XXPERMDI X1, X1, $2, X1 CALL p256MulInternal<>(SB) VOR T0, T0, U1L // SAVE: U1L VOR T1, T1, U1H // SAVE: U1H // SUB(H<H-T) // H = H-U1 p256SubInternal(HH,HL,HH,HL,T1,T0) // if H == 0 or H^P == 0 then ret=1 else ret=0 // clobbers T1H and T1L MOVD $1, TRUE VSPLTISB $0, ZER VOR HL, HH, T1H VCMPEQUDCC ZER, T1H, T1H // 26 = CR6 NE ISEL $26, R0, TRUE, RES1 VXOR HL, PL, T1L // SAVE: T1L VXOR HH, PH, T1H // SAVE: T1H VOR T1L, T1H, T1H VCMPEQUDCC ZER, T1H, T1H // 26 = CR6 NE ISEL $26, R0, TRUE, RES2 OR RES2, RES1,...

        as arg with default value `None` to choose the I/O device for loading
        models and weights.
    *   Update `tf.saved_model.SaveOptions` with
        [`experimental_io_device`](https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/saved_model/SaveOptions?hl=en)
        as arg with default value `None` to choose the I/O device for saving

XXPERMDI X1, X1, $2, X1 CALL p256MulInternal<>(SB) VOR T0, T0, U1L // SAVE: U1L VOR T1, T1, U1H // SAVE: U1H // SUB(H<H-T) // H = H-U1 p256SubInternal(HH,HL,HH,HL,T1,T0) // if H == 0 or H^P == 0 then ret=1 else ret=0 // clobbers T1H and T1L MOVD $1, TRUE VSPLTISB $0, ZER VOR HL, HH, T1H VCMPEQUDCC ZER, T1H, T1H // 26 = CR6 NE ISEL $26, R0, TRUE, RES1 VXOR HL, PL, T1L // SAVE: T1L VXOR HH, PH, T1H // SAVE: T1H VOR T1L, T1H, T1H VCMPEQUDCC ZER, T1H, T1H // 26 = CR6 NE ISEL $26, R0, TRUE, RES2 OR RES2, RES1,...