`timescale 1ps/100fs

// ============================================================
// EXP-0096 -- real FUNCTIONAL verification of the N=8 hybrid systolic
// system (n8_system_ddr3_top.v), the real, definitive deployment
// target -- directly adapted from tb_n16_system_ddr3.v's own real
// methodology (EXP-0092/0094), scaled down to N_GROUPS=2 instead of 4.
// Exists specifically because EXP-0095's own real P&R closure at N=8
// (WNS=0.000ns, 0 failing endpoints) was measured via a `-generic
// N_GROUPS=2` override against n16_system_ddr3_top.v, WITHOUT a
// dedicated functional test at that specific N -- this closes that
// real, disclosed gap before trusting N=8 as a real, deployable
// signoff.
//
// STRUCTURE: identical real harness to tb_n16_system_ddr3.v (real 2-
// chip 32-bit DDR3 model via WireDelay, real mig_7series_0_mig with
// SIM_BYPASS_INIT_CAL="FAST", the pre_active-muxed direct preload path,
// weight_byte/input_byte golden functions, sdram_write_burst task) --
// only N_GROUPS/N_PES/M change (2 groups instead of 4, 16 positions
// instead of 32, filling every one of the 2 groups x 4 PEs x 2 lanes
// exactly once), plus neural_director_grouped.v + sdram_arbiter_hier.v
// + 2x systolic_group.v instead of 4x (host slot tied off inactive,
// same real precedent as tb_n2_system_ddr3.v never instantiating
// spi_host_bridge_v3.v).
// ============================================================
module tb;
    localparam CLKIN_PERIOD  = 3225;   // ps, this project's real, CLOSED MIG config (EXP-0086)
    localparam REFCLK_FREQ   = 200.0;  // MHz
    localparam real REFCLK_PERIOD = (1000000.0/(2*REFCLK_FREQ));
    localparam RESET_PERIOD = 200000;  // ps

    localparam DATA_WIDTH  = 8;
    localparam P_IN        = 8;
    localparam ACC_WIDTH   = 32;
    localparam ADDR_WIDTH  = 26;      // this project's byte-address convention (Director/systolic_group)
    localparam MIG_ADDR_WIDTH = 25;   // word-address convention (BURST_LEN=8) at the arbiter/adapter
    localparam BURST_LEN   = 8;
    localparam N_INPUTS    = 128;
    localparam N_TILES     = N_INPUTS/P_IN;
    localparam LAYER_BYTES = N_INPUTS;
    localparam WORDS_PER_LAYER = LAYER_BYTES/2;
    localparam N_GROUPS     = 2;
    localparam N_PES        = N_GROUPS*4; // 8
    localparam QUEUE_DEPTH  = 16;

    localparam L = 1;   // one shared layer -- simplest real addressing that still
    localparam M = 16;  // exercises every one of the 2 groups x 4 PEs x 2 lanes exactly once

    // ---- clock/reset (mirrors tb_n2_system_ddr3.v's own proven pattern) ----
    reg sys_rst_n;
    wire sys_rst = sys_rst_n;
    reg sys_clk_i = 1'b0;
    always #(CLKIN_PERIOD/2.0) sys_clk_i = ~sys_clk_i;
    wire sys_clk_p = sys_clk_i;
    wire sys_clk_n = ~sys_clk_i;
    reg clk_ref_i = 1'b0;
    always #REFCLK_PERIOD clk_ref_i = ~clk_ref_i;
    wire clk_ref_p = clk_ref_i;
    wire clk_ref_n = ~clk_ref_i;
    initial begin
        sys_rst_n = 1'b0;
        #RESET_PERIOD sys_rst_n = 1'b1;
    end

    // ---- real DDR3 pins + model (identical to tb_n2_system_ddr3.v) ----
    wire        ddr3_reset_n;
    wire [31:0] ddr3_dq_fpga;
    wire [3:0]  ddr3_dqs_p_fpga, ddr3_dqs_n_fpga;
    wire [13:0] ddr3_addr_fpga;
    wire [2:0]  ddr3_ba_fpga;
    wire        ddr3_ras_n_fpga, ddr3_cas_n_fpga, ddr3_we_n_fpga;
    wire [0:0]  ddr3_cke_fpga, ddr3_ck_p_fpga, ddr3_ck_n_fpga, ddr3_cs_n_fpga;
    wire [3:0]  ddr3_dm_fpga;
    wire [0:0]  ddr3_odt_fpga;

    wire [31:0] ddr3_dq_sdram;
    reg  [13:0] ddr3_addr_sdram;
    reg  [2:0]  ddr3_ba_sdram;
    reg         ddr3_ras_n_sdram, ddr3_cas_n_sdram, ddr3_we_n_sdram;
    wire [0:0]  ddr3_cs_n_sdram;
    wire [0:0]  ddr3_odt_sdram;
    reg  [0:0]  ddr3_cke_sdram;
    wire [3:0]  ddr3_dm_sdram;
    wire [3:0]  ddr3_dqs_p_sdram, ddr3_dqs_n_sdram;
    reg  [0:0]  ddr3_ck_p_sdram, ddr3_ck_n_sdram;
    reg  [0:0]  ddr3_cs_n_sdram_tmp;
    reg  [3:0]  ddr3_dm_sdram_tmp;
    reg  [0:0]  ddr3_odt_sdram_tmp;

    always @(*) begin
        ddr3_ck_p_sdram  <= ddr3_ck_p_fpga;
        ddr3_ck_n_sdram  <= ddr3_ck_n_fpga;
        ddr3_addr_sdram  <= ddr3_addr_fpga;
        ddr3_ba_sdram    <= ddr3_ba_fpga;
        ddr3_ras_n_sdram <= ddr3_ras_n_fpga;
        ddr3_cas_n_sdram <= ddr3_cas_n_fpga;
        ddr3_we_n_sdram  <= ddr3_we_n_fpga;
        ddr3_cke_sdram   <= ddr3_cke_fpga;
    end
    always @(*) ddr3_cs_n_sdram_tmp <= ddr3_cs_n_fpga;
    assign ddr3_cs_n_sdram = ddr3_cs_n_sdram_tmp;
    always @(*) ddr3_dm_sdram_tmp <= ddr3_dm_fpga;
    assign ddr3_dm_sdram = ddr3_dm_sdram_tmp;
    always @(*) ddr3_odt_sdram_tmp <= ddr3_odt_fpga;
    assign ddr3_odt_sdram = ddr3_odt_sdram_tmp;

    genvar dqwd;
    generate
        for (dqwd = 0; dqwd < 32; dqwd = dqwd + 1) begin : dq_delay
            WireDelay #(.Delay_g(0.00), .Delay_rd(0.00), .ERR_INSERT("OFF")) u_delay_dq (
                .A(ddr3_dq_fpga[dqwd]), .B(ddr3_dq_sdram[dqwd]),
                .reset(sys_rst_n), .phy_init_done(init_calib_complete)
            );
        end
    endgenerate
    genvar dqswd;
    generate
        for (dqswd = 0; dqswd < 4; dqswd = dqswd + 1) begin : dqs_delay
            WireDelay #(.Delay_g(0.00), .Delay_rd(0.00), .ERR_INSERT("OFF")) u_delay_dqs_p (
                .A(ddr3_dqs_p_fpga[dqswd]), .B(ddr3_dqs_p_sdram[dqswd]),
                .reset(sys_rst_n), .phy_init_done(init_calib_complete)
            );
            WireDelay #(.Delay_g(0.00), .Delay_rd(0.00), .ERR_INSERT("OFF")) u_delay_dqs_n (
                .A(ddr3_dqs_n_fpga[dqswd]), .B(ddr3_dqs_n_sdram[dqswd]),
                .reset(sys_rst_n), .phy_init_done(init_calib_complete)
            );
        end
    endgenerate

    genvar ci;
    generate
        for (ci = 0; ci < 2; ci = ci + 1) begin : gen_mem
            ddr3_model u_comp_ddr3 (
                .rst_n(ddr3_reset_n), .ck(ddr3_ck_p_sdram), .ck_n(ddr3_ck_n_sdram),
                .cke(ddr3_cke_sdram[0]), .cs_n(ddr3_cs_n_sdram[0]),
                .ras_n(ddr3_ras_n_sdram), .cas_n(ddr3_cas_n_sdram), .we_n(ddr3_we_n_sdram),
                .dm_tdqs(ddr3_dm_sdram[2*ci +: 2]), .ba(ddr3_ba_sdram), .addr(ddr3_addr_sdram),
                .dq(ddr3_dq_sdram[16*ci +: 16]),
                .dqs(ddr3_dqs_p_sdram[2*ci +: 2]), .dqs_n(ddr3_dqs_n_sdram[2*ci +: 2]),
                .tdqs_n(), .odt(ddr3_odt_sdram[0])
            );
        end
    endgenerate

    wire [27:0]  app_addr;
    wire [2:0]   app_cmd;
    wire         app_en, app_rdy;
    wire [127:0] app_wdf_data;
    wire         app_wdf_end;
    wire [15:0]  app_wdf_mask;
    wire         app_wdf_wren, app_wdf_rdy;
    wire [127:0] app_rd_data;
    wire         app_rd_data_end, app_rd_data_valid;
    wire         ui_clk, ui_clk_sync_rst, init_calib_complete;

    mig_7series_0_mig #(
        .SIM_BYPASS_INIT_CAL("FAST")
    ) u_mig (
        .ddr3_dq(ddr3_dq_fpga), .ddr3_dqs_n(ddr3_dqs_n_fpga), .ddr3_dqs_p(ddr3_dqs_p_fpga),
        .ddr3_addr(ddr3_addr_fpga), .ddr3_ba(ddr3_ba_fpga),
        .ddr3_ras_n(ddr3_ras_n_fpga), .ddr3_cas_n(ddr3_cas_n_fpga), .ddr3_we_n(ddr3_we_n_fpga),
        .ddr3_reset_n(ddr3_reset_n),
        .ddr3_ck_p(ddr3_ck_p_fpga), .ddr3_ck_n(ddr3_ck_n_fpga),
        .ddr3_cke(ddr3_cke_fpga), .ddr3_cs_n(ddr3_cs_n_fpga),
        .ddr3_dm(ddr3_dm_fpga), .ddr3_odt(ddr3_odt_fpga),
        .sys_clk_p(sys_clk_p), .sys_clk_n(sys_clk_n), .clk_ref_p(clk_ref_p), .clk_ref_n(clk_ref_n),
        .app_addr(app_addr), .app_cmd(app_cmd), .app_en(app_en),
        .app_wdf_data(app_wdf_data), .app_wdf_end(app_wdf_end),
        .app_wdf_mask(app_wdf_mask), .app_wdf_wren(app_wdf_wren),
        .app_rd_data(app_rd_data), .app_rd_data_end(app_rd_data_end),
        .app_rd_data_valid(app_rd_data_valid), .app_rdy(app_rdy), .app_wdf_rdy(app_wdf_rdy),
        .app_sr_req(1'b0), .app_ref_req(1'b0), .app_zq_req(1'b0),
        .app_sr_active(), .app_ref_ack(), .app_zq_ack(),
        .ui_clk(ui_clk), .ui_clk_sync_rst(ui_clk_sync_rst),
        .init_calib_complete(init_calib_complete),
        .device_temp(),
        .sys_rst(sys_rst)
    );

    // ---- preload path: direct access to mig_native_adapter.v,
    // bypassing the arbiter, exactly like tb_n2_system_ddr3.v's own
    // "pre_active" mux -- used only before job submission begins. ----
    reg                        pre_active;
    reg                        pre_req, pre_wr;
    reg  [MIG_ADDR_WIDTH-1:0]  pre_addr;
    reg  [32*BURST_LEN-1:0]    pre_wdata;

    wire                     adp_req, adp_wr;
    wire [MIG_ADDR_WIDTH-1:0] adp_addr;
    wire [32*BURST_LEN-1:0]  adp_wdata;
    wire [4*BURST_LEN-1:0]   adp_wmask;
    wire [32*BURST_LEN-1:0]  adp_rdata;
    wire                     adp_ready, adp_busy;

    wire arb_ctrl_req_o, arb_ctrl_wr_o;
    wire [MIG_ADDR_WIDTH-1:0] arb_ctrl_addr_o;
    wire [32*BURST_LEN-1:0]  arb_ctrl_wdata_o;
    wire [4*BURST_LEN-1:0]   arb_ctrl_wmask_o;

    assign adp_req   = pre_active ? pre_req   : arb_ctrl_req_o;
    assign adp_wr    = pre_active ? pre_wr    : arb_ctrl_wr_o;
    assign adp_addr  = pre_active ? pre_addr  : arb_ctrl_addr_o;
    assign adp_wdata = pre_active ? pre_wdata : arb_ctrl_wdata_o;
    assign adp_wmask = pre_active ? {(4*BURST_LEN){1'b0}} : arb_ctrl_wmask_o;

    mig_native_adapter #(.BURST_LEN(BURST_LEN), .ADDR_WIDTH(MIG_ADDR_WIDTH)) u_adapter (
        .clk(ui_clk), .rst(ui_clk_sync_rst),
        .req(adp_req), .wr(adp_wr), .addr(adp_addr), .wdata(adp_wdata), .wmask(adp_wmask),
        .rdata(adp_rdata), .ready(adp_ready), .busy(adp_busy),
        .app_addr(app_addr), .app_cmd(app_cmd), .app_en(app_en), .app_rdy(app_rdy),
        .app_wdf_data(app_wdf_data), .app_wdf_end(app_wdf_end), .app_wdf_mask(app_wdf_mask),
        .app_wdf_wren(app_wdf_wren), .app_wdf_rdy(app_wdf_rdy),
        .app_rd_data(app_rd_data), .app_rd_data_end(app_rd_data_end), .app_rd_data_valid(app_rd_data_valid)
    );

    // EXP-0086 fix (see tb_n2_system_ddr3.v): plain intermediate 8-bit
    // reg instead of SV-only `8'(expr)` sized-cast syntax.
    function automatic signed [7:0] weight_byte(input integer li, input integer t);
        reg [7:0] tmp;
        begin
            tmp = (li*17 + t*29 + 13) & 8'hFF;
            weight_byte = $signed(tmp);
        end
    endfunction
    function automatic signed [7:0] input_byte(input integer li, input integer pos, input integer t);
        reg [7:0] tmp;
        begin
            tmp = (li*11 + pos*41 + t*7 + 3) & 8'hFF;
            input_byte = $signed(tmp);
        end
    endfunction

    task automatic sdram_write_burst(input [MIG_ADDR_WIDTH-1:0] word_addr, input [32*BURST_LEN-1:0] data);
        begin
            @(posedge ui_clk); while (adp_busy) @(posedge ui_clk);
            pre_req = 1'b1; pre_wr = 1'b1; pre_addr = word_addr; pre_wdata = data;
            @(posedge ui_clk); pre_req = 1'b0;
            while (!adp_ready) @(posedge ui_clk);
        end
    endtask

    task automatic preload_sdram_layers;
        integer li, bi, wb, tt;
        reg [32*BURST_LEN-1:0] burst_data;
        begin
            for (li = 0; li < L; li = li + 1) begin
                for (bi = 0; bi < (LAYER_BYTES/(4*BURST_LEN)); bi = bi + 1) begin
                    for (wb = 0; wb < BURST_LEN; wb = wb + 1) begin
                        tt = bi*(4*BURST_LEN) + wb*4;
                        burst_data[wb*32 +: 32] = {weight_byte(li, tt+3), weight_byte(li, tt+2),
                                                    weight_byte(li, tt+1), weight_byte(li, tt)};
                    end
                    sdram_write_burst((li*WORDS_PER_LAYER + bi*BURST_LEN), burst_data);
                end
            end
        end
    endtask

    localparam [MIG_ADDR_WIDTH-1:0] ACT_MEM_BASE = 25'h10000;
    function automatic [ADDR_WIDTH-1:0] act_x_base(input integer li, input integer pos);
        act_x_base = {{(ADDR_WIDTH-MIG_ADDR_WIDTH){1'b0}}, ACT_MEM_BASE} + (li*M + pos) * ((N_TILES/4)*BURST_LEN);
    endfunction

    task automatic preload_ddr3_activations;
        integer li, pos, tq, qi;
        reg [32*BURST_LEN-1:0] burst_data;
        reg [ADDR_WIDTH-1:0] base;
        begin
            for (li = 0; li < L; li = li + 1) begin
                for (pos = 0; pos < M; pos = pos + 1) begin
                    base = act_x_base(li, pos);
                    for (tq = 0; tq < N_TILES/4; tq = tq + 1) begin
                        burst_data = {(32*BURST_LEN){1'b0}};
                        for (qi = 0; qi < 4; qi = qi + 1)
                            burst_data[qi*64 +: 64] = {input_byte(li, pos, (4*tq+qi)*P_IN + 7), input_byte(li, pos, (4*tq+qi)*P_IN + 6),
                                                        input_byte(li, pos, (4*tq+qi)*P_IN + 5), input_byte(li, pos, (4*tq+qi)*P_IN + 4),
                                                        input_byte(li, pos, (4*tq+qi)*P_IN + 3), input_byte(li, pos, (4*tq+qi)*P_IN + 2),
                                                        input_byte(li, pos, (4*tq+qi)*P_IN + 1), input_byte(li, pos, (4*tq+qi)*P_IN + 0)};
                        sdram_write_burst(base[MIG_ADDR_WIDTH-1:0] + tq*BURST_LEN, burst_data);
                    end
                end
            end
        end
    endtask

    // ---- neural_director_grouped.v ----
    reg                     job_in_valid;
    wire                    job_in_ready;
    reg  [ADDR_WIDTH-1:0]   job_in_x_base, job_in_w_base, job_in_result_addr;
    reg  [15:0]             job_in_n_tiles, job_in_node_id;

    wire [N_GROUPS-1:0]                  group_job_start;
    wire [ADDR_WIDTH*N_GROUPS-1:0]       group_w_base;
    wire [16*N_GROUPS-1:0]               group_n_tiles;
    wire [4*ADDR_WIDTH*N_GROUPS-1:0]     group_pe_x_base_a, group_pe_x_base_b;
    wire [4*ADDR_WIDTH*N_GROUPS-1:0]     group_pe_result_addr_a, group_pe_result_addr_b;
    wire [4*16*N_GROUPS-1:0]             group_pe_node_id_a, group_pe_node_id_b;
    wire [N_GROUPS-1:0]                  group_job_done;
    wire                        job_out_done;
    wire [$clog2(N_GROUPS)-1:0] job_out_group;
    wire [3:0]                  dir_state;
    wire                        dir_error;
    wire                        queue_empty;

    neural_director_grouped #(
        .ADDR_WIDTH(ADDR_WIDTH), .N_GROUPS(N_GROUPS), .QUEUE_DEPTH(QUEUE_DEPTH)
    ) u_dir (
        .clk(ui_clk), .rst(ui_clk_sync_rst),
        .job_in_valid(job_in_valid), .job_in_ready(job_in_ready),
        .job_in_x_base(job_in_x_base), .job_in_w_base(job_in_w_base),
        .job_in_n_tiles(job_in_n_tiles), .job_in_result_addr(job_in_result_addr),
        .job_in_node_id(job_in_node_id),
        .group_job_start(group_job_start), .group_w_base(group_w_base), .group_n_tiles(group_n_tiles),
        .group_pe_x_base_a(group_pe_x_base_a), .group_pe_x_base_b(group_pe_x_base_b),
        .group_pe_result_addr_a(group_pe_result_addr_a), .group_pe_result_addr_b(group_pe_result_addr_b),
        .group_pe_node_id_a(group_pe_node_id_a), .group_pe_node_id_b(group_pe_node_id_b),
        .group_job_done(group_job_done),
        .job_out_done(job_out_done), .job_out_group(job_out_group),
        .dir_state(dir_state), .dir_error(dir_error), .queue_empty(queue_empty)
    );

    // ---- real, hierarchical 2-level arbiter (EXP-0094): 2 groups' own
    // weight-fetch + 8 PEs' own activation-fetch+writeback + 1 host
    // slot, matching n8_system_ddr3_top.v's own real, fixed topology
    // exactly -- sdram_arbiter_hier.v always includes a host slot, so
    // this testbench ties it off inactive (doesn't instantiate
    // host_mem_bridge.v at all, same real precedent as
    // tb_n2_system_ddr3.v never instantiating spi_host_bridge_v3.v). ----
    localparam NUM_REQ = N_GROUPS + N_PES + 1; // 2 + 8 + 1 = 11
    localparam HOST_SLOT = NUM_REQ - 1; // 10, tied off inactive below

    wire [NUM_REQ-1:0]                  req_active, req_grant, req_req, req_wr;
    wire [NUM_REQ-1:0]                  req_ready, req_busy;
    wire [NUM_REQ*MIG_ADDR_WIDTH-1:0]   req_addr;
    wire [NUM_REQ*32*BURST_LEN-1:0]     req_wdata;
    wire [NUM_REQ*4*BURST_LEN-1:0]      req_wmask;
    wire [NUM_REQ*32*BURST_LEN-1:0]     req_rdata;

    assign req_active[HOST_SLOT] = 1'b0;
    assign req_req[HOST_SLOT]    = 1'b0;
    assign req_wr[HOST_SLOT]     = 1'b0;
    assign req_addr[HOST_SLOT*MIG_ADDR_WIDTH +: MIG_ADDR_WIDTH]  = {MIG_ADDR_WIDTH{1'b0}};
    assign req_wdata[HOST_SLOT*32*BURST_LEN +: 32*BURST_LEN]     = {(32*BURST_LEN){1'b0}};
    assign req_wmask[HOST_SLOT*4*BURST_LEN +: 4*BURST_LEN]       = {(4*BURST_LEN){1'b0}};

    sdram_arbiter_hier #(
        .N_GROUPS(N_GROUPS), .PES_PER_GROUP(4), .ADDR_WIDTH(MIG_ADDR_WIDTH), .BURST_LEN(BURST_LEN)
    ) u_arb (
        .clk(ui_clk), .rst(ui_clk_sync_rst),
        .req_active(req_active), .req_grant(req_grant),
        .req_req(req_req), .req_wr(req_wr), .req_addr(req_addr),
        .req_wdata(req_wdata), .req_wmask(req_wmask),
        .req_rdata(req_rdata), .req_ready(req_ready), .req_busy(req_busy),
        .ctrl_req(arb_ctrl_req_o), .ctrl_wr(arb_ctrl_wr_o), .ctrl_addr(arb_ctrl_addr_o),
        .ctrl_wdata(arb_ctrl_wdata_o), .ctrl_wmask(arb_ctrl_wmask_o),
        .ctrl_rdata(adp_rdata), .ctrl_ready(adp_ready), .ctrl_busy(adp_busy)
    );

    wire [4*DATA_WIDTH*N_GROUPS-1:0] all_pe_result_data_a, all_pe_result_data_b;
    wire [4*16*N_GROUPS-1:0]         all_pe_result_node_id_a, all_pe_result_node_id_b;

    genvar gg;
    generate
        for (gg = 0; gg < N_GROUPS; gg = gg + 1) begin : GEN_GROUP
            localparam PE_BASE = N_GROUPS + gg*4;

            systolic_group #(
                .DATA_WIDTH(DATA_WIDTH), .P_IN(P_IN), .ACC_WIDTH(ACC_WIDTH),
                .BURST_LEN(BURST_LEN), .ADDR_WIDTH(ADDR_WIDTH), .LAYER_BYTES(LAYER_BYTES)
            ) u_group (
                .clk(ui_clk), .rst(ui_clk_sync_rst),
                .job_start(group_job_start[gg]),
                .w_base(group_w_base[gg*ADDR_WIDTH +: ADDR_WIDTH]),
                .n_tiles(group_n_tiles[gg*16 +: 16]),
                .pe_x_base_a(group_pe_x_base_a[gg*4*ADDR_WIDTH +: 4*ADDR_WIDTH]),
                .pe_x_base_b(group_pe_x_base_b[gg*4*ADDR_WIDTH +: 4*ADDR_WIDTH]),
                .pe_result_addr_a(group_pe_result_addr_a[gg*4*ADDR_WIDTH +: 4*ADDR_WIDTH]),
                .pe_result_addr_b(group_pe_result_addr_b[gg*4*ADDR_WIDTH +: 4*ADDR_WIDTH]),
                .pe_node_id_a(group_pe_node_id_a[gg*4*16 +: 4*16]),
                .pe_node_id_b(group_pe_node_id_b[gg*4*16 +: 4*16]),
                .job_done(group_job_done[gg]),
                .pe_result_data_a(all_pe_result_data_a[gg*4*DATA_WIDTH +: 4*DATA_WIDTH]),
                .pe_result_data_b(all_pe_result_data_b[gg*4*DATA_WIDTH +: 4*DATA_WIDTH]),
                .pe_result_node_id_a(all_pe_result_node_id_a[gg*4*16 +: 4*16]),
                .pe_result_node_id_b(all_pe_result_node_id_b[gg*4*16 +: 4*16]),
                .pe_result_addr_a_out(), .pe_result_addr_b_out(),
                .mem_active(req_active[gg]), .mem_grant(req_grant[gg]),
                .ctrl_req(req_req[gg]), .ctrl_wr(req_wr[gg]),
                .ctrl_addr(req_addr[gg*MIG_ADDR_WIDTH +: MIG_ADDR_WIDTH]),
                .ctrl_wdata(req_wdata[gg*32*BURST_LEN +: 32*BURST_LEN]),
                .ctrl_wmask(req_wmask[gg*4*BURST_LEN +: 4*BURST_LEN]),
                .ctrl_rdata(req_rdata[gg*32*BURST_LEN +: 32*BURST_LEN]),
                .ctrl_ready(req_ready[gg]), .ctrl_busy(req_busy[gg]),
                .pe_mem_active(req_active[PE_BASE +: 4]), .pe_mem_grant(req_grant[PE_BASE +: 4]),
                .pe_ctrl_req(req_req[PE_BASE +: 4]), .pe_ctrl_wr(req_wr[PE_BASE +: 4]),
                .pe_ctrl_addr(req_addr[PE_BASE*MIG_ADDR_WIDTH +: 4*MIG_ADDR_WIDTH]),
                .pe_ctrl_wdata(req_wdata[PE_BASE*32*BURST_LEN +: 4*32*BURST_LEN]),
                .pe_ctrl_wmask(req_wmask[PE_BASE*4*BURST_LEN +: 4*4*BURST_LEN]),
                .pe_ctrl_rdata(req_rdata[PE_BASE*32*BURST_LEN +: 4*32*BURST_LEN]),
                .pe_ctrl_ready(req_ready[PE_BASE +: 4]), .pe_ctrl_busy(req_busy[PE_BASE +: 4])
            );
        end
    endgenerate

    integer errors, tests, completions, n_expected;
    reg [15:0] expect_node [0:15];
    reg signed [7:0] expect_val [0:15];

    function automatic signed [7:0] golden_result(input integer li, input integer pos);
        integer t, acc;
        reg signed [7:0] r;
        begin
            acc = 0;
            for (t = 0; t < N_INPUTS; t = t + 1)
                acc = acc + (input_byte(li, pos, t) * weight_byte(li, t));
            if (acc <= 0) r = 0; else if (acc > 127) r = 8'sd127; else r = acc[7:0];
            golden_result = r;
        end
    endfunction

    task automatic check_completion(input integer idx, input [15:0] nid, input signed [7:0] val);
        integer ei, found;
        begin
            found = 0;
            for (ei = 0; ei < n_expected; ei = ei + 1) begin
                if (expect_node[ei] === nid && !found) begin
                    found = 1;
                    tests = tests + 1;
                    if (expect_val[ei] !== val) begin
                        $display("FAIL idx=%0d node_id=%0d: got=%0d expected=%0d", idx, nid, $signed(val), $signed(expect_val[ei]));
                        errors = errors + 1;
                    end else begin
                        $display("PASS idx=%0d node_id=%0d: result=%0d", idx, nid, $signed(val));
                    end
                end
            end
        end
    endtask

    integer gg2, pp2;
    always @(posedge ui_clk) begin
        if (!ui_clk_sync_rst) begin
            for (gg2 = 0; gg2 < N_GROUPS; gg2 = gg2 + 1) begin
                if (group_job_done[gg2]) begin
                    completions = completions + 8;
                    for (pp2 = 0; pp2 < 4; pp2 = pp2 + 1) begin
                        check_completion(gg2*4+pp2,
                            all_pe_result_node_id_a[(gg2*4+pp2)*16 +: 16],
                            all_pe_result_data_a[(gg2*4+pp2)*DATA_WIDTH +: DATA_WIDTH]);
                        check_completion(gg2*4+pp2,
                            all_pe_result_node_id_b[(gg2*4+pp2)*16 +: 16],
                            all_pe_result_data_b[(gg2*4+pp2)*DATA_WIDTH +: DATA_WIDTH]);
                    end
                end
            end
        end
    end

    // real, root-caused fix (EXP-0090, CLAUDE.md): driving stimulus on
    // @(posedge clk) races the DUT's own posedge-sampling always block
    // when called back-to-back with zero real simulated gap -- drive on
    // @(negedge ui_clk) instead.
    task automatic submit_job(
        input [ADDR_WIDTH-1:0] xb, input [ADDR_WIDTH-1:0] wb,
        input [15:0] nt, input [ADDR_WIDTH-1:0] resaddr, input [15:0] nid
    );
        begin
            @(negedge ui_clk);
            job_in_valid = 1'b1; job_in_x_base = xb; job_in_w_base = wb;
            job_in_n_tiles = nt; job_in_result_addr = resaddr; job_in_node_id = nid;
            @(negedge ui_clk);
            job_in_valid = 1'b0;
        end
    endtask

    integer pp_i, wd;

    initial begin
        errors = 0; tests = 0; completions = 0; n_expected = 0;
        pre_active = 1'b1; pre_req = 0; pre_wr = 0; pre_addr = 0; pre_wdata = 0;
        job_in_valid = 0; job_in_x_base = 0; job_in_w_base = 0;
        job_in_n_tiles = 0; job_in_result_addr = 0; job_in_node_id = 0;

        $display("=== waiting for real DDR3 init_calib_complete ===");
        wait (init_calib_complete);
        $display("=== calibration done at time %0t ===", $time);
        repeat (10) @(posedge ui_clk);

        $display("=== preload SDRAM with %0d resident-filter weight set(s) ===", L);
        preload_sdram_layers;
        $display("=== preload SDRAM with real activation data (%0d positions) ===", M);
        preload_ddr3_activations;
        @(posedge ui_clk);
        pre_active = 1'b0;
        repeat (5) @(posedge ui_clk);

        $display("=== N=8 hybrid systolic system on REAL DDR3: submitting %0d positions (2 groups x 4 PEs x 2 lanes) ===", M);
        for (pp_i = 0; pp_i < M; pp_i = pp_i + 1) begin
            submit_job(act_x_base(0, pp_i), {ADDR_WIDTH{1'b0}}, N_TILES[15:0],
                       26'h9000 + pp_i, pp_i[15:0]);
            expect_node[n_expected] = pp_i[15:0];
            expect_val[n_expected]  = golden_result(0, pp_i);
            n_expected = n_expected + 1;
        end

        wd = 0;
        while (completions < n_expected && wd < 400000) begin
            @(posedge ui_clk);
            wd = wd + 1;
        end

        if (completions < n_expected) begin
            $display("FAIL: only %0d/%0d position-results completed within watchdog", completions, n_expected);
            errors = errors + 1;
        end

        $display("=== %0d/%0d tests, %0d errors, %0d/%0d positions completed ===", tests-errors, tests, errors, completions, n_expected);
        if (errors == 0 && completions == n_expected) $display("ALL TESTS PASSED (tb_n8_system_ddr3, REAL DDR3)");
        $finish;
    end
endmodule