Here is some Verilog code for a 32×128 DMD I am designing.

module LED_Matrix_32x128
(
clk,e_cnt,row_cnt,col,SDRAM_CS,SRAM_CS,LAT,DATA,SCLK
);

input  wire    clk;
input  wire    LAT;
input  wire    DATA;
input  wire    SCLK;

output  reg [63:0]  col;
output  reg [0:0]   SDRAM_CS;
output  reg [0:0]   SRAM_CS;
output  reg [5:0]  row_cnt;
output  reg [4:0]  e_cnt;

reg [24:0]  clk_slow;
reg [4096:0]  col_buffer;
reg [63:0]  col_temp [63:0];

initial
begin
col <= 16'b0000000000000000;
    SDRAM_CS <= 1'b0;
    SRAM_CS <= 1'b0;
    clk_slow <= 16'b0000000000000000;
    row_cnt <= 5'b00000;
    e_cnt <= 4'b1000;
  end

always @(posedge clk) clk_slow=clk_slow + 1'b1;  

always @(posedge clk_slow[10]) 
begin
  if(row_cnt > 5'b01111)
begin
row_cnt <= 5'b00000;
    e_cnt <= {row[2:0],row[3]};
  end
  col <= col_temp[row_cnt];  
  row_cnt <= row_cnt + 1'b1;
end

always @(posedge SCLK)
begin
  if(LAT)
  begin
    col_buffer <= {col_buffer[4094:0],DATA[0]};
  end
  else
  begin
    col_temp [0] <= col_buffer [4095:4032];
    col_temp [1] <= col_buffer [4031:3968];
    col_temp [2] <= col_buffer [3967:3904];
    col_temp [3] <= col_buffer [3903:3840];
    col_temp [4] <= col_buffer [3839:3776];
    col_temp [5] <= col_buffer [3775:3712];
    col_temp [6] <= col_buffer [3711:3648];
    col_temp [7] <= col_buffer [3647:3584];
    col_temp [8] <= col_buffer [3583:3520];
    col_temp [9] <= col_buffer [3519:3456];
    col_temp [10] <= col_buffer [3455:3392];
    col_temp [11] <= col_buffer [3391:3328];
    col_temp [12] <= col_buffer [3327:3264];
    col_temp [13] <= col_buffer [3263:3200];
    col_temp [14] <= col_buffer [3199:3136];
    col_temp [15] <= col_buffer [3135:3072];
    col_temp [16] <= col_buffer [3071:3008];
    col_temp [17] <= col_buffer [3007:2944];
    col_temp [18] <= col_buffer [2943:2880];
    col_temp [19] <= col_buffer [2879:2816];
    col_temp [20] <= col_buffer [2815:2752];
    col_temp [21] <= col_buffer [2751:2688];
    col_temp [22] <= col_buffer [2687:2624];
    col_temp [23] <= col_buffer [2623:2560];
    col_temp [24] <= col_buffer [2559:2496];
    col_temp [25] <= col_buffer [2495:2432];
    col_temp [26] <= col_buffer [2431:2368];
    col_temp [27] <= col_buffer [2367:2304];
    col_temp [28] <= col_buffer [2303:2240];
    col_temp [29] <= col_buffer [2239:2176];
    col_temp [30] <= col_buffer [2175:2112];
    col_temp [31] <= col_buffer [2111:2048];
    col_temp [32] <= col_buffer [2047:1984];
    col_temp [33] <= col_buffer [1983:1920];
    col_temp [34] <= col_buffer [1919:1856];
    col_temp [35] <= col_buffer [1855:1792];
    col_temp [36] <= col_buffer [1791:1728];
    col_temp [37] <= col_buffer [1727:1664];
    col_temp [38] <= col_buffer [1663:1600];
    col_temp [39] <= col_buffer [1599:1536];
    col_temp [40] <= col_buffer [1535:1472];
    col_temp [41] <= col_buffer [1471:1408];
    col_temp [42] <= col_buffer [1407:1344];
    col_temp [43] <= col_buffer [1343:1280];
    col_temp [44] <= col_buffer [1279:1216];
    col_temp [45] <= col_buffer [1215:1152];
    col_temp [46] <= col_buffer [1151:1088];
    col_temp [47] <= col_buffer [1087:1024];
    col_temp [48] <= col_buffer [1023:960];
    col_temp [49] <= col_buffer [959:896];
    col_temp [50] <= col_buffer [895:832];
    col_temp [51] <= col_buffer [831:768];
    col_temp [52] <= col_buffer [767:704];
    col_temp [53] <= col_buffer [703:640];
    col_temp [54] <= col_buffer [639:576];
    col_temp [55] <= col_buffer [575:512];
    col_temp [56] <= col_buffer [511:448];
    col_temp [57] <= col_buffer [447:384];
    col_temp [58] <= col_buffer [383:320];
    col_temp [59] <= col_buffer [319:256];
    col_temp [60] <= col_buffer [255:192];
    col_temp [61] <= col_buffer [191:128];
    col_temp [62] <= col_buffer [127:64];
    col_temp [63] <= col_buffer [63:0];
  end
end
endmodule