org 7C00h
jmp short bootmain

bootmain:
        xor ax, ax      ; We want a segment of 0 for DS for this question
        mov ds, ax      ; Set AX to appropriate segment value for your situation
        mov bx, 0x8000  ; Stack segment can be any usable memory

        cli            ; Disable interrupts to circumvent bug on early 8088 CPUs
        mov ss, bx     ; Top of the stack @ 0x80000.
        mov sp, ax     ; Set SP=0 so the bottom of stack will be just below 0x90000
        sti            ; Re-enable interrupts
        cld            ; Set the direction flag to be positive direction

        mov ah, 0x02 ; Read sectors from drive
        mov al, 2    ; Read 1 sector
        mov ch, 0    ; Cylinder 0
        mov cl, 2    ; Sector 2
        mov dh, 0    ; Head 0
        mov bx, CODE_SEG
        mov es, bx   ; ES = CODE_SEG
        xor bx, bx   ; BX = 0
        int 0x13

        cli
        lgdt [gdt_descriptor]
        mov eax, cr0
        or eax, 0x1
        mov cr0, eax

        jmp CODE_SEG:prekernel_main

gdt_start:
gdt_null:
    dd 0x0
    dd 0x0
gdt_code:
    dw 0xffff
    dw 0x0
    db 0x0
    db 10011010b
    db 11001111b
    db 0x0
gdt_data:
    dw 0xffff
    dw 0x0
    db 0x0
    db 10010010b
    db 11001111b
    db 0x0
gdt_end:
gdt_descriptor:
    dw gdt_end - gdt_start
    dd gdt_start

CODE_SEG equ gdt_code - gdt_start
DATA_SEG equ gdt_data - gdt_start

[bits 32]
prekernel_main:
    mov ax, DATA_SEG
    mov ds, ax
    mov es, ax
    mov fs, ax
    mov gs, ax
    mov ss, ax

    mov ebp, 0x2000
    mov esp, ebp
    mov eax, 0xB8000

.loop:
    cmp eax, 0xB8FA0 ;0xB8000 + 4000
    je .end
    mov byte [eax], 'A'
    inc eax
    mov byte [eax], 0x07
    inc eax
    jmp .loop

.end:
    hlt
    jmp $

times 0200h - 2 - ($ - $$)  db 0
dw 0AA55h