diff --git a/programs/RPS.ch8 b/programs/RPS.ch8
new file mode 100644
index 0000000..3ea42d4
Binary files /dev/null and b/programs/RPS.ch8 differ
diff --git a/programs/flightrunner.ch8 b/programs/flightrunner.ch8
new file mode 100644
index 0000000..b379353
Binary files /dev/null and b/programs/flightrunner.ch8 differ
diff --git a/programs/octojam1title.ch8 b/programs/octojam1title.ch8
new file mode 100644
index 0000000..7e8dd9f
Binary files /dev/null and b/programs/octojam1title.ch8 differ
diff --git a/programs/outlaw.ch8 b/programs/outlaw.ch8
new file mode 100644
index 0000000..71eff28
Binary files /dev/null and b/programs/outlaw.ch8 differ
diff --git a/src/chip8.rs b/src/chip8.rs
index 22b77ba..45fb4f1 100644
--- a/src/chip8.rs
+++ b/src/chip8.rs
@@ -11,7 +11,7 @@ static MEMORY_LIMIT: i32 = 4096;
 static STACK_LIMIT: i32 = 16;
 static VARIABLE_REGISTER_COUNT: i32 = 16;
 static TIMER_TICK_RATE: u32 = 60;
-static DESIRED_FPS: u32 = 165;
+static DESIRED_FPS: u32 = 60;
 static CYCLES_PER_FRAME: u32 = 10;
 
 #[derive(Clone)]
diff --git a/src/chip8/cpu.rs b/src/chip8/cpu.rs
index ddf10e3..914717a 100644
--- a/src/chip8/cpu.rs
+++ b/src/chip8/cpu.rs
@@ -63,24 +63,24 @@ pub fn execute_instruction(state: &mut Chip8State, instruction: u16) {
             }
         }
         (0x8, _, _, 0x5) => {
-            let flag = state.r_v[x as usize] > state.r_v[y as usize];
+            let flag = state.r_v[x as usize] >= state.r_v[y as usize];
             state.r_v[x as usize] = state.r_v[x as usize].wrapping_sub(state.r_v[y as usize]);
             state.r_v[0xF] = if flag { 1 } else { 0 };
         }
         (0x8, _, _, 0x6) => {
             let flag = (state.r_v[x as usize] & 0b00000001) == 1;
-            state.r_v[0xF] = if flag { 1 } else { 0 };
             state.r_v[x as usize] = state.r_v[x as usize] / 2;
+            state.r_v[0xF] = if flag { 1 } else { 0 };
         }
         (0x8, _, _, 0x7) => {
-            let flag = state.r_v[x as usize] < state.r_v[y as usize];
+            let flag = state.r_v[x as usize] <= state.r_v[y as usize];
             state.r_v[x as usize] = state.r_v[y as usize].wrapping_sub(state.r_v[x as usize]);
             state.r_v[0xF] = if flag { 1 } else { 0 };
         }
         (0x8, _, _, 0xE) => {
             let flag = ((state.r_v[x as usize] & 0b10000000) >> 7) == 1;
-            state.r_v[0xF] = if flag { 1 } else { 0 };
             state.r_v[x as usize] = state.r_v[x as usize].wrapping_mul(2);
+            state.r_v[0xF] = if flag { 1 } else { 0 };
         }
         (0x9, _, _, _) => {
             if state.r_v[x as usize] != state.r_v[y as usize] {
@@ -97,7 +97,7 @@ pub fn execute_instruction(state: &mut Chip8State, instruction: u16) {
         (0xD, _, _, _) => {
             state.r_v[0xF] = 0;
             let bytes = read_n_bytes(&state.mem, state.mem.len(), state.r_i as usize, n as usize);
-            gpu::draw(state, x, y, &bytes, n);
+            gpu::wrapping_draw(state, x, y, &bytes, n);
         }
         (0xE, _, _, 0xE) => {
             let key_index = state.r_v[x as usize];
diff --git a/src/chip8/debug.rs b/src/chip8/debug.rs
index 22fc0f0..e31fab7 100644
--- a/src/chip8/debug.rs
+++ b/src/chip8/debug.rs
@@ -22,6 +22,6 @@ pub fn print_debug(state: &Chip8State, current_instruction: u16) {
     }
     println!("Current Instruction: {:04X}", current_instruction);
     println!("----------------");
-    println!("Press Enter to continue...");
-    let _ = io::stdin().read(&mut [0u8]).unwrap();
+    // println!("Press Enter to continue...");
+    // let _ = io::stdin().read(&mut [0u8]).unwrap();
 }
diff --git a/src/chip8/gpu.rs b/src/chip8/gpu.rs
index c12f2e2..9e82f42 100644
--- a/src/chip8/gpu.rs
+++ b/src/chip8/gpu.rs
@@ -13,10 +13,12 @@ pub fn draw(state: &mut Chip8State, vx: u8, vy: u8, bytes_to_draw: &[u8], bytes_
     let start_x = state.r_v[vx as usize];
     let start_y = state.r_v[vy as usize];
     for y in start_y..start_y + bytes_to_draw_len {
+        println!("{}", bytes_idx);
         if (y as i32) < CHIP8_DISPLAY_HEIGHT {
             // 8 is the hardcoded sprite width, has to atleast have 1 8 bit value to display
             let mut bit_idx = 0;
             for x in start_x..start_x + SPRITE_WIDTH {
+                println!("(X,Y): ({},{})", x, y);
                 if (x as i32) < CHIP8_DISPLAY_WIDTH {
                     let sprite_pixel = ((bytes_to_draw[bytes_idx] >> (7 - bit_idx)) & 1) == 1;
                     let current_pixel = state.display[y as usize][x as usize];
@@ -36,6 +38,48 @@ pub fn draw(state: &mut Chip8State, vx: u8, vy: u8, bytes_to_draw: &[u8], bytes_
     }
 }
 
+pub fn wrapping_draw(
+    state: &mut Chip8State,
+    vx: u8,
+    vy: u8,
+    bytes_to_draw: &[u8],
+    bytes_to_draw_len: u8,
+) {
+    let mut bytes_idx = 0;
+    let start_x = state.r_v[vx as usize];
+    let start_y = state.r_v[vy as usize];
+
+    while bytes_idx < bytes_to_draw_len {
+        let mut y = start_y.wrapping_add(bytes_idx);
+        if y as i32 >= CHIP8_DISPLAY_HEIGHT {
+            y = (y - CHIP8_DISPLAY_HEIGHT as u8) % CHIP8_DISPLAY_HEIGHT as u8;
+        }
+
+        let mut bit_idx = 0;
+
+        while bit_idx < SPRITE_WIDTH {
+            let mut x = start_x.wrapping_add(bit_idx);
+            if x as i32 >= CHIP8_DISPLAY_WIDTH {
+                x = (x - CHIP8_DISPLAY_WIDTH as u8) % CHIP8_DISPLAY_WIDTH as u8;
+            }
+
+            let sprite_pixel = ((bytes_to_draw[bytes_idx as usize] >> (7 - bit_idx)) & 1) == 1;
+            let current_pixel = state.display[y as usize][x as usize];
+            let new_pixel = current_pixel ^ sprite_pixel;
+
+            state.display[y as usize][x as usize] = new_pixel;
+
+            if new_pixel != current_pixel {
+                state.r_v[0xF] = 1;
+            }
+
+            bit_idx += 1;
+        }
+
+        bytes_idx += 1;
+    }
+}
+
 pub fn load_builtin_sprites(state: &mut Chip8State) {
     memory::load_bytes(
         state,