`timescale 1ns/1ps

module popcount #(
    parameter int WIDTH = 512,
    parameter int GROUP = 8,
    parameter int OUT_WIDTH = $clog2(WIDTH + 1)
) (
    input  logic [WIDTH-1:0] bits_i,
    output logic [OUT_WIDTH-1:0] count_o
);
    localparam int NUM_GROUPS = (WIDTH + GROUP - 1) / GROUP;
    localparam int GROUP_COUNT_WIDTH = $clog2(GROUP + 1);

    logic [GROUP_COUNT_WIDTH-1:0] group_counts [NUM_GROUPS];

    genvar g;
    generate
        for (g = 0; g < NUM_GROUPS; g++) begin : gen_group_popcount
            always_comb begin
                group_counts[g] = '0;
                for (int b = 0; b < GROUP; b++) begin
                    int idx;
                    idx = g * GROUP + b;
                    if (idx < WIDTH) begin
                        group_counts[g] = group_counts[g] + bits_i[idx];
                    end
                end
            end
        end
    endgenerate

    // Reduction over small group counts. This is intentionally simple and
    // synthesis-friendly enough for the first prototype. If timing fails,
    // replace this block with a fully staged adder tree.
    always_comb begin
        count_o = '0;
        for (int i = 0; i < NUM_GROUPS; i++) begin
            count_o = count_o + group_counts[i];
        end
    end
endmodule