Fix range of immediate argument in vst2q_lane_f64 (#343)

* Rectify range of immediate argument in vst2q_lane_f64

The range of 'lane' vstq_lane_f64 is documented as 0 <= lane <= 2. However, the
64-bit variant of ST2 specifies that this immediate has a range of 0 <= lane <= 1.

- ST2: https://developer.arm.com/documentation/dui0801/l/A64-SIMD-Vector-Instructions/ST2--vector--single-structure---A64-

Author: SpencerAbson

neon_intrinsics/advsimd.md

@@ -149,6 +149,7 @@ for more information about Arm’s trademarks.
 ### Changes for next release
 
 * Textual improvements (non-functional changes).
+* Fixed the range of the ``lane`` immediate argument for ``vst2q_lane_f64``.
 
 <!---
 **** Do not remove! ****
@@ -4279,7 +4280,7 @@ The intrinsics in this section are guarded by the macro ``__ARM_NEON``.
 | <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_p64" target="_blank">vst2_lane_p64</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; poly64_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; poly64x1x2_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>     | `val.val[1] -> Vt2.1D`<br>`val.val[0] -> Vt.1D`<br>`ptr -> Xn`<br>`0 <= lane <= 0`                                                          | `ST2 {Vt.d - Vt2.d}[lane],[Xn]` |          | `A64`                     |
 | <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_p64" target="_blank">vst2q_lane_p64</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; poly64_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; poly64x2x2_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>   | `val.val[1] -> Vt2.2D`<br>`val.val[0] -> Vt.2D`<br>`ptr -> Xn`<br>`0 <= lane <= 1`                                                          | `ST2 {Vt.d - Vt2.d}[lane],[Xn]` |          | `A64`                     |
 | <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2_lane_f64" target="_blank">vst2_lane_f64</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float64_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; float64x1x2_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>   | `val.val[1] -> Vt2.1D`<br>`val.val[0] -> Vt.1D`<br>`ptr -> Xn`<br>`0 <= lane <= 0`                                                          | `ST2 {Vt.d - Vt2.d}[lane],[Xn]` |          | `A64`                     |
-| <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_f64" target="_blank">vst2q_lane_f64</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float64_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; float64x2x2_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code> | `val.val[1] -> Vt2.2D`<br>`val.val[0] -> Vt.2D`<br>`ptr -> Xn`<br>`0 <= lane <= 2`                                                          | `ST2 {Vt.d - Vt2.d}[lane],[Xn]` |          | `A64`                     |
+| <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst2q_lane_f64" target="_blank">vst2q_lane_f64</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float64_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; float64x2x2_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code> | `val.val[1] -> Vt2.2D`<br>`val.val[0] -> Vt.2D`<br>`ptr -> Xn`<br>`0 <= lane <= 1`                                                          | `ST2 {Vt.d - Vt2.d}[lane],[Xn]` |          | `A64`                     |
 | <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s16" target="_blank">vst3_lane_s16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; int16_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; int16x4x3_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>       | `val.val[2] -> Vt3.4H`<br>`val.val[1] -> Vt2.4H`<br>`val.val[0] -> Vt.4H`<br>`ptr -> Xn`<br>`0 <= lane <= 3`                                | `ST3 {Vt.h - Vt3.h}[lane],[Xn]` |          | `v7/A32/A64`              |
 | <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3q_lane_s16" target="_blank">vst3q_lane_s16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; int16_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; int16x8x3_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>     | `val.val[2] -> Vt3.8H`<br>`val.val[1] -> Vt2.8H`<br>`val.val[0] -> Vt.8H`<br>`ptr -> Xn`<br>`0 <= lane <= 7`                                | `ST3 {Vt.h - Vt3.h}[lane],[Xn]` |          | `v7/A32/A64`              |
 | <code>void <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vst3_lane_s32" target="_blank">vst3_lane_s32</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; int32_t *ptr,<br>&nbsp;&nbsp;&nbsp;&nbsp; int32x2x3_t val,<br>&nbsp;&nbsp;&nbsp;&nbsp; const int lane)</code>       | `val.val[2] -> Vt3.2S`<br>`val.val[1] -> Vt2.2S`<br>`val.val[0] -> Vt.2S`<br>`ptr -> Xn`<br>`0 <= lane <= 1`                                | `ST3 {Vt.s - Vt3.s}[lane],[Xn]` |          | `v7/A32/A64`              |

neon_intrinsics/advsimd.template.md

@@ -149,6 +149,7 @@ for more information about Arm’s trademarks.
 ### Changes for next release
 
 * Textual improvements (non-functional changes).
+* Fixed the range of the ``lane`` immediate argument for ``vst2q_lane_f64``.
 
 <!---
 **** Do not remove! ****

tools/intrinsic_db/advsimd.csv

@@ -2583,7 +2583,7 @@ void vst2q_lane_u64(uint64_t *ptr, uint64x2x2_t val, __builtin_constant_p(lane))
 void vst2_lane_p64(poly64_t *ptr, poly64x1x2_t val, __builtin_constant_p(lane))	val.val[1] -> Vt2.1D;val.val[0] -> Vt.1D;ptr -> Xn;0 <= lane <= 0	ST2 {Vt.d - Vt2.d}[lane],[Xn]		A64
 void vst2q_lane_p64(poly64_t *ptr, poly64x2x2_t val, __builtin_constant_p(lane))	val.val[1] -> Vt2.2D;val.val[0] -> Vt.2D;ptr -> Xn;0 <= lane <= 1	ST2 {Vt.d - Vt2.d}[lane],[Xn]		A64
 void vst2_lane_f64(float64_t *ptr, float64x1x2_t val, __builtin_constant_p(lane))	val.val[1] -> Vt2.1D;val.val[0] -> Vt.1D;ptr -> Xn;0 <= lane <= 0	ST2 {Vt.d - Vt2.d}[lane],[Xn]		A64
-void vst2q_lane_f64(float64_t *ptr, float64x2x2_t val, __builtin_constant_p(lane))	val.val[1] -> Vt2.2D;val.val[0] -> Vt.2D;ptr -> Xn;0 <= lane <= 2	ST2 {Vt.d - Vt2.d}[lane],[Xn]		A64
+void vst2q_lane_f64(float64_t *ptr, float64x2x2_t val, __builtin_constant_p(lane))	val.val[1] -> Vt2.2D;val.val[0] -> Vt.2D;ptr -> Xn;0 <= lane <= 1	ST2 {Vt.d - Vt2.d}[lane],[Xn]		A64
 void vst3_lane_s16(int16_t *ptr, int16x4x3_t val, __builtin_constant_p(lane))	val.val[2] -> Vt3.4H;val.val[1] -> Vt2.4H;val.val[0] -> Vt.4H;ptr -> Xn;0 <= lane <= 3	ST3 {Vt.h - Vt3.h}[lane],[Xn]		v7/A32/A64
 void vst3q_lane_s16(int16_t *ptr, int16x8x3_t val, __builtin_constant_p(lane))	val.val[2] -> Vt3.8H;val.val[1] -> Vt2.8H;val.val[0] -> Vt.8H;ptr -> Xn;0 <= lane <= 7	ST3 {Vt.h - Vt3.h}[lane],[Xn]		v7/A32/A64
 void vst3_lane_s32(int32_t *ptr, int32x2x3_t val, __builtin_constant_p(lane))	val.val[2] -> Vt3.2S;val.val[1] -> Vt2.2S;val.val[0] -> Vt.2S;ptr -> Xn;0 <= lane <= 1	ST3 {Vt.s - Vt3.s}[lane],[Xn]		v7/A32/A64