# Matrix Multiplication in RISC-V without loops
.data
A:      .word 2, 1, 3
        .word 3, 4, 1
        .word 5, 2, 3

B:      .word 1, 2, 0
        .word 4, 1, 2
        .word 3, 2, 1

C:      .space 36     # 9 elements * 4 bytes = 36 bytes

.text
.globl main
main:
    la t0, A       # t0 = base of A
    la t1, B       # t1 = base of B
    la t2, C       # t2 = base of C

    # Calculate C[0] = A[0]*B[0] + A[1]*B[3] + A[2]*B[6]
    lw t3, 0(t0)    # A[0]
    lw t4, 0(t1)    # B[0]
    mul t5, t3, t4

    lw t3, 4(t0)    # A[1]
    lw t4, 16(t1)   # B[3]
    mul t6, t3, t4
    add t5, t5, t6

    lw t3, 8(t0)    # A[2]
    lw t4, 32(t1)   # B[6]
    mul t6, t3, t4
    add t5, t5, t6

    sw t5, 0(t2)    # Store C[0]

    # Calculate C[1] = A[0]*B[1] + A[1]*B[4] + A[2]*B[7]
    lw t3, 0(t0)    # A[0]
    lw t4, 4(t1)    # B[1]
    mul t5, t3, t4

    lw t3, 4(t0)    # A[1]
    lw t4, 20(t1)   # B[4]
    mul t6, t3, t4
    add t5, t5, t6

    lw t3, 8(t0)    # A[2]
    lw t4, 28(t1)   # B[7]
    mul t6, t3, t4
    add t5, t5, t6

    sw t5, 4(t2)    # Store C[1]

    # Calculate C[2] = A[0]*B[2] + A[1]*B[5] + A[2]*B[8]
    lw t3, 0(t0)    # A[0]
    lw t4, 8(t1)    # B[2]
    mul t5, t3, t4

    lw t3, 4(t0)    # A[1]
    lw t4, 24(t1)   # B[5]
    mul t6, t3, t4
    add t5, t5, t6

    lw t3, 8(t0)    # A[2]
    lw t4, 36(t1)   # B[8]
    mul t6, t3, t4
    add t5, t5, t6

    sw t5, 8(t2)    # Store C[2]

    # Calculate C[3] = A[3]*B[0] + A[4]*B[3] + A[5]*B[6]
    lw t3, 12(t0)   # A[3]
    lw t4, 0(t1)    # B[0]
    mul t5, t3, t4

    lw t3, 16(t0)   # A[4]
    lw t4, 16(t1)   # B[3]
    mul t6, t3, t4
    add t5, t5, t6

    lw t3, 20(t0)   # A[5]
    lw t4, 32(t1)   # B[6]
    mul t6, t3, t4
    add t5, t5, t6

    sw t5, 12(t2)   # Store C[3]

    # Calculate C[4] = A[3]*B[1] + A[4]*B[4] + A[5]*B[7]
    lw t3, 12(t0)   # A[3]
    lw t4, 4(t1)    # B[1]
    mul t5, t3, t4

    lw t3, 16(t0)   # A[4]
    lw t4, 20(t1)   # B[4]
    mul t6, t3, t4
    add t5, t5, t6

    lw t3, 20(t0)   # A[5]
    lw t4, 28(t1)   # B[7]
    mul t6, t3, t4
    add t5, t5, t6

    sw t5, 16(t2)   # Store C[4]

    # Calculate C[5] = A[3]*B[2] + A[4]*B[5] + A[5]*B[8*