[PATCH][committed] aarch64: Factorise widening add/sub high-half expanders with iterators

[PATCH][committed] aarch64: Factorise widening add/sub high-half expanders with iterators

[Kyrylo Tkachov]

[-- Attachment #1: Type: text/plain, Size: 548 bytes --]

Hi all,

I noticed these define_expand are almost identical modulo some string substitutions.
This patch compresses them together with a couple of code iterators.
No functional change intended.
Bootstrapped and tested on aarch64-none-linux-gnu.

Pushing to trunk.
Thanks,
Kyrill

gcc/ChangeLog:

	* config/aarch64/aarch64-simd.md (aarch64_saddw2<mode>): Delete.
	(aarch64_uaddw2<mode>): Delete.
	(aarch64_ssubw2<mode>): Delete.
	(aarch64_usubw2<mode>): Delete.
	(aarch64_<ANY_EXTEND:su><ADDSUB:optab>w2<mode>): New define_expand.

[-- Attachment #2: factor.patch --]
[-- Type: application/octet-stream, Size: 2717 bytes --]

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index a38497f6e068e32258e9a770d41e2eabdb0607db..c88d68ab4a5bcf748d7c3669bdd84da7eed0157a 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -4815,52 +4815,26 @@ (define_insn "aarch64_<ANY_EXTEND:su>addw2<mode>_internal"
   [(set_attr "type" "neon_add_widen")]
 )
 
-(define_expand "aarch64_saddw2<mode>"
-  [(match_operand:<VWIDE> 0 "register_operand")
-   (match_operand:<VWIDE> 1 "register_operand")
-   (match_operand:VQW 2 "register_operand")]
-  "TARGET_SIMD"
-{
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
-  emit_insn (gen_aarch64_saddw2<mode>_internal (operands[0], operands[1],
-						operands[2], p));
-  DONE;
-})
-
-(define_expand "aarch64_uaddw2<mode>"
-  [(match_operand:<VWIDE> 0 "register_operand")
-   (match_operand:<VWIDE> 1 "register_operand")
-   (match_operand:VQW 2 "register_operand")]
-  "TARGET_SIMD"
-{
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
-  emit_insn (gen_aarch64_uaddw2<mode>_internal (operands[0], operands[1],
-						operands[2], p));
-  DONE;
-})
-
-
-(define_expand "aarch64_ssubw2<mode>"
-  [(match_operand:<VWIDE> 0 "register_operand")
-   (match_operand:<VWIDE> 1 "register_operand")
-   (match_operand:VQW 2 "register_operand")]
-  "TARGET_SIMD"
-{
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
-  emit_insn (gen_aarch64_ssubw2<mode>_internal (operands[0], operands[1],
-						operands[2], p));
-  DONE;
-})
-
-(define_expand "aarch64_usubw2<mode>"
-  [(match_operand:<VWIDE> 0 "register_operand")
-   (match_operand:<VWIDE> 1 "register_operand")
-   (match_operand:VQW 2 "register_operand")]
-  "TARGET_SIMD"
-{
-  rtx p = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
-  emit_insn (gen_aarch64_usubw2<mode>_internal (operands[0], operands[1],
-						operands[2], p));
+(define_expand "aarch64_<ANY_EXTEND:su><ADDSUB:optab>w2<mode>"
+  [(set (match_operand:<VWIDE> 0 "register_operand")
+	(ADDSUB:<VWIDE>
+	  (ANY_EXTEND:<VWIDE>
+	    (vec_select:<VHALF>
+	      (match_operand:VQW 2 "register_operand")
+	      (match_dup 3)))
+	  (match_operand:<VWIDE> 1 "register_operand")))]
+  "TARGET_SIMD"
+{
+  /* We still do an emit_insn rather than relying on the pattern above
+     because for the MINUS case the operands would need to be swapped
+     around.  */
+  operands[3]
+    = aarch64_simd_vect_par_cnst_half (<MODE>mode, <nunits>, true);
+  emit_insn (gen_aarch64_<ANY_EXTEND:su><ADDSUB:optab>w2<mode>_internal(
+						       operands[0],
+						       operands[1],
+						       operands[2],
+						       operands[3]));
   DONE;
 })