From eed4d7bd668bf6a223f5637bc4ca7acf479a4fad Mon Sep 17 00:00:00 2001
From: Kyrylo Tkachov <ktkachov@nvidia.com>
Date: Thu, 3 Jul 2025 08:37:33 -0700
Subject: [PATCH 1/7] aarch64: Allow 64-bit vector modes in pattern for BCAX
 instruction

The BCAX instruction from TARGET_SHA3 only operates on the full .16b form
of the inputs but as it's a pure bitwise operation we can use it for the 64-bit
modes as well as there we don't care about the upper 64 bits.  This patch extends
the relevant pattern in aarch64-simd.md to accept the 64-bit vector modes.

Thus, for the input:
uint32x2_t
bcax_s (uint32x2_t a, uint32x2_t b, uint32x2_t c)
{
  return BCAX (a, b, c);
}

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

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

This patch doesn't cover the DI/V1DI modes as that would require extending
the bcaxqdi4 pattern with =r,r alternatives and adding splitting logic to
handle the cases where the operands arrive in GP regs.  It is doable, but can
be a separate patch.  This patch as is should be a straightforward improvement
always.

Bootstrapped and tested on aarch64-none-linux-gnu.

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

gcc/

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

gcc/testsuite/

	* gcc.target/aarch64/simd/bcax_d.c: New test.
---
 gcc/config/aarch64/aarch64-simd.md             | 12 ++++++------
 gcc/testsuite/gcc.target/aarch64/simd/bcax_d.c | 15 +++++++++++++++
 2 files changed, 21 insertions(+), 6 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/simd/bcax_d.c

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 8de79caa86d..879b1a27bb1 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -9241,12 +9241,12 @@
 )
 
 (define_insn "bcaxq<mode>4"
-  [(set (match_operand:VQ_I 0 "register_operand" "=w")
-	(xor:VQ_I
-	 (and:VQ_I
-	  (not:VQ_I (match_operand:VQ_I 3 "register_operand" "w"))
-	  (match_operand:VQ_I 2 "register_operand" "w"))
-	 (match_operand:VQ_I 1 "register_operand" "w")))]
+  [(set (match_operand:VDQ_I 0 "register_operand" "=w")
+	(xor:VDQ_I
+	 (and:VDQ_I
+	  (not:VDQ_I (match_operand:VDQ_I 3 "register_operand" "w"))
+	  (match_operand:VDQ_I 2 "register_operand" "w"))
+	 (match_operand:VDQ_I 1 "register_operand" "w")))]
   "TARGET_SHA3"
   "bcax\\t%0.16b, %1.16b, %2.16b, %3.16b"
   [(set_attr "type" "crypto_sha3")]
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/bcax_d.c b/gcc/testsuite/gcc.target/aarch64/simd/bcax_d.c
new file mode 100644
index 00000000000..d68f0e102bf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/simd/bcax_d.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+#include <arm_neon.h>
+
+#pragma GCC target "+sha3"
+
+#define BCAX(x,y,z)  ((x) ^ ((y) & ~(z)))
+
+uint32x2_t bcax_s (uint32x2_t a, uint32x2_t b, uint32x2_t c) { return BCAX (a, b, c); }
+uint16x4_t bcax_h (uint16x4_t a, uint16x4_t b, uint16x4_t c) { return BCAX (a, b, c); }
+uint8x8_t bcax_b (uint8x8_t a, uint8x8_t b, uint8x8_t c) { return BCAX (a, b, c); }
+
+/* { dg-final { scan-assembler-times {bcax\tv0.16b, v0.16b, v1.16b, v2.16b} 3 } } */
+
-- 
2.44.0

