diff --git a/Makefile b/Makefile
index c2e7ed0..597a9f1 100644
--- a/Makefile
+++ b/Makefile
@@ -1,5 +1,6 @@
 AS = nasm
 CC = gcc
+CFLAGS = -std=c11 -m32 -ffreestanding -c -fno-stack-protector -fno-pie
 LD = ld
 QEMU = qemu-system-i386
 IMG_SIZE = 1440k
@@ -10,8 +11,15 @@ BOOT_SRC = bootloader/boot.asm
 BOOT_OBJ = $(BUILD_DIR)/boot.o
 BOOT_ELF = $(BUILD_DIR)/boot.elf
 BOOT_IMG = $(BUILD_DIR)/boot.img
-KERNEL_SRC = kernel/kmain.c
+
+KERNEL_C_SRC = $(wildcard kernel/*.c)
+KERNEL_ASM_SRC = $(wildcard kernel/*.asm)
+KERNEL_OBJ = $(patsubst kernel/%.c, $(BUILD_DIR)/%.o, $(KERNEL_C_SRC))
+KERNEL_OBJ += $(patsubst kernel/%.asm, $(BUILD_DIR)/asm_%.o, $(KERNEL_ASM_SRC))
+KERNEL_OBJ += $(BUILD_DIR)/boot1.o
+KERNEL_ELF = $(BUILD_DIR)/kernel.elf
 KERNEL_BIN = $(BUILD_DIR)/kernel.bin
+
 DISK_IMG = $(BUILD_DIR)/disk.img
 
 all: $(BOOT_IMG) $(KERNEL_BIN) $(DISK_IMG)
@@ -29,9 +37,17 @@ $(BOOT_IMG): $(BOOT_ELF)
 	objcopy -O binary $< $@
 	truncate -s $(IMG_SIZE) $@
 
-$(KERNEL_BIN): $(KERNEL_SRC) | $(BUILD_DIR)
-	$(CC) -ffreestanding -c $< -o $(BUILD_DIR)/kernel.o
-	$(LD) -T bootloader/linker.ld -o $@ $(BUILD_DIR)/kernel.o
+$(BUILD_DIR)/boot1.o: bootloader/boot1.asm
+	$(AS) -f elf32 -o $@ $<
+
+$(BUILD_DIR)/asm_%.o: kernel/%.asm
+	$(AS) -f elf32 -o $@ $<
+
+$(BUILD_DIR)/%.o: kernel/%.c
+	$(CC) $(CFLAGS) $< -o $@
+
+$(KERNEL_BIN): $(KERNEL_OBJ) | $(BUILD_DIR)
+	$(LD) -melf_i386 --oformat binary -T bootloader/linker.ld -o $@ $(KERNEL_OBJ)
 
 $(DISK_IMG): $(BOOT_IMG) $(KERNEL_BIN)
 	dd if=$(BOOT_IMG) of=$@ bs=512 seek=4
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 96aa335..a18041b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -5,7 +5,7 @@
 #include "print.h"
 
 void cpuid(uint32_t function, uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx) {
-    asm volatile (
+    __asm__(
         "cpuid"
         : "=a"(*eax), "=b"(*ebx), "=c"(*ecx), "=d"(*edx)
         : "a"(function)
@@ -32,6 +32,6 @@ void identify_cpu() {
     serial_write("\n");
 
     terminal_write("CPUID max leaf: ");
-    print_hex(eax);  // You must implement this (see below)
+    print_hex(eax, false, false);  // You must implement this (see below)
     terminal_write("\n");
 }
diff --git a/kernel/idt.c b/kernel/idt.c
index 2bb5af3..2cbfc4f 100644
--- a/kernel/idt.c
+++ b/kernel/idt.c
@@ -52,7 +52,7 @@ void idt_set_gate(int n, uint32_t handler) {
 
 // Load IDT via lidt
 static void idt_load() {
-    asm volatile("lidt (%0)" : : "r" (&idt_ptr));
+    __asm__("lidt (%0)" : : "r" (&idt_ptr));
 }
 
 // IDT initialization
diff --git a/kernel/io.h b/kernel/io.h
index aaaee3a..76d696b 100644
--- a/kernel/io.h
+++ b/kernel/io.h
@@ -4,12 +4,12 @@
 #include <stdint.h>
 
 static inline void outb(uint16_t port, uint8_t val) {
-    asm volatile ("outb %0, %1" : : "a"(val), "Nd"(port));
+    __asm__("outb %0, %1" : : "a"(val), "Nd"(port));
 }
 
 static inline uint8_t inb(uint16_t port) {
     uint8_t ret;
-    asm volatile ("inb %1, %0" : "=a"(ret) : "Nd"(port));
+    __asm__("inb %1, %0" : "=a"(ret) : "Nd"(port));
     return ret;
 }
 
diff --git a/kernel/isr.asm b/kernel/isr.asm
index deba3e0..7bd4999 100644
--- a/kernel/isr.asm
+++ b/kernel/isr.asm
@@ -1,8 +1,8 @@
 [BITS 32]
-[GLOBAL isr0, isr1, isr2, isr3, isr4, isr5, isr6, isr7, isr8, isr9]
-[GLOBAL isr10, isr11, isr12, isr13, isr14, isr15, isr16, isr17, isr18, isr19]
-[GLOBAL isr20, isr21, isr22, isr23, isr24, isr25, isr26, isr27, isr28, isr29]
-[GLOBAL isr30, isr31, isr_default]
+GLOBAL isr0, isr1, isr2, isr3, isr4, isr5, isr6, isr7, isr8, isr9
+GLOBAL isr10, isr11, isr12, isr13, isr14, isr15, isr16, isr17, isr18, isr19
+GLOBAL isr20, isr21, isr22, isr23, isr24, isr25, isr26, isr27, isr28, isr29
+GLOBAL isr30, isr31, isr_default
 
 [EXTERN isr_handler]
 
diff --git a/kernel/isr.c b/kernel/isr.c
index 636a189..c4d7189 100644
--- a/kernel/isr.c
+++ b/kernel/isr.c
@@ -2,20 +2,20 @@
 #include "serial.h"
 #include "isr.h"
 #include "io.h"
-#include "utils.h"
+#include "print.h"
 
 static isr_callback_t interrupt_handlers[MAX_INTERRUPTS] = { 0 };
 
 void isr_handler(uint32_t int_num, uint32_t err_code) {
     terminal_write("Interrupt occurred: ");
 
-    print_hex(int_num);
+    print_hex(int_num, true, false);
     terminal_write("\n");
 
     serial_write("INT triggered\n");
 
     terminal_write("Error code: ");
-    print_hex(err_code);
+    print_hex(err_code, true, false);
     terminal_write("\n");
 
     if (interrupt_handlers[int_num]) {
@@ -33,7 +33,7 @@ void isr_handler(uint32_t int_num, uint32_t err_code) {
 
         // Halt CPU
         while (1) {
-            asm volatile ("hlt");
+            __asm__("hlt");
         }
     }
 
diff --git a/kernel/kmain.c b/kernel/kmain.c
index 05ea503..b522142 100644
--- a/kernel/kmain.c
+++ b/kernel/kmain.c
@@ -1,5 +1,4 @@
 #include <stdint.h>
-#include <stdbool.h>
 #include "io.h"
 #include "serial.h"
 #include "terminal.h"
@@ -9,6 +8,7 @@
 #include "gdt.h"
 #include "cpu.h"
 #include "kmalloc.h"
+#include "print.h"
 #include "timer.h"
 #include "utils.h"
 #include "keyboard.h"
@@ -69,9 +69,9 @@ void kmain(void) {
     char buf[32];
     for (uint32_t i = 0; i < mmap_size; i++) {
         terminal_write(" - Base: ");
-        print_hex((uint32_t)(mmap[i].base_addr & 0xFFFFFFFF));  // Lower 32 bits
+        print_hex((uint32_t)(mmap[i].base_addr & 0xFFFFFFFF), true, false);  // Lower 32 bits
         terminal_write(", Length: ");
-        print_hex((uint32_t)(mmap[i].length & 0xFFFFFFFF));     // Lower 32 bits
+        print_hex((uint32_t)(mmap[i].length & 0xFFFFFFFF), true, false);     // Lower 32 bits
         terminal_write(", Type: ");
         itoa(mmap[i].type, buf, 10);
         terminal_write(buf);
@@ -82,6 +82,6 @@ void kmain(void) {
 
     // Halt CPU in loop
     while (1) {
-        asm volatile("hlt");
+        __asm__("hlt");
     }
 }
diff --git a/kernel/mouse.c b/kernel/mouse.c
index 514844c..8d6ece6 100644
--- a/kernel/mouse.c
+++ b/kernel/mouse.c
@@ -10,7 +10,7 @@ static mouse_data_t mouse_data;
 // Read USB mouse data
 mouse_data_t usb_read_mouse(void) {
     uint8_t buffer[3]; // USB HID Mouse reports typically use 3 bytes
-    if (usb_interrupt_transfer(buffer, sizeof(buffer))) { // Ensure buffer is filled
+    if (usb_interrupt_transfer()) { // Ensure buffer is filled
         // Process the received data
         mouse_data.x += buffer[1]; // X movement
         mouse_data.y += buffer[2]; // Y movement
diff --git a/kernel/paging.c b/kernel/paging.c
index 17509ee..847d150 100644
--- a/kernel/paging.c
+++ b/kernel/paging.c
@@ -37,12 +37,12 @@ void enable_paging() {
     uint32_t cr0;
 
     // Load page directory into CR3
-    asm volatile("mov %0, %%cr3" : : "r"(page_directory));
+    __asm__("mov %0, %%cr3" : : "r"(page_directory));
 
     // Enable paging (set the PG bit in CR0)
-    asm volatile("mov %%cr0, %0" : "=r"(cr0));
+    __asm__("mov %%cr0, %0" : "=r"(cr0));
     cr0 |= 0x80000000;  // Set the PG (paging) bit
-    asm volatile("mov %0, %%cr0" : : "r"(cr0));
+    __asm__("mov %0, %%cr0" : : "r"(cr0));
 }
 
 // Initialize paging: set up the page directory and enable paging
diff --git a/kernel/panic.c b/kernel/panic.c
index 477ff66..6de41cc 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -14,6 +14,6 @@ void panic(const char *message) {
 
     // Halt the system
     while (true) {
-        asm volatile ("cli; hlt");
+        __asm__("cli; hlt");
     }
 }
diff --git a/kernel/print.c b/kernel/print.c
index d5a829f..54251fd 100644
--- a/kernel/print.c
+++ b/kernel/print.c
@@ -1,13 +1,14 @@
-#include <stdio.h>
 #include <stdarg.h>
 #include "print.h"
+#include "serial.h"
+#include "terminal.h"
 
 void my_putchar(char ch) {
     // Write a single character to standard output
     // In a freestanding environment, you might need to implement this differently
     // For now, we will use the standard putchar for demonstration
     // Replace this with your own implementation if needed
-    putchar(ch);
+    terminal_putchar(ch);
 }
 
 void print_string(const char *str) {
@@ -33,7 +34,9 @@ void my_printf(const char *format, ...) {
                 case 'd': { // Integer
                     int num = va_arg(args, int);
                     char buffer[20]; // Buffer to hold the string representation
-                    snprintf(buffer, sizeof(buffer), "%d", num);
+                    
+                    //TODO: implement `snprintf()`
+                    //snprintf(buffer, sizeof(buffer), "%d", num);
                     print_string(buffer);
                     break;
                 }
@@ -56,29 +59,44 @@ void my_printf(const char *format, ...) {
     va_end(args);
 }
 
+void print_hex(uint32_t val, int include_prefix, int suppress_leading_zeros) { 
+    char hex_chars[] = "0123456789ABCDEF";
+    char buffer[11]; // 8 hex digits + "0x" + null terminator
+    int pos = 10;    // Start from end of buffer (null terminator)
 
-void print_hex(unsigned int num) {
-    // Buffer to hold the hexadecimal representation
-    char buffer[9]; // 8 hex digits + null terminator
-    buffer[8] = '\0'; // Null-terminate the string
+    // Null-terminate the buffer
+    buffer[pos--] = '\0';
 
+    // Convert value to hex digits
     for (int i = 7; i >= 0; i--) {
-        int digit = num & 0xF; // Get the last 4 bits
-        buffer[i] = (digit < 10) ? (digit + '0') : (digit - 10 + 'A'); // Convert to hex character
-        num >>= 4; // Shift right by 4 bits
+        int digit = val & 0xF; // Get last 4 bits
+        buffer[pos--] = hex_chars[digit];
+        val >>= 4; // Shift right by 4 bits
     }
 
-    // Print the buffer, skipping leading zeros
-    int leading_zero = 1;
-    for (int i = 0; i < 8; i++) {
-        if (buffer[i] != '0') {
-            leading_zero = 0; // Found a non-zero digit
-        }
-        if (!leading_zero) {
-            my_putchar(buffer[i]);
-        }
+    // Add "0x" prefix if requested
+    if (include_prefix) {
+        buffer[pos--] = 'x';
+        buffer[pos--] = '0';
     }
-    if (leading_zero) {
-        my_putchar('0'); // If all were zeros, print a single '0'
+
+    // Determine start of output (skip leading zeros if requested)
+    int start = include_prefix ? 0 : 2; // Start after "0x" if prefix included
+    if (suppress_leading_zeros && !include_prefix) {
+        int i = start;
+        while (i < 9 && buffer[i] == '0') {
+            i++;
+        }
+        if (i == 10) {
+            // All zeros, output single '0'
+            terminal_write("0");
+            serial_write("0");
+            return;
+        }
+        start = i;
     }
-}
\ No newline at end of file
+
+    // Output the result
+    terminal_write(buffer + start);
+    serial_write(buffer + start);
+}
diff --git a/kernel/print.h b/kernel/print.h
index 61c08ae..bf07e4a 100644
--- a/kernel/print.h
+++ b/kernel/print.h
@@ -1,9 +1,11 @@
 #ifndef PRINT_H
 #define PRINT_H
 
+#include "types.h"
+
 void print_string(const char *str);
 void my_printf(const char *format, ...);
-void print_hex(unsigned int num);
+void print_hex(uint32_t val, int include_prefix, int suppress_leading_zeros);
 void my_putchar(char ch);
 
 #endif
diff --git a/kernel/shell.c b/kernel/shell.c
index 43b261c..f975f58 100644
--- a/kernel/shell.c
+++ b/kernel/shell.c
@@ -2,8 +2,6 @@
 #include "keyboard.h"
 #include "terminal.h"
 #include "print.h"
-#include <stdio.h>
-#include <string.h>
 #include "string_utils.h"
 
 void execute(char *input) {
@@ -49,7 +47,7 @@ void shell_loop()
             {
                 if (index < sizeof(input) - 1) {
                     input[index++] = c;
-                    putchar(c);
+                    terminal_putchar(c);
                 }
             }
         }
diff --git a/kernel/threading.c b/kernel/threading.c
index f8b3c0a..c7b6ba5 100644
--- a/kernel/threading.c
+++ b/kernel/threading.c
@@ -1,8 +1,9 @@
+#include "malloc.h"
+#include "print.h"
 #include "threading.h"
-#include <stdlib.h>
+#include "types.h"
+#include "utils.h"
 #include <stdint.h>
-#include <stdio.h>
-#include <string.h>
 
 #define MAX_THREADS 16           // Maximum number of threads
 #define THREAD_STACK_SIZE 8192   // Stack size for each thread
@@ -27,7 +28,7 @@ void thread_init(void) {
 // Create a new thread
 void thread_create(Thread *thread __attribute__((unused)), void (*start_routine)(void *), void *arg) {
     if (num_threads >= MAX_THREADS) {
-        printf("Error: Maximum thread count reached.\n");
+        my_printf("Error: Maximum thread count reached.\n");
         return;
     }
 
@@ -98,7 +99,7 @@ void scheduler(void) {
 void context_switch(Thread *next) {
     // For simplicity, context switching in this example would involve saving/restoring registers.
     // In a real system, you would need to save the CPU state (registers) and restore the next thread's state.
-    printf("Switching to thread...\n");
+    my_printf("Switching to thread...\n");
     next->start_routine(next->arg);  // Start running the next thread
 }
 
diff --git a/kernel/timer.c b/kernel/timer.c
index ab4a859..f47ec36 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -3,6 +3,7 @@
 #include "isr.h"
 #include "terminal.h"
 #include "stdio.h"
+#include "utils.h"
 
 static volatile uint32_t tick = 0;
 
diff --git a/kernel/types.c b/kernel/types.c
index 6936871..8e71fd1 100644
--- a/kernel/types.c
+++ b/kernel/types.c
@@ -1,9 +1 @@
 #include "types.h"
-
-// Example: Basic memory helper (unnecessary if libc exists)
-void *memset(void *dest, int value, size_t len) {
-    unsigned char *ptr = (unsigned char *)dest;
-    while (len-- > 0)
-        *ptr++ = (unsigned char)value;
-    return dest;
-}
diff --git a/kernel/utils.c b/kernel/utils.c
index 04dd14c..f41ceff 100644
--- a/kernel/utils.c
+++ b/kernel/utils.c
@@ -1,6 +1,4 @@
 #include "utils.h"
-#include "serial.h"
-#include "terminal.h"
 
 static void reverse(char* str, int len) {
     int start = 0;
@@ -79,13 +77,19 @@ char* utoa(unsigned int value, char* str, int base) {
     return str;
 }
 
-void print_hex(uint32_t val) {
-    char hex_chars[] = "0123456789ABCDEF";
-    char buf[11] = "0x00000000";
-    for (int i = 9; i >= 2; i--) {
-        buf[i] = hex_chars[val & 0xF];
-        val >>= 4;
+int memcmp(const void *ptr1, const void *ptr2, size_t num) {
+    const uint8_t *p1 = ptr1, *p2 = ptr2;
+    for (size_t i = 0; i < num; i++) {
+        if (p1[i] != p2[i]) {
+            return p1[i] < p2[i] ? -1 : 1;
+        }
     }
-    terminal_write(buf);
-    serial_write(buf);
-}
\ No newline at end of file
+    return 0;
+}
+
+void *memset(void *dest, int value, size_t len) {
+    unsigned char *ptr = (unsigned char *)dest;
+    while (len-- > 0)
+        *ptr++ = (unsigned char)value;
+    return dest;
+}
diff --git a/kernel/utils.h b/kernel/utils.h
index 9ef78d9..78f9d44 100644
--- a/kernel/utils.h
+++ b/kernel/utils.h
@@ -1,7 +1,7 @@
 #ifndef UTILS_H
 #define UTILS_H
-#include <stdint.h>
 
+#include "types.h"
 
 // Convert integer to string (base is typically 10, 16, etc.)
 char* itoa(int value, char* str, int base);
@@ -9,6 +9,7 @@ char* itoa(int value, char* str, int base);
 // Convert unsigned integer to string (base is typically 10, 16, etc.)
 char* utoa(unsigned int value, char* str, int base);
 
-void print_hex(uint32_t val);
+int memcmp(const void *ptr1, const void *ptr2, size_t num);
+void *memset(void *dest, int value, size_t len);
 
 #endif // UTILS_H