#version 450

#include "dequant_head.comp"

layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;

layout (binding = 0) readonly buffer A {float data_a[];};
layout (binding = 1) writeonly buffer D {D_TYPE data_b[];};

void main() {
    const uint i = gl_GlobalInvocationID.x * 16;

    if (i >= p.nel) {
        return;
    }

    [[unroll]] for (uint l = 0; l < 16; l++) {
        data_b[i + l] = D_TYPE(data_a[i + l]);
    }
}