-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathriscv.tlv
279 lines (226 loc) · 12.6 KB
/
riscv.tlv
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
\m4_TLV_version 1d: tl-x.org
\SV
// Template code can be found in: https://github.com/stevehoover/RISC-V_MYTH_Workshop
m4_include_lib(['https://raw.githubusercontent.com/BalaDhinesh/RISC-V_MYTH_Workshop/master/tlv_lib/risc-v_shell_lib.tlv'])
\SV
m4_makerchip_module // (Expanded in Nav-TLV pane.)
\TLV
// /====================\
// | Sum 1 to 9 Program |
// \====================/
//
// Add 1,2,3,...,9 (in that order).
//
// Regs:
// r10 (a0): In: 0, Out: final sum
// r12 (a2): 10
// r13 (a3): 1..10
// r14 (a4): Sum
//
// External to function:
m4_asm(ADD, r10, r0, r0) // Initialize r10 (a0) to 0.
// Function:
m4_asm(ADD, r14, r10, r0) // Initialize sum register a4 with 0x0
m4_asm(ADDI, r12, r10, 1010) // Store count of 10 in register a2.
m4_asm(ADD, r13, r10, r0) // Initialize intermediate sum register a3 with 0
// Loop:
m4_asm(ADD, r14, r13, r14) // Incremental addition
m4_asm(ADDI, r13, r13, 1) // Increment intermediate register by 1
m4_asm(BLT, r13, r12, 1111111111000) // If a3 is less than a2, branch to label named <loop>
m4_asm(ADD, r10, r14, r0) // Store final result to register a0 so that it can be read by main program
m4_asm(SW, r0, r10, 10000) // Store r10 result in dmem
m4_asm(LW, r17, r0, 10000) // Load contents of dmem to r17
m4_asm(JAL, r7, 00000000000000000000) // Done. Jump to itself (infinite loop). (Up to 20-bit signed immediate plus implicit 0 bit (unlike JALR) provides byte address; last immediate bit should also be 0)
m4_define_hier(['M4_IMEM'], M4_NUM_INSTRS)
|cpu
@0
$reset = *reset;
//PC fetch - branch, jumps and loads introduce 2 cycle bubbles in this pipeline
$pc[31:0] = >>1$reset ? '0 : (>>3$valid_taken_br ? >>3$br_tgt_pc :
>>3$valid_load ? >>3$inc_pc[31:0] :
>>3$jal_valid ? >>3$br_tgt_pc :
>>3$jalr_valid ? >>3$jalr_tgt_pc :
(>>1$inc_pc[31:0]));
// Access instruction memory using PC
$imem_rd_en = ~ $reset;
$imem_rd_addr[M4_IMEM_INDEX_CNT-1:0] = $pc[M4_IMEM_INDEX_CNT+1:2];
@1
//Getting instruction from IMem
$instr[31:0] = $imem_rd_data[31:0];
//Increment PC
$inc_pc[31:0] = $pc[31:0] + 32'h4;
//Decoding I,R,S,U,B,J type of instructions based on opcode [6:0]
//Only [6:2] is used here because this implementation is for RV64I which does not use [1:0]
$is_i_instr = $instr[6:2] ==? 5'b0000x ||
$instr[6:2] ==? 5'b001x0 ||
$instr[6:2] == 5'b11001;
$is_r_instr = $instr[6:2] == 5'b01011 ||
$instr[6:2] ==? 5'b011x0 ||
$instr[6:2] == 5'b10100;
$is_s_instr = $instr[6:2] ==? 5'b0100x;
$is_u_instr = $instr[6:2] ==? 5'b0x101;
$is_b_instr = $instr[6:2] == 5'b11000;
$is_j_instr = $instr[6:2] == 5'b11011;
//Immediate value decode
$imm[31:0] = $is_i_instr ? { {21{$instr[31]}} , $instr[30:20]} :
$is_s_instr ? { {21{$instr[31]}} , $instr[30:25] , $instr[11:8] , $instr[7]} :
$is_b_instr ? { {20{$instr[31]}} , $instr[7] , $instr[30:25] , $instr[11:8] , 1'b0} :
$is_u_instr ? { $instr[31] , $instr[30:12] , { 12{1'b0}} } :
$is_j_instr ? { {12{$instr[31]}} , $instr[19:12] , $instr[20] , $instr[30:21] , 1'b0} :
>>1$imm[31:0];
//Generate valid signals for each instruction fields
$rs1_or_funct3_valid = $is_r_instr || $is_i_instr || $is_s_instr || $is_b_instr;
$rs2_valid = $is_r_instr || $is_s_instr || $is_b_instr;
$rd_valid = $is_r_instr || $is_i_instr || $is_u_instr || $is_j_instr;
$funct7_valid = $is_r_instr;
//Decode other fields of instruction - source and destination registers, funct, opcode
?$rs1_or_funct3_valid
$rs1[4:0] = $instr[19:15];
$funct3[2:0] = $instr[14:12];
?$rs2_valid
$rs2[4:0] = $instr[24:20];
?$rd_valid
$rd[4:0] = $instr[11:7];
?$funct7_valid
$funct7[6:0] = $instr[31:25];
$opcode[6:0] = $instr[6:0];
//Decode instruction in subset of base instruction set based on RISC-V 32I
$dec_bits[10:0] = {$funct7[5],$funct3,$opcode};
//Branch instructions
$is_beq = $dec_bits ==? 11'bx_000_1100011;
$is_bne = $dec_bits ==? 11'bx_001_1100011;
$is_blt = $dec_bits ==? 11'bx_100_1100011;
$is_bge = $dec_bits ==? 11'bx_101_1100011;
$is_bltu = $dec_bits ==? 11'bx_110_1100011;
$is_bgeu = $dec_bits ==? 11'bx_111_1100011;
//Jump instructions
$is_auipc = $dec_bits ==? 11'bx_xxx_0010111;
$is_jal = $dec_bits ==? 11'bx_xxx_1101111;
$is_jalr = $dec_bits ==? 11'bx_000_1100111;
//Arithmetic instructions
$is_addi = $dec_bits ==? 11'bx_000_0010011;
$is_add = $dec_bits == 11'b0_000_0110011;
$is_lui = $dec_bits ==? 11'bx_xxx_0110111;
$is_slti = $dec_bits ==? 11'bx_010_0010011;
$is_sltiu = $dec_bits ==? 11'bx_011_0010011;
$is_xori = $dec_bits ==? 11'bx_100_0010011;
$is_ori = $dec_bits ==? 11'bx_110_0010011;
$is_andi = $dec_bits ==? 11'bx_111_0010011;
$is_slli = $dec_bits ==? 11'b0_001_0010011;
$is_srli = $dec_bits ==? 11'b0_101_0010011;
$is_srai = $dec_bits ==? 11'b1_101_0010011;
$is_sub = $dec_bits ==? 11'b1_000_0110011;
$is_sll = $dec_bits ==? 11'b0_001_0110011;
$is_slt = $dec_bits ==? 11'b0_010_0110011;
$is_sltu = $dec_bits ==? 11'b0_011_0110011;
$is_xor = $dec_bits ==? 11'b0_100_0110011;
$is_srl = $dec_bits ==? 11'b0_101_0110011;
$is_sra = $dec_bits ==? 11'b1_101_0110011;
$is_or = $dec_bits ==? 11'b0_110_0110011;
$is_and = $dec_bits ==? 11'b0_111_0110011;
//Store instructions
$is_sb = $dec_bits ==? 11'bx_000_0100011;
$is_sh = $dec_bits ==? 11'bx_001_0100011;
$is_sw = $dec_bits ==? 11'bx_010_0100011;
//Load instructions - support only 4 byte load
$is_load = $dec_bits ==? 11'bx_xxx_0000011;
$is_jump = $is_jal || $is_jalr;
@2
//Get Source register values from reg file
$rf_rd_en1 = $rs1_or_funct3_valid;
$rf_rd_en2 = $rs2_valid;
$rf_rd_index1[4:0] = $rs1[4:0];
$rf_rd_index2[4:0] = $rs2[4:0];
//Register file bypass logic - data forwarding from ALU to resolve RAW dependence
$src1_value[31:0] = $rs1_bypass ? >>1$result[31:0] : $rf_rd_data1[31:0];
$src2_value[31:0] = $rs2_bypass ? >>1$result[31:0] : $rf_rd_data2[31:0];
//Branch target PC computation for branches and JAL
$br_tgt_pc[31:0] = $imm[31:0] + $pc[31:0];
//RAW dependence check for ALU data forwarding
//If previous instruction was writing to reg file, and current instruction is reading from same register
$rs1_bypass = >>1$rf_wr_en && (>>1$rd == $rs1);
$rs2_bypass = >>1$rf_wr_en && (>>1$rd == $rs2);
@3
//ALU
$result[31:0] = $is_addi ? $src1_value + $imm :
$is_add ? $src1_value + $src2_value :
$is_andi ? $src1_value & $imm :
$is_ori ? $src1_value | $imm :
$is_xori ? $src1_value ^ $imm :
$is_slli ? $src1_value << $imm[5:0]:
$is_srli ? $src1_value >> $imm[5:0]:
$is_and ? $src1_value & $src2_value:
$is_or ? $src1_value | $src2_value:
$is_xor ? $src1_value ^ $src2_value:
$is_sub ? $src1_value - $src2_value:
$is_sll ? $src1_value << $src2_value:
$is_srl ? $src1_value >> $src2_value:
$is_sltu ? $sltu_rslt[31:0]:
$is_sltiu ? $sltiu_rslt[31:0]:
$is_lui ? {$imm[31:12], 12'b0}:
$is_auipc ? $pc + $imm:
$is_jal ? $pc + 4:
$is_jalr ? $pc + 4:
$is_srai ? ({ {32{$src1_value[31]}} , $src1_value} >> $imm[4:0]) :
$is_slt ? (($src1_value[31] == $src2_value[31]) ? $sltu_rslt : {31'b0, $src1_value[31]}):
$is_slti ? (($src1_value[31] == $imm[31]) ? $sltiu_rslt : {31'b0, $src1_value[31]}) :
$is_sra ? ({ {32{$src1_value[31]}}, $src1_value} >> $src2_value[4:0]) :
$is_load ? $src1_value + $imm :
$is_s_instr ? $src1_value + $imm :
32'bx;
$sltu_rslt[31:0] = $src1_value < $src2_value;
$sltiu_rslt[31:0] = $src1_value < $imm;
//Jump instruction target PC computation
$jalr_tgt_pc[31:0] = $imm[31:0] + $src1_value[31:0];
//Branch resolution
$taken_br = $is_beq ? ($src1_value == $src2_value) :
$is_bne ? ($src1_value != $src2_value) :
$is_blt ? (($src1_value < $src2_value) ^ ($src1_value[31] != $src2_value[31])) :
$is_bge ? (($src1_value >= $src2_value) ^ ($src1_value[31] != $src2_value[31])) :
$is_bltu ? ($src1_value < $src2_value) :
$is_bgeu ? ($src1_value >= $src2_value) :
1'b0;
//Current instruction is valid if one of the previous 2 instructions were not (taken_branch or load or jump)
$valid = ~(>>1$valid_taken_br || >>2$valid_taken_br || >>1$is_load || >>2$is_load || >>2$jump_valid || >>1$jump_valid);
//Current instruction is valid & is a taken branch
$valid_taken_br = $valid && $taken_br;
//Current instruction is valid & is a load
$valid_load = $valid && $is_load;
//Current instruction is valid & is jump
$jump_valid = $valid && $is_jump;
$jal_valid = $valid && $is_jal;
$jalr_valid = $valid && $is_jalr;
//Destination register update - ALU result or load result depending on instruction
$rf_wr_en = (($rd != '0) && $rd_valid && $valid) || >>2$valid_load;
$rf_wr_index[4:0] = $valid ? $rd[4:0] : >>2$rd[4:0];
$rf_wr_data[31:0] = $valid ? $result[31:0] : >>2$ld_data[31:0];
@4
//Data memory access for load, store
$dmem_addr[3:0] = $result[5:2];
$dmem_wr_en = $valid && $is_s_instr;
$dmem_wr_data[31:0] = $src2_value[31:0];
$dmem_rd_en = $valid_load;
//Write back data read from load instruction to register
$ld_data[31:0] = $dmem_rd_data[31:0];
// Note: Because of the magic we are using for visualisation, if visualisation is enabled below,
// be sure to avoid having unassigned signals (which you might be using for random inputs)
// other than those specifically expected in the labs. You'll get strange errors for these.
// Assert these to end simulation (before Makerchip cycle limit).
//Checks if sum of numbers from 1 to 9 is obtained in reg[17] and runs 10 cycles extra after this is met
*passed = |cpu/xreg[17]>>10$value == (1+2+3+4+5+6+7+8+9);
//Run for 200 cycles without any checks
//*passed = *cyc_cnt > 200;
*failed = 1'b0;
// Macro instantiations for:
// o instruction memory
// o register file
// o data memory
// o CPU visualization
|cpu
m4+imem(@1) // Args: (read stage)
m4+rf(@2, @3) // Args: (read stage, write stage) - if equal, no register bypass is required
m4+dmem(@4) // Args: (read/write stage)
m4+cpu_viz(@4) // For visualisation, argument should be at least equal to the last stage of CPU logic
// @4 would work for all labs
\SV
endmodule