import { init } from "@thi.ng/simd";

// the WASM module doesn't specify any own memory and it must be provided by user
// the returned object contains all available vector functions & memory views
// (an error will be thrown if WASM isn't available or SIMD unsupported)
const simd = init(new WebAssembly.Memory({ initial: 1 }));

// input data: 3x vec4 buffers
const a = simd.f32.subarray(0, 4);
const b = simd.f32.subarray(4, 16);
const out = simd.f32.subarray(16, 18);

a.set([1, 2, 3, 4])
b.set([10, 20, 30, 40,  40, 30, 20, 10]);

// compute dot products: dot(A[i], B[i])
// by using 0 as stride for A, all dot products are using the same vec
simd.dot4_f32_aos(
    out.byteOffset, // output addr / pointer
    a.byteOffset,   // vector A addr
    b.byteOffset,   // vector B addr
    2,              // number of vectors to process
    1,              // output stride (floats)
    0,              // A stride (floats)
    4               // B stride (floats)
);

// results for [dot(a0, b0), dot(a0, b1)]
out
// [300, 200]

// mat4 * vec4 matrix-vector multiplies
const mat = simd.f32.subarray(0, 16);
const points = simd.f32.subarray(16, 24);

// mat4 (col major)
mat.set([
    10, 0, 0, 0,
    0, 20, 0, 0,
    0, 0, 30, 0,
    100, 200, 300, 1
]);

// vec4 array
points.set([
    1, 2, 3, 1,
    4, 5, 6, 1,
]);

simd.mul_m44v4_aos(
    points.byteOffset, // output addr / pointer
    mat.byteOffset,    // mat4 addr
    points.byteOffset, // vec4 addr
    2,                 // number of vectors to process
    4,                 // output stride (float)
    4                  // vec stride (float)
);

// transformed points
points
// [110, 240, 390, 1, 140, 300, 480, 1]