Method concatenate

tests/python/relax/test_transform_fuse_tir.py:1049–1069

(
            rxplaceholder: T.Buffer((T.int64(1), T.int64(4), T.int64(64), T.int64(64)), "float32"),
            rxplaceholder_1: T.Buffer(
                (T.int64(1), T.int64(4), T.int64(64), T.int64(64)), "float32"
            ),
            T_concat: T.Buffer((T.int64(2), T.int64(4), T.int64(64), T.int64(64)), "float32"),
        )

    class Module:
        @T.prim_func(private=True, s_tir=True)
        def concatenate(
            rxplaceholder: T.Buffer((T.int64(1), T.int64(4), T.int64(64), T.int64(64)), "float32"),
            rxplaceholder_1: T.Buffer(
                (T.int64(1), T.int64(4), T.int64(64), T.int64(64)), "float32"
            ),
            T_concat: T.Buffer((T.int64(2), T.int64(4), T.int64(64), T.int64(64)), "float32"),
        ):
            T.func_attr({"op_pattern": 2, "tirx.noalias": True})
            for ax0, ax1, ax2, ax3 in T.grid(T.int64(2), T.int64(4), T.int64(64), T.int64(64)):
                with T.sblock("T_concat"):
                    v_ax0, v_ax1, v_ax2, v_ax3 = T.axis.remap("SSSS", [ax0, ax1, ax2, ax3])
                    T.reads(
                        rxplaceholder_1[v_ax0 - T.int64(1), v_ax1, v_ax2, v_ax3],
                        rxplaceholder[v_ax0, v_ax1, v_ax2, v_ax3],
                    )
                    T.writes(T_concat[v_ax0, v_ax1, v_ax2, v_ax3])
                    T_concat[v_ax0, v_ax1, v_ax2, v_ax3] = T.if_then_else(
                        T.int64(1) <= v_ax0,
                        rxplaceholder_1[v_ax0 - T.int64(1), v_ax1, v_ax2, v_ax3],
                        rxplaceholder[v_ax0, v_ax1, v_ax2, v_ax3],
                    )

        @T.prim_func(private=True, s_tir=True)
        def transpose2(