T0, $2, T0 XXPERMDI T1, T1, $2, T1 // First round VPERM T1, T0, SEL1, RED2 // d1 d0 d1 d0 VPERM ZER, RED2, SEL2, RED1 // 0 d1 d0 0 VSUBUQM RED2, RED1, RED2 // VSQ RED1, RED2, RED2 // Guaranteed not to underflow VSLDOI $8, T1, T0, T0 // VSLDB $8, T1, T0, T0 VSLDOI $8, T2, T1, T1 // VSLDB $8, T2, T1, T1 VADDCUQ T0, RED1, CAR1 // VACCQ T0, RED1, CAR1 VADDUQM T0, RED1, T0 // VAQ T0, RED1, T0 VADDECUQ T1, RED2, CAR1, CAR2 // VACCCQ T1, RED2, CAR1, CAR2 VADDEUQM T1, RED2, CAR1, T1 // VACQ T1, RED2, CAR1,...

    change, but please check the
    [API doc](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/experimental)
    if any API used in your workflow is changed or deprecated, and make
    adaptations. If you decide to keep using the old optimizer, please
    explicitly change your optimizer to `tf.keras.optimizers.legacy.Optimizer`.
*   RNG behavior change for `tf.keras.initializers`. Keras initializers will now