[AArch64, Patch] Generate MLA when multiply + add vector by scalar

(On behalf of jackson.woodruff@arm.com)

This merges vector multiplies and adds into a single mla instruction
when the multiplication is done by a scalar.

    typedef int __attribute__((vector_size(16))) vec;

    vec
    mla1(vec v0, vec v1, int v2)
    {
      return v0 + v1 * c;
    }

Now generates:

    mla1:
        fmov   s2, w0
        mla    v0.4s, v1.4s, v2.s[0]

This is also done for the identical case for a multiply followed by a
subtract of vectors with an integer operand on the multiply.

gcc/

2017-07-24  Jackson Woodruff  <jackson.woodruff@arm.com>

        * config/aarch64/aarch64-simd.md (aarch64_mla_elt_merge<mode>): New.
        (aarch64_mls_elt_merge<mode>): Likewise.

gcc/testsuite/

2017-07-24  Jackson Woodruff  <jackson.woodruff@arm.com>

	* gcc.target/aarch64/simd/vmla_elem_1.c: New.

From-SVN: r250475

gcc/ChangeLog

+2017-07-24  Jackson Woodruff  <jackson.woodruff@arm.com>
+
+	* config/aarch64/aarch64-simd.md (aarch64_mla_elt_merge<mode>): New.
+	(aarch64_mls_elt_merge<mode>): Likewise.
+
 2017-07-23  Krister Walfridsson  <krister.walfridsson@gmail.com>
 
 	* config.gcc (*-*-netbsd*): Remove check for NetBSD versions not

gcc/config/aarch64/aarch64-simd.md

@@ -1033,6 +1033,18 @@
   [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
 )
 
+(define_insn "*aarch64_mla_elt_merge<mode>"
+  [(set (match_operand:VDQHS 0 "register_operand" "=w")
+	(plus:VDQHS
+	  (mult:VDQHS (vec_duplicate:VDQHS
+		  (match_operand:<VEL> 1 "register_operand" "w"))
+		(match_operand:VDQHS 2 "register_operand" "w"))
+	  (match_operand:VDQHS 3 "register_operand" "0")))]
+ "TARGET_SIMD"
+ "mla\t%0.<Vtype>, %2.<Vtype>, %1.<Vetype>[0]"
+  [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
+)
+
 (define_insn "aarch64_mls<mode>"
  [(set (match_operand:VDQ_BHSI 0 "register_operand" "=w")
        (minus:VDQ_BHSI (match_operand:VDQ_BHSI 1 "register_operand" "0")
@@ -1080,6 +1092,18 @@
   [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
 )
 
+(define_insn "*aarch64_mls_elt_merge<mode>"
+  [(set (match_operand:VDQHS 0 "register_operand" "=w")
+	(minus:VDQHS
+	  (match_operand:VDQHS 1 "register_operand" "0")
+	  (mult:VDQHS (vec_duplicate:VDQHS
+		  (match_operand:<VEL> 2 "register_operand" "w"))
+		(match_operand:VDQHS 3 "register_operand" "w"))))]
+  "TARGET_SIMD"
+  "mls\t%0.<Vtype>, %3.<Vtype>, %2.<Vetype>[0]"
+  [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
+)
+
 ;; Max/Min operations.
 (define_insn "<su><maxmin><mode>3"
  [(set (match_operand:VDQ_BHSI 0 "register_operand" "=w")

gcc/testsuite/ChangeLog

+2017-07-24  Jackson Woodruff  <jackson.woodruff@arm.com>
+
+	* gcc.target/aarch64/simd/vmla_elem_1.c: New.
+
 2017-07-24  Thomas Koenig  <tkoenig@gcc.gnu.org>
 	    Mikael Morin <mikael@gcc.gnu.org>
 

gcc/testsuite/gcc.target/aarch64/simd/vmla_elem_1.c

+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+
+typedef short int __attribute__ ((vector_size (16))) v8hi;
+
+v8hi
+mla8hi (v8hi v0, v8hi v1, short int v2)
+{
+  /* { dg-final { scan-assembler "mla\\tv\[0-9\]\+\\.8h, v\[0-9\]\+\\.8h, v\[0-9\]\+\\.h\\\[0\\\]" } } */
+  return v0 + v1 * v2;
+}
+
+
+v8hi
+mls8hi (v8hi v0, v8hi v1, short int v2)
+{
+  /* { dg-final { scan-assembler "mls\\tv\[0-9\]\+\\.8h, v\[0-9\]\+\\.8h, v\[0-9\]\+\\.h\\\[0\\\]" } } */
+  return v0 - v1 * v2;
+}
+
+typedef short int __attribute__ ((vector_size (8))) v4hi;
+
+v4hi
+mla4hi (v4hi v0, v4hi v1, short int v2)
+{
+  /* { dg-final { scan-assembler "mla\\tv\[0-9\]\+\\.4h, v\[0-9\]\+\\.4h, v\[0-9\]\+\\.h\\\[0\\\]" } } */
+  return v0 + v1 * v2;
+}
+
+v4hi
+mls4hi (v4hi v0, v4hi v1, short int v2)
+{
+  /* { dg-final { scan-assembler "mls\\tv\[0-9\]\+\\.4h, v\[0-9\]\+\\.4h, v\[0-9\]\+\\.h\\\[0\\\]" } } */
+  return v0 - v1 * v2;
+}
+
+typedef int __attribute__ ((vector_size (16))) v4si;
+
+v4si
+mla4si (v4si v0, v4si v1, int v2)
+{
+  /* { dg-final { scan-assembler "mla\\tv\[0-9\]\+\\.4s, v\[0-9\]\+\\.4s, v\[0-9\]\+\\.s\\\[0\\\]" } } */
+  return v0 + v1 * v2;
+}
+
+v4si
+mls4si (v4si v0, v4si v1, int v2)
+{
+  /* { dg-final { scan-assembler "mls\\tv\[0-9\]\+\\.4s, v\[0-9\]\+\\.4s, v\[0-9\]\+\\.s\\\[0\\\]" } } */
+  return v0 - v1 * v2;
+}
+
+typedef int __attribute__((vector_size (8))) v2si;
+
+v2si
+mla2si (v2si v0, v2si v1, int v2)
+{
+  /* { dg-final { scan-assembler "mla\\tv\[0-9\]\+\\.2s, v\[0-9\]\+\\.2s, v\[0-9\]\+\\.s\\\[0\\\]" } } */
+  return v0 + v1 * v2;
+}
+
+v2si
+mls2si (v2si v0, v2si v1, int v2)
+{
+  /* { dg-final { scan-assembler "mls\\tv\[0-9\]\+\\.2s, v\[0-9\]\+\\.2s, v\[0-9\]\+\\.s\\\[0\\\]" } } */
+  return v0 - v1 * v2;
+}