYPE signed
+
+#include "vect-dot-qi.h"
+
+/* { dg-final { scan-assembler-times {sdot\tv[0-9]+\.4s, v[0-9]+\.16b, v[0-9]+\.16b} 4 } } */

gcc/testsuite/gcc.target/aarch64/advsimd-intrinsics/vect-dot-u8.c

+/* { dg-do compile { target { aarch64*-*-* } } } */
+/* { dg-additional-options "-O3 -march=armv8.2-a+dotprod" } */
+
+#define N 64
+#define TYPE unsigned
+
+#include "vect-dot-qi.h"
+
+/* { dg-final { scan-assembler-times {udot\tv[0-9]+\.4s, v[0-9]+\.16b, v[0-9]+\.16b} 4 } } */