// ntt_core.v - NTT core with individual coefficient registers
//
// Uses 256 individual 12-bit registers and a deeply pipelined butterfly path.
// The arithmetic hot path is split into:
//   address/operand/zeta register -> pipelined Barrett butterfly -> writeback
// Each NTT layer is issued continuously into the butterfly pipeline, then the
// core drains pending writebacks before starting the next dependent layer.
// In inverse mode, final x3303 output scaling also uses a pipelined Barrett
// multiplier so the output path does not reintroduce a combinational reducer.

module ntt_core (
    input         clk, rst_n,
    input  [11:0] coeff_in,
    input         valid_i,
    output        ready_o,
    input         mode,
    output [11:0] coeff_out,
    output        valid_o,
    input         ready_i,
    output        done_o
);
    localparam N = 256, LAYERS = 7, DW = 12;

    reg [DW-1:0] cr [0:N-1];
    integer ci;

    localparam S_IDLE      = 4'd0;
    localparam S_LOAD      = 4'd1;
    localparam S_CMP_RUN   = 4'd2;
    localparam S_CMP_DRAIN = 4'd3;
    localparam S_OUT_PREP  = 4'd7;
    localparam S_OUTPUT    = 4'd8;
    localparam S_OUT_SCALE = 4'd9;
    localparam S_DONE      = 4'd10;

    reg [3:0] state, next_state;

    reg [7:0] load_cnt;
    reg [7:0] out_cnt;
    reg [8:0] scale_issue_cnt;
    reg [8:0] scale_emit_cnt;
    reg [7:0] j, start, layer_len;
    reg [6:0] zeta_idx;
    reg [2:0] layer;
    reg       bf_done;
    reg       mode_r;
    reg       layer_issue_done;
    reg [4:0] bf_inflight;

    reg [7:0]    wa_d0, wa_d1, wa_d2, wa_d3, wa_d4, wa_d5, wa_d6, wa_d7;
    reg [7:0]    wb_d0, wb_d1, wb_d2, wb_d3, wb_d4, wb_d5, wb_d6, wb_d7;
    reg          wb_valid_r;
    reg [DW-1:0] wb_a_data_r, wb_b_data_r;
    reg [7:0]    wb_wa_r, wb_wb_r;

    reg [DW-1:0] coeff_out_r;
    reg          valid_o_r;
    reg          scale_valid_i;
    reg [DW-1:0] scale_a_i;

    wire [DW-1:0] zeta;
    zeta_rom u_z (.addr(zeta_idx), .zeta(zeta));

    wire [8:0] group_end        = {1'b0, start} + {1'b0, layer_len};
    wire [8:0] next_group_start = {1'b0, start} + {1'b0, layer_len} + {1'b0, layer_len};
    wire       issue_group_last = ({1'b0, j} + 9'd1 >= group_end);
    wire       issue_layer_last = issue_group_last && (next_group_start >= 9'd256);
    wire [7:0] next_layer_len   = mode_r ? (layer_len << 1) : (layer_len >> 1);
    wire       issue_fire       = (state == S_CMP_RUN) && !layer_issue_done;
    wire [DW-1:0] issue_a       = cr[j];
    wire [DW-1:0] issue_b       = cr[j + layer_len];

    wire [DW-1:0] bf_a_out, bf_b_out;
    wire          bf_valid;
    butterfly_unit_pipe u_bf (
        .clk(clk),
        .rst_n(rst_n),
        .valid_i(issue_fire),
        .a(issue_a),
        .b(issue_b),
        .zeta(zeta),
        .mode(mode_r),
        .a_out(bf_a_out),
        .b_out(bf_b_out),
        .valid_o(bf_valid)
    );

    wire [DW-1:0] scale_product;
    wire          scale_valid_o;
    barrett_mul_pipe u_scl (
        .clk(clk),
        .rst_n(rst_n),
        .valid_i(scale_valid_i),
        .a(scale_a_i),
        .b(12'd3303),
        .product(scale_product),
        .valid_o(scale_valid_o)
    );

    assign ready_o   = (state == S_IDLE) || (state == S_LOAD);
    assign coeff_out = coeff_out_r;
    assign valid_o   = valid_o_r;
    assign done_o    = (state == S_DONE);

    always @* begin
        next_state = state;
        case (state)
            S_IDLE:      if (valid_i) next_state = S_LOAD;
            S_LOAD:      if (load_cnt >= 8'd255 && valid_i) next_state = S_CMP_RUN;
            S_CMP_RUN:   if (layer_issue_done) next_state = S_CMP_DRAIN;
            S_CMP_DRAIN: if (bf_inflight == 5'd0)
                              next_state = (layer + 3'd1 >= LAYERS) ? S_OUT_PREP : S_CMP_RUN;
            S_OUT_PREP:  next_state = mode_r ? S_OUT_SCALE : S_OUTPUT;
            S_OUTPUT:    if (valid_o_r && ready_i && out_cnt >= 8'd255) next_state = S_DONE;
            S_OUT_SCALE: if (scale_emit_cnt >= 9'd256) next_state = S_DONE;
            S_DONE:      next_state = S_IDLE;
            default:     next_state = S_IDLE;
        endcase
    end

    always @(posedge clk or negedge rst_n) begin
        if (!rst_n) begin
            state <= S_IDLE;
            load_cnt <= 8'd0;
            out_cnt <= 8'd0;
            scale_issue_cnt <= 9'd0;
            scale_emit_cnt <= 9'd0;
            j <= 8'd0;
            start <= 8'd0;
            layer_len <= 8'd0;
            zeta_idx <= 7'd0;
            layer <= 3'd0;
            bf_done <= 1'b0;
            mode_r <= 1'b0;
            layer_issue_done <= 1'b0;
            bf_inflight <= 5'd0;
            wa_d0 <= 8'd0; wa_d1 <= 8'd0; wa_d2 <= 8'd0; wa_d3 <= 8'd0;
            wa_d4 <= 8'd0; wa_d5 <= 8'd0; wa_d6 <= 8'd0; wa_d7 <= 8'd0;
            wb_d0 <= 8'd0; wb_d1 <= 8'd0; wb_d2 <= 8'd0; wb_d3 <= 8'd0;
            wb_d4 <= 8'd0; wb_d5 <= 8'd0; wb_d6 <= 8'd0; wb_d7 <= 8'd0;
            wb_valid_r <= 1'b0;
            wb_a_data_r <= 12'd0;
            wb_b_data_r <= 12'd0;
            wb_wa_r <= 8'd0;
            wb_wb_r <= 8'd0;
            coeff_out_r <= 12'd0;
            valid_o_r <= 1'b0;
            scale_valid_i <= 1'b0;
            scale_a_i <= 12'd0;
            for (ci = 0; ci < N; ci = ci + 1) cr[ci] <= 12'd0;
        end else begin
            state <= next_state;
            scale_valid_i <= 1'b0;

            wa_d0 <= j; wa_d1 <= wa_d0; wa_d2 <= wa_d1; wa_d3 <= wa_d2;
            wa_d4 <= wa_d3; wa_d5 <= wa_d4; wa_d6 <= wa_d5; wa_d7 <= wa_d6;
            wb_d0 <= j + layer_len; wb_d1 <= wb_d0; wb_d2 <= wb_d1; wb_d3 <= wb_d2;
            wb_d4 <= wb_d3; wb_d5 <= wb_d4; wb_d6 <= wb_d5; wb_d7 <= wb_d6;

            if (issue_fire && !wb_valid_r)
                bf_inflight <= bf_inflight + 5'd1;
            else if (!issue_fire && wb_valid_r)
                bf_inflight <= bf_inflight - 5'd1;

            if (state != S_OUTPUT && state != S_OUT_SCALE)
                valid_o_r <= 1'b0;

            if (state == S_IDLE && valid_i) begin
                cr[0] <= coeff_in;
                load_cnt <= 8'd1;
                out_cnt <= 8'd0;
                scale_issue_cnt <= 9'd0;
                scale_emit_cnt <= 9'd0;
                j <= 8'd0;
                start <= 8'd0;
                layer <= 3'd0;
                bf_done <= 1'b0;
                layer_issue_done <= 1'b0;
                bf_inflight <= 5'd0;
                mode_r <= mode;
                if (!mode) begin
                    layer_len <= 8'd128;
                    zeta_idx  <= 7'd1;
                end else begin
                    layer_len <= 8'd2;
                    zeta_idx  <= 7'd127;
                end
            end

            if (state == S_LOAD && valid_i) begin
                cr[load_cnt] <= coeff_in;
                load_cnt <= load_cnt + 8'd1;
            end

            if (state == S_CMP_RUN && !layer_issue_done) begin
                if (issue_group_last) begin
                    if (!mode_r) zeta_idx <= zeta_idx + 7'd1;
                    else         zeta_idx <= zeta_idx - 7'd1;

                    if (issue_layer_last) begin
                        layer_issue_done <= 1'b1;
                    end else begin
                        start <= next_group_start[7:0];
                        j <= next_group_start[7:0];
                    end
                end else begin
                    j <= j + 8'd1;
                end
            end

            if (wb_valid_r) begin
                cr[wb_wa_r] <= wb_a_data_r;
                cr[wb_wb_r] <= wb_b_data_r;
            end

            wb_valid_r <= bf_valid;
            if (bf_valid) begin
                wb_a_data_r <= bf_a_out;
                wb_b_data_r <= bf_b_out;
                wb_wa_r <= wa_d7;
                wb_wb_r <= wb_d7;
            end

            if (state == S_CMP_DRAIN && bf_inflight == 5'd0) begin
                if (layer + 3'd1 >= LAYERS) begin
                    bf_done <= 1'b1;
                end else begin
                    layer <= layer + 3'd1;
                    layer_len <= next_layer_len;
                    start <= 8'd0;
                    j <= 8'd0;
                    layer_issue_done <= 1'b0;
                end
            end

            if (state == S_OUT_PREP) begin
                out_cnt <= 8'd0;
                scale_issue_cnt <= 9'd0;
                scale_emit_cnt <= 9'd0;
                if (!mode_r) begin
                    coeff_out_r <= cr[0];
                    valid_o_r <= 1'b1;
                end
            end

            if (state == S_OUTPUT && valid_o_r && ready_i) begin
                if (out_cnt < 8'd255) begin
                    out_cnt <= out_cnt + 8'd1;
                    coeff_out_r <= cr[out_cnt + 8'd1];
                    valid_o_r <= 1'b1;
                end else begin
                    out_cnt <= 8'd0;
                    valid_o_r <= 1'b0;
                end
            end

            if (state == S_OUT_SCALE) begin
                if (scale_issue_cnt < 9'd256) begin
                    scale_valid_i <= 1'b1;
                    scale_a_i <= cr[scale_issue_cnt[7:0]];
                    scale_issue_cnt <= scale_issue_cnt + 9'd1;
                end

                valid_o_r <= 1'b0;
                if (scale_valid_o) begin
                    coeff_out_r <= scale_product;
                    valid_o_r <= 1'b1;
                    scale_emit_cnt <= scale_emit_cnt + 9'd1;
                end
            end

            if (state == S_DONE) begin
                load_cnt <= 8'd0;
                out_cnt <= 8'd0;
                scale_issue_cnt <= 9'd0;
                scale_emit_cnt <= 9'd0;
                layer_issue_done <= 1'b0;
                bf_inflight <= 5'd0;
                wb_valid_r <= 1'b0;
                valid_o_r <= 1'b0;
            end
        end
    end

endmodule