//        |         |
    //      Const_0    Const_1
    //
    const float const0_val[] = {1.0, 2.0, 3.0, 4.0};
    const float const1_val[] = {1.0, 0.0, 0.0, 1.0};
    TF_Operation* const0 = FloatConst2x2(graph_, s_, const0_val, "Const_0");
    TF_Operation* const1 = FloatConst2x2(graph_, s_, const1_val, "Const_1");
    TF_Operation* matmul = MatMul(graph_, s_, const0, const1, "MatMul");
    inputs[0] = TF_Output{const0, 0};

needed // First reduction step ADDS acc0<<32, acc1, acc1 LSR $32, acc0, t0 MUL acc0, const1, t1 UMULH acc0, const1, acc0 ADCS t0, acc2 ADCS t1, acc3 ADC $0, acc0 // Second reduction step ADDS acc1<<32, acc2, acc2 LSR $32, acc1, t0 MUL acc1, const1, t1 UMULH acc1, const1, acc1 ADCS t0, acc3 ADCS t1, acc0 ADC $0, acc1 // Third reduction step ADDS acc2<<32, acc3, acc3 LSR $32, acc2, t0 MUL acc2, const1, t1 UMULH acc2, const1, acc2 ADCS t0, acc0 ADCS t1, acc1 ADC $0, acc2 // Last reduction step ADDS acc3<<32,...

needed // First reduction step ADDS acc0<<32, acc1, acc1 LSR $32, acc0, t0 MUL acc0, const1, t1 UMULH acc0, const1, acc0 ADCS t0, acc2 ADCS t1, acc3 ADC $0, acc0 // Second reduction step ADDS acc1<<32, acc2, acc2 LSR $32, acc1, t0 MUL acc1, const1, t1 UMULH acc1, const1, acc1 ADCS t0, acc3 ADCS t1, acc0 ADC $0, acc1 // Third reduction step ADDS acc2<<32, acc3, acc3 LSR $32, acc2, t0 MUL acc2, const1, t1 UMULH acc2, const1, acc2 ADCS t0, acc0 ADCS t1, acc1 ADC $0, acc2 // Last reduction step ADDS acc3<<32,...

This improves the readability of assembly code, and keeps it robust to
changes in data layout either in the Go type definitions or in the
layout rules used by the Go compiler.
</p>

<p>
Constants are of the form <code>const_<i>name</i></code>.
For example, given the Go declaration <code>const bufSize =
1024</code>, assembly code can refer to the value of this constant
as <code>const_bufSize</code>.
</p>

<p>