A8 over A8
12 values:
  v0 = load8 arg(0)
  v1 = to_f32 v0
  v2 = mul_f32 v1 3B808081 (0.0039215689)
  v3 = load8 arg(1)
  v4 = to_f32 v3
  v5 = mul_f32 v4 3B808081 (0.0039215689)
↑ v6 = splat 3F800000 (1)
  v7 = sub_f32 v6 v2
  v8 = mad_f32 v5 v7 v2
  v9 = mul_f32 v8 437F0000 (255)
  v10 = round v9
  store8 arg(1) v10

4 registers, 12 instructions:
r0 = splat 3F800000 (1)
loop:
    r1 = load8 arg(0)
    r1 = to_f32 r1
    r1 = mul_f32 r1 3B808081 (0.0039215689)
    r2 = load8 arg(1)
    r2 = to_f32 r2
    r2 = mul_f32 r2 3B808081 (0.0039215689)
    r3 = sub_f32 r0 r1
    r1 = mad_f32 r2 r3 r1
    r1 = mul_f32 r1 437F0000 (255)
    r1 = round r1
    store8 arg(1) r1

A8 over G8
17 values:
  v0 = load8 arg(1)
  v1 = to_f32 v0
  v2 = mul_f32 v1 3B808081 (0.0039215689)
  v3 = load8 arg(0)
  v4 = to_f32 v3
  v5 = mul_f32 v4 3B808081 (0.0039215689)
↑ v6 = splat 3F800000 (1)
  v7 = sub_f32 v6 v5
  v8 = mul_f32 v2 v7
↑ v9 = splat 3E59B3D0 (0.21259999)
↑ v10 = splat 3F371759 (0.71520001)
  v11 = mul_f32 v8 3D93DD98 (0.0722)
  v12 = mad_f32 v8 v10 v11
  v13 = mad_f32 v8 v9 v12
  v14 = mul_f32 v13 437F0000 (255)
  v15 = round v14
  store8 arg(1) v15

5 registers, 17 instructions:
r0 = splat 3F800000 (1)
r1 = splat 3E59B3D0 (0.21259999)
r2 = splat 3F371759 (0.71520001)
loop:
    r3 = load8 arg(1)
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r4 = load8 arg(0)
    r4 = to_f32 r4
    r4 = mul_f32 r4 3B808081 (0.0039215689)
    r4 = sub_f32 r0 r4
    r4 = mul_f32 r3 r4
    r3 = mul_f32 r4 3D93DD98 (0.0722)
    r3 = mad_f32 r4 r2 r3
    r3 = mad_f32 r4 r1 r3
    r3 = mul_f32 r3 437F0000 (255)
    r3 = round r3
    store8 arg(1) r3

A8 over RGBA_8888
35 values:
  v0 = load32 arg(1)
↑ v1 = splat FF (3.5733111e-43)
  v2 = extract v0 0 v1
  v3 = to_f32 v2
  v4 = mul_f32 v3 3B808081 (0.0039215689)
  v5 = load8 arg(0)
  v6 = to_f32 v5
  v7 = mul_f32 v6 3B808081 (0.0039215689)
↑ v8 = splat 3F800000 (1)
  v9 = sub_f32 v8 v7
  v10 = mul_f32 v4 v9
  v11 = mul_f32 v10 437F0000 (255)
  v12 = round v11
  v13 = extract v0 8 v1
  v14 = to_f32 v13
  v15 = mul_f32 v14 3B808081 (0.0039215689)
  v16 = mul_f32 v15 v9
  v17 = mul_f32 v16 437F0000 (255)
  v18 = round v17
  v19 = pack v12 v18 8
  v20 = extract v0 16 v1
  v21 = to_f32 v20
  v22 = mul_f32 v21 3B808081 (0.0039215689)
  v23 = mul_f32 v22 v9
  v24 = mul_f32 v23 437F0000 (255)
  v25 = round v24
  v26 = extract v0 24 v1
  v27 = to_f32 v26
  v28 = mul_f32 v27 3B808081 (0.0039215689)
  v29 = mad_f32 v28 v9 v7
  v30 = mul_f32 v29 437F0000 (255)
  v31 = round v30
  v32 = pack v25 v31 8
  v33 = pack v19 v32 16
  store32 arg(1) v33

7 registers, 35 instructions:
r0 = splat FF (3.5733111e-43)
r1 = splat 3F800000 (1)
loop:
    r2 = load32 arg(1)
    r3 = extract r2 0 r0
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r4 = load8 arg(0)
    r4 = to_f32 r4
    r4 = mul_f32 r4 3B808081 (0.0039215689)
    r5 = sub_f32 r1 r4
    r3 = mul_f32 r3 r5
    r3 = mul_f32 r3 437F0000 (255)
    r3 = round r3
    r6 = extract r2 8 r0
    r6 = to_f32 r6
    r6 = mul_f32 r6 3B808081 (0.0039215689)
    r6 = mul_f32 r6 r5
    r6 = mul_f32 r6 437F0000 (255)
    r6 = round r6
    r6 = pack r3 r6 8
    r3 = extract r2 16 r0
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r3 = mul_f32 r3 r5
    r3 = mul_f32 r3 437F0000 (255)
    r3 = round r3
    r2 = extract r2 24 r0
    r2 = to_f32 r2
    r2 = mul_f32 r2 3B808081 (0.0039215689)
    r4 = mad_f32 r2 r5 r4
    r4 = mul_f32 r4 437F0000 (255)
    r4 = round r4
    r4 = pack r3 r4 8
    r4 = pack r6 r4 16
    store32 arg(1) r4

G8 over A8
9 values:
↑ v0 = splat 3F800000 (1)
  v1 = load8 arg(1)
  v2 = to_f32 v1
  v3 = mul_f32 v2 3B808081 (0.0039215689)
↑ v4 = sub_f32 v0 v0
  v5 = mad_f32 v3 v4 v0
  v6 = mul_f32 v5 437F0000 (255)
  v7 = round v6
  store8 arg(1) v7

3 registers, 9 instructions:
r0 = splat 3F800000 (1)
r1 = sub_f32 r0 r0
loop:
    r2 = load8 arg(1)
    r2 = to_f32 r2
    r2 = mul_f32 r2 3B808081 (0.0039215689)
    r2 = mad_f32 r2 r1 r0
    r2 = mul_f32 r2 437F0000 (255)
    r2 = round r2
    store8 arg(1) r2

G8 over G8
17 values:
  v0 = load8 arg(0)
  v1 = to_f32 v0
  v2 = mul_f32 v1 3B808081 (0.0039215689)
  v3 = load8 arg(1)
  v4 = to_f32 v3
  v5 = mul_f32 v4 3B808081 (0.0039215689)
↟ v6 = splat 3F800000 (1)
↑ v7 = sub_f32 v6 v6
  v8 = mad_f32 v5 v7 v2
↑ v9 = splat 3E59B3D0 (0.21259999)
↑ v10 = splat 3F371759 (0.71520001)
  v11 = mul_f32 v8 3D93DD98 (0.0722)
  v12 = mad_f32 v8 v10 v11
  v13 = mad_f32 v8 v9 v12
  v14 = mul_f32 v13 437F0000 (255)
  v15 = round v14
  store8 arg(1) v15

5 registers, 17 instructions:
r0 = splat 3F800000 (1)
r0 = sub_f32 r0 r0
r1 = splat 3E59B3D0 (0.21259999)
r2 = splat 3F371759 (0.71520001)
loop:
    r3 = load8 arg(0)
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r4 = load8 arg(1)
    r4 = to_f32 r4
    r4 = mul_f32 r4 3B808081 (0.0039215689)
    r3 = mad_f32 r4 r0 r3
    r4 = mul_f32 r3 3D93DD98 (0.0722)
    r4 = mad_f32 r3 r2 r4
    r4 = mad_f32 r3 r1 r4
    r4 = mul_f32 r4 437F0000 (255)
    r4 = round r4
    store8 arg(1) r4

G8 over RGBA_8888
35 values:
  v0 = load8 arg(0)
  v1 = to_f32 v0
  v2 = mul_f32 v1 3B808081 (0.0039215689)
  v3 = load32 arg(1)
↑ v4 = splat FF (3.5733111e-43)
  v5 = extract v3 0 v4
  v6 = to_f32 v5
  v7 = mul_f32 v6 3B808081 (0.0039215689)
↑ v8 = splat 3F800000 (1)
↑ v9 = sub_f32 v8 v8
  v10 = mad_f32 v7 v9 v2
  v11 = mul_f32 v10 437F0000 (255)
  v12 = round v11
  v13 = extract v3 8 v4
  v14 = to_f32 v13
  v15 = mul_f32 v14 3B808081 (0.0039215689)
  v16 = mad_f32 v15 v9 v2
  v17 = mul_f32 v16 437F0000 (255)
  v18 = round v17
  v19 = pack v12 v18 8
  v20 = extract v3 16 v4
  v21 = to_f32 v20
  v22 = mul_f32 v21 3B808081 (0.0039215689)
  v23 = mad_f32 v22 v9 v2
  v24 = mul_f32 v23 437F0000 (255)
  v25 = round v24
  v26 = extract v3 24 v4
  v27 = to_f32 v26
  v28 = mul_f32 v27 3B808081 (0.0039215689)
  v29 = mad_f32 v28 v9 v8
  v30 = mul_f32 v29 437F0000 (255)
  v31 = round v30
  v32 = pack v25 v31 8
  v33 = pack v19 v32 16
  store32 arg(1) v33

7 registers, 35 instructions:
r0 = splat FF (3.5733111e-43)
r1 = splat 3F800000 (1)
r2 = sub_f32 r1 r1
loop:
    r3 = load8 arg(0)
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r4 = load32 arg(1)
    r5 = extract r4 0 r0
    r5 = to_f32 r5
    r5 = mul_f32 r5 3B808081 (0.0039215689)
    r5 = mad_f32 r5 r2 r3
    r5 = mul_f32 r5 437F0000 (255)
    r5 = round r5
    r6 = extract r4 8 r0
    r6 = to_f32 r6
    r6 = mul_f32 r6 3B808081 (0.0039215689)
    r6 = mad_f32 r6 r2 r3
    r6 = mul_f32 r6 437F0000 (255)
    r6 = round r6
    r6 = pack r5 r6 8
    r5 = extract r4 16 r0
    r5 = to_f32 r5
    r5 = mul_f32 r5 3B808081 (0.0039215689)
    r3 = mad_f32 r5 r2 r3
    r3 = mul_f32 r3 437F0000 (255)
    r3 = round r3
    r4 = extract r4 24 r0
    r4 = to_f32 r4
    r4 = mul_f32 r4 3B808081 (0.0039215689)
    r4 = mad_f32 r4 r2 r1
    r4 = mul_f32 r4 437F0000 (255)
    r4 = round r4
    r4 = pack r3 r4 8
    r4 = pack r6 r4 16
    store32 arg(1) r4

RGBA_8888 over A8
14 values:
  v0 = load32 arg(0)
↑ v1 = splat FF (3.5733111e-43)
  v2 = extract v0 24 v1
  v3 = to_f32 v2
  v4 = mul_f32 v3 3B808081 (0.0039215689)
  v5 = load8 arg(1)
  v6 = to_f32 v5
  v7 = mul_f32 v6 3B808081 (0.0039215689)
↑ v8 = splat 3F800000 (1)
  v9 = sub_f32 v8 v4
  v10 = mad_f32 v7 v9 v4
  v11 = mul_f32 v10 437F0000 (255)
  v12 = round v11
  store8 arg(1) v12

5 registers, 14 instructions:
r0 = splat FF (3.5733111e-43)
r1 = splat 3F800000 (1)
loop:
    r2 = load32 arg(0)
    r2 = extract r2 24 r0
    r2 = to_f32 r2
    r2 = mul_f32 r2 3B808081 (0.0039215689)
    r3 = load8 arg(1)
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r4 = sub_f32 r1 r2
    r2 = mad_f32 r3 r4 r2
    r2 = mul_f32 r2 437F0000 (255)
    r2 = round r2
    store8 arg(1) r2

RGBA_8888 over G8
30 values:
  v0 = load32 arg(0)
↑ v1 = splat FF (3.5733111e-43)
  v2 = extract v0 0 v1
  v3 = to_f32 v2
  v4 = mul_f32 v3 3B808081 (0.0039215689)
  v5 = load8 arg(1)
  v6 = to_f32 v5
  v7 = mul_f32 v6 3B808081 (0.0039215689)
  v8 = extract v0 24 v1
  v9 = to_f32 v8
  v10 = mul_f32 v9 3B808081 (0.0039215689)
↑ v11 = splat 3F800000 (1)
  v12 = sub_f32 v11 v10
  v13 = mad_f32 v7 v12 v4
↑ v14 = splat 3E59B3D0 (0.21259999)
  v15 = extract v0 8 v1
  v16 = to_f32 v15
  v17 = mul_f32 v16 3B808081 (0.0039215689)
  v18 = mad_f32 v7 v12 v17
↑ v19 = splat 3F371759 (0.71520001)
  v20 = extract v0 16 v1
  v21 = to_f32 v20
  v22 = mul_f32 v21 3B808081 (0.0039215689)
  v23 = mad_f32 v7 v12 v22
  v24 = mul_f32 v23 3D93DD98 (0.0722)
  v25 = mad_f32 v18 v19 v24
  v26 = mad_f32 v13 v14 v25
  v27 = mul_f32 v26 437F0000 (255)
  v28 = round v27
  store8 arg(1) v28

9 registers, 30 instructions:
r0 = splat FF (3.5733111e-43)
r1 = splat 3F800000 (1)
r2 = splat 3E59B3D0 (0.21259999)
r3 = splat 3F371759 (0.71520001)
loop:
    r4 = load32 arg(0)
    r5 = extract r4 0 r0
    r5 = to_f32 r5
    r5 = mul_f32 r5 3B808081 (0.0039215689)
    r6 = load8 arg(1)
    r6 = to_f32 r6
    r6 = mul_f32 r6 3B808081 (0.0039215689)
    r7 = extract r4 24 r0
    r7 = to_f32 r7
    r7 = mul_f32 r7 3B808081 (0.0039215689)
    r7 = sub_f32 r1 r7
    r5 = mad_f32 r6 r7 r5
    r8 = extract r4 8 r0
    r8 = to_f32 r8
    r8 = mul_f32 r8 3B808081 (0.0039215689)
    r8 = mad_f32 r6 r7 r8
    r4 = extract r4 16 r0
    r4 = to_f32 r4
    r4 = mul_f32 r4 3B808081 (0.0039215689)
    r4 = mad_f32 r6 r7 r4
    r4 = mul_f32 r4 3D93DD98 (0.0722)
    r4 = mad_f32 r8 r3 r4
    r4 = mad_f32 r5 r2 r4
    r4 = mul_f32 r4 437F0000 (255)
    r4 = round r4
    store8 arg(1) r4

RGBA_8888 over RGBA_8888
45 values:
  v0 = load32 arg(0)
↑ v1 = splat FF (3.5733111e-43)
  v2 = extract v0 0 v1
  v3 = to_f32 v2
  v4 = mul_f32 v3 3B808081 (0.0039215689)
  v5 = load32 arg(1)
  v6 = extract v5 0 v1
  v7 = to_f32 v6
  v8 = mul_f32 v7 3B808081 (0.0039215689)
  v9 = extract v0 24 v1
  v10 = to_f32 v9
  v11 = mul_f32 v10 3B808081 (0.0039215689)
↑ v12 = splat 3F800000 (1)
  v13 = sub_f32 v12 v11
  v14 = mad_f32 v8 v13 v4
  v15 = mul_f32 v14 437F0000 (255)
  v16 = round v15
  v17 = extract v0 8 v1
  v18 = to_f32 v17
  v19 = mul_f32 v18 3B808081 (0.0039215689)
  v20 = extract v5 8 v1
  v21 = to_f32 v20
  v22 = mul_f32 v21 3B808081 (0.0039215689)
  v23 = mad_f32 v22 v13 v19
  v24 = mul_f32 v23 437F0000 (255)
  v25 = round v24
  v26 = pack v16 v25 8
  v27 = extract v0 16 v1
  v28 = to_f32 v27
  v29 = mul_f32 v28 3B808081 (0.0039215689)
  v30 = extract v5 16 v1
  v31 = to_f32 v30
  v32 = mul_f32 v31 3B808081 (0.0039215689)
  v33 = mad_f32 v32 v13 v29
  v34 = mul_f32 v33 437F0000 (255)
  v35 = round v34
  v36 = extract v5 24 v1
  v37 = to_f32 v36
  v38 = mul_f32 v37 3B808081 (0.0039215689)
  v39 = mad_f32 v38 v13 v11
  v40 = mul_f32 v39 437F0000 (255)
  v41 = round v40
  v42 = pack v35 v41 8
  v43 = pack v26 v42 16
  store32 arg(1) v43

9 registers, 45 instructions:
r0 = splat FF (3.5733111e-43)
r1 = splat 3F800000 (1)
loop:
    r2 = load32 arg(0)
    r3 = extract r2 0 r0
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r4 = load32 arg(1)
    r5 = extract r4 0 r0
    r5 = to_f32 r5
    r5 = mul_f32 r5 3B808081 (0.0039215689)
    r6 = extract r2 24 r0
    r6 = to_f32 r6
    r6 = mul_f32 r6 3B808081 (0.0039215689)
    r7 = sub_f32 r1 r6
    r3 = mad_f32 r5 r7 r3
    r3 = mul_f32 r3 437F0000 (255)
    r3 = round r3
    r5 = extract r2 8 r0
    r5 = to_f32 r5
    r5 = mul_f32 r5 3B808081 (0.0039215689)
    r8 = extract r4 8 r0
    r8 = to_f32 r8
    r8 = mul_f32 r8 3B808081 (0.0039215689)
    r5 = mad_f32 r8 r7 r5
    r5 = mul_f32 r5 437F0000 (255)
    r5 = round r5
    r5 = pack r3 r5 8
    r2 = extract r2 16 r0
    r2 = to_f32 r2
    r2 = mul_f32 r2 3B808081 (0.0039215689)
    r3 = extract r4 16 r0
    r3 = to_f32 r3
    r3 = mul_f32 r3 3B808081 (0.0039215689)
    r2 = mad_f32 r3 r7 r2
    r2 = mul_f32 r2 437F0000 (255)
    r2 = round r2
    r4 = extract r4 24 r0
    r4 = to_f32 r4
    r4 = mul_f32 r4 3B808081 (0.0039215689)
    r6 = mad_f32 r4 r7 r6
    r6 = mul_f32 r6 437F0000 (255)
    r6 = round r6
    r6 = pack r2 r6 8
    r6 = pack r5 r6 16
    store32 arg(1) r6

I32 (Naive) 8888 over 8888
29 values:
  v0 = load32 arg(0)
↑ v1 = splat FF (3.5733111e-43)
  v2 = extract v0 0 v1
  v3 = load32 arg(1)
  v4 = extract v3 0 v1
  v5 = extract v0 24 v1
↑ v6 = splat 100 (3.5873241e-43)
  v7 = sub_i32 v6 v5
  v8 = mul_i32 v4 v7
  v9 = shr_i32 v8 8
  v10 = add_i32 v2 v9
  v11 = extract v0 8 v1
  v12 = extract v3 8 v1
  v13 = mul_i32 v12 v7
  v14 = shr_i32 v13 8
  v15 = add_i32 v11 v14
  v16 = pack v10 v15 8
  v17 = extract v0 16 v1
  v18 = extract v3 16 v1
  v19 = mul_i32 v18 v7
  v20 = shr_i32 v19 8
  v21 = add_i32 v17 v20
  v22 = extract v3 24 v1
  v23 = mul_i32 v22 v7
  v24 = shr_i32 v23 8
  v25 = add_i32 v5 v24
  v26 = pack v21 v25 8
  v27 = pack v16 v26 16
  store32 arg(1) v27

9 registers, 29 instructions:
r0 = splat FF (3.5733111e-43)
r1 = splat 100 (3.5873241e-43)
loop:
    r2 = load32 arg(0)
    r3 = extract r2 0 r0
    r4 = load32 arg(1)
    r5 = extract r4 0 r0
    r6 = extract r2 24 r0
    r7 = sub_i32 r1 r6
    r5 = mul_i32 r5 r7
    r5 = shr_i32 r5 8
    r5 = add_i32 r3 r5
    r3 = extract r2 8 r0
    r8 = extract r4 8 r0
    r8 = mul_i32 r8 r7
    r8 = shr_i32 r8 8
    r8 = add_i32 r3 r8
    r8 = pack r5 r8 8
    r2 = extract r2 16 r0
    r5 = extract r4 16 r0
    r5 = mul_i32 r5 r7
    r5 = shr_i32 r5 8
    r5 = add_i32 r2 r5
    r4 = extract r4 24 r0
    r7 = mul_i32 r4 r7
    r7 = shr_i32 r7 8
    r7 = add_i32 r6 r7
    r7 = pack r5 r7 8
    r7 = pack r8 r7 16
    store32 arg(1) r7

I32 8888 over 8888
29 values:
  v0 = load32 arg(0)
↑ v1 = splat FF (3.5733111e-43)
  v2 = bit_and v0 v1
  v3 = load32 arg(1)
  v4 = bit_and v3 v1
  v5 = shr_i32 v0 24
↑ v6 = splat 100 (3.5873241e-43)
  v7 = sub_i32 v6 v5
  v8 = mul_i16x2 v4 v7
  v9 = shr_i32 v8 8
  v10 = add_i32 v2 v9
  v11 = bytes v0 2
  v12 = bytes v3 2
  v13 = mul_i16x2 v12 v7
  v14 = shr_i32 v13 8
  v15 = add_i32 v11 v14
  v16 = pack v10 v15 8
  v17 = bytes v0 3
  v18 = bytes v3 3
  v19 = mul_i16x2 v18 v7
  v20 = shr_i32 v19 8
  v21 = add_i32 v17 v20
  v22 = shr_i32 v3 24
  v23 = mul_i16x2 v22 v7
  v24 = shr_i32 v23 8
  v25 = add_i32 v5 v24
  v26 = pack v21 v25 8
  v27 = pack v16 v26 16
  store32 arg(1) v27

9 registers, 29 instructions:
r0 = splat FF (3.5733111e-43)
r1 = splat 100 (3.5873241e-43)
loop:
    r2 = load32 arg(0)
    r3 = bit_and r2 r0
    r4 = load32 arg(1)
    r5 = bit_and r4 r0
    r6 = shr_i32 r2 24
    r7 = sub_i32 r1 r6
    r5 = mul_i16x2 r5 r7
    r5 = shr_i32 r5 8
    r5 = add_i32 r3 r5
    r3 = bytes r2 2
    r8 = bytes r4 2
    r8 = mul_i16x2 r8 r7
    r8 = shr_i32 r8 8
    r8 = add_i32 r3 r8
    r8 = pack r5 r8 8
    r2 = bytes r2 3
    r5 = bytes r4 3
    r5 = mul_i16x2 r5 r7
    r5 = shr_i32 r5 8
    r5 = add_i32 r2 r5
    r4 = shr_i32 r4 24
    r7 = mul_i16x2 r4 r7
    r7 = shr_i32 r7 8
    r7 = add_i32 r6 r7
    r7 = pack r5 r7 8
    r7 = pack r8 r7 16
    store32 arg(1) r7

I32 (SWAR) 8888 over 8888
15 values:
  v0 = load32 arg(0)
  v1 = bytes v0 404
↑ v2 = splat 1000100 (2.3510604e-38)
  v3 = sub_i16x2 v2 v1
  v4 = load32 arg(1)
↑ v5 = splat FF00FF (2.3418409e-38)
  v6 = bit_and v4 v5
  v7 = mul_i16x2 v6 v3
  v8 = shr_i16x2 v7 8
  v9 = shr_i16x2 v4 8
  v10 = mul_i16x2 v9 v3
  v11 = bit_clear v10 v5
  v12 = bit_or v8 v11
  v13 = add_i32 v0 v12
  store32 arg(1) v13

6 registers, 15 instructions:
r0 = splat 1000100 (2.3510604e-38)
r1 = splat FF00FF (2.3418409e-38)
loop:
    r2 = load32 arg(0)
    r3 = bytes r2 404
    r3 = sub_i16x2 r0 r3
    r4 = load32 arg(1)
    r5 = bit_and r4 r1
    r5 = mul_i16x2 r5 r3
    r5 = shr_i16x2 r5 8
    r4 = shr_i16x2 r4 8
    r3 = mul_i16x2 r4 r3
    r3 = bit_clear r3 r1
    r3 = bit_or r5 r3
    r3 = add_i32 r2 r3
    store32 arg(1) r3

6 values:
↟ v0 = splat 1 (1.4012985e-45)
↟ v1 = splat 2 (2.8025969e-45)
↑ v2 = add_i32 v0 v1
  v3 = load32 arg(0)
  v4 = mul_i32 v3 v2
  store32 arg(0) v4

2 registers, 6 instructions:
r0 = splat 1 (1.4012985e-45)
r1 = splat 2 (2.8025969e-45)
r1 = add_i32 r0 r1
loop:
    r0 = load32 arg(0)
    r0 = mul_i32 r0 r1
    store32 arg(0) r0

19 values:
↑ v0 = splat FF (3.5733111e-43)
  v1 = load32 arg(0)
  v2 = extract v1 0 v0
  v3 = load32 arg(1)
  v4 = extract v3 0 v0
  v5 = add_i32 v2 v4
  v6 = extract v1 8 v0
  v7 = extract v3 8 v0
  v8 = add_i32 v6 v7
  v9 = pack v5 v8 8
  v10 = extract v1 16 v0
  v11 = extract v3 16 v0
  v12 = add_i32 v10 v11
  v13 = extract v1 24 v0
  v14 = extract v3 24 v0
  v15 = add_i32 v13 v14
  v16 = pack v12 v15 8
  v17 = pack v9 v16 16
  store32 arg(1) v17

6 registers, 19 instructions:
r0 = splat FF (3.5733111e-43)
loop:
    r1 = load32 arg(0)
    r2 = extract r1 0 r0
    r3 = load32 arg(1)
    r4 = extract r3 0 r0
    r4 = add_i32 r2 r4
    r2 = extract r1 8 r0
    r5 = extract r3 8 r0
    r5 = add_i32 r2 r5
    r5 = pack r4 r5 8
    r4 = extract r1 16 r0
    r2 = extract r3 16 r0
    r2 = add_i32 r4 r2
    r1 = extract r1 24 r0
    r3 = extract r3 24 r0
    r3 = add_i32 r1 r3
    r3 = pack r2 r3 8
    r3 = pack r5 r3 16
    store32 arg(1) r3