CPU设计实战：Loongarch版 lab6--20条指令单周期CPU_cpu设计实战loongarch版

        本文章是为了记录学习Loongarch参加龙芯杯，所有实验均来自LoongarchCPU设计实验

        debug到一半才想起来写个博客，就不写过程了，下个lab再写过程。

        这个debug卡我时间最长的就是通用寄存器的写使能信号，当时一直没找到，甚至把golden—trace生成了一遍又一遍，对照test，检查了各种，卡了很长时间，我都以为是我之前哪一步搞错了，或者环境什么的，但是一步步做下来并没有，并且“机器永远是对的”让我终于查到了错。

        其他的bug就还好，如果认真跟着实验手册走，按逻辑检查并且查龙芯架构参考手册就能马上找出来，，上面的每一句话都很重要。

        下面是两个模块的代码，运行已通过仿真验证。

        mycpu_top 

module mycpu_top(
    input  wire        clk,
    input  wire        resetn,
    // inst sram interface
    output wire        inst_sram_we,
    output wire [31:0] inst_sram_addr,
    output wire [31:0] inst_sram_wdata,
    input  wire [31:0] inst_sram_rdata,
    // data sram interface
    output wire        data_sram_we,
    output wire [31:0] data_sram_addr,
    output wire [31:0] data_sram_wdata,
    input  wire [31:0] data_sram_rdata,
    // trace debug interface
    output wire [31:0] debug_wb_pc,
    output wire [ 3:0] debug_wb_rf_we,
    output wire [ 4:0] debug_wb_rf_wnum,
    output wire [31:0] debug_wb_rf_wdata
);
reg         reset;
always @(posedge clk) reset <= ~resetn;
 
reg         valid;
always @(posedge clk) begin
    if (reset) begin
        valid <= 1'b0;
    end
    else begin
        valid <= 1'b1;
    end
end
 
wire [31:0] seq_pc;
wire [31:0] nextpc;
wire        br_taken;
wire [31:0] br_target;
wire [31:0] inst;
reg  [31:0] pc;
 
wire [11:0] alu_op;
wire        load_op;
wire        src1_is_pc;
wire        src2_is_imm;
wire        res_from_mem;
wire        dst_is_r1;
wire        gr_we;
wire        mem_we;
wire        src_reg_is_rd;
wire [4: 0] dest;
wire [31:0] rj_value;
wire [31:0] rkd_value;
wire [31:0] imm;
wire [31:0] br_offs;
wire [31:0] jirl_offs;
 
wire [ 5:0] op_31_26;
wire [ 3:0] op_25_22;
wire [ 1:0] op_21_20;
wire [ 4:0] op_19_15;
wire [ 4:0] rd;
wire [ 4:0] rj;
wire [ 4:0] rk;
wire [11:0] i12;
wire [19:0] i20;
wire [15:0] i16;
wire [25:0] i26;
 
wire [63:0] op_31_26_d;
wire [15:0] op_25_22_d;
wire [ 3:0] op_21_20_d;
wire [31:0] op_19_15_d;
 
wire        inst_add_w;
wire        inst_sub_w;
wire        inst_slt;
wire        inst_sltu;
wire        inst_nor;
wire        inst_and;
wire        inst_or;
wire        inst_xor;
wire        inst_slli_w;
wire        inst_srli_w;
wire        inst_srai_w;
wire        inst_addi_w;
wire        inst_ld_w;
wire        inst_st_w;
wire        inst_jirl;
wire        inst_b;
wire        inst_bl;
wire        inst_beq;
wire        inst_bne;
wire        inst_lu12i_w;
 
wire        need_ui5;
wire        need_si12;
wire        need_si16;
wire        need_si20;
wire        need_si26;
wire        src2_is_4;
 
wire [ 4:0] rf_raddr1;
wire [31:0] rf_rdata1;
wire [ 4:0] rf_raddr2;
wire [31:0] rf_rdata2;
wire        rf_we   ;
wire [ 4:0] rf_waddr;
wire [31:0] rf_wdata;
 
wire [31:0] alu_src1   ;
wire [31:0] alu_src2   ;
wire [31:0] alu_result ;
 
wire [31:0] mem_result;
wire [31:0] final_result;
assign seq_pc       = pc + 3'h4;
assign nextpc       = br_taken ? br_target : seq_pc;
always @(posedge clk) begin
    if (reset) begin
        pc <= 32'h1bfffffc;     //trick: to make nextpc be 0x1c000000 during reset 
    end
    else begin
        pc <= nextpc;
    end
end
 
assign inst_sram_we    = 1'b0;
assign inst_sram_addr  = pc;
assign inst_sram_wdata = 32'b0;
assign inst            = inst_sram_rdata;
 
assign op_31_26  = inst[31:26];
assign op_25_22  = inst[25:22];
assign op_21_20  = inst[21:20];
assign op_19_15  = inst[19:15];
 
assign rd   = inst[ 4: 0];
assign rj   = inst[ 9: 5];
assign rk   = inst[14:10];
 
assign i12  = inst[21:10];
assign i20  = inst[24: 5];
assign i16  = inst[25:10];
assign i26  = {inst[ 9: 0], inst[25:10]};
 
decoder_6_64 u_dec0(.in(op_31_26 ), .out(op_31_26_d ));
decoder_4_16 u_dec1(.in(op_25_22 ), .out(op_25_22_d ));
decoder_2_4  u_dec2(.in(op_21_20 ), .out(op_21_20_d ));
decoder_5_32 u_dec3(.in(op_19_15 ), .out(op_19_15_d ));
 
assign inst_add_w  = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h00];
assign inst_sub_w  = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h02];
assign inst_slt    = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h04];
assign inst_sltu   = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h05];
assign inst_nor    = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h08];
assign inst_and    = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h09];
assign inst_or     = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h0a];
assign inst_xor    = op_31_26_d[6'h00] & op_25_22_d[4'h0] & op_21_20_d[2'h1] & op_19_15_d[5'h0b];
assign inst_slli_w = op_31_26_d[6'h00] & op_25_22_d[4'h1] & op_21_20_d[2'h0] & op_19_15_d[5'h01];
assign inst_srli_w = op_31_26_d[6'h00] & op_25_22_d[4'h1] & op_21_20_d[2'h0] & op_19_15_d[5'h09];
assign inst_srai_w = op_31_26_d[6'h00] & op_25_22_d[4'h1] & op_21_20_d[2'h0] & op_19_15_d[5'h11];
assign inst_addi_w = op_31_26_d[6'h00] & op_25_22_d[4'ha];
assign inst_ld_w   = op_31_26_d[6'h0a] & op_25_22_d[4'h2];
assign inst_st_w   = op_31_26_d[6'h0a] & op_25_22_d[4'h6];
assign inst_jirl   = op_31_26_d[6'h13];
assign inst_b      = op_31_26_d[6'h14];
assign inst_bl     = op_31_26_d[6'h15];
assign inst_beq    = op_31_26_d[6'h16];
assign inst_bne    = op_31_26_d[6'h17];
assign inst_lu12i_w= op_31_26_d[6'h05] & ~inst[25];
 
assign alu_op[ 0] = inst_add_w | inst_addi_w | inst_ld_w | inst_st_w
                    | inst_jirl | inst_bl;
assign alu_op[ 1] = inst_sub_w;
assign alu_op[ 2] = inst_slt;
assign alu_op[ 3] = inst_sltu;
assign alu_op[ 4] = inst_and;
assign alu_op[ 5] = inst_nor;
assign alu_op[ 6] = inst_or;
assign alu_op[ 7] = inst_xor;
assign alu_op[ 8] = inst_slli_w;
assign alu_op[ 9] = inst_srli_w;
assign alu_op[10] = inst_srai_w;
assign alu_op[11] = inst_lu12i_w;
 
assign need_ui5   =  inst_slli_w | inst_srli_w | inst_srai_w;
assign need_si12  =  inst_addi_w | inst_ld_w | inst_st_w;
assign need_si16  =  inst_jirl | inst_beq | inst_bne;
assign need_si20  =  inst_lu12i_w;
assign need_si26  =  inst_b | inst_bl;
assign src2_is_4  =  inst_jirl | inst_bl;
 
assign imm = src2_is_4 ? 32'h4                      :
             need_si20 ? {i20[19:0], 12'b0}         :
/*need_ui5 || need_si12*/{{20{i12[11]}}, i12[11:0]} ;
 
assign br_offs = need_si26 ? {{ 4{i26[25]}}, i26[25:0], 2'b0} :
                             {{14{i16[15]}}, i16[15:0], 2'b0} ;
 
assign jirl_offs = {{14{i16[15]}}, i16[15:0], 2'b0};
assign src_reg_is_rd = inst_beq | inst_bne | inst_st_w;
assign src1_is_pc    = inst_jirl | inst_bl;
assign src2_is_imm   = inst_slli_w |
                       inst_srli_w |
                       inst_srai_w |
                       inst_addi_w |
                       inst_ld_w   |
                       inst_st_w   |
                       inst_lu12i_w|
                       inst_jirl   |
                       inst_bl     ;
assign res_from_mem  = inst_ld_w;
assign dst_is_r1     = inst_bl;
assign gr_we         = ~inst_st_w & ~inst_beq & ~inst_bne & ~inst_b;
assign mem_we        = inst_st_w;
assign dest          = dst_is_r1 ? 5'd1 : rd;
 
assign rf_raddr1 = rj;
assign rf_raddr2 = src_reg_is_rd ? rd :rk;
regfile u_regfile(
    .clk    (clk      ),
    .raddr1 (rf_raddr1),
    .rdata1 (rf_rdata1),
    .raddr2 (rf_raddr2),
    .rdata2 (rf_rdata2),
    .we     (rf_we    ),
    .waddr  (rf_waddr ),
    .wdata  (rf_wdata )
    );
 
assign rj_value  = rf_rdata1;
assign rkd_value = rf_rdata2;
 
assign rj_eq_rd = (rj_value == rkd_value);
assign br_taken = (   inst_beq  &&  rj_eq_rd
                   || inst_bne  && !rj_eq_rd
                   || inst_jirl
                   || inst_bl
                   || inst_b
                  ) && valid;
assign br_target = (inst_beq || inst_bne || inst_bl || inst_b) ? (pc + br_offs) :
                                                   /*inst_jirl*/ (rj_value + jirl_offs);
 
assign alu_src1 = src1_is_pc  ? pc[31:0] : rj_value;
assign alu_src2 = src2_is_imm ? imm : (inst_bl ? 32'd4 : rkd_value);
alu u_alu(
    .alu_op     (alu_op    ),
    .alu_src1   (alu_src1  ),
    .alu_src2   (alu_src2  ),
    .alu_result (alu_result)
    );
assign data_sram_we    = mem_we && valid;
assign data_sram_addr  = alu_result;
assign data_sram_wdata = rkd_value;
assign mem_result   = data_sram_rdata;
assign final_result = res_from_mem ? mem_result : alu_result;
assign rf_we    = gr_we && valid;
assign rf_waddr = dest;
assign rf_wdata = final_result;
// debug info generate
assign debug_wb_pc       = rf_we ? pc : debug_wb_pc;
assign debug_wb_rf_we   = {4{rf_we}};
assign debug_wb_rf_wnum  = rf_we ? dest : debug_wb_rf_wnum;
assign debug_wb_rf_wdata = rf_we ? final_result : debug_wb_rf_wdata;
endmodule

        alu

module alu(
  input  wire [11:0] alu_op,
  input  wire [31:0] alu_src1,
  input  wire [31:0] alu_src2,
  output wire [31:0] alu_result
);
 
wire op_add;   //add operation
wire op_sub;   //sub operation
wire op_slt;   //signed compared and set less than
wire op_sltu;  //unsigned compared and set less than
wire op_and;   //bitwise and
wire op_nor;   //bitwise nor
wire op_or;    //bitwise or
wire op_xor;   //bitwise xor
wire op_sll;   //logic left shift
wire op_srl;   //logic right shift
wire op_sra;   //arithmetic right shift
wire op_lui;   //Load Upper Immediate
 
// control code decomposition
assign op_add  = alu_op[ 0];
assign op_sub  = alu_op[ 1];
assign op_slt  = alu_op[ 2];
assign op_sltu = alu_op[ 3];
assign op_and  = alu_op[ 4];
assign op_nor  = alu_op[ 5];
assign op_or   = alu_op[ 6];
assign op_xor  = alu_op[ 7];
assign op_sll  = alu_op[ 8];
assign op_srl  = alu_op[ 9];
assign op_sra  = alu_op[10];
assign op_lui  = alu_op[11];
 
wire [31:0] add_sub_result;
wire [31:0] slt_result;
wire [31:0] sltu_result;
wire [31:0] and_result;
wire [31:0] nor_result;
wire [31:0] or_result;
wire [31:0] xor_result;
wire [31:0] lui_result;
wire [31:0] sll_result;
wire [63:0] sr64_result;
wire [31:0] sr_result;
 
 
// 32-bit adder
wire [31:0] adder_a;
wire [31:0] adder_b;
wire        adder_cin;
wire [31:0] adder_result;
wire        adder_cout;
 
assign adder_a   = alu_src1;
assign adder_b   = (op_sub | op_slt | op_sltu) ? ~alu_src2 : alu_src2;  //src1 - src2 rj-rk
assign adder_cin = (op_sub | op_slt | op_sltu) ? 1'b1      : 1'b0;
assign {adder_cout, adder_result} = adder_a + adder_b + adder_cin;
 
// ADD, SUB result
assign add_sub_result = adder_result;
 
// SLT result
assign slt_result[31:1] = 31'b0;   //rj < rk 1
assign slt_result[0]    = (alu_src1[31] & ~alu_src2[31])
                        | ((alu_src1[31] ~^ alu_src2[31]) & adder_result[31]);
// SLTU result
assign sltu_result[31:1] = 31'b0;
assign sltu_result[0]    = ~adder_cout;
 
// bitwise operation
assign and_result = alu_src1 & alu_src2;
assign or_result  = alu_src1 | alu_src2;
assign nor_result = ~or_result;
assign xor_result = alu_src1 ^ alu_src2;
assign lui_result = alu_src2;
 
// SLL result
assign sll_result = alu_src1 << alu_src2[4:0];   //rj << i5
 
// SRL, SRA result
assign sr64_result = {{32{op_sra & alu_src1[31]}}, alu_src1[31:0]} >> alu_src2[4:0]; //rj >> i5
 
assign sr_result   = sr64_result[31:0];
 
// final result mux
assign alu_result = ({32{op_add|op_sub}} & add_sub_result)
                  | ({32{op_slt       }} & slt_result)
                  | ({32{op_sltu      }} & sltu_result)
                  | ({32{op_and       }} & and_result)
                  | ({32{op_nor       }} & nor_result)
                  | ({32{op_or        }} & or_result)
                  | ({32{op_xor       }} & xor_result)
                  | ({32{op_lui       }} & lui_result)
                  | ({32{op_sll       }} & sll_result)
                  | ({32{op_srl|op_sra}} & sr_result);
 
endmodule