aarch64: Model zero-high-half semantics of [SU]QXTN instructions

Split the aarch64_<su>qmovn<mode> pattern into separate scalar and
vector variants. Further split the vector RTL  pattern into big/
little endian variants that model the zero-high-half semantics of the
underlying instruction. Modeling these semantics allows for better
RTL combinations while also removing some register allocation issues
as the compiler now knows that the operation is totally destructive.

Add new tests to narrow_zero_high_half.c to verify the benefit of
this change.

gcc/ChangeLog:

2021-06-14  Jonathan Wright  <jonathan.wright@arm.com>

	* config/aarch64/aarch64-simd-builtins.def: Split generator
	for aarch64_<su>qmovn builtins into scalar and vector
	variants.
	* config/aarch64/aarch64-simd.md (aarch64_<su>qmovn<mode>_insn_le):
	Define.
	(aarch64_<su>qmovn<mode>_insn_be): Define.
	(aarch64_<su>qmovn<mode>): Split into scalar and vector
	variants. Change vector variant to an expander that emits the
	correct instruction depending on endianness.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/narrow_zero_high_half.c: Add new tests.

3 files changed, 59 insertions, 4 deletions

diff --git a/gcc/config/aarch64/aarch64-simd-builtins.def b/gcc/config/aarch64/aarch64-simd-builtins.def
index 2adb4b1..ac5d4fc 100644
--- a/gcc/config/aarch64/aarch64-simd-builtins.def
+++ b/gcc/config/aarch64/aarch64-simd-builtins.def
@@ -271,8 +271,10 @@
   BUILTIN_VQN (BINOP_UUS, sqxtun2, 0, NONE)
 
   /* Implemented by aarch64_<su>qmovn<mode>.  */
-  BUILTIN_VSQN_HSDI (UNOP, sqmovn, 0, NONE)
-  BUILTIN_VSQN_HSDI (UNOP, uqmovn, 0, NONE)
+  BUILTIN_VQN (UNOP, sqmovn, 0, NONE)
+  BUILTIN_SD_HSDI (UNOP, sqmovn, 0, NONE)
+  BUILTIN_VQN (UNOP, uqmovn, 0, NONE)
+  BUILTIN_SD_HSDI (UNOP, uqmovn, 0, NONE)
 
   /* Implemented by aarch64_<su>qxtn2<mode>.  */
   BUILTIN_VQN (BINOP, sqxtn2, 0, NONE)
diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 59779b8..2b75e57 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -4875,10 +4875,54 @@
 (define_insn "aarch64_<su>qmovn<mode>"
   [(set (match_operand:<VNARROWQ> 0 "register_operand" "=w")
 	(SAT_TRUNC:<VNARROWQ>
-    (match_operand:VSQN_HSDI 1 "register_operand" "w")))]
+	  (match_operand:SD_HSDI 1 "register_operand" "w")))]
   "TARGET_SIMD"
   "<su>qxtn\\t%<vn2>0<Vmntype>, %<v>1<Vmtype>"
-   [(set_attr "type" "neon_sat_shift_imm_narrow_q")]
+  [(set_attr "type" "neon_sat_shift_imm_narrow_q")]
+)
+
+(define_insn "aarch64_<su>qmovn<mode>_insn_le"
+  [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
+	(vec_concat:<VNARROWQ2>
+	  (SAT_TRUNC:<VNARROWQ>
+	    (match_operand:VQN 1 "register_operand" "w"))
+	  (match_operand:<VNARROWQ> 2 "aarch64_simd_or_scalar_imm_zero")))]
+  "TARGET_SIMD && !BYTES_BIG_ENDIAN"
+  "<su>qxtn\\t%<vn2>0<Vmntype>, %<v>1<Vmtype>"
+  [(set_attr "type" "neon_sat_shift_imm_narrow_q")]
+)
+
+(define_insn "aarch64_<su>qmovn<mode>_insn_be"
+  [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
+	(vec_concat:<VNARROWQ2>
+	  (match_operand:<VNARROWQ> 2 "aarch64_simd_or_scalar_imm_zero")
+	  (SAT_TRUNC:<VNARROWQ>
+	    (match_operand:VQN 1 "register_operand" "w"))))]
+  "TARGET_SIMD && BYTES_BIG_ENDIAN"
+  "<su>qxtn\\t%<vn2>0<Vmntype>, %<v>1<Vmtype>"
+  [(set_attr "type" "neon_sat_shift_imm_narrow_q")]
+)
+
+(define_expand "aarch64_<su>qmovn<mode>"
+  [(set (match_operand:<VNARROWQ> 0 "register_operand")
+	(SAT_TRUNC:<VNARROWQ>
+	  (match_operand:VQN 1 "register_operand")))]
+  "TARGET_SIMD"
+  {
+    rtx tmp = gen_reg_rtx (<VNARROWQ2>mode);
+    if (BYTES_BIG_ENDIAN)
+      emit_insn (gen_aarch64_<su>qmovn<mode>_insn_be (tmp, operands[1],
+				CONST0_RTX (<VNARROWQ>mode)));
+    else
+      emit_insn (gen_aarch64_<su>qmovn<mode>_insn_le (tmp, operands[1],
+				CONST0_RTX (<VNARROWQ>mode)));
+
+    /* The intrinsic expects a narrow result, so emit a subreg that will get
+       optimized away as appropriate.  */
+    emit_move_insn (operands[0], lowpart_subreg (<VNARROWQ>mode, tmp,
+						 <VNARROWQ2>mode));
+    DONE;
+  }
 )
 
 (define_insn "aarch64_<su>qxtn2<mode>_le"
diff --git a/gcc/testsuite/gcc.target/aarch64/narrow_zero_high_half.c b/gcc/testsuite/gcc.target/aarch64/narrow_zero_high_half.c
index 53e03d3..aa6c7ef 100644
--- a/gcc/testsuite/gcc.target/aarch64/narrow_zero_high_half.c
+++ b/gcc/testsuite/gcc.target/aarch64/narrow_zero_high_half.c
@@ -67,6 +67,13 @@ TEST_UNARY (vqmovun, uint8x16_t, int16x8_t, s16, u8)
 TEST_UNARY (vqmovun, uint16x8_t, int32x4_t, s32, u16)
 TEST_UNARY (vqmovun, uint32x4_t, int64x2_t, s64, u32)
 
+TEST_UNARY (vqmovn, int8x16_t, int16x8_t, s16, s8)
+TEST_UNARY (vqmovn, int16x8_t, int32x4_t, s32, s16)
+TEST_UNARY (vqmovn, int32x4_t, int64x2_t, s64, s32)
+TEST_UNARY (vqmovn, uint8x16_t, uint16x8_t, u16, u8)
+TEST_UNARY (vqmovn, uint16x8_t, uint32x4_t, u32, u16)
+TEST_UNARY (vqmovn, uint32x4_t, uint64x2_t, u64, u32)
+
 /* { dg-final { scan-assembler-not "dup\\t" } } */
 
 /* { dg-final { scan-assembler-times "\\tshrn\\tv" 6} }  */
@@ -79,3 +86,5 @@ TEST_UNARY (vqmovun, uint32x4_t, int64x2_t, s64, u32)
 /* { dg-final { scan-assembler-times "\\tsqrshrun\\tv" 3} }  */
 /* { dg-final { scan-assembler-times "\\txtn\\tv" 6} }  */
 /* { dg-final { scan-assembler-times "\\tsqxtun\\tv" 3} }  */
+/* { dg-final { scan-assembler-times "\\tuqxtn\\tv" 3} }  */
+/* { dg-final { scan-assembler-times "\\tsqxtn\\tv" 3} }  */