// Test of CBZ and B instruction.
// Requires:
// CBZ, B, & ADDI instructions
// Expected results:
// X0 = 1
// X1 = 0 (anything else indicates an error)
// X2 = 0 on a single-cycle CPU, 4 on pipelined CPUs (counts delay slots executed)
// X3 = 1 (signifies program end was reached)
// X4 = 16+8+4+2+1 = 31 (bit per properly executed branch)
// X5 = 0 (should never get incremented, means accelerated branches not working).

//ADDI: I-type, Reg[Rd] = Reg[Rn] + {'0, Imm12}
//OP         Imm12        Rn    Rd
//3322222222 221111111111 00000 00000
//1098765432 109876543210 98765 43210
//1001000100 Unsigned     0..31 0..31

//B: B-type, PC = PC + SignExtend({Imm26, 2'b00})
//OP     Imm26
//332222 22222211111111110000000000
//109876 54321098765432109876543210
//000101 2's Comp Imm26

//CBZ: CB-type, if (R[Rt] == 0) PC = PC + SignExtend({Imm19, 2'b00})
//OP       Imm19               Rt
//33222222 2222111111111100000 00000
//10987654 3210987654321098765 43210
//10110100 2's Comp Imm19      0..31

               // MAIN:
1001000100_000000000001_11111_00000 // ADDI X0, X31, #1     // Constant 1 register for testing
1001000100_000000000000_11111_00001 // ADDI X1, X31, #0     // Error register, should never be non-zero
1001000100_000000000000_11111_00010 // ADDI X2, X31, #0     // Delay slot counter.  Value depends on delay slots.
1001000100_000000000000_11111_00011 // ADDI X3, X31, #0     // Flag for when we get to the final result.
1001000100_000000000000_11111_00100 // ADDI X4, X31, #0     // Set each bit as you do a branch correctly.
1001000100_000000000000_11111_00101 // ADDI X5, X31, #0     // Set if branches have >1 delay slot.
000101_00000000000000000000001100   // B FORWARD_B          // 1st taken branch (+12*4)
1001000100_000000000001_00010_00010 // ADDI X2, X2, #1      // delay_slot++
1001000100_000000000001_00101_00101 // ADDI X5, X5, #1      // Should never reach here.
                                    // ERROR:               // Should never get here.
1001000100_000000000001_11111_00001 // ADDI X1, X31, #1     // Error = 1
000101_11111111111111111111111111   // B ERROR              // Loop forever (-1)
1001000100_000000000000_11111_11111 // ADDI X31, X31, #0    // NOOP
               // BACKWARD_B:       // Target for a backwards branch
1001000100_000000000010_00100_00100 // ADDI X4, X4, #2      // 2nd branch succeeded
10110100_0000000000000010100_11111  // CBZ X31, FORWARD_CBZ // 3rd taken branch (+20)
1001000100_000000000001_00010_00010 // ADDI X2, X2, #1      // delay_slot++
1001000100_000000000001_00101_00101 // ADDI X5, X5, 1       // Should never reach here
000101_11111111111111111111111001   // B ERROR              // Should never reach here (-7)
1001000100_000000000000_11111_11111 // ADDI X31, X31, 0     // NOP
               // FORWARD_B:
1001000100_000000000001_00100_00100 // ADDI X4, X4, 1       // 1st branch succeeded.
000101_11111111111111111111111001   // B BACKWARD_B         // 2nd taken branch (-7)
1001000100_000000000001_00010_00010 // ADDI X2, X2, 1       // delay_slot++
1001000100_000000000001_00101_00101 // ADDI X5, X5, 1       // Should never reach here
000101_11111111111111111111110011   // B ERROR              // Should never reach here (-13)
1001000100_000000000000_11111_11111 // ADDI X31, X31, 0     // NOOP
               // BACKWARD_CBZ:
1001000100_000000001000_00100_00100 // ADDI X4, X4, 8       // 4th branch succeeded.
10110100_0000000000000000110_00000  // CBZ X0, NOT_TAKEN    // X0 != 0, so no branch (+6)
1001000100_000000000000_11111_11111 // ADDI X31, X31, 0     // NOOP
1001000100_000000010000_00100_00100 // ADDI X4, X4, 16      // Successfully didn't branch.
1001000100_000000000001_11111_00011 // ADDI X3, X31, 1      // Flag for finishing.
               // HALT:
000101_00000000000000000000000000   // B HALT               // Loop forever (0)
1001000100_000000000000_11111_11111 // ADDI X31, X31, 0     // NOOP
               // NOT_TAKEN:
000101_11111111111111111111101010   // B ERROR              // Should never reach here (-22)
1001000100_000000000000_11111_11111 // ADDI X31, X31, 0     // NOOP
               // FORWARD_CBZ:
1001000100_000000000100_00100_00100 // ADDI X4, X4, 4       // 3rd branch succeeded.
10110100_1111111111111110110_11111  // CBZ X31, BACKWARD_CBZ   // 4th taken branch (-10)
1001000100_000000000001_00010_00010 // ADDI X2, X2, 1       // delay_slot++
1001000100_000000000001_00101_00101 // ADDI X5, X5, 1       // Should never reach here.
000101_11111111111111111111100100   // B ERROR              // Should never reach here (-28)
1001000100_000000000000_11111_11111 // ADDI X31, X31, 0     // NOOP