#version 450

#include "types.comp"
#include "generic_binary_head.comp"

void main() {
    const uint i00 = gl_GlobalInvocationID.x;
    const uint i10 = gl_GlobalInvocationID.y;
    const uint i11 = (gl_GlobalInvocationID.z)/p.ne12;
    const uint i12 = (gl_GlobalInvocationID.z)%p.ne12;

    if (i00 >= p.ne00) {
        return;
    }

    const uint i01 = data_b[i10*p.nb10 + i11*p.nb11 + i12*p.nb12];

    const uint a_offset = i01*p.nb01 + i11*p.nb02 + i12*p.nb03;
    const uint d_offset = i10*p.nb21 + i11*p.nb22 + i12*p.nb23;

#ifndef OPTIMIZATION_ERROR_WORKAROUND
    data_d[d_offset + i00] = D_TYPE(data_a[a_offset + i00]);
#else
    data_d[d_offset + i00] = data_a[a_offset + i00];
#endif
}