[PATCH][committed] aarch64: Simplify sqmovun expander

[PATCH][committed] aarch64: Simplify sqmovun expander

[Kyrylo Tkachov]

[-- Attachment #1: Type: text/plain, Size: 685 bytes --]

Hi all,

This patch is a no-op as it removes the explicit vec-concat-zero patterns in favour of vczle/vczbe.
This allows us to delete the explicit expander too. Tests are added to ensure the optimisation required
still triggers.

Bootstrapped and tested on aarch64-none-linux-gnu and aarch64_be-none-elf.

Pushing to trunk.
Thanks,
Kyrill

gcc/ChangeLog:

	* config/aarch64/aarch64-simd.md (aarch64_sqmovun<mode>_insn_le): Delete.
	(aarch64_sqmovun<mode>_insn_be): Delete.
	(aarch64_sqmovun<mode><vczle><vczbe>): New define_insn.
	(aarch64_sqmovun<mode>): Delete expander.

gcc/testsuite/ChangeLog:

	* gcc.target/aarch64/simd/pr99195_4.c: Add tests for sqmovun.

[-- Attachment #2: sqmovun.patch --]
[-- Type: application/octet-stream, Size: 3128 bytes --]

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index 363f64c7a25c563718e1f383b38c385c3daf0325..3698aab6d6df22ae780c0c6fb57ed222f14eff36 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -5361,50 +5361,15 @@ (define_insn "aarch64_sqmovun<mode>"
    [(set_attr "type" "neon_sat_shift_imm_narrow_q")]
 )
 
-(define_insn "aarch64_sqmovun<mode>_insn_le"
-  [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
-	(vec_concat:<VNARROWQ2>
-	  (unspec:<VNARROWQ> [(match_operand:VQN 1 "register_operand" "w")]
-			     UNSPEC_SQXTUN)
-	  (match_operand:<VNARROWQ> 2 "aarch64_simd_or_scalar_imm_zero")))]
-  "TARGET_SIMD && !BYTES_BIG_ENDIAN"
-  "sqxtun\\t%<vn2>0<Vmntype>, %<v>1<Vmtype>"
-  [(set_attr "type" "neon_sat_shift_imm_narrow_q")]
-)
-
-(define_insn "aarch64_sqmovun<mode>_insn_be"
-  [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
-	(vec_concat:<VNARROWQ2>
-	  (match_operand:<VNARROWQ> 2 "aarch64_simd_or_scalar_imm_zero")
-	  (unspec:<VNARROWQ> [(match_operand:VQN 1 "register_operand" "w")]
-			     UNSPEC_SQXTUN)))]
-  "TARGET_SIMD && BYTES_BIG_ENDIAN"
+(define_insn "aarch64_sqmovun<mode><vczle><vczbe>"
+  [(set (match_operand:<VNARROWQ> 0 "register_operand" "=w")
+	(unspec:<VNARROWQ> [(match_operand:VQN 1 "register_operand" "w")]
+	  UNSPEC_SQXTUN))]
+  "TARGET_SIMD"
   "sqxtun\\t%<vn2>0<Vmntype>, %<v>1<Vmtype>"
   [(set_attr "type" "neon_sat_shift_imm_narrow_q")]
 )
 
-(define_expand "aarch64_sqmovun<mode>"
-  [(set (match_operand:<VNARROWQ> 0 "register_operand")
-	(unspec:<VNARROWQ> [(match_operand:VQN 1 "register_operand")]
-			   UNSPEC_SQXTUN))]
-  "TARGET_SIMD"
-  {
-    rtx tmp = gen_reg_rtx (<VNARROWQ2>mode);
-    if (BYTES_BIG_ENDIAN)
-      emit_insn (gen_aarch64_sqmovun<mode>_insn_be (tmp, operands[1],
-				CONST0_RTX (<VNARROWQ>mode)));
-    else
-      emit_insn (gen_aarch64_sqmovun<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_sqxtun2<mode>_le"
   [(set (match_operand:<VNARROWQ2> 0 "register_operand" "=w")
 	(vec_concat:<VNARROWQ2>
diff --git a/gcc/testsuite/gcc.target/aarch64/simd/pr99195_4.c b/gcc/testsuite/gcc.target/aarch64/simd/pr99195_4.c
index 6127cb26781bbd2b727b3ac11489cf0a673e4597..8faf5691661eb55e304dcc564e8d8089a1f2f75c 100644
--- a/gcc/testsuite/gcc.target/aarch64/simd/pr99195_4.c
+++ b/gcc/testsuite/gcc.target/aarch64/simd/pr99195_4.c
@@ -50,6 +50,14 @@ MYOP (uint32x4_t, uint64x2_t, uint32x2_t, OP, u64, u32)	\
 FUNC (movn)
 FUNC (qmovn)
 
+#undef FUNC
+#define FUNC(OP)					\
+MYOP (uint8x16_t, int16x8_t, uint8x8_t, OP, s16, u8)	\
+MYOP (uint16x8_t, int32x4_t, uint16x4_t, OP, s32, u16)	\
+MYOP (uint32x4_t, int64x2_t, uint32x2_t, OP, s64, u32)	\
+
+FUNC (qmovun)
+
 /* { dg-final { scan-assembler-not {\tfmov\t} } }  */
 /* { dg-final { scan-assembler-not {\tmov\t} } }  */