# Arithmetic (R and I type)
add   a0, a1, a2      # a0 = a1 + a2
sub   a0, a1, a2      # a0 = a1 - a2
addi  a0, a1, 42      # a0 = a1 + 42 (immediate)
mul   a0, a1, a2      # a0 = a1 * a2 (M extension)
div   a0, a1, a2      # signed divide (M extension)
rem   a0, a1, a2      # remainder (M extension)

# Logical
and   a0, a1, a2      # bitwise AND
or    a0, a1, a2      # bitwise OR
xor   a0, a1, a2      # bitwise XOR
sll   a0, a1, a2      # shift left logical
srl   a0, a1, a2      # shift right logical (unsigned)
sra   a0, a1, a2      # shift right arithmetic (signed)

# Load / store
lw    a0, 0(sp)       # load word (32-bit)
ld    a0, 0(sp)       # load doubleword (64-bit, RV64)
lh    a0, 4(sp)       # load halfword (sign-extended)
lbu   a0, 8(sp)       # load byte (zero-extended)
sw    a0, 0(sp)       # store word
sd    a0, 0(sp)       # store doubleword (RV64)

# Branches (compare and branch)
beq   a0, a1, label   # branch if equal
bne   a0, a1, label   # branch if not equal
blt   a0, a1, label   # branch if less than (signed)
bltu  a0, a1, label   # branch if less than (unsigned)
bge   a0, a1, label   # branch if ≥ (signed)

# Jumps
j     label           # unconditional jump (pseudoinstruction: jal x0, label)
jal   ra, func        # jump and link (call)
jalr  zero, ra, 0     # jump to ra (return: pseudoinstruction: ret)

.section .text
.global add_numbers
# int add_numbers(int a, int b);  — a in a0, b in a1, return in a0
add_numbers:
    add   a0, a0, a1   # result = a + b
    ret                # return (jalr zero, ra, 0)

.global factorial
# long factorial(int n);  — n in a0
factorial:
    addi  sp, sp, -16      # allocate stack frame
    sd    ra, 8(sp)        # save return address (RV64)
    sd    s0, 0(sp)        # save s0 (callee-saved)

    mv    s0, a0           # s0 = n
    li    a0, 1            # default return 1
    blez  s0, .done        # if n <= 0, return 1

    addi  a0, s0, -1      # a0 = n - 1
    call  factorial        # recursive call: factorial(n-1)
    mul   a0, a0, s0       # a0 = result * n

.done:
    ld    ra, 8(sp)        # restore ra
    ld    s0, 0(sp)        # restore s0
    addi  sp, sp, 16       # deallocate
    ret

// Read a CSR register (e.g., cycle counter)
static inline uint64_t read_cycle(void) {
    uint64_t val;
    asm volatile ("rdcycle %0" : "=r"(val));
    return val;
}

// Atomic swap
static inline int atomic_swap(int *ptr, int new_val) {
    int old;
    asm volatile (
        "amoswap.w.aqrl %0, %2, (%1)"
        : "=r"(old)
        : "r"(ptr), "r"(new_val)
        : "memory"
    );
    return old;
}

// Memory fence
static inline void memory_fence(void) {
    asm volatile ("fence rw, rw" ::: "memory");
}

// CSR read/write
#define csr_read(csr) ({                    \
    uint64_t _v;                            \
    asm volatile ("csrr %0, " #csr : "=r"(_v)); \
    _v;                                     \
})

uint64_t mstatus = csr_read(mstatus);

# Enable C extension in GCC
riscv64-linux-gnu-gcc -march=rv64gc prog.c -o prog

# Check if compressed instructions were generated
riscv64-linux-gnu-objdump -d prog | grep "c\."
# c.addi, c.ld, c.sw, c.j, etc.

# Disable compressed (for debugging or targets without C)
riscv64-linux-gnu-gcc -march=rv64g prog.c -o prog

# Install QEMU RISC-V
apt-get install qemu-user qemu-system-riscv64

# User-mode emulation (run RV64 binary on x86 host)
qemu-riscv64 ./prog

# System emulation (full bare-metal VM)
qemu-system-riscv64 \
  -machine virt \
  -nographic \
  -kernel firmware.elf \
  -gdb tcp::1234 \
  -S     # start paused

# GDB remote session
riscv64-linux-gnu-gdb prog
(gdb) target remote :1234
(gdb) load
(gdb) break main
(gdb) continue