Skip to content

Assembly Cheatsheet

Low-level x86-64 assembly language (Intel/NASM syntax) for systems, performance, and bare-metal programming.

01

Registers & Data Movement

Registers Overview

x86-64 has 16 general-purpose 64-bit registers. Writing to a 32-bit sub-register (e.g. eax) zero-extends the upper 32 bits of the full register; writing to 16/8-bit sub-registers leaves the upper bits unchanged.

assembly
; General-purpose 64-bit registers (x86-64)
; rax, rbx, rcx, rdx         — main accumulators / scratch
; rsi, rdi                    — source/destination index (string ops)
; rbp, rsp                    — base pointer / stack pointer
; r8  .. r15                  — extended registers
; 32-bit: eax, 32-bit: ecx, 16-bit: ax, 8-bit: al/ah

mov rax, 42        ; load immediate into 64-bit register
mov eax, 0x1F      ; 32-bit move (zero-extends to rax)

mov — Move Data

mov copies data between registers, memory, and immediates. Memory-to-memory moves are not allowed — go through a register. Always specify the size (byte/word/dword/qword) when the operand size is ambiguous, e.g. mov dword [rsp], 1.

assembly
mov rax, 60          ; immediate  -> register
mov rbx, rax         ; register   -> register
mov qword [rsp-8], 7 ; immediate  -> memory (qword = 8 bytes)
mov rcx, [rsp-8]     ; memory     -> register

; INVALID: mov [rsp-8], [rsp-16]  (memory-to-memory not allowed)
; Use two steps: mov rax, [src]; mov [dst], rax

lea — Load Effective Address

lea computes the address of a memory operand without accessing memory. It is frequently used as a fast arithmetic instruction (multiplication by 5/3/9 etc. via scale+index) and to take the address of stack variables or data labels.

assembly
; Compute address without dereferencing
lea rax, [rbx + rcx*8 + 16]   ; rax = rbx + rcx*8 + 16

; Common idiom: fast arithmetic (no memory access)
lea rax, [rax + rax*4]        ; rax *= 5  (rax = rax + rax*4)

; Pointer into a buffer
lea rsi, [buffer]             ; rsi = address of buffer
lea rdi, [rsp + 32]           ; rdi = address of stack slot

push / pop — Stack Operations

push decrements rsp by 8 (64-bit mode) then stores the value; pop loads then increments rsp. In the System V AMD64 ABI, the first 6 integer args go in rdi, rsi, rdx, rcx, r8, r9 — push is mainly used to save callee-saved registers (rbx, rbp, r12-r15) and to spill temporaries.

assembly
push rax       ; rsp -= 8; [rsp] = rax
push qword 42  ; push immediate
pop rbx        ; rbx = [rsp]; rsp += 8

; Save/restore callee-saved registers
push rbx
push r12
; ... function body ...
pop r12
pop rbx
ret

; Push arguments in reverse (C calling convention)
push 3
push 2
push 1

xchg / xadd — Atomic Exchange

xchg with a memory operand is always atomic (implicit lock). xadd combines exchange and add. Together with lock cmpxchg (compare-and-swap) these form the foundation of lock-free synchronization primitives.

assembly
; xchg swaps two operands (implicitly LOCKed with memory)
xchg rax, rbx          ; swap register/register
xchg [counter], rcx    ; swap memory/register (atomic)

; xadd: swap then add (returns old value in src)
; lock xadd [counter], rax   ; atomic fetch-and-add

; Spinlock idiom
spin:
  xor eax, eax
  lock cmpxchg [lock_var], 1  ; if [lock_var]==0, set to 1
  jnz spin                     ; retry if not acquired

movzx / movsx — Zero/Sign Extend

movzx zero-extends a smaller value into a larger register (unsigned load). movsx sign-extends (signed load). Use movsxd to load a 32-bit signed value into a 64-bit register; movsx on 32->64 is encoded as movsxd in 64-bit mode.

assembly
; movzx: zero-extend (unsigned)
movzx rax, byte [rsi]    ; load byte, zero-extend to 64-bit
movzx eax, word [rdi]    ; load word, zero-extend to 32-bit

; movsx: sign-extend (signed)
movsx rax, byte [rsi]    ; sign-extend byte to 64-bit
movsx rax, dword [rdi]   ; sign-extend 32-bit to 64-bit (movsxd)
02

Arithmetic & Logic

add / sub — Integer Arithmetic

add/sub set CF (unsigned carry/borrow), OF (signed overflow), SF (sign), ZF (zero), PF (parity), and AF (auxiliary carry). Use jc/jo to detect unsigned/signed overflow. Subtracting from rsp allocates stack space — keep rsp 16-byte aligned before calls per the ABI.

assembly
add rax, rbx      ; rax = rax + rbx
add rax, 10       ; rax = rax + 10
sub rcx, rdx      ; rcx = rcx - rdx
sub rsp, 32       ; allocate 32 bytes of stack (align!)

; 64-bit addition with carry check
add rax, rbx
jc .overflow      ; jump if unsigned overflow (CF=1)

imul / idiv — Multiply & Divide

Two-operand imul is the common form — it keeps only the low 64 bits and is what compilers emit for a*b. For full-width multiplication use one-operand mul/imul (result in rdx:rax). Before idiv, sign-extend the dividend with cqo (or cdq for 32-bit); for unsigned div, zero rdx with xor rdx,rdx.

assembly
; Two-operand imul (most common): dst = dst * src
imul rax, rbx        ; rax = rax * rbx (lower 64 bits)
imul rcx, 10         ; rcx = rcx * 10

; One-operand: rdx:rax = rax * src (full 128-bit)
mul  rbx             ; unsigned: rdx:rax = rax * rbx
imul rbx             ; signed:   rdx:rax = rax * rbx

; idiv: signed divide rdx:rax by src
; Must sign-extend rax into rdx:rax first!
cqo                  ; sign-extend rax -> rdx:rax
idiv rcx             ; rax = rdx:rax / rcx, rdx = remainder

; Unsigned: use div (zero rdx first)
xor rdx, rdx
div  rcx             ; rax = rdx:rax / rcx, rdx = remainder

inc / dec / neg

inc and dec do NOT update the carry flag (CF) — this lets you use them inside multi-precision add/sub chains that rely on CF. They do update ZF/SF/OF. neg computes two's complement negation (0 - dst) and sets CF=1 unless the operand was 0.

assembly
inc rax          ; rax++  (does NOT affect CF!)
dec rcx          ; rcx--  (does NOT affect CF!)
neg rdx          ; rdx = -rdx  (two's complement negate)

; Common loop pattern
mov rcx, 10
.loop:
  ; ... loop body ...
  dec rcx
  jnz .loop       ; repeat until rcx == 0

and / or / xor / not / test

xor reg,reg is the idiomatic way to zero a register (shorter encoding than mov reg,0). test a,a is equivalent to and a,a but discards the result — commonly used to check sign/zero without modifying the operand. and/or/xor clear CF and OF.

assembly
and rax, 0xFF    ; mask low byte (rax &= 0xFF)
or  rcx, 0x10    ; set bit 4
xor rdx, rdx     ; rdx = 0 (idiomatic zeroing)
xor rax, rax     ; clear rax (shorter than mov rax,0)
not r8           ; bitwise NOT (one's complement)
test rax, rax    ; set flags from rax & rax (checks zero/sign)
test rcx, 0x1    ; test if low bit set (odd/even check)

shl / shr / sar — Shifts

shl/shr are logical shifts (zero-fill); sar preserves the sign bit (arithmetic shift). Multiplying/dividing by powers of two via shifts is much faster than imul/idiv. The shift count is masked to 5 bits (32-bit operand) or 6 bits (64-bit operand).

assembly
shl rax, 4       ; logical left shift  (rax *= 16)
shr rax, 3       ; logical right shift (unsigned rax /= 8)
sar rax, 3       ; arithmetic right shift (signed rax /= 8)

; Rotate (carry not involved)
rol rax, 4       ; rotate left
ror rax, 4       ; rotate right

; Shift by CL (only low 5 bits used in 64-bit mode)
mov cl, 4
shl rax, cl      ; shift left by 4
03

Control Flow & Branching

cmp / test — Compare

cmp sets flags as if subtracting without storing. For signed comparisons use je/jne/jl/jg/jle/jge; for unsigned use jb/ja/jbe/jae (below/above). Mixing them is a classic bug — jl checks SF!=OF while jb just checks CF.

assembly
cmp rax, rbx     ; compute rax - rbx, set flags (discard result)
cmp rax, 10      ; compare with immediate

; Signed comparisons
cmp rax, rbx
je  .equal       ; jump if rax == rbx        (ZF=1)
jl  .less        ; jump if rax <  rbx signed (SF!=OF)
jg  .greater     ; jump if rax >  rbx signed (ZF=0 and SF==OF)
jle .le          ; jump if rax <= rbx signed
jge .ge          ; jump if rax >= rbx signed

; Unsigned comparisons (use 'below'/'above' mnemonics)
cmp rax, rbx
jb  .below       ; rax <  rbx unsigned (CF=1)
ja  .above       ; rax >  rbx unsigned (CF=0 and ZF=0)
jbe .be          ; rax <= rbx unsigned
jae .ae          ; rax >= rbx unsigned

jmp — Unconditional Jump

jmp performs an unconditional jump. Conditional jumps (jcc) test flags set by cmp/test/arithmetic. In 64-bit mode near conditional jumps can reach ±2GB, so the 'short jump too far' problem is largely gone. Indirect jumps via register/memory enable switch/case jump tables.

assembly
; Direct jump to a label
jmp .end

; Conditional jumps (short/near, 64-bit allows near)
.loop:
  dec rcx
  jnz .loop        ; jump if ZF=0 (rcx != 0)

; Indirect jump through register/memory (jump table)
lea rax, [table]
mov rdi, [rax + rbx*8]
jmp rdi            ; jump to address in rdi

; Jump table example (switch statement)
table: dq .case0, .case1, .case2, .case3

Common Conditional Jumps

There are many synonyms (je==jz, jb==jc==jnae). The signed (l/g) vs unsigned (b/a) distinction is critical: jl/jg test SF and OF; jb/ja test CF. Use signed forms after comparing signed ints, unsigned forms after comparing pointers/unsigned ints.

assembly
; After cmp/test:
je  / jz   ; jump if equal / zero        (ZF=1)
jne / jnz  ; jump if not equal / nonzero (ZF=0)

; Signed
jl / jnge  ; less            (SF!=OF)
jge / jnl  ; greater-or-equal (SF==OF)
jle / jng  ; less-or-equal   (ZF=1 or SF!=OF)
jg  / jnle ; greater         (ZF=0 and SF==OF)

; Unsigned
jb / jnae / jc  ; below / carry       (CF=1)
jae / jnb / jnc ; above-or-equal      (CF=0)
jbe / jna       ; below-or-equal      (CF=1 or ZF=1)
ja  / jnbe      ; above               (CF=0 and ZF=0)

; Special
js  ; jump if sign     (SF=1)
jns ; jump if not sign (SF=0)
jo  ; jump if overflow (OF=1)
jno ; jump if no overflow (OF=0)

Loop with cx

loop decrements rcx and jumps if rcx!=0. Although convenient, it is slower on modern CPUs than a dec/jnz pair, so compilers emit dec/jnz instead. loope/loopz additionally require ZF=1; loopne/loopnz require ZF=0.

assembly
; loop: dec rcx then jump if rcx != 0
mov rcx, 5
.loop:
  ; ... body executes 5 times ...
  loop .loop

; loope/loopz: loop while equal/zero
; loopne/loopnz: loop while not equal/not zero

; Modern compilers prefer dec + jnz (loop is slower on many CPUs)
mov rcx, 5
.loop:
  ; ...
  dec rcx
  jnz .loop

cmov — Conditional Move

cmovcc performs a conditional move — branchless code that avoids branch misprediction penalties. The destination must be a register (not memory). Be aware cmov always evaluates both source operands, so avoid it when one path has side effects or when the source memory access could fault.

assembly
; cmovcc: move only if condition is true (branchless)
cmp rax, rbx
cmovl rax, rbx    ; if rax < rbx (signed), rax = rbx  -> rax = min(a,b)

; max(a, b)
cmp rax, rbx
cmovl rax, rbx    ; rax = max(rax, rbx)? No: if rax<rbx, set rax=rbx -> max

; Branchless abs:
; abs(x): mask = x >> 63; result = (x ^ mask) - mask
mov rax, rdi
sar rdi, 63       ; all 1s if negative, 0 if positive
xor rax, rdi
sub rax, rdi      ; rax = |original rdi|
04

Stack, Functions & Calling Convention

Function Prologue & Epilogue

The standard prologue saves rbp, sets rbp as frame pointer, and allocates locals by subtracting from rsp. leave is a one-byte epilogue equivalent to mov rsp,rbp; pop rbp. The System V AMD64 ABI requires rsp to be 16-byte aligned at the point of a call (so 8 bytes off after the return address is pushed).

assembly
; System V AMD64 calling convention (Linux/macOS)
; Args: rdi, rsi, rdx, rcx, r8, r9 (then stack)
; Return: rax. Callee-saved: rbx, rbp, r12-r15

my_func:
    push rbp
    mov  rbp, rsp        ; standard prologue
    sub  rsp, 32         ; allocate locals (keep 16-byte aligned)

    ; ... function body ...

    mov  rsp, rbp        ; or: leave
    pop  rbp             ; standard epilogue
    ret

; Compact form using leave
my_func2:
    push rbp
    mov  rbp, rsp
    sub  rsp, 16
    ; ...
    leave               ; mov rsp,rbp; pop rbp
    ret

call / ret — Call & Return

call pushes the return address (8 bytes in 64-bit) onto the stack and jumps to the target; ret pops it back into rip. For tail calls use jmp so the callee returns directly to your caller — this preserves the stack and enables tail-call optimization.

assembly
; call pushes return address, then jumps
call my_func

; ret pops return address into rip
my_func:
    ; ...
    ret

; Call with arguments (System V AMD64)
mov rdi, 1     ; 1st arg
mov rsi, 2     ; 2nd arg
mov rdx, 3     ; 3rd arg
call add_three ; result in rax

; Tail call: jmp instead of call+ret
my_wrapper:
    jmp target_func   ; reuses our return address

Leaf Functions & Red Zone

The System V AMD64 ABI reserves a 128-byte 'red zone' below rsp that leaf functions (functions that make no calls) can use without adjusting rsp. Windows x64 does NOT have a red zone. Leaf functions often need no prologue at all.

assembly
; Leaf function (no calls) can use the red zone:
; 128 bytes below rsp that won't be clobbered by signals/interrupts
leaf_sqrt_sum:
    ; rdi, rsi = args, rax = result
    mov rax, rdi
    add rax, rsi
    ret             ; no prologue needed!

; Non-leaf functions MUST save rsp properly because
; a call would write into the red zone.
; Red zone is NOT honored on Windows x64.

Local Variables & Stack Frame

With a frame pointer (rbp), locals are accessed at [rbp - offset] and incoming stack arguments at [rbp + offset]. Compilers often omit the frame pointer (-fomit-frame-pointer) and reference locals directly from rsp, freeing up rbp as a general register.

assembly
my_func:
    push rbp
    mov  rbp, rsp
    sub  rsp, 32          ; 32 bytes for locals

    ; Local variables accessed via [rbp - offset]
    mov qword [rbp-8],  10   ; local1
    mov qword [rbp-16], 20   ; local2

    ; Read arguments (also via rbp once saved on stack,
    ; or directly from registers)
    mov rax, [rbp-8]
    add rax, [rbp-16]

    leave
    ret

Preserving Callee-Saved Registers

Callee-saved registers (rbx, rbp, r12-r15) must be preserved across your function — push them on entry, pop in reverse order on exit. Caller-saved registers (rax, rcx, rdx, rsi, rdi, r8-r11) may be freely clobbered, but if you need their values across a call you must save them yourself.

assembly
; rbx, rbp, r12, r13, r14, r15 are callee-saved
; rax, rcx, rdx, rsi, rdi, r8-r11 are caller-saved

my_func:
    push rbx          ; we want to use rbx
    push r12          ; and r12

    mov rbx, rdi      ; use them
    mov r12, rsi

    ; ... do work, may call other functions ...
    ; (those calls will preserve rbx/r12 for us)

    mov rax, rbx      ; prepare return value

    pop r12           ; restore in REVERSE order
    pop rbx
    ret
05

System Calls & Hello World

syscall — Linux System Call

On Linux x86-64, syscalls use the syscall instruction with the number in rax and up to 6 args in rdi, rsi, rdx, r10, r8, r9 (note r10, not rcx, for the 4th arg). Common numbers: write=1, read=0, exit=60, mmap=9. syscall clobbers rcx and r11. macOS uses different numbers (e.g. write=0x2000004).

assembly
; Linux x86-64 syscall convention:
; rax = syscall number
; rdi, rsi, rdx, r10, r8, r9 = args (NOTE: r10 not rcx!)
; return value in rax; clobbers rcx and r11

; write(1, msg, 12)
mov rax, 1          ; syscall: write
mov rdi, 1          ; fd = stdout
lea rsi, [msg]      ; buf
mov rdx, 12         ; count
syscall

; exit(0)
mov rax, 60         ; syscall: exit
xor rdi, rdi        ; status = 0
syscall

section .data
msg: db "hello world", 10   ; 12 bytes with newline

Complete Hello World (NASM, Linux)

A freestanding hello world links against no libc — it calls the kernel directly via syscall. $ - msg computes the length at assembly time (the $ symbol is the current address). _start is the default entry point for ld. The program ends with the exit syscall; returning from _start is undefined.

assembly
; nasm -f elf64 hello.asm && ld hello.o -o hello && ./hello
section .data
    msg:     db "Hello, World!", 10
    msg_len: equ $ - msg          ; length computed at assemble time

section .text
    global _start

_start:
    ; write(1, msg, msg_len)
    mov rax, 1          ; write
    mov rdi, 1          ; stdout
    mov rsi, msg
    mov rdx, msg_len
    syscall

    ; exit(0)
    mov rax, 60
    xor rdi, rdi
    syscall

Reading Command-Line argc / argv

On entry to _start (Linux, no libc), the kernel sets up the stack with argc at [rsp], then argv pointers, then envp, then NULL. If you link against libc and use main, the C runtime parses these for you — main receives argc and argv in rdi/rsi instead.

assembly
; At _start the stack looks like:
;   [rsp]      = argc
;   [rsp+8]    = argv[0]
;   [rsp+16]   = argv[1]
;   ...
;   [rsp + 8*(argc+1)] = NULL

_start:
    mov rdi, [rsp]           ; argc
    mov rsi, [rsp+8]         ; argv[0] (program name)
    mov rdx, [rsp+16]        ; argv[1] (first user arg)

    ; Loop over argv
    mov rbx, rsp
    add rbx, 8               ; skip argc, point at argv[0]
.loop:
    mov rax, [rbx]
    test rax, rax
    jz .done                 ; NULL terminator
    ; rax -> one argv string
    add rbx, 8
    jmp .loop
.done:
    ; exit
    mov rax, 60
    xor rdi, rdi
    syscall

Calling C Library Functions

When calling C functions, align rsp to 16 bytes before the call (the call pushes 8 bytes, leaving it 8 off). For variadic functions like printf, rax must hold the number of vector (XMM) register arguments — set it to 0 for integer-only calls. Use main as the entry point so the C runtime sets up libc and libc can call your destructors on exit.

assembly
; Link with gcc: nasm -f elf64 demo.asm && gcc demo.o -o demo -no-pie
extern printf

section .data
    fmt:  db "sum = %d", 10, 0
section .text
    global main

main:
    push rbp
    mov  rbp, rsp
    sub  rsp, 16                ; keep stack 16-byte aligned

    ; printf("sum = %d\n", 42)
    ; Variadic: rdi=fmt, rsi=arg, rax=#vector regs (0)
    lea  rdi, [fmt]
    mov  rsi, 42
    xor  rax, rax               ; 0 floating-point args
    call printf

    xor  rax, rax               ; return 0
    leave
    ret

Was this helpful?