aarch64: Use EOR3 for 64-bit vector modes

Similar to the BCAX patch, we can also use EOR3 for 64-bit modes,
just by adjusting the mode iterator used.
Thus for input:

uint32x2_t
bcax_s (uint32x2_t a, uint32x2_t b, uint32x2_t c)
{
  return EOR3 (a, b, c);
}

we now generate:
bcax_s:
        eor3    v0.16b, v0.16b, v1.16b, v2.16b
        ret

instead of:
bcax_s:
        eor     v1.8b, v1.8b, v2.8b
        eor     v0.8b, v1.8b, v0.8b
        ret

Signed-off-by: Kyrylo Tkachov <ktkachov@nvidia.com>
gcc/

	* config/aarch64/aarch64-simd.md (eor3q<mode>4): Use VDQ_I mode
	iterator.

gcc/testsuite/

	* gcc.target/aarch64/simd/eor3_d.c: New test.

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 879b1a27bb198eb10d1945527018d96b0b9fae3c..4493e55603d1f74672c003c7427a83cabb1b6ba4 100644 (file)
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -9180,12 +9180,12 @@
 ;; sha3
 
 (define_insn "eor3q<mode>4"
-  [(set (match_operand:VQ_I 0 "register_operand" "=w")
-       (xor:VQ_I
-        (xor:VQ_I
-         (match_operand:VQ_I 2 "register_operand" "w")
-         (match_operand:VQ_I 3 "register_operand" "w"))
-        (match_operand:VQ_I 1 "register_operand" "w")))]
+  [(set (match_operand:VDQ_I 0 "register_operand" "=w")
+       (xor:VDQ_I
+        (xor:VDQ_I
+         (match_operand:VDQ_I 2 "register_operand" "w")
+         (match_operand:VDQ_I 3 "register_operand" "w"))
+        (match_operand:VDQ_I 1 "register_operand" "w")))]
   "TARGET_SHA3"
   "eor3\\t%0.16b, %1.16b, %2.16b, %3.16b"
   [(set_attr "type" "crypto_sha3")]

diff --git a/gcc/testsuite/gcc.target/aarch64/simd/eor3_d.c b/gcc/testsuite/gcc.target/aarch64/simd/eor3_d.c
new file mode 100644 (file)
index 0000000..7f2b2b4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/eor3_d.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#include <arm_neon.h>
+
+#pragma GCC target "+sha3"
+
+#define EOR3(x,y,z)  ((x) ^ (y) ^ (z))
+
+uint32x2_t bcax_s (uint32x2_t a, uint32x2_t b, uint32x2_t c) { return EOR3 (a, b, c); }
+uint16x4_t bcax_h (uint16x4_t a, uint16x4_t b, uint16x4_t c) { return EOR3 (a, b, c); }
+uint8x8_t bcax_b (uint8x8_t a, uint8x8_t b, uint8x8_t c) { return EOR3 (a, b, c); }
+
+/* { dg-final { scan-assembler-times {eor3\tv0.16b, v[0-9]+.16b, v[0-9]+.16b, v[0-9]+.16b} 3 } } */
+