is_highbit_set(const pg_u8x16_t v)
{
+#if defined(USE_NEON)
+ return to_bool(bitwise_and(v, vmovq_n_u8(0x80)));
--> return vmaxq_u8(v) > 0x7F
(Technically, their convention is: is_ascii(v) { return vmaxq_u8(v) < 0x80; } , but same effect)
+#if defined(USE_NEON)
+static pg_attribute_always_inline pg_u8x16_t
+vset(uint8 v0, uint8 v1, uint8 v2, uint8 v3,
+ uint8 v4, uint8 v5, uint8 v6, uint8 v7,
+ uint8 v8, uint8 v9, uint8 v10, uint8 v11,
+ uint8 v12, uint8 v13, uint8 v14, uint8 v15)
+{
+ uint8 pg_attribute_aligned(16) values[16] = {
+ v0, v1, v2, v3, v4, v5, v6, v7, v8, v9, v10, v11, v12, v13, v14, v15
+ };
+ return vld1q_u8(values);
+}
--> They have this strange beast instead:
// Doing a load like so end ups generating worse code.
// uint8_t array[16] = {x1, x2, x3, x4, x5, x6, x7, x8,
// x9, x10,x11,x12,x13,x14,x15,x16};
// return vld1q_u8(array);
uint8x16_t x{};
// incredibly, Visual Studio does not allow x[0] = x1
x = vsetq_lane_u8(x1, x, 0);
x = vsetq_lane_u8(x2, x, 1);
x = vsetq_lane_u8(x3, x, 2);
...
x = vsetq_lane_u8(x15, x, 14);
x = vsetq_lane_u8(x16, x, 15);
return x;
Since you aligned the array, that might not have the problem alluded to above, and it looks nicer.
