[AArch64] Fix lane specifier syntax

The syntax for lane specifiers uses a vector element rather than a vector:

fmls    v0.2s, v1.2s, v1.s[1]  // rather than v1.2s[1]

Fix all the lane specifiers to use Vetype which uses the correct element type.

    gcc/
	* aarch64/aarch64-simd.md (aarch64_mla_elt<mode>): Correct lane syntax.
	(aarch64_mla_elt_<vswap_width_name><mode>): Likewise.
	(aarch64_mls_elt<mode>): Likewise.
	(aarch64_mls_elt_<vswap_width_name><mode>): Likewise.
	(aarch64_fma4_elt<mode>): Likewise.
	(aarch64_fma4_elt_<vswap_width_name><mode>): Likewise.
	(aarch64_fma4_elt_to_64v2df): Likewise.
	(aarch64_fnma4_elt<mode>): Likewise.
	(aarch64_fnma4_elt_<vswap_width_name><mode>): Likewise.
	(aarch64_fnma4_elt_to_64v2df): Likewise.

    testsuite/
	* gcc.target/aarch64/fmla_intrinsic_1.c: Check for correct lane syntax.
	* gcc.target/aarch64/fmls_intrinsic_1.c: Likewise.
	* gcc.target/aarch64/mla_intrinsic_1.c: Likewise.
	* gcc.target/aarch64/mls_intrinsic_1.c: Likewise.

gcc/ChangeLog

+2020-03-06  Wilco Dijkstra  <wdijkstr@arm.com>
+
+	* aarch64/aarch64-simd.md (aarch64_mla_elt<mode>): Correct lane syntax.
+	(aarch64_mla_elt_<vswap_width_name><mode>): Likewise.
+	(aarch64_mls_elt<mode>): Likewise.
+	(aarch64_mls_elt_<vswap_width_name><mode>): Likewise.
+	(aarch64_fma4_elt<mode>): Likewise.
+	(aarch64_fma4_elt_<vswap_width_name><mode>): Likewise.
+	(aarch64_fma4_elt_to_64v2df): Likewise.
+	(aarch64_fnma4_elt<mode>): Likewise.
+	(aarch64_fnma4_elt_<vswap_width_name><mode>): Likewise.
+	(aarch64_fnma4_elt_to_64v2df): Likewise.
+
 2020-03-06  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
 	* config/aarch64/aarch64-sve2.md (@aarch64_sve_<sve_int_op><mode>:

gcc/config/aarch64/aarch64-simd.md

@@ -1350,7 +1350,7 @@
  "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2]));
-    return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
 )
@@ -1368,7 +1368,7 @@
  "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2]));
-    return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "mla\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
 )
@@ -1408,7 +1408,7 @@
  "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2]));
-    return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
 )
@@ -1426,7 +1426,7 @@
  "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2]));
-    return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "mls\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_mla_<Vetype>_scalar<q>")]
 )
@@ -2003,7 +2003,7 @@
   "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2]));
-    return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")]
 )
@@ -2020,7 +2020,7 @@
   "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2]));
-    return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "fmla\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")]
 )
@@ -2048,7 +2048,7 @@
   "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (V2DFmode, INTVAL (operands[2]));
-    return "fmla\\t%0.2d, %3.2d, %1.2d[%2]";
+    return "fmla\\t%0.2d, %3.2d, %1.d[%2]";
   }
   [(set_attr "type" "neon_fp_mla_d_scalar_q")]
 )
@@ -2077,7 +2077,7 @@
   "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<MODE>mode, INTVAL (operands[2]));
-    return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")]
 )
@@ -2095,7 +2095,7 @@
   "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (<VSWAP_WIDTH>mode, INTVAL (operands[2]));
-    return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vtype>[%2]";
+    return "fmls\\t%0.<Vtype>, %3.<Vtype>, %1.<Vetype>[%2]";
   }
   [(set_attr "type" "neon_fp_mla_<Vetype>_scalar<q>")]
 )
@@ -2125,7 +2125,7 @@
   "TARGET_SIMD"
   {
     operands[2] = aarch64_endian_lane_rtx (V2DFmode, INTVAL (operands[2]));
-    return "fmls\\t%0.2d, %3.2d, %1.2d[%2]";
+    return "fmls\\t%0.2d, %3.2d, %1.d[%2]";
   }
   [(set_attr "type" "neon_fp_mla_d_scalar_q")]
 )

gcc/testsuite/ChangeLog

+2020-03-06  Wilco Dijkstra  <wdijkstr@arm.com>
+
+	* gcc.target/aarch64/fmla_intrinsic_1.c: Check for correct lane syntax.	
+	* gcc.target/aarch64/fmls_intrinsic_1.c: Likewise.
+	* gcc.target/aarch64/mla_intrinsic_1.c: Likewise.
+	* gcc.target/aarch64/mls_intrinsic_1.c: Likewise.
+
 2020-03-06  Claudiu Zissulescu  <claziss@synopsys.com>
 
 	* gcc.target/arc/tumaddsidi4.c: Step-up optimization level.

gcc/testsuite/gcc.target/aarch64/fmla_intrinsic_1.c

@@ -98,11 +98,11 @@ main (int argc, char **argv)
 
 /* vfma_laneq_f32.
    vfma_lane_f32.  */
-/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.2s\\\[\[0-9\]+\\\]" 2 } } */
+/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */
 
 /* vfmaq_lane_f32.
    vfmaq_laneq_f32.  */
-/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 2 } } */
+/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */
 
 /* vfma_lane_f64.  */
 /* { dg-final { scan-assembler-times "fmadd\\td\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+" 1 } } */
@@ -110,6 +110,6 @@ main (int argc, char **argv)
 /* vfmaq_lane_f64.
    vfma_laneq_f64.
    vfmaq_laneq_f64.  */
-/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.2?d\\\[\[0-9\]+\\\]" 3 } } */
+/* { dg-final { scan-assembler-times "fmla\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.d\\\[\[0-9\]+\\\]" 3 } } */
 
 

gcc/testsuite/gcc.target/aarch64/fmls_intrinsic_1.c

@@ -99,11 +99,11 @@ main (int argc, char **argv)
 
 /* vfms_laneq_f32.
    vfms_lane_f32.  */
-/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.2s\\\[\[0-9\]+\\\]" 2 } } */
+/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2s, v\[0-9\]+\.2s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */
 
 /* vfmsq_lane_f32.
    vfmsq_laneq_f32.  */
-/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 2 } } */
+/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 2 } } */
 
 /* vfms_lane_f64.  */
 /* { dg-final { scan-assembler-times "fmsub\\td\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+\, d\[0-9\]+" 1 } } */
@@ -111,6 +111,6 @@ main (int argc, char **argv)
 /* vfmsq_lane_f64.
    vfms_laneq_f64.
    vfmsq_laneq_f64.  */
-/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.2?d\\\[\[0-9\]+\\\]" 3 } } */
+/* { dg-final { scan-assembler-times "fmls\\tv\[0-9\]+\.2d, v\[0-9\]+\.2d, v\[0-9\]+\.d\\\[\[0-9\]+\\\]" 3 } } */
 
 

gcc/testsuite/gcc.target/aarch64/mla_intrinsic_1.c

@@ -78,6 +78,6 @@ main (int argc, char **argv)
   return 0;
 }
 
-/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 4 } } */
-/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.8h\\\[\[0-9\]+\\\]" 4 } } */
+/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 4 } } */
+/* { dg-final { scan-assembler-times "mla\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.h\\\[\[0-9\]+\\\]" 4 } } */
 

gcc/testsuite/gcc.target/aarch64/mls_intrinsic_1.c

@@ -83,6 +83,6 @@ main (int argc, char **argv)
   return 0;
 }
 
-/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.4s\\\[\[0-9\]+\\\]" 4 } } */
-/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.8h\\\[\[0-9\]+\\\]" 4 } } */
+/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.4s, v\[0-9\]+\.4s, v\[0-9\]+\.s\\\[\[0-9\]+\\\]" 4 } } */
+/* { dg-final { scan-assembler-times "mls\\tv\[0-9\]+\.8h, v\[0-9\]+\.8h, v\[0-9\]+\.h\\\[\[0-9\]+\\\]" 4 } } */